Add pybind11 as a pip module requirement for azure.

* fix pytorch-training history

* fix pytorch-training

fix

.azuredevops/ci-builds/mathlibs-trigger.yml

@@ -0,0 +1,33 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml@pipelines_repo
+
+parameters:
+- name: pipelinesRepoRef
+  type: string
+  default: refs/heads/develop
+- name: librariesRepoRef
+  type: string
+  default: refs/heads/develop
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+    ref: ${{ parameters.pipelinesRepoRef }}
+  - repository: libraries_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/rocm-libraries
+    ref: ${{ parameters.librariesRepoRef }}
+
+trigger: none
+pr: none
+
+jobs:
+  - template: /.azuredevops/ci-builds/mathlibs.yml@pipelines_repo
+    parameters:
+      checkoutRepo: libraries_repo
+      buildDependsOn: false

.azuredevops/ci-builds/mathlibs.yml

@@ -0,0 +1,38 @@
+# entrypoint for kicking off a unified build of the mathlibs
+# this template is designed to be called by another pipeline (llvm, clr, etc.)
+# `buildDependsOn` will need to be set when calling this template
+# passes a `unifiedBuild` param to downstream pipelines, which will prevent duplicate jobs
+# logic needs to be added in individual mathlib pipelines for handling `unifiedBuild`
+
+parameters:
+- name: checkoutRepo
+  type: string
+  default: monorepo
+- name: buildDependsOn
+  type: object
+  default: false
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocRAND:
+      name: rocRAND
+      sparseCheckoutDir: projects/rocrand
+    - rocPRIM:
+      name: rocPRIM
+      sparseCheckoutDir: projects/rocprim
+    - hipBLAS-common:
+      name: hipBLAS-common
+      sparseCheckoutDir: projects/hipblas-common
+    # - composable_kernel:
+    #   name: composable_kernel
+    #   sparseCheckoutDir: projects/composablekernel
+
+jobs:
+- ${{ each component in parameters.downstreamComponentMatrix }}:
+  - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+    parameters:
+      checkoutRepo: ${{ parameters.checkoutRepo }}
+      sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+      buildDependsOn: ${{ parameters.buildDependsOn }}
+      triggerDownstreamJobs: true
+      unifiedBuild: true

.azuredevops/components/HIP.yml

@@ -20,7 +20,7 @@ parameters:
     - ocl-icd-libopencl1
     - ocl-icd-opencl-dev
     - opencl-headers
-    - python3-pip
+    - zlib1g-dev
 - name: pipModules
   type: object
   default:
@@ -41,120 +41,148 @@ parameters:
 # any changes for clr should just trigger HIP pipeline
 # similarly for hipother repo, for Nvidia backend
 
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
+
 # HIP with AMD backend
 jobs:
-- job: hip_clr_combined_amd
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-# checkout triggering repo (either HIP or clr)
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-# if this is triggered by HIP repo, matching repo is clr
-# if this is triggered by clr repo, matching repo is HIP
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: matching_repo
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: hipother_repo
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependenciesAMD }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-# compile clr
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: clr
-      cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
-      extraBuildFlags: >-
-        -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
-        -DHIP_PLATFORM=amd
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        -DROCM_PATH=$(Agent.BuildDirectory)/rocm
-        -DHIPCC_BIN_DIR=$(Agent.BuildDirectory)/rocm/bin
-        -DCLR_BUILD_HIP=ON
-        -DCLR_BUILD_OCL=ON
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-    parameters:
-      artifactName: amd
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-    parameters:
-      artifactName: amd
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     environment: amd
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: hip_clr_combined_${{ job.os }}_amd
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+  # checkout triggering repo (either HIP or clr)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+  # if this is triggered by HIP repo, matching repo is clr
+  # if this is triggered by clr repo, matching repo is HIP
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: matching_repo
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: hipother_repo
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependenciesAMD }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        os: ${{ job.os }}
+  # compile clr
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        componentName: clr
+        cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
+          -DHIP_PLATFORM=amd
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
+          -DHIPCC_BIN_DIR=$(Agent.BuildDirectory)/rocm/bin
+          -DCLR_BUILD_HIP=ON
+          -DCLR_BUILD_OCL=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        artifactName: amd
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        artifactName: amd
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
+    #     pipModules: ${{ parameters.pipModules }}
+    #     environment: amd
 
 # HIP with Nvidia backend
-- job: hip_clr_combined_nvidia
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-# checkout triggering repo (either HIP or clr)
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-# if this is triggered by HIP repo, matching repo is clr
-# if this is triggered by clr repo, matching repo is HIP
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: matching_repo
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: hipother_repo
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependenciesNvidia }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - script: 'ls -1R $(Agent.BuildDirectory)/rocm'
-    displayName: 'Artifact listing'
-# compile clr
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: clr
-      cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
-      extraBuildFlags: >-
-        -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
-        -DHIP_PLATFORM=nvidia
-        -DHIPCC_BIN_DIR=$(Agent.BuildDirectory)/rocm/bin
-        -DCLR_BUILD_HIP=ON
-        -DCLR_BUILD_OCL=OFF
-        -DHIPNV_DIR=$(Build.SourcesDirectory)/hipother/hipnv
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-    parameters:
-      artifactName: nvidia
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     environment: nvidia
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: hip_clr_combined_${{ job.os }}_nvidia
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+  # checkout triggering repo (either HIP or clr)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+  # if this is triggered by HIP repo, matching repo is clr
+  # if this is triggered by clr repo, matching repo is HIP
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: matching_repo
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: hipother_repo
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependenciesNvidia }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        os: ${{ job.os }}
+    - script: 'ls -1R $(Agent.BuildDirectory)/rocm'
+      displayName: 'Artifact listing'
+  # compile clr
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        componentName: clr
+        cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
+          -DHIP_PLATFORM=nvidia
+          -DHIPCC_BIN_DIR=$(Agent.BuildDirectory)/rocm/bin
+          -DCLR_BUILD_HIP=ON
+          -DCLR_BUILD_OCL=OFF
+          -DHIPNV_DIR=$(Build.SourcesDirectory)/hipother/hipnv
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        artifactName: nvidia
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
+    #     pipModules: ${{ parameters.pipModules }}
+    #     environment: nvidia

.azuredevops/components/HIPIFY.yml

@@ -1,4 +1,7 @@
 parameters:
+- name: componentName
+  type: string
+  default: HIPIFY
 - name: checkoutRepo
   type: string
   default: 'self'
@@ -13,113 +16,140 @@ parameters:
 - name: aptPackages
   type: object
   default:
-    - cmake
-    - ninja-build
+    - cuda-toolkit-12-9
+    - libcudnn9-dev-cuda-12
     - libnuma-dev
+    - mesa-common-dev
+    - ninja-build
+    - python-is-python3
     - python3-dev
     - python3-pip
-    - python-is-python3
-    - mesa-common-dev
-    - ccache
-    - cuda-toolkit
-    - cudnn
+- name: pipModules
+  type: object
+  default:
+    - lit
+- name: rocmDependencies
+  type: object
+  default:
+    - llvm-project
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
+    testJobs:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: HIPIFY
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  - name: UPSTREAM_LLVM_GIT_URL
-    value: https://github.com/llvm/llvm-project.git
-  - name: UPSTREAM_LLVM_TAG
-    value: llvmorg-18.1.2
-  pool: ${{ variables.MEDIUM_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - task: Bash@3
-    displayName: 'Register CUDA packages'
-    inputs:
-      targetType: inline
-      script: |
-        wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
-        sudo dpkg -i cuda-keyring_1.1-1_all.deb
-        sudo rm -f cuda-keyring_1.1-1_all.deb
-        sudo apt update
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - task: Bash@3
-    displayName: git clone upstream llvm-project
-    inputs:
-      targetType: inline
-      script: git clone $(UPSTREAM_LLVM_GIT_URL) --depth=1 --branch $(UPSTREAM_LLVM_TAG) --recurse-submodules
-      workingDirectory: $(Pipeline.Workspace)
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - script: |
-      mkdir -p $(CCACHE_DIR)
-      echo "##vso[task.prependpath]/usr/lib/ccache:/usr/local/cuda/bin"
-    displayName: Update path for cuda and ccache
-  - task: Cache@2
-    displayName: Ccache caching
-    inputs:
-      key: HIPIFY | $(Agent.OS) | "$(UPSTREAM_LLVM_TAG)"
-      path: $(CCACHE_DIR)
-      restoreKeys: HIPIFY | $(Agent.OS)
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: upstream-llvm
-      cmakeBuildDir: $(Pipeline.Workspace)/llvm-project/llvm/build
-      cmakeSourceDir: $(Pipeline.Workspace)/llvm-project/llvm
-      installDir: $(Pipeline.Workspace)/llvm
-      extraBuildFlags: >-
-        -DCMAKE_BUILD_TYPE=Release
-        -DLLVM_ENABLE_PROJECTS=clang
-        -DLLVM_INCLUDE_TESTS=OFF
-        -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
-        -DCMAKE_C_COMPILER_LAUNCHER=ccache
-        -GNinja
-  - task: Bash@3
-    displayName: python install lit
-    inputs:
-      targetType: inline
-      script: sudo python3 $(Pipeline.Workspace)/llvm-project/llvm/utils/lit/setup.py install
-  - task: Bash@3
-    displayName: install FileCheck
-    inputs:
-      targetType: inline
-      script: cp $(Pipeline.Workspace)/llvm-project/llvm/build/bin/FileCheck $(Pipeline.Workspace)/llvm/bin
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: HIPIFY
-      extraBuildFlags: >-
-        -DHIPIFY_CLANG_TESTS=ON
-        -DCMAKE_BUILD_TYPE=Release
-        -DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda/targets/x86_64-linux
-        -DCUDA_DNN_ROOT_DIR=/usr/local/cuda/targets/x86_64-linux
-        -DCMAKE_PREFIX_PATH=$(Pipeline.Workspace)/llvm;/usr/local/cuda/targets/x86_64-linux/lib
-        -DLLVM_EXTERNAL_LIT=$(Pipeline.Workspace)/llvm-project/llvm/build/bin/llvm-lit
-      multithreadFlag: -- -j32
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: HIPIFY
-      testDir: $(Build.SourcesDirectory)/build
-      testExecutable: make
-      testParameters: test-hipify
-      testPublishResults: false
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      environment: combined
-      registerCUDAPackages: true
-      extraCopyDirectories:
-        - llvm-project
-      extraEnvVars:
-        - UPSTREAM_LLVM_GIT_URL:::https://github.com/llvm/llvm-project.git
-        - UPSTREAM_LLVM_TAG:::llvmorg-18.1.2
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        name: rocm-ci_medium_build_pool_2404
+      ${{ else }}:
+        name: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - task: Bash@3
+      displayName: 'Register CUDA packages'
+      inputs:
+        targetType: inline
+        ${{ if eq(job.os, 'ubuntu2204') }}:
+          script: |
+            wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
+            sudo dpkg -i cuda-keyring_1.1-1_all.deb
+            sudo rm -f cuda-keyring_1.1-1_all.deb
+            sudo apt update
+        ${{ if eq(job.os, 'almalinux8') }}:
+          script: |
+            sudo dnf config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-rhel8.repo
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - task: Bash@3
+      displayName: Add lit to PATH
+      inputs:
+        targetType: inline
+        script: |
+          site_packages=$(python3 -m site --user-base)/bin
+          sudo ln -sf $site_packages/bin/lit $(Pipeline.Workspace)/llvm-lit
+          echo "##vso[task.prependpath]$site_packages"
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+    # cutensor is not available from apt or dnf
+    - task: Bash@3
+      displayName: 'Download and install cutensor'
+      inputs:
+        targetType: inline
+        script: |
+          wget -q --show-progress https://developer.download.nvidia.com/compute/cutensor/redist/libcutensor/linux-x86_64/libcutensor-linux-x86_64-2.2.0.0-archive.tar.xz
+          tar -xvJf libcutensor-linux-x86_64-*.tar.xz
+          mkdir -p $(Pipeline.Workspace)/cutensor
+          cp -r libcutensor-linux-x86_64-*/* $(Pipeline.Workspace)/cutensor/
+    - task: Bash@3
+      displayName: 'List downloaded CUDA files'
+      inputs:
+        targetType: inline
+        script: ls -la1R /usr/local/cuda-12.9
+    # script: cp $(Pipeline.Workspace)/llvm-project/llvm/build/bin/FileCheck $(Pipeline.Workspace)/llvm/bin
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;/usr/local/cuda/targets/x86_64-linux/lib
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
+          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
+          -DHIPIFY_CLANG_TESTS=ON
+          -DCMAKE_BUILD_TYPE=Release
+          -DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda-12.9
+          -DCUDA_DNN_ROOT_DIR=/usr/local/cuda-12.9
+          -DCUDA_CUB_ROOT_DIR=/usr/local/cuda-12.9/targets/x86_64-linux/include/cub
+          -DCUDA_TENSOR_ROOT_DIR=$(Pipeline.Workspace)/cutensor/
+        multithreadFlag: -- -j32
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+    #  parameters:
+    #    componentName: HIPIFY
+    #    testDir: $(Build.SourcesDirectory)/build
+    #    testExecutable: make
+    #    testParameters: -j 32 test-hipify
+    #    testPublishResults: false
+    #    os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: combined
+          registerCUDAPackages: true
+          extraCopyDirectories:
+            - llvm-project

.azuredevops/components/MIOpen.yml

@@ -16,6 +16,7 @@ parameters:
     - cmake
     - jq
     - libdrm-dev
+    - libmsgpack-dev
     - libsqlite3-dev
     - libstdc++-12-dev
     - ninja-build

.azuredevops/components/MIVisionX.yml

@@ -43,18 +43,20 @@ parameters:
 - name: rocmDependencies
   type: object
   default:
-    - rocm-cmake
-    - llvm-project
-    - ROCR-Runtime
+    - AMDMIGraphX
     - clr
+    - half
+    - hipBLAS-common
+    - hipBLASLt
+    - llvm-project
+    - MIOpen
+    - rocBLAS
+    - rocDecode
+    - rocm-cmake
     - rocminfo
     - rocprofiler-register
-    - half
-    - rocBLAS
-    - MIOpen
-    - AMDMIGraphX
+    - ROCR-Runtime
     - rpp
-    - rocDecode
 - name: rocmTestDependencies
   type: object
   default:
@@ -90,8 +92,7 @@ jobs:
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
-    pool:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
     workspace:
       clean: all
     steps:

.azuredevops/components/ROCR-Runtime.yml

@@ -20,7 +20,6 @@ parameters:
     - libnuma-dev
     - ninja-build
     - pkg-config
-    - python3-pip
 - name: rocmDependencies
   type: object
   default:
@@ -36,51 +35,65 @@ parameters:
 - name: jobMatrix
   type: object
   default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: ROCR_Runtime_build
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        -DBUILD_SHARED_LIBS=ON
-        -DCMAKE_BUILD_TYPE=Release
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ROCR_Runtime_build_${{ job.os }}
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DBUILD_SHARED_LIBS=ON
+          -DCMAKE_BUILD_TYPE=Release
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ROCR_Runtime_test_${{ job.target }}
-    dependsOn: ROCR_Runtime_build
+  - job: ROCR_Runtime_test_${{ job.os }}_${{ job.target }}
+    dependsOn: ROCR_Runtime_build_${{ job.os }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -97,6 +110,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - task: Bash@3
       displayName: Install libhwloc5
       inputs:
@@ -107,12 +121,15 @@ jobs:
           sudo apt install -y --allow-downgrades ./libhwloc5_1.11.12-3_amd64.deb ./libhwloc-dev_1.11.12-3_amd64.deb
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
@@ -121,11 +138,13 @@ jobs:
         runRocminfo: false
     - task: Bash@3
       displayName: Build kfdtest
-      continueOnError: true
       inputs:
         targetType: 'inline'
         workingDirectory: $(Build.SourcesDirectory)/libhsakmt/tests/kfdtest
         script: |
+          if [ -e /opt/rh/gcc-toolset-14/enable ]; then
+            source /opt/rh/gcc-toolset-14/enable
+          fi
           mkdir build && cd build
           cmake -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm ..
           make
@@ -135,13 +154,16 @@ jobs:
         testExecutable: BIN_DIR=$(Build.SourcesDirectory)/libhsakmt/tests/kfdtest/build ./run_kfdtest.sh
         testParameters: '-p core --gtest_output=xml:./test_output.xml --gtest_color=yes'
         testDir: $(Build.SourcesDirectory)/libhsakmt/tests/kfdtest/scripts
+        os: ${{ job.os }}
     - task: Bash@3
       displayName: Build rocrtst
-      continueOnError: true
       inputs:
         targetType: 'inline'
         workingDirectory: $(Build.SourcesDirectory)/rocrtst/suites/test_common
         script: |
+          if [ -e /opt/rh/gcc-toolset-14/enable ]; then
+            source /opt/rh/gcc-toolset-14/enable
+          fi
           BASE_CLANG_DIR=$(Agent.BuildDirectory)/rocm/llvm/lib/clang
           export NEWEST_CLANG_VER=$(ls -1 $BASE_CLANG_DIR | sort -V | tail -n 1)
           mkdir build && cd build
@@ -159,6 +181,7 @@ jobs:
         testExecutable: ./rocrtst64
         testParameters: '--gtest_filter="-rocrtstNeg.Memory_Negative_Tests:rocrtstFunc.Memory_Max_Mem" --gtest_output=xml:./test_output.xml --gtest_color=yes'
         testDir: $(Build.SourcesDirectory)/rocrtst/suites/test_common/build/${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/ROCdbgapi.yml

@@ -15,7 +15,6 @@ parameters:
   default:
     - cmake
     - ninja-build
-    - python3-pip
 - name: rocmDependencies
   type: object
   default:
@@ -24,37 +23,57 @@ parameters:
     - rocminfo
     - ROCR-Runtime
 
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
+
 jobs:
-- job: ROCdbgapi
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DCMAKE_BUILD_TYPE=Release
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ROCdbgapi_build_${{ job.os }}
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/ROCgdb.yml

@@ -1,4 +1,7 @@
 parameters:
+- name: componentName
+  type: string
+  default: ROCgdb
 - name: checkoutRepo
   type: string
   default: 'self'
@@ -23,8 +26,10 @@ parameters:
     - libgmp-dev
     - liblzma-dev
     - libmpfr-dev
-    - pkg-config
     - ncurses-dev
+    - pkg-config
+    - python3-dev
+    - python3-pip
     - texinfo
     - zlib1g-dev
 - name: rocmDependencies
@@ -40,67 +45,87 @@ parameters:
 - name: jobMatrix
   type: object
   default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: ROCgdb
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  - name: PKG_CONFIG_PATH
-    value: $(Agent.BuildDirectory)/rocm/share/pkgconfig
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-autotools.yml
-    parameters:
-      configureFlags: >-
-        --program-prefix=roc
-        --enable-64-bit-bfd
-        --enable-targets="x86_64-linux-gnu,amdgcn-amd-amdhsa"
-        --disable-ld
-        --disable-gas
-        --disable-gdbserver
-        --disable-sim
-        --enable-tui
-        --disable-gdbtk
-        --disable-shared
-        --disable-gprofng
-        --with-expat
-        --with-system-zlib
-        --without-guile
-        --with-babeltrace
-        --with-lzma
-        --with-python=python3
-        --with-rocm-dbgapi=$(Agent.BuildDirectory)/rocm
-        LDFLAGS="-Wl,--enable-new-dtags,-rpath=$(Agent.BuildDirectory)/rocm/lib"
-      makeCallPrefix: LD_RUN_PATH='${ORIGIN}/../lib'
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: PKG_CONFIG_PATH
+      value: $(Agent.BuildDirectory)/rocm/share/pkgconfig
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        name: rocm-ci_medium_build_pool_2404
+      ${{ else }}:
+        name: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-autotools.yml
+      parameters:
+        os: ${{ job.os }}
+        configureFlags: >-
+          --program-prefix=roc
+          --enable-64-bit-bfd
+          --enable-targets="x86_64-linux-gnu,amdgcn-amd-amdhsa"
+          --disable-ld
+          --disable-gas
+          --disable-gdbserver
+          --disable-sim
+          --enable-tui
+          --disable-gdbtk
+          --disable-shared
+          --disable-gprofng
+          --with-expat
+          --with-system-zlib
+          --without-guile
+          --with-babeltrace
+          --with-lzma
+          --with-python=python3
+          --with-rocm-dbgapi=$(Agent.BuildDirectory)/rocm
+          LDFLAGS="-Wl,--enable-new-dtags,-rpath=$(Agent.BuildDirectory)/rocm/lib"
+        makeCallPrefix: LD_RUN_PATH='${ORIGIN}/../lib'
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ROCgdb_test_${{ job.target }}
-    dependsOn: ROCgdb
+  - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -119,18 +144,23 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-autotools.yml
       parameters:
+        os: ${{ job.os }}
         configureFlags: >-
           --program-prefix=roc
           --enable-64-bit-bfd
@@ -166,7 +196,9 @@ jobs:
       continueOnError: true
       inputs:
         targetType: inline
-        script: make check-gdb TESTS=gdb.rocm/simple.exp
+        script: |
+          ${{ iif(eq(job.os, 'almalinux8'), 'source /opt/rh/gcc-toolset-14/enable', '') }}
+          make check-gdb TESTS=gdb.rocm/simple.exp
         workingDirectory: $(Build.SourcesDirectory)
     - task: Bash@3
       displayName: print gdb log

.azuredevops/components/Tensile.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: Tensile
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -13,7 +32,6 @@ parameters:
 - name: aptPackages
   type: object
   default:
-    - python3-pip
     - cmake
     - libmsgpack-dev
     - libboost-program-options-dev
@@ -38,75 +56,97 @@ parameters:
 - name: jobMatrix
   type: object
   default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: Tensile_build
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - task: Bash@3
-    displayName: Create wheel file
-    inputs:
-      targetType: inline
-      script: python3 setup.py bdist_wheel
-      workingDirectory: $(Build.SourcesDirectory)
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
-    parameters:
-      sourceDir: $(Build.SourcesDirectory)/dist
-      contentsString: '*.whl'
-      targetDir: $(Build.ArtifactStagingDirectory)
-      clean: false
-  - task: PublishPipelineArtifact@1
-    displayName: 'wheel file Publish'
-    retryCountOnTaskFailure: 3
-    inputs:
-      targetPath: $(Build.ArtifactStagingDirectory)
-  - task: Bash@3
-    displayName: Save pipeline artifact file names
-    inputs:
-      workingDirectory: $(Pipeline.Workspace)
-      targetType: inline
-      script: |
-        whlFile=$(find "$(Build.ArtifactStagingDirectory)" -type f -name "*.whl" | head -n 1)
-        if [ -n "$whlFile" ]; then
-          echo $(basename "$whlFile") >> pipelineArtifacts.txt
-        fi
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn: ${{ parameters.buildDependsOn[job.target] }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: ROCM_PATH
+      value: $(Agent.BuildDirectory)/rocm
+    pool:
+      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - task: Bash@3
+      displayName: Create wheel file
+      inputs:
+        targetType: inline
+        script: python3 setup.py bdist_wheel
+        workingDirectory: $(Agent.BuildDirectory)/s
+    - task: Bash@3
+      displayName: Rename wheel file with job OS
+      inputs:
+        targetType: inline
+        workingDirectory: $(Agent.BuildDirectory)/s
+        script: |
+          wheelFile=$(find "$(Agent.BuildDirectory)/s/dist" -type f -name "*.whl" | head -n 1)
+          newWheelFile="$(basename "$wheelFile" .whl)-${{ job.os }}.whl"
+          mv "$wheelFile" "$(dirname "$wheelFile")/$newWheelFile"
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
+      parameters:
+        sourceDir: $(Agent.BuildDirectory)/s/dist
+        contentsString: '*.whl'
+        targetDir: $(Build.ArtifactStagingDirectory)
+        clean: false
+    - task: PublishPipelineArtifact@1
+      displayName: 'wheel file Publish'
+      retryCountOnTaskFailure: 3
+      inputs:
+        targetPath: $(Build.ArtifactStagingDirectory)
+    - task: Bash@3
+      displayName: Save pipeline artifact file names
+      inputs:
+        workingDirectory: $(Pipeline.Workspace)
+        targetType: inline
+        script: |
+          whlFile=$(find "$(Build.ArtifactStagingDirectory)" -type f -name "*.whl" | head -n 1)
+          if [ -n "$whlFile" ]; then
+            echo $(basename "$whlFile") >> pipelineArtifacts.txt
+          fi
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
+    #     pipModules: ${{ parameters.pipModules }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: Tensile_test_${{ job.target }}
+  - job: Tensile_test_${{ job.os }}_${{ job.target }}
     timeoutInMinutes: 180
-    dependsOn: Tensile_build
+    dependsOn: Tensile_build_${{ job.os }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -126,20 +166,23 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - task: DownloadPipelineArtifact@2
       displayName: 'Download Pipeline Wheel Files'
       inputs:
-        itemPattern: '**/*.whl'
+        itemPattern: '**/*${{ job.os }}*.whl'
         targetPath: $(Agent.BuildDirectory)
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - task: Bash@3
       displayName: pip install
@@ -164,7 +207,7 @@ jobs:
       inputs:
         targetType: inline
         script: tox run -v -e ci -- -m pre_checkin
-        workingDirectory: $(Build.SourcesDirectory)
+        workingDirectory: $(Agent.BuildDirectory)/s
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/amdsmi.yml

@@ -16,50 +16,66 @@ parameters:
     - cmake
     - libdrm-dev
     - ninja-build
-    - python3-pip
     - pkg-config
 
 - name: jobMatrix
   type: object
   default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: ubuntu2404, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: amdsmi_build
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DBUILD_TESTS=ON
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: amdsmi_build_${{ job.os }}
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        vmImage: 'ubuntu-24.04'
+      ${{ else }}:
+        vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DBUILD_TESTS=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: amdsmi_test_${{ job.target }}
-    dependsOn: amdsmi_build
+  - job: amdsmi_test_${{ job.os }}_${{ job.target }}
+    dependsOn: amdsmi_build_${{ job.os }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -76,8 +92,11 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
       parameters:
         runRocminfo: false
@@ -85,8 +104,9 @@ jobs:
       parameters:
         componentName: amdsmi
         testDir: '$(Agent.BuildDirectory)'
-        testExecutable: './rocm/share/amd_smi/tests/amdsmitst'
+        testExecutable: 'sudo ./rocm/share/amd_smi/tests/amdsmitst'
         testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/aomp.yml

@@ -1,4 +1,7 @@
 parameters:
+- name: componentName
+  type: string
+  default: aomp
 - name: checkoutRepo
   type: string
   default: 'self'
@@ -15,173 +18,187 @@ parameters:
 - name: aptPackages
   type: object
   default:
+    - bison
+    - ccache
     - cmake
-    - python3-pip
-    - ninja-build
-    - pkg-config
-    - libpci-dev
-    - libnuma-dev
-    - libffi-dev
-    - git
-    - libopenmpi-dev
+    - flex
     - gawk
+    - git
     - mesa-common-dev
-    - libtool
+    - ninja-build
+    - libbabeltrace-dev
+    - libbison-dev
     - libdrm-amdgpu1
     - libdrm-dev
     - libdw-dev
-    - libgtest-dev
-    - libsystemd-dev
+    - libffi-dev
+    - libgmp-dev
+    - liblzma-dev
+    - libmpfr-dev
+    - libncurses5-dev
+    - libnuma-dev
+    - libopenmpi-dev
+    - libpci-dev
     - libssl-dev
     - libstdc++-12-dev
-    - ccache
-    - libgmp-dev
-    - libmpfr-dev
-    - texinfo
-    - libbison-dev
-    - bison
-    - flex
-    - libbabeltrace-dev
-    - libncurses5-dev
-    - liblzma-dev
-    - python3-setuptools
-    - python3-dev
+    - libsystemd-dev
+    - libtool
     - libudev-dev
     - parallel
-  # Referencing comment snippet.
-  #
-  # snippet from https://github.com/ROCm/aomp/blob/aomp-dev/bin/build_aomp.sh#L131-L134
-  #
-  # For ROCM build (AOMP_STANDALONE_BUILD=0) the components roct, rocr,
-  # libdevice, project, comgr, rocminfo, hipamd, rocdbgapi, rocgdb,
-  # roctracer, rocprofiler, rocm_smi_lib, and amdsmi should be found
-  # in ROCM in /opt/rocm.  The ROCM build only needs these components:
+    - pkg-config
+    - python3-dev
+    - python3-pip
+    - python3-setuptools
+    - texinfo
 - name: rocmDependencies
   type: object
   default:
-    - amdsmi
+    - llvm-project
+    - ROCR-Runtime
+- name: rocmTestDependencies
+  type: object
+  default:
     - clr
     - llvm-project
-    - ROCdbgapi
-    - ROCgdb
-    - rocm-cmake
     - rocm-core
     - rocminfo
-    - rocm_smi_lib
-    - rocprofiler
-    - rocprofiler-register
-    - rocprofiler-sdk
     - ROCR-Runtime
-    - roctracer
+    - rocprofiler-register
 
 - name: jobMatrix
   type: object
   default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: aomp
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.MEDIUM_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-# checkout the repos tied to openmp-extras, plus llvm-project
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: aomp-extras_repo
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: flang_repo
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: llvm-project_repo
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: extras
-      cmakeBuildDir: '$(Build.SourcesDirectory)/aomp-extras/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/aomp-extras'
-      installDir: '$(Build.BinariesDirectory)/llvm'
-      extraBuildFlags: >-
-        -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm
-        -DCMAKE_BUILD_TYPE=Release
-        -DAOMP_STANDALONE_BUILD=0
-        -DAOMP_VERSION_STRING=9.99.99
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: openmp
-      cmakeBuildDir: '$(Build.SourcesDirectory)/llvm-project/openmp/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/llvm-project/openmp'
-      installDir: '$(Build.BinariesDirectory)/llvm'
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Build.BinariesDirectory)"
-        -DCMAKE_BUILD_TYPE=Release
-        -DOPENMP_TEST_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-        -DOPENMP_TEST_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-        -DOPENMP_ENABLE_LIBOMPTARGET=1
-        -DLIBOMP_COPY_EXPORTS=OFF
-        -DLIBOMP_OMPT_SUPPORT=ON
-        -DLIBOMP_OMPD_SUPPORT=ON
-        -DCMAKE_SKIP_INSTALL_RPATH=TRUE
-        -DLLVM_MAIN_INCLUDE_DIR=$(Build.SourcesDirectory)/llvm-project/llvm/include
-        -DLIBOMP_FORTRAN_MODULES_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/flang
-        -DLIBOMP_MODULES_INSTALL_PATH=$(Build.BinariesDirectory)/llvm/include/flang/
-        -GNinja
-  - task: Bash@3
-    displayName: 'ROCm symbolic link'
-    inputs:
-      targetType: inline
-      script: sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: offload
-      cmakeBuildDir: '$(Build.SourcesDirectory)/llvm-project/offload/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/llvm-project/offload'
-      installDir: '$(Build.BinariesDirectory)/llvm'
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Build.BinariesDirectory)"
-        -DCMAKE_BUILD_TYPE=Release
-        -DOPENMP_TEST_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-        -DOPENMP_TEST_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
-        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
-        -DCMAKE_SKIP_INSTALL_RPATH=TRUE
-        -DLLVM_MAIN_INCLUDE_DIR=$(Build.SourcesDirectory)/llvm-project/llvm/include
-        -DLIBOMPTARGET_LLVM_INCLUDE_DIRS=$(Build.SourcesDirectory)/llvm-project/llvm/include
-        -DCMAKE_EXE_LINKER_FLAGS="-L$(Agent.BuildDirectory)/rocm/llvm/lib"
-        -DCMAKE_SHARED_LINKER_FLAGS="-L$(Agent.BuildDirectory)/rocm/llvm/lib"
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        name: rocm-ci_medium_build_pool_2404
+      ${{ else }}:
+        name: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    # checkout the repos tied to openmp-extras, plus llvm-project
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: aomp-extras_repo
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: flang_repo
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: llvm-project_repo
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
+        componentName: extras
+        cmakeBuildDir: '$(Build.SourcesDirectory)/aomp-extras/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/aomp-extras'
+        installDir: '$(Build.BinariesDirectory)/llvm'
+        extraBuildFlags: >-
+          -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm
+          -DCMAKE_BUILD_TYPE=Release
+          -DAOMP_STANDALONE_BUILD=0
+          -DAOMP_VERSION_STRING=9.99.99
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        componentName: openmp
+        cmakeBuildDir: '$(Build.SourcesDirectory)/llvm-project/openmp/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/llvm-project/openmp'
+        installDir: '$(Build.BinariesDirectory)/llvm'
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Build.BinariesDirectory)"
+          -DCMAKE_BUILD_TYPE=Release
+          -DOPENMP_TEST_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
+          -DOPENMP_TEST_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
+          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
+          -DOPENMP_ENABLE_LIBOMPTARGET=1
+          -DLIBOMP_COPY_EXPORTS=OFF
+          -DLIBOMP_OMPD_SUPPORT=ON
+          -DCMAKE_SKIP_INSTALL_RPATH=TRUE
+          -DLLVM_MAIN_INCLUDE_DIR=$(Build.SourcesDirectory)/llvm-project/llvm/include
+          -DLIBOMP_FORTRAN_MODULES_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/flang
+          -DLIBOMP_MODULES_INSTALL_PATH=$(Build.BinariesDirectory)/llvm/include/flang/
+        multithreadFlag: -- -j32
+    - task: Bash@3
+      displayName: 'ROCm symbolic link'
+      inputs:
+        targetType: inline
+        script: sudo ln -s $(Agent.BuildDirectory)/rocm /opt/rocm
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        componentName: offload
+        cmakeBuildDir: '$(Build.SourcesDirectory)/llvm-project/offload/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/llvm-project/offload'
+        installDir: '$(Build.BinariesDirectory)/llvm'
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Build.BinariesDirectory)"
+          -DCMAKE_BUILD_TYPE=Release
+          -DOPENMP_TEST_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
+          -DOPENMP_TEST_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
+          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
+          -DCMAKE_SKIP_INSTALL_RPATH=TRUE
+          -DLLVM_MAIN_INCLUDE_DIR=$(Build.SourcesDirectory)/llvm-project/llvm/include
+          -DLIBOMPTARGET_LLVM_INCLUDE_DIRS=$(Build.SourcesDirectory)/llvm-project/llvm/include
+          -DCMAKE_EXE_LINKER_FLAGS="-L$(Agent.BuildDirectory)/rocm/llvm/lib"
+          -DCMAKE_SHARED_LINKER_FLAGS="-L$(Agent.BuildDirectory)/rocm/llvm/lib"
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: aomp_test_${{ job.target }}
-    dependsOn: aomp
+  - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -198,12 +215,16 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmDependencies }}
+        dependencyList: ${{ parameters.rocmTestDependencies }}
+        os: ${{ job.os }}
     - task: Bash@3
       displayName: ROCm symbolic link
       inputs:
@@ -215,7 +236,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: aomp-extras_repo
-  # these copy steps are from the aomp prototype script for test prep
+    # these copy steps are from the aomp prototype script for test prep
     - task: CopyFiles@2
       displayName: 'Copy AOMP contents'
       inputs:

.azuredevops/components/copyHIP.yml

@@ -1,36 +1,42 @@
 parameters:
-- name: checkoutRepo
-  type: string
-  default: 'self'
-- name: checkoutRef
-  type: string
-  default: ''
+- name: jobMatrix
+  type: object
+  default:
+    copyJobs:
+      - { os: ubuntu2204, backend: amd }
+      - { os: almalinux8, backend: amd }
+      - { os: ubuntu2204, backend: nvidia }
+      - { os: almalinux8, backend: nvidia }
 
 # hip and clr are tightly-coupled
 # run this same template for both repos
 # any changes for clr should just trigger HIP pipeline
 jobs:
-- job: hip_clr_combined
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-# checkout nothing, just copy artifacts from triggering HIP job
-# and then publish for this clr job or for this hipother job to maintain latest
-  - checkout: none
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-download.yml
-    parameters:
-      componentName: HIP
-      pipelineId: $(HIP_PIPELINE_ID)
-  - task: Bash@3
-    displayName: Copy HIP artifacts
-    inputs:
-      targetType: inline
-      script: cp -a $(Agent.BuildDirectory)/rocm/* $(Build.BinariesDirectory)/
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+- ${{ each job in parameters.jobMatrix.copyJobs }}:
+  - job: hip_clr_combined_${{ job.os }}_${{ job.backend }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    workspace:
+      clean: all
+    steps:
+  # checkout nothing, just copy artifacts from triggering HIP job
+  # and then publish for this clr job or for this hipother job to maintain latest
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-download.yml
+      parameters:
+        componentName: HIP
+        pipelineId: $(HIP_PIPELINE_ID)
+        fileFilter: ${{ job.os }}*${{ job.backend }}
+    - task: Bash@3
+      displayName: Copy HIP artifacts
+      inputs:
+        targetType: inline
+        script: cp -a $(Agent.BuildDirectory)/rocm/* $(Build.BinariesDirectory)/
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml

.azuredevops/components/hipBLAS-common.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipBLAS-common
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -14,54 +33,103 @@ parameters:
   type: object
   default:
     - cmake
-    - ninja-build
     - git
+    - ninja-build
     - wget
-    - python3-pip
 - name: rocmDependencies
   type: object
   default:
-    - rocm-cmake
-    - llvm-project
-    - ROCR-Runtime
     - clr
+    - llvm-project
+    - rocm-cmake
     - rocminfo
+    - ROCR-Runtime
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
+# - name: downstreamComponentMatrix
+#   type: object
+#   default:
+#     - hipBLASLt:
+#       name: hipBLASLt
+#       sparseCheckoutDir: projects/hipblaslt
+#       skipUnifiedBuild: 'false'
+#       buildDependsOn:
+#         - hipBLAS_common_build
 
 jobs:
-- job: hipBLAS_common
-  variables:
-  - group: common
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     extraEnvVars:
-  #       - ROCM_PATH:::/home/user/workspace/rocm
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: hipBLAS_common_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: ROCM_PATH
+      value: $(Agent.BuildDirectory)/rocm
+    pool:
+      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+        componentName: ${{ parameters.componentName }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
+    #     extraEnvVars:
+    #       - ROCM_PATH:::/home/user/workspace/rocm
+
+# - ${{ if parameters.triggerDownstreamJobs }}:
+#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+#         parameters:
+#           checkoutRepo: ${{ parameters.checkoutRepo }}
+#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+#           buildDependsOn: ${{ component.buildDependsOn }}
+#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+#           triggerDownstreamJobs: true
+#           unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/hipBLASLt.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipBLASLt
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -13,6 +32,8 @@ parameters:
 - name: aptPackages
   type: object
   default:
+    - ccache
+    - gfortran
     - git
     - libdrm-dev
     - libmsgpack-dev
@@ -20,9 +41,6 @@ parameters:
     - ninja-build
     - python3-pip
     - python3-venv
-    - gfortran
-    - libblas-dev
-    - ccache
 - name: pipModules
   type: object
   default:
@@ -37,6 +55,7 @@ parameters:
     - hipBLAS-common
     - llvm-project
     - rocminfo
+    - rocm-cmake
     - rocm_smi_lib
     - rocprofiler-register
     - ROCR-Runtime
@@ -58,20 +77,37 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+# - name: downstreamComponentMatrix
+#   type: object
+#   default:
+#     - rocBLAS:
+#       name: rocBLAS
+#       sparseCheckoutDir: projects/rocblas
+#       skipUnifiedBuild: 'false'
+#       buildDependsOn:
+#         - hipBLASLt_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipBLASLt_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
     timeoutInMinutes: 300
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -86,6 +122,10 @@ jobs:
     - name: DAY_STRING
       value: $[format('{0:ddMMyyyy}', pipeline.startTime)]
     pool: ${{ variables.ULTRA_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
@@ -93,17 +133,22 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - task: Bash@3
       displayName: Add ROCm binaries to PATH
       inputs:
@@ -111,22 +156,20 @@ jobs:
         script: |
           echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
           echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
-  # Build and install gtest, lapack, hipBLAS-common
-  # $(Pipeline.Workspace)/deps is a temporary folder for the build process
-  # $(Pipeline.Workspace)/s/deps is part of the hipBLASLt repo
-    - script: mkdir $(Pipeline.Workspace)/deps
-      displayName: Create temp folder for external dependencies
-  # hipBLASLt already has a CMake script for external deps, so we can just run that
-  # https://github.com/ROCm/hipBLASLt/blob/develop/deps/CMakeLists.txt
-    - script: cmake $(Pipeline.Workspace)/s/deps
-      displayName: Configure hipBLASLt external dependencies
-      workingDirectory: $(Pipeline.Workspace)/deps
-    - script: make
-      displayName: Build hipBLASLt external dependencies
-      workingDirectory: $(Pipeline.Workspace)/deps
-    - script: sudo make install
-      displayName: Install hipBLASLt external dependencies
-      workingDirectory: $(Pipeline.Workspace)/deps
+    # hipBLASLt has a script for gtest and lapack
+    # https://github.com/ROCm/hipBLASLt/blob/develop/deps/CMakeLists.txt
+    # $(Agent.BuildDirectory)/deps is a temporary folder for the build process
+    # $(Agent.BuildDirectory)/s/deps is part of the hipBLASLt repo
+    - task: Bash@3
+      displayName: Build and install external dependencies
+      inputs:
+        targetType: inline
+        script: |
+          mkdir -p $(Agent.BuildDirectory)/deps
+          cd $(Agent.BuildDirectory)/deps
+          cmake -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/s/deps
+          make
+          sudo make install
     - script: |
         mkdir -p $(CCACHE_DIR)
         echo "##vso[task.prependpath]/usr/lib/ccache"
@@ -134,93 +177,117 @@ jobs:
     - task: Cache@2
       displayName: Ccache caching
       inputs:
-        key: hipBLASLt | $(Agent.OS) | ${{ job.target }} | $(DAY_STRING) | $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+        key: hipBLASLt | ${{ job.os }} | ${{ job.target }} | $(DAY_STRING) | $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
         path: $(CCACHE_DIR)
         restoreKeys: |
-          hipBLASLt | $(Agent.OS) | ${{ job.target }} | $(DAY_STRING)
-          hipBLASLt | $(Agent.OS) | ${{ job.target }}
-          hipBLASLt | $(Agent.OS)
+          hipBLASLt | ${{ job.os }} | ${{ job.target }} | $(DAY_STRING)
+          hipBLASLt | ${{ job.os }} | ${{ job.target }}
+          hipBLASLt | ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
         extraBuildFlags: >-
-          -DCMAKE_BUILD_TYPE=Release
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_INCLUDE_PATH=$(Agent.BuildDirectory)/rocm/llvm/include
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
           -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
           -DCMAKE_C_COMPILER_LAUNCHER=ccache
           -DAMDGPU_TARGETS=${{ job.target }}
-          -DTensile_LOGIC=
-          -DTensile_CPU_THREADS=
-          -DTensile_LIBRARY_FORMAT=msgpack
-          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
           -DBUILD_CLIENTS_TESTS=ON
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        gpuTarget: ${{ job.target }}
-        extraPaths: /home/user/workspace/rocm/llvm/bin:/home/user/workspace/rocm/bin
-        installLatestCMake: true
-        extraEnvVars:
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-          - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/amdclang
-          - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
-          - ROCM_PATH:::/home/user/workspace/rocm
-        extraCopyDirectories:
-          - deps
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          gpuTarget: ${{ job.target }}
+          extraPaths: /home/user/workspace/rocm/llvm/bin:/home/user/workspace/rocm/bin
+          installLatestCMake: true
+          extraEnvVars:
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+            - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/amdclang
+            - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
+            - ROCM_PATH:::/home/user/workspace/rocm
+          extraCopyDirectories:
+            - deps
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipBLASLt_test_${{ job.target }}
-    timeoutInMinutes: 300
-    dependsOn: hipBLASLt_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    - name: ROCM_PATH
-      value: $(Agent.BuildDirectory)/rocm
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipBLASLt
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        testExecutable: './hipblaslt-test'
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes --gtest_filter=*pre_checkin*'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      timeoutInMinutes: 300
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      - name: ROCM_PATH
+        value: $(Agent.BuildDirectory)/rocm
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+        parameters:
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './hipblaslt-test'
+          testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes --gtest_filter=*pre_checkin*'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+# - ${{ if parameters.triggerDownstreamJobs }}:
+#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+#         parameters:
+#           checkoutRepo: ${{ parameters.checkoutRepo }}
+#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+#           buildDependsOn: ${{ component.buildDependsOn }}
+#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+#           triggerDownstreamJobs: true
+#           unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/hipCUB.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipCUB
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -14,9 +33,8 @@ parameters:
   type: object
   default:
     - cmake
-    - ninja-build
-    - libgtest-dev
     - git
+    - ninja-build
     - python3-pip
 - name: rocmDependencies
   type: object
@@ -33,103 +51,143 @@ parameters:
     - llvm-project
     - rocminfo
     - rocPRIM
-    - ROCR-Runtime
     - rocprofiler-register
+    - ROCR-Runtime
 
 - name: jobMatrix
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipCUB_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
         extraBuildFlags: >-
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor"
+          -DBUILD_BENCHMARK=ON
           -DBUILD_TEST=ON
           -DAMDGPU_TARGETS=${{ job.target }}
           -GNinja
+        extraCxxFlags: -Wno-deprecated-declarations
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        gpuTarget: ${{ job.target }}
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipCUB_test_${{ job.target }}
-    dependsOn: hipCUB_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipCUB
-        testDir: '$(Agent.BuildDirectory)/rocm/bin/hipcub'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin/hipcub'
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/hipFFT.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipFFT
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -61,7 +80,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipFFT_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.target }} # todo: add OS
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -79,12 +102,15 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         extraBuildFlags: >-
@@ -102,9 +128,11 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -113,8 +141,8 @@ jobs:
     #     gpuTarget: ${{ job.target }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipFFT_test_${{ job.target }}
-    dependsOn: hipFFT_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -134,6 +162,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
       parameters:
+        preTargetFilter: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
@@ -141,10 +170,12 @@ jobs:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
-        componentName: hipFFT
+        componentName: ${{ parameters.componentName }}
         testDir: '$(Agent.BuildDirectory)/rocm/bin'
         testExecutable: './hipfft-test'
         testParameters: '--test_prob 0.002 --gtest_output=xml:./test_output.xml --gtest_color=yes'

.azuredevops/components/hipRAND.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipRAND
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -14,18 +33,18 @@ parameters:
   type: object
   default:
     - cmake
-    - ninja-build
-    - googletest
     - git
+    - ninja-build
     - python3-pip
 - name: rocmDependencies
   type: object
   default:
-    - llvm-project
-    - ROCR-Runtime
     - clr
+    - llvm-project
+    - rocm-cmake
     - rocminfo
     - rocRAND
+    - ROCR-Runtime
 - name: rocmTestDependencies
   type: object
   default:
@@ -33,110 +52,168 @@ parameters:
     - llvm-project
     - rocminfo
     - rocprofiler-register
-    - ROCR-Runtime
     - rocRAND
+    - ROCR-Runtime
 
 - name: jobMatrix
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+# - name: downstreamComponentMatrix
+#   type: object
+#   default:
+#     - rocFFT:
+#       name: rocFFT
+#       sparseCheckoutDir: projects/rocfft
+#       skipUnifiedBuild: 'false'
+#       buildDependsOn:
+#         - hipRAND_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipRAND_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     - name: HIP_ROCCLR_HOME
       value: $(Build.BinariesDirectory)/rocm
-    pool:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
         extraBuildFlags: >-
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
           -DBUILD_TEST=ON
           -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor"
           -DCMAKE_BUILD_TYPE=Release
           -DAMDGPU_TARGETS=${{ job.target }}
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    #   parameters:
-    #     aptPackages: ${{ parameters.aptPackages }}
-    #     gpuTarget: ${{ job.target }}
-    #     extraEnvVars:
-    #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
+          extraEnvVars:
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipRAND_test_${{ job.target }}
-    dependsOn: hipRAND_build_${{ job.target }}
-    condition:
-        and(succeeded(),
-          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-          eq(${{ parameters.aggregatePipeline }}, False)
-        )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipRAND
-        testDir: '$(Agent.BuildDirectory)/rocm/bin/hipRAND'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+          and(succeeded(),
+            eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+            not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+            eq(${{ parameters.aggregatePipeline }}, False)
+          )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin/hipRAND'
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+# - ${{ if parameters.triggerDownstreamJobs }}:
+#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+#         parameters:
+#           checkoutRepo: ${{ parameters.checkoutRepo }}
+#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+#           buildDependsOn: ${{ component.buildDependsOn }}
+#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+#           triggerDownstreamJobs: true
+#           unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/llvm-project.yml

@@ -14,146 +14,188 @@ parameters:
   type: object
   default:
     - cmake
-    - python3-pip
     - libnuma-dev
     - ninja-build
-    - python-is-python3
-    - zlib1g-dev
     - pkg-config
+    - python-is-python3
+    - python3-pip
+    - zlib1g-dev
 - name: rocmDependencies
   type: object
   default:
     - rocm-cmake
 
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: ubuntu2404, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
+
 jobs:
-- job: llvm_project
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  - name: HIP_DEVICE_LIB_PATH
-    value: '$(Build.BinariesDirectory)/amdgcn/bitcode'
-  - name: HIP_PATH
-    value: '$(Agent.BuildDirectory)/rocm'
-  pool: ${{ variables.ULTRA_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      skipLlvmSymlink: true
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: rocm-llvm
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH="$(Build.BinariesDirectory)/llvm;$(Build.BinariesDirectory)"
-        -DCMAKE_BUILD_TYPE=Release
-        -DLLVM_ENABLE_PROJECTS=clang;lld;clang-tools-extra;mlir;flang
-        -DLLVM_ENABLE_RUNTIMES=compiler-rt;libunwind;libcxx;libcxxabi
-        -DCLANG_ENABLE_AMDCLANG=ON
-        -DLLVM_TARGETS_TO_BUILD=AMDGPU;X86
-        -DLIBCXX_ENABLE_SHARED=OFF
-        -DLIBCXX_ENABLE_STATIC=ON
-        -DLIBCXX_INSTALL_LIBRARY=OFF
-        -DLIBCXX_INSTALL_HEADERS=OFF
-        -DLIBCXXABI_ENABLE_SHARED=OFF
-        -DLIBCXXABI_ENABLE_STATIC=ON
-        -DLIBCXXABI_INSTALL_STATIC_LIBRARY=OFF
-        -DLLVM_BUILD_DOCS=OFF
-        -DLLVM_ENABLE_SPHINX=OFF
-        -DLLVM_ENABLE_ASSERTIONS=OFF
-        -DLLVM_ENABLE_Z3_SOLVER=OFF
-        -DLLVM_ENABLE_ZLIB=ON
-        -DCLANG_DEFAULT_LINKER=lld
-        -DCLANG_DEFAULT_RTLIB=compiler-rt
-        -DCLANG_DEFAULT_UNWINDLIB=libgcc
-        -DSANITIZER_AMDGPU=OFF
-        -DPACKAGE_VENDOR=AMD
-        -DCLANG_LINK_FLANG_LEGACY=ON
-        -DCMAKE_CXX_STANDARD=17
-        -DROCM_LLVM_BACKWARD_COMPAT_LINK=$(Build.BinariesDirectory)/llvm
-        -DROCM_LLVM_BACKWARD_COMPAT_LINK_TARGET=./lib/llvm
-        -GNinja
-      cmakeBuildDir: '$(Build.SourcesDirectory)/llvm/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/llvm'
-      installDir: '$(Build.BinariesDirectory)/llvm'
-# use llvm-lit to run unit tests for llvm, clang, and lld
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: check-llvm
-      testDir: 'llvm/build'
-      testExecutable: './bin/llvm-lit'
-      testParameters: '-q --xunit-xml-output=llvm_test_output.xml --filter-out="live-debug-values-spill-tracking" ./test'
-      testOutputFile: llvm_test_output.xml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: check-clang
-      testDir: 'llvm/build'
-      testExecutable: './bin/llvm-lit'
-      testParameters: '-q --xunit-xml-output=clang_test_output.xml ./tools/clang/test'
-      testOutputFile: clang_test_output.xml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: check-lld
-      testDir: 'llvm/build'
-      testExecutable: './bin/llvm-lit'
-      testParameters: '-q --xunit-xml-output=lld_test_output.xml ./tools/lld/test'
-      testOutputFile: lld_test_output.xml
-  - task: CopyFiles@2
-    displayName: Copy FileCheck for Publishing
-    inputs:
-      CleanTargetFolder: false
-      SourceFolder: llvm/build/bin
-      Contents: FileCheck
-      TargetFolder: $(Build.BinariesDirectory)/llvm/bin
-      retryCount: 3
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: device-libs
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH="$(Build.SourcesDirectory)/llvm/build"
-        -DCMAKE_BUILD_TYPE=Release
-      cmakeBuildDir: '$(Build.SourcesDirectory)/amd/device-libs/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/amd/device-libs'
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: comgr
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH="$(Build.SourcesDirectory)/llvm/build;$(Build.SourcesDirectory)/amd/device-libs/build"
-        -DCOMGR_DISABLE_SPIRV=1
-        -DCMAKE_BUILD_TYPE=Release
-      cmakeBuildDir: '$(Build.SourcesDirectory)/amd/comgr/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/amd/comgr'
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: comgr
-      testParameters: '--output-on-failure --force-new-ctest-process --output-junit comgr_test_output.xml'
-      testDir: 'amd/comgr/build'
-      testOutputFile: comgr_test_output.xml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: hipcc
-      extraBuildFlags: >-
-        -DCMAKE_BUILD_TYPE=Release
-        -DHIPCC_BACKWARD_COMPATIBILITY=OFF
-      cmakeBuildDir: '$(Build.SourcesDirectory)/amd/hipcc/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/amd/hipcc'
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      environment: combined
-      extraEnvVars:
-        - HIP_DEVICE_LIB_PATH:::/home/user/workspace/bin/amdgcn/bitcode
-        - HIP_PATH:::/home/user/workspace/rocm
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: llvm_project_${{ job.os }}
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        name: 'rocm-ci_high_build_pool_2404' #temporarily using 'high' pool while 'ultra' is down
+      ${{ else }}:
+        name: 'rocm-ci_ultra_build_pool'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: HIP_DEVICE_LIB_PATH
+      value: '$(Build.BinariesDirectory)/amdgcn/bitcode'
+    - name: HIP_PATH
+      value: '$(Agent.BuildDirectory)/rocm'
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        skipLlvmSymlink: true
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        componentName: rocm-llvm
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH="$(Build.BinariesDirectory)/llvm;$(Build.BinariesDirectory)"
+          -DCMAKE_BUILD_TYPE=Release
+          -DLLVM_ENABLE_PROJECTS=clang;lld;clang-tools-extra;mlir;flang
+          -DLLVM_ENABLE_RUNTIMES=compiler-rt;libunwind;libcxx;libcxxabi
+          -DCLANG_ENABLE_AMDCLANG=ON
+          -DLLVM_TARGETS_TO_BUILD=AMDGPU;X86
+          -DLIBCXX_ENABLE_SHARED=OFF
+          -DLIBCXX_ENABLE_STATIC=ON
+          -DLIBCXX_INSTALL_LIBRARY=OFF
+          -DLIBCXX_INSTALL_HEADERS=OFF
+          -DLIBCXXABI_ENABLE_SHARED=OFF
+          -DLIBCXXABI_ENABLE_STATIC=ON
+          -DLIBCXXABI_INSTALL_STATIC_LIBRARY=OFF
+          -DLLVM_BUILD_DOCS=OFF
+          -DLLVM_ENABLE_SPHINX=OFF
+          -DLLVM_ENABLE_ASSERTIONS=OFF
+          -DLLVM_ENABLE_Z3_SOLVER=OFF
+          -DLLVM_ENABLE_ZLIB=ON
+          -DCLANG_DEFAULT_LINKER=lld
+          -DCLANG_DEFAULT_RTLIB=compiler-rt
+          -DCLANG_DEFAULT_UNWINDLIB=libgcc
+          -DSANITIZER_AMDGPU=OFF
+          -DPACKAGE_VENDOR=AMD
+          -DCLANG_LINK_FLANG_LEGACY=ON
+          -DCMAKE_CXX_STANDARD=17
+          -DROCM_LLVM_BACKWARD_COMPAT_LINK=$(Build.BinariesDirectory)/llvm
+          -DROCM_LLVM_BACKWARD_COMPAT_LINK_TARGET=./lib/llvm
+          -GNinja
+        cmakeBuildDir: '$(Build.SourcesDirectory)/llvm/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/llvm'
+        installDir: '$(Build.BinariesDirectory)/llvm'
+    # use llvm-lit to run unit tests for llvm, clang, and lld
+    - task: Bash@3
+      displayName: 'Copy llvm-lit to install directory'
+      inputs:
+        targetType: inline
+        script: |
+          cp $(Build.SourcesDirectory)/llvm/build/bin/llvm-lit $(Build.BinariesDirectory)/llvm/bin/
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      parameters:
+        componentName: check-llvm
+        testDir: 'llvm/build'
+        testExecutable: './bin/llvm-lit'
+        testParameters: '-q --xunit-xml-output=llvm_test_output.xml --filter-out="live-debug-values-spill-tracking" ./test'
+        testOutputFile: llvm_test_output.xml
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      parameters:
+        componentName: check-clang
+        testDir: 'llvm/build'
+        testExecutable: './bin/llvm-lit'
+        testParameters: '-q --xunit-xml-output=clang_test_output.xml ./tools/clang/test'
+        testOutputFile: clang_test_output.xml
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      parameters:
+        componentName: check-lld
+        testDir: 'llvm/build'
+        testExecutable: './bin/llvm-lit'
+        testParameters: '-q --xunit-xml-output=lld_test_output.xml ./tools/lld/test'
+        testOutputFile: lld_test_output.xml
+        os: ${{ job.os }}
+    - task: CopyFiles@2
+      displayName: Copy FileCheck for Publishing
+      inputs:
+        CleanTargetFolder: false
+        SourceFolder: llvm/build/bin
+        Contents: FileCheck
+        TargetFolder: $(Build.BinariesDirectory)/llvm/bin
+        retryCount: 3
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        componentName: device-libs
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH="$(Build.SourcesDirectory)/llvm/build"
+          -DCMAKE_BUILD_TYPE=Release
+        cmakeBuildDir: '$(Build.SourcesDirectory)/amd/device-libs/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/amd/device-libs'
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        componentName: comgr
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH="$(Build.SourcesDirectory)/llvm/build;$(Build.SourcesDirectory)/amd/device-libs/build"
+          -DCOMGR_DISABLE_SPIRV=1
+          -DCMAKE_BUILD_TYPE=Release
+        cmakeBuildDir: '$(Build.SourcesDirectory)/amd/comgr/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/amd/comgr'
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      parameters:
+        componentName: comgr
+        testParameters: '--output-on-failure --force-new-ctest-process --output-junit comgr_test_output.xml'
+        testDir: 'amd/comgr/build'
+        testOutputFile: comgr_test_output.xml
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        componentName: hipcc
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -DHIPCC_BACKWARD_COMPATIBILITY=OFF
+        cmakeBuildDir: '$(Build.SourcesDirectory)/amd/hipcc/build'
+        cmakeSourceDir: '$(Build.SourcesDirectory)/amd/hipcc'
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: combined
+          extraEnvVars:
+            - HIP_DEVICE_LIB_PATH:::/home/user/workspace/bin/amdgcn/bitcode
+            - HIP_PATH:::/home/user/workspace/rocm

.azuredevops/components/rccl.yml

@@ -15,7 +15,6 @@ parameters:
   default:
     - cmake
     - git
-    - googletest
     - libboost-program-options-dev
     - libdrm-dev
     - libfftw3-dev
@@ -90,6 +89,10 @@ jobs:
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
         submoduleBehaviour: recursive
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
@@ -101,12 +104,11 @@ jobs:
         extraBuildFlags: >-
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-          -DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
           -DCMAKE_BUILD_TYPE=Release
           -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DBUILD_TESTS=ON
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/share/rocm/cmake;$(Agent.BuildDirectory)/rocm/libexec/hipify
-          -DAMDGPU_TARGETS=${{ job.target }}
+          -DGPU_TARGETS=${{ job.target }}
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:

.azuredevops/components/rocBLAS.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocBLAS
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -64,19 +83,43 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+# - name: downstreamComponentMatrix
+#   type: object
+#   default:
+#     # rocSOLVER depends on both rocBLAS and rocPRIM
+#     # for a unified build, rocBLAS will be the one to call rocSOLVER
+#     - rocSOLVER:
+#       name: rocSOLVER
+#       sparseCheckoutDir: projects/rocsolver
+#       skipUnifiedBuild: 'false'
+#       buildDependsOn:
+#         - rocBLAS_build
+#       unifiedBuild:
+#         downstreamAggregateNames: rocBLAS+rocPRIM
+#         buildDependsOn:
+#           - rocBLAS_build
+#           - rocPRIM_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocBLAS_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -89,6 +132,10 @@ jobs:
     - name: ROCM_PATH
       value: $(Agent.BuildDirectory)/rocm
     pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
@@ -96,19 +143,26 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aocl.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
         extraBuildFlags: >-
           -DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
@@ -128,63 +182,94 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        installAOCL: true
-        gpuTarget: ${{ job.target }}
-        extraEnvVars:
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-          - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
-          - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
-          - ROCM_PATH:::/home/user/workspace/rocm
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          installAOCL: true
+          gpuTarget: ${{ job.target }}
+          extraEnvVars:
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+            - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
+            - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
+            - ROCM_PATH:::/home/user/workspace/rocm
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocBLAS_test_${{ job.target }}
-    dependsOn: rocBLAS_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocBLAS
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        testExecutable: './rocblas-test'
-        testParameters: '--yaml rocblas_smoke.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+        parameters:
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './rocblas-test'
+          testParameters: '--yaml rocblas_smoke.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+# - ${{ if parameters.triggerDownstreamJobs }}:
+#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+#         parameters:
+#           checkoutRepo: ${{ parameters.checkoutRepo }}
+#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+#           triggerDownstreamJobs: true
+#           unifiedBuild: ${{ parameters.unifiedBuild }}
+#           ${{ if parameters.unifiedBuild }}:
+#             buildDependsOn: ${{ component.unifiedBuild.buildDependsOn }}
+#             downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ component.unifiedBuild.downstreamAggregateNames }}
+#           ${{ else }}:
+#             buildDependsOn: ${{ component.buildDependsOn }}
+#             downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}

.azuredevops/components/rocDecode.yml

@@ -1,4 +1,7 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocDecode
 - name: checkoutRepo
   type: string
   default: 'self'
@@ -13,29 +16,28 @@ parameters:
 - name: aptPackages
   type: object
   default:
-    - python3-pip
     - cmake
-    - ninja-build
-    - pkg-config
     - ffmpeg
     - libavcodec-dev
     - libavformat-dev
     - libavutil-dev
+    - libdrm-dev
     - libstdc++-12-dev
     - libva-amdgpu-dev
     - mesa-amdgpu-va-drivers
-    - libdrm-dev
+    - ninja-build
+    - pkg-config
     - python3-pip
 - name: rocmDependencies
   type: object
   default:
-    - rocm-cmake
-    - llvm-project
-    - ROCR-Runtime
     - clr
-    - rocminfo
+    - llvm-project
+    - rocm-cmake
     - rocm-core
+    - rocminfo
     - rocprofiler-register
+    - ROCR-Runtime
 - name: rocmTestDependencies
   type: object
   default:
@@ -48,53 +50,70 @@ parameters:
 - name: jobMatrix
   type: object
   default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: rocDecode_build
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  - name: ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DCMAKE_BUILD_TYPE=Release
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     registerROCmPackages: true
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: ROCM_PATH
+      value: $(Agent.BuildDirectory)/rocm
+    pool:
+      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+        registerROCmPackages: true
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_BUILD_TYPE=Release
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
+    #     registerROCmPackages: true
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocDecode_test_${{ job.target }}
-    dependsOn: rocDecode_build
+  - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -114,20 +133,27 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - task: Bash@3
       displayName: Build rocDecode tests
       inputs:
         targetType: inline
         script: |
+          ${{ iif(eq(job.os, 'almalinux8'), 'source /opt/rh/gcc-toolset-14/enable', '') }}
           mkdir rocDecode-tests
           cd rocDecode-tests
           cmake $(Agent.BuildDirectory)/rocm/share/rocdecode/test
@@ -136,6 +162,7 @@ jobs:
       parameters:
         componentName: rocDecode
         testDir: 'rocDecode-tests'
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocFFT.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocFFT
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -59,10 +78,23 @@ parameters:
         target: gfx942
       - gfx90a:
         target: gfx90a
+# - name: downstreamComponentMatrix
+#   type: object
+#   default:
+#     - hipFFT:
+#       name: hipFFT
+#       sparseCheckoutDir: projects/hipfft
+#       skipUnifiedBuild: 'false'
+#       buildDependsOn:
+#         - rocFFT_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocFFT_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }} # todo: un-hardcode OS
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -79,12 +111,15 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         extraBuildFlags: >-
@@ -101,9 +136,11 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -114,8 +151,8 @@ jobs:
           - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocFFT_test_${{ job.target }}
-    dependsOn: rocFFT_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -135,6 +172,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
       parameters:
+        preTargetFilter: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
@@ -142,10 +180,12 @@ jobs:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
-        componentName: rocFFT
+        componentName: ${{ parameters.componentName }}
         testDir: '$(Agent.BuildDirectory)/rocm/bin'
         testExecutable: './rocfft-test'
         testParameters: '--test_prob 0.004 --gtest_output=xml:./test_output.xml --gtest_color=yes'
@@ -154,3 +194,15 @@ jobs:
         aptPackages: ${{ parameters.aptPackages }}
         environment: test
         gpuTarget: ${{ job.target }}
+
+# - ${{ if parameters.triggerDownstreamJobs }}:
+#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+#         parameters:
+#           checkoutRepo: ${{ parameters.checkoutRepo }}
+#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+#           buildDependsOn: ${{ component.buildDependsOn }}
+#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+#           triggerDownstreamJobs: true
+#           unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rocJPEG.yml

@@ -1,4 +1,7 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocJPEG
 - name: checkoutRepo
   type: string
   default: 'self'
@@ -44,32 +47,44 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocJPEG_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     - name: ROCM_PATH
       value: $(Agent.BuildDirectory)/rocm
     pool:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        name: rocm-ci_medium_build_pool_2404
+      ${{ else }}:
+        name: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
@@ -80,17 +95,26 @@ jobs:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
         extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
           -DCMAKE_BUILD_TYPE=Release
           -DGPU_TARGETS=${{ job.target }}
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     #   parameters:
@@ -99,8 +123,8 @@ jobs:
     #     registerROCmPackages: true
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocJPEG_test_${{ job.target }}
-    dependsOn: rocJPEG_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -120,22 +144,28 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - task: Bash@3
       displayName: Build rocJPEG tests
       inputs:
         targetType: inline
         script: |
+          ${{ iif(eq(job.os, 'almalinux8'), 'source /opt/rh/gcc-toolset-14/enable', '') }}
           mkdir rocJPEG-tests
           cd rocJPEG-tests
           cmake $(Agent.BuildDirectory)/rocm/share/rocjpeg/test
@@ -144,6 +174,7 @@ jobs:
       parameters:
         componentName: rocJPEG
         testDir: 'rocJPEG-tests'
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocMLIR.yml

@@ -27,6 +27,7 @@ parameters:
     - numpy
     - tomli
     - scipy
+    - pybind11
 - name: rocmDependencies
   type: object
   default:

.azuredevops/components/rocPRIM.yml

@@ -1,16 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocPRIM
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
-- name: sparseCheckout
-  type: boolean
-  default: false
+# monorepo related parameters
 - name: sparseCheckoutDir
   type: string
   default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -20,18 +33,17 @@ parameters:
   type: object
   default:
     - cmake
-    - ninja-build
-    - libgtest-dev
     - git
+    - ninja-build
     - python3-pip
 - name: rocmDependencies
   type: object
   default:
-    - rocm-cmake
-    - llvm-project
-    - ROCR-Runtime
     - clr
+    - llvm-project
+    - rocm-cmake
     - rocminfo
+    - ROCR-Runtime
 - name: rocmTestDependencies
   type: object
   default:
@@ -45,98 +57,175 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942, shard: 1, shardCount: 3 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx942, shard: 2, shardCount: 3 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx942, shard: 3, shardCount: 3 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a, shard: 1, shardCount: 3 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a, shard: 2, shardCount: 3 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a, shard: 3, shardCount: 3 }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocThrust:
+      name: rocThrust
+      sparseCheckoutDir: projects/rocthrust
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocPRIM_build
+    - hipCUB:
+      name: hipCUB
+      sparseCheckoutDir: projects/hipcub
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocPRIM_build
+    # rocSOLVER depends on both rocBLAS and rocPRIM
+    # for a unified build, rocBLAS will be the one to call rocSOLVER
+    # - rocSOLVER:
+    #   name: rocSOLVER
+    #   sparseCheckoutDir: projects/rocsolver
+    #   skipUnifiedBuild: 'true'
+    #   buildDependsOn:
+    #     - rocPRIM_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocPRIM_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
-        sparseCheckout: ${{ parameters.sparseCheckout }}
         sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
         extraBuildFlags: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-          -DBUILD_BENCHMARK=ON
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor"
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DAMDGPU_TARGETS=${{ job.target }}
+          -DBUILD_BENCHMARK=ON
           -DBUILD_TEST=ON
           -GNinja
+        extraCxxFlags: -Wno-deprecated-declarations
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        gpuTarget: ${{ job.target }}
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocPRIM_test_${{ job.target }}
-    dependsOn: rocPRIM_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocPRIM
-        testDir: '$(Agent.BuildDirectory)/rocm/bin/rocprim'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}_shard_${{ job.shard }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin/rocprim'
+          extraTestParameters: '-I ${{ job.shard }},,${{ job.shardCount }}'
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rocRAND.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocRAND
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -15,18 +34,16 @@ parameters:
   default:
     - cmake
     - git
-    - googletest
-    - libgtest-dev
     - ninja-build
     - python3-pip
 - name: rocmDependencies
   type: object
   default:
-    - rocm-cmake
-    - llvm-project
-    - ROCR-Runtime
     - clr
+    - llvm-project
+    - rocm-cmake
     - rocminfo
+    - ROCR-Runtime
 - name: rocmTestDependencies
   type: object
   default:
@@ -40,56 +57,96 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - hipRAND:
+      name: hipRAND
+      sparseCheckoutDir: projects/hiprand
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocRAND_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocRAND_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     - name: HIP_ROCCLR_HOME
       value: $(Build.BinariesDirectory)/rocm
     pool:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        vmImage: 'ubuntu-24.04'
+      ${{ else }}:
+        name: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        os: ${{ job.os }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
         extraBuildFlags: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-          -DBUILD_TEST=ON
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DAMDGPU_TARGETS=${{ job.target }}
+          -DBUILD_TEST=ON
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     #   parameters:
@@ -98,42 +155,63 @@ jobs:
     #     extraEnvVars:
     #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocRAND_test_${{ job.target }}
-    dependsOn: rocRAND_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocRAND
-        testDir: '$(Agent.BuildDirectory)/rocm/bin/rocRAND'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin/rocRAND'
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rocSOLVER.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocSOLVER
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -26,14 +45,12 @@ parameters:
   type: object
   default:
     - clr
-    - hipSPARSE
     - llvm-project
     - rocBLAS
     - rocm-cmake
     - rocminfo
     - rocPRIM
     - ROCR-Runtime
-    - rocSPARSE
 - name: rocmTestDependencies
   type: object
   default:
@@ -55,33 +72,47 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      # - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocSOLVER_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - task: Bash@3
       displayName: 'Clone lapack'
       inputs:
@@ -92,11 +123,15 @@ jobs:
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         componentName: lapack
+        os: ${{ job.os }}
         extraBuildFlags: >-
           -DCMAKE_BUILD_TYPE=Release
           -DCMAKE_Fortran_FLAGS=-fno-optimize-sibling-calls
@@ -109,6 +144,7 @@ jobs:
         installDir: '$(Pipeline.Workspace)/deps-install'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
         extraBuildFlags: >-
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Pipeline.Workspace)/deps-install
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
@@ -120,56 +156,71 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        gpuTarget: ${{ job.target }}
-        extraCopyDirectories:
-          - deps-install
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
+          extraCopyDirectories:
+            - deps-install
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocSOLVER_test_${{ job.target }}
-    dependsOn: rocSOLVER_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocSOLVER
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        testExecutable: './rocsolver-test'
-        testParameters: '--gtest_filter="*checkin*" --gtest_output=xml:./test_output.xml --gtest_color=yes'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+        parameters:
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './rocsolver-test'
+          testParameters: '--gtest_filter="*checkin*" --gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/rocThrust.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocThrust
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -14,18 +33,17 @@ parameters:
   type: object
   default:
     - cmake
+    - git
     - ninja-build
     - libboost-program-options-dev
-    - googletest
     - libfftw3-dev
-    - git
     - python3-pip
 - name: rocmDependencies
   type: object
   default:
     - clr
-    - hipRAND
     - llvm-project
+    - rocm-cmake
     - rocminfo
     - rocPRIM
     - ROCR-Runtime
@@ -36,104 +54,142 @@ parameters:
     - llvm-project
     - rocminfo
     - rocPRIM
-    - ROCR-Runtime
-    - hipRAND
     - rocprofiler-register
+    - ROCR-Runtime
 
 - name: jobMatrix
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocThrust_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
         extraBuildFlags: >-
           -GNinja
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DROCM_PATH=$(Agent.BuildDirectory)/rocm
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor"
           -DAMDGPU_TARGETS=${{ job.target }}
           -DBUILD_TEST=ON
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        gpuTarget: ${{ job.target }}
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocThrust_test_${{ job.target }}
-    dependsOn: rocThrust_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocThrust
-        testDir: '$(Agent.BuildDirectory)/rocm/bin/rocthrust'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin/rocthrust'
+          testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex "scan.hip"'
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/rocm-cmake.yml

@@ -16,8 +16,6 @@ parameters:
     - doxygen
     - doxygen-doc
     - ninja-build
-    - python3-pip
-    - python3-sphinx
 - name: pipModules
   type: object
   default:
@@ -25,49 +23,75 @@ parameters:
     - cmake==3.20.5
     - ninja
     - rocm-docs-core
+    - sphinx
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: ubuntu2404, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
 
 jobs:
-- job: rocm_cmake
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-  - task: Bash@3
-    displayName: Add CMake to PATH
-    inputs:
-      targetType: inline
-      script: echo "##vso[task.prependpath]$(python3 -m site --user-base)/bin"
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-  - task: Bash@3
-    displayName: CTest setup
-    inputs:
-      targetType: inline
-      script: |
-        python -m pip install -r $(Build.SourcesDirectory)/docs/requirements.txt
-        python -m pip install -r $(Build.SourcesDirectory)/test/docsphinx/docs/.sphinx/requirements.txt
-        git config --global user.email "you@example.com"
-        git config --global user.name "Your Name"
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: rocm-cmake
-      testParameters: '-E "pass-version-parent" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     pipModules: ${{ parameters.pipModules }}
-  #     environment: combined
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: rocm_cmake_${{ job.os }}
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        vmImage: 'ubuntu-24.04'
+      ${{ else }}:
+        vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - task: Bash@3
+      displayName: Add CMake to PATH
+      inputs:
+        targetType: inline
+        script: echo "##vso[task.prependpath]$(python3 -m site --user-base)/bin"
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
+    - task: Bash@3
+      displayName: CTest setup
+      inputs:
+        targetType: inline
+        script: |
+          python -m pip install -r $(Build.SourcesDirectory)/docs/requirements.txt
+          python -m pip install -r $(Build.SourcesDirectory)/test/docsphinx/docs/.sphinx/requirements.txt
+          git config --global user.email "you@example.com"
+          git config --global user.name "Your Name"
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      parameters:
+        componentName: rocm-cmake
+        testParameters: '-E "pass-version-parent" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
+    #     pipModules: ${{ parameters.pipModules }}
+    #     environment: combined

.azuredevops/components/rocm-core.yml

@@ -15,39 +15,61 @@ parameters:
   default:
     - cmake
     - ninja-build
-    - python3-pip
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: ubuntu2404, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
 
 jobs:
-- job: rocm_core
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DCMAKE_CURRENT_BINARY_DIR=$PWD
-        -DCMAKE_CURRENT_SOURCE_DIR=$PWD/../
-        -DCMAKE_VERBOSE_MAKEFILE=1
-        -DCPACK_GENERATOR=DEB
-        -DCPACK_DEBIAN_PACKAGE_RELEASE="local.9999~99.99"
-        -DCPACK_RPM_PACKAGE_RELEASE="local.9999"
-        -DROCM_VERSION="$(NEXT_RELEASE_VERSION)"
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: rocm_core_${{ job.os }}
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        vmImage: 'ubuntu-24.04'
+      ${{ else }}:
+        vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_CURRENT_BINARY_DIR=$PWD
+          -DCMAKE_CURRENT_SOURCE_DIR=$PWD/../
+          -DCMAKE_VERBOSE_MAKEFILE=1
+          -DCPACK_GENERATOR=DEB
+          -DCPACK_DEBIAN_PACKAGE_RELEASE="local.9999~99.99"
+          -DCPACK_RPM_PACKAGE_RELEASE="local.9999"
+          -DROCM_VERSION="$(NEXT_RELEASE_VERSION)"
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocm-examples.yml

@@ -15,6 +15,7 @@ parameters:
   default:
     - cmake
     - libglfw3-dev
+    - libmsgpack-dev
     - libtbb-dev
     - ninja-build
     - python3-pip

.azuredevops/components/rocm_smi_lib.yml

@@ -17,50 +17,66 @@ parameters:
     - libdrm-dev
     - ninja-build
     - pkg-config
-    - python3-pip
 
 - name: jobMatrix
   type: object
   default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: ubuntu2404, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: rocm_smi_lib_build
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DBUILD_TESTS=ON
-        -DROCM_DEP_ROCMCORE=ON
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: rocm_smi_lib_build_${{ job.os }}
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        vmImage: 'ubuntu-24.04'
+      ${{ else }}:
+        vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DBUILD_TESTS=ON
+          -DROCM_DEP_ROCMCORE=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocm_smi_lib_test_${{ job.target }}
-    dependsOn: rocm_smi_lib_build
+  - job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
+    dependsOn: rocm_smi_lib_build_${{ job.os }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -77,8 +93,11 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
       parameters:
         runRocminfo: false
@@ -86,8 +105,9 @@ jobs:
       parameters:
         componentName: rocm_smi_lib
         testDir: '$(Agent.BuildDirectory)'
-        testExecutable: './rocm/share/rocm_smi/rsmitst_tests/rsmitst'
+        testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
         testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocminfo.yml

@@ -17,7 +17,6 @@ parameters:
     - libdrm-amdgpu-dev
     - libdrm-dev
     - ninja-build
-    - python3-pip
 - name: rocmDependencies
   type: object
   default:
@@ -32,49 +31,63 @@ parameters:
 - name: jobMatrix
   type: object
   default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
-- job: rocminfo
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      checkoutRef: ${{ parameters.checkoutRef }}
-      dependencyList: ${{ parameters.rocmDependencies }}
-      aggregatePipeline: ${{ parameters.aggregatePipeline }}
-      skipLlvmSymlink: true
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        -DROCRTST_BLD_TYPE=release
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: rocminfo_build_${{ job.os }}
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+        registerROCmPackages: true
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        skipLlvmSymlink: true
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DROCRTST_BLD_TYPE=release
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
   - job: rocminfo_test_${{ job.target }}
-    dependsOn: rocminfo
+    dependsOn: rocminfo_build_${{ job.os }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -91,14 +104,18 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
       parameters:
         runRocminfo: false
@@ -109,6 +126,7 @@ jobs:
         testExecutable: './rocm/bin/rocminfo'
         testParameters: ''
         testPublishResults: false
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
         componentName: rocm_agent_enumerator
@@ -116,6 +134,7 @@ jobs:
         testExecutable: './rocm/bin/rocm_agent_enumerator'
         testParameters: ''
         testPublishResults: false
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocprofiler-compute.yml

@@ -24,24 +24,28 @@ parameters:
   default:
     - astunparse==1.6.2
     - colorlover
-    - "dash>=1.12.0"
+    - dash-bootstrap-components
+    - dash-svg
+    - "dash>=3.0.0"
+    - kaleido==0.2.1
     - matplotlib
     - "numpy>=1.17.5"
     - "pandas>=1.4.3"
+    - plotext
+    - plotille
     - pymongo
     - pyyaml
-    - tabulate
-    - tqdm
-    - dash-svg
-    - dash-bootstrap-components
-    - kaleido
     - setuptools
-    - plotille
+    - tabulate
+    - textual
+    - textual_plotext
+    - textual-fspicker
+    - tqdm
     - mock
     - pytest
     - pytest-cov
     - pytest-xdist
-- name: rocmDependencies
+- name: rocmTestDependencies
   type: object
   default:
     - amdsmi
@@ -114,14 +118,6 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmDependencies }}
-        dependencySource: ${{ job.dependencySource }}
-        gpuTarget: ${{ job.target }}
-        aggregatePipeline: ${{ parameters.aggregatePipeline }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         extraBuildFlags: >-
@@ -165,14 +161,6 @@ jobs:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - task: Bash@3
-      displayName: Add en_US.UTF-8 locale
-      inputs:
-        targetType: inline
-        script: |
-          sudo locale-gen en_US.UTF-8
-          sudo update-locale
-          locale -a
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
@@ -184,9 +172,17 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmDependencies }}
+        dependencyList: ${{ parameters.rocmTestDependencies }}
         dependencySource: ${{ job.dependencySource }}
         gpuTarget: ${{ job.target }}
+    - task: Bash@3
+      displayName: Add en_US.UTF-8 locale
+      inputs:
+        targetType: inline
+        script: |
+          sudo locale-gen en_US.UTF-8
+          sudo update-locale
+          locale -a
     - task: Bash@3
       displayName: Add ROCm binaries to PATH
       inputs:

.azuredevops/components/rocprofiler-register.yml

@@ -15,40 +15,62 @@ parameters:
   default:
     - cmake
     - ninja-build
-    - python3-pip
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: ubuntu2404, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
 
 jobs:
-- job: rocprofiler_register
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      componentName: rocprofiler-register
-      extraBuildFlags: >-
-        -DCMAKE_PREFIX_PATH=$(Build.BinariesDirectory)
-        -DROCPROFILER_REGISTER_BUILD_TESTS=ON
-        -DROCPROFILER_REGISTER_BUILD_SAMPLES=ON
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: rocprofiler-register
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-  #   parameters:
-  #     aptPackages: ${{ parameters.aptPackages }}
-  #     environment: combined
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: rocprofiler_register_${{ job.os }}
+    pool:
+      ${{ if eq(job.os, 'ubuntu2404') }}:
+        vmImage: 'ubuntu-24.04'
+      ${{ else }}:
+        vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        componentName: rocprofiler-register
+        os: ${{ job.os }}
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Build.BinariesDirectory)
+          -DROCPROFILER_REGISTER_BUILD_TESTS=ON
+          -DROCPROFILER_REGISTER_BUILD_SAMPLES=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+      parameters:
+        componentName: rocprofiler-register
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+    #   parameters:
+    #     aptPackages: ${{ parameters.aptPackages }}
+    #     environment: combined

.azuredevops/components/rocprofiler-sdk.yml

@@ -14,10 +14,12 @@ parameters:
   type: object
   default:
     - build-essential
+    - cmake
     - libdrm-amdgpu-dev
     - libdrm-dev
     - libdw-dev
     - libelf-dev
+    - libsqlite3-dev
     - libva-dev
     - ninja-build
     - pkg-config
@@ -74,8 +76,7 @@ jobs:
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
-    pool:
-      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
     workspace:
       clean: all
     steps:

.azuredevops/components/rocprofiler.yml

@@ -1,4 +1,7 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocprofiler
 - name: checkoutRepo
   type: string
   default: 'self'
@@ -15,7 +18,6 @@ parameters:
   type: object
   default:
     - cmake
-    - libgtest-dev
     - libdrm-dev
     - libdw-dev
     - libsystemd-dev
@@ -26,13 +28,13 @@ parameters:
 - name: pipModules
   type: object
   default:
-    - pyyaml==5.3.1
-    - Cppheaderparser
-    - websockets
-    - matplotlib
-    - lxml
     - barectf
+    - Cppheaderparser
+    - lxml
+    - matplotlib
     - pandas
+    - pyyaml==5.3.1
+    - websockets
 - name: rocmDependencies
   type: object
   default:
@@ -41,29 +43,33 @@ parameters:
     - ROCdbgapi
     - rocm-cmake
     - rocm-core
-    - rocm_smi_lib
     - rocminfo
-    - ROCR-Runtime
+    - rocm_smi_lib
     - rocprofiler-register
+    - ROCR-Runtime
     - roctracer
 
 - name: jobMatrix
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocprofiler_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -72,6 +78,10 @@ jobs:
     - name: ROCM_PATH
       value: $(Agent.BuildDirectory)/rocm
     pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
@@ -79,46 +89,59 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
         extraBuildFlags: >-
-          -DCMAKE_MODULE_PATH=$(Build.SourcesDirectory)/cmake_modules;$(Agent.BuildDirectory)/rocm/lib/cmake;$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_MODULE_PATH=$(Build.SourcesDirectory)/cmake_modules;$(Agent.BuildDirectory)/rocm/lib/cmake;$(Agent.BuildDirectory)/rocm/lib/cmake/hip;$(Agent.BuildDirectory)/rocm/lib64/cmake;$(Agent.BuildDirectory)/rocm/lib64/cmake/hip
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor"
+          -DCMAKE_POSITION_INDEPENDENT_CODE=ON
           -DENABLE_LDCONFIG=OFF
           -DUSE_PROF_API=1
           -DGPU_TARGETS=${{ job.target }}
-          -DAMDGPU_TARGETS=${{ job.target }}
         multithreadFlag: -- -j32
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        gpuTarget: ${{ job.target }}
-        extraEnvVars:
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-          - ROCM_PATH:::/home/user/workspace/rocm
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          gpuTarget: ${{ job.target }}
+          extraEnvVars:
+            - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+            - ROCM_PATH:::/home/user/workspace/rocm
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocprofiler_test_${{ job.target }}
-    dependsOn: rocprofiler_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -139,16 +162,21 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      parameters:
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
@@ -157,12 +185,14 @@ jobs:
         testExecutable:  ./run.sh
         testParameters: ''
         testPublishResults: false
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
         componentName: rocprofilerV2
         testDir: $(Agent.BuildDirectory)/rocm
         testExecutable:  share/rocprofiler/tests/runUnitTests
         testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/roctracer.yml

@@ -1,4 +1,7 @@
 parameters:
+- name: componentName
+  type: string
+  default: roctracer
 - name: checkoutRepo
   type: string
   default: 'self'
@@ -18,7 +21,7 @@ parameters:
     - graphviz
     - libdrm-amdgpu-dev
     - ninja-build
-    - python3-pip
+    - zlib1g-dev
 - name: pipModules
   type: object
   default:
@@ -45,26 +48,32 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      - { os: almalinux8, packageManager: dnf, target: gfx942 }
+      - { os: almalinux8, packageManager: dnf, target: gfx90a }
+      - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+      - { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: roctracer_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
-    - name: HIP_ROCCLR_HOME
-      value: $(Build.BinariesDirectory)/rocm
     pool:
       vmImage: ${{ variables.BASE_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
     workspace:
       clean: all
     steps:
@@ -72,6 +81,7 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
@@ -83,21 +93,27 @@ jobs:
         dependencyList: ${{ parameters.rocmDependencies }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        os: ${{ job.os }}
+    # the linker flags will not affect ubuntu2204 builds as the paths do not exist
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        os: ${{ job.os }}
+        useAmdclang: false
         extraBuildFlags: >-
           -DCMAKE_BUILD_TYPE=release
           -DROCM_PATH=$(Agent.BuildDirectory)/rocm
-          -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
+          -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip;$(Agent.BuildDirectory)/rocm/lib64/cmake/hip
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
           -DGPU_TARGETS=${{ job.target }}
-          -DAMDGPU_TARGETS=${{ job.target }}
+          -DCMAKE_POSITION_INDEPENDENT_CODE=ON
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -108,8 +124,8 @@ jobs:
     #     registerROCmPackages: true
 
 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: roctracer_test_${{ job.target }}
-    dependsOn: roctracer_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
     condition:
       and(succeeded(),
         eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -127,17 +143,20 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
       parameters:
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmTestDependencies }}
         gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
       parameters:
@@ -146,6 +165,7 @@ jobs:
         testParameters: ''
         testDir: $(Agent.BuildDirectory)
         testPublishResults: false
+        os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}

.azuredevops/dependencies/gtest.yml

@@ -11,36 +11,54 @@ parameters:
 - name: aptPackages
   type: object
   default:
-    - git
     - cmake
+    - git
     - ninja-build
 
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
+
 jobs:
-- job: gtest
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - task: Bash@3
-    displayName: 'git clone gtest'
-    inputs:
-      targetType: inline
-      script: git clone -b ${{ parameters.gtestVersion }} https://github.com/google/googletest --depth=1 --shallow-submodules --recurse-submodules
-      workingDirectory: $(Agent.BuildDirectory)
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      cmakeBuildDir: $(Agent.BuildDirectory)/googletest/build
-      cmakeSourceDir: $(Agent.BuildDirectory)/googletest
-      extraBuildFlags: >-
-        -DGTEST_FORCE_SHARED_CRT=ON
-        -DCMAKE_DEBUG_POSTFIX=d
-        -GNinja
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: gtest_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone GTest ${{ parameters.gtestVersion }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/google/googletest -b ${{ parameters.gtestVersion }} --depth=1 --shallow-submodules --recurse-submodules
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/googletest/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/googletest
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DGTEST_FORCE_SHARED_CRT=ON
+          -DCMAKE_DEBUG_POSTFIX=d
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/nightly/pytorch.yml

@@ -4,71 +4,71 @@ parameters:
 - name: aptPackages
   type: object
   default:
-    - build-essential
-    - git
-    - ninja-build
-    - openjdk-8-jdk
-    - ca-certificates
+    - autoconf
     - bc
     - bridge-utils
+    - build-essential
+    - ca-certificates
+    - ccache
     - devscripts
     - dkms
     - doxygen
+    - fakeroot
+    - ffmpeg
+    - gfortran
+    - git
+    - gnutls-bin
+    - libamd2
+    - libavformat-dev
+    - libblas3
+    - libcamd2
+    - libccolamd2
+    - libcholmod3
+    - libcolamd2
     - libdpkg-dev
     - libdpkg-perl
+    - libdrm-amdgpu1
+    - libdrm-dev
     - libelf-dev
+    - libfreetype-dev
+    - libgfortran5
+    - libgomp1
+    - libjpeg-dev
+    - libjpeg-turbo-official
+    - liblapack-dev
+    - liblapack3
+    - libmetis5
+    - libncurses-dev
+    - libnuma-dev
+    - libopenblas-dev
+    - libpth-dev
+    - libquadmath0
+    - libssh-dev
+    - libstdc++-12-dev
+    - libsuitesparseconfig5
+    - libswscale-dev
+    - libtinfo-dev
+    - libunwind-dev
+    - libwebp-dev
+    - llvm-dev
+    - ncurses-base
+    - ninja-build
+    - numactl
+    - openjdk-8-jdk
+    - python-is-python3
     - python3-dev
     - python3-pip
     - python3-venv
-    - wget
-    - ncurses-base
-    - libncurses-dev
-    - numactl
-    - libnuma-dev
-    - libssh-dev
-    - libunwind-dev
-    - llvm-dev
-    - libpth-dev
     - qemu-kvm
     - re2c
     - subversion
-    - fakeroot
-    - autoconf
-    - libgomp1
-    - libtinfo-dev
-    - libcholmod3
-    - libsuitesparseconfig5
-    - libstdc++-12-dev
-    - python-is-python3
-    - gfortran
-    - libgfortran5
-    - liblapack3
-    - libblas3
-    - libquadmath0
-    - libmetis5
-    - libamd2
-    - libcamd2
-    - libcolamd2
-    - libccolamd2
-    - libdrm-amdgpu1
-    - ccache
+    - wget
     - zip
-    - libjpeg-turbo-official
-    - libjpeg-dev
-    - libwebp-dev
-    - libfreetype-dev
-    - gnutls-bin
-    - ffmpeg
-    - libopenblas-dev
-    - liblapack-dev
-    - libswscale-dev
-    - libavformat-dev
 - name: pipModules
   type: object
   default:
-    - cmake
     - astunparse
-    - "expecttest>=0.2.1"
+    - "expecttest>=0.3.0"
     - hypothesis
     - numpy
     - psutil
@@ -76,8 +76,8 @@ parameters:
     - requests
     - setuptools==75.8.0
     - types-dataclasses
-    - "typing-extensions>=4.8.0"
-    - "sympy>=1.13.0"
+    - "typing-extensions>=4.10.0"
+    - "sympy>=1.13.3"
     - filelock
     - networkx
     - jinja2
@@ -97,36 +97,39 @@ parameters:
 - name: rocmDependencies
   type: object
   default:
-    - rocminfo
-    - MIOpen
     - clr
     - hipBLAS
+    - hipBLASLt
     - hipFFT
     - hipRAND
     - hipSOLVER
     - hipSPARSE
-    - ROCR-Runtime
+    - hipSPARSELt
     - llvm-project
+    - MIOpen
     - rccl
     - rocBLAS
     - rocFFT
+    - rocm-core
+    - rocminfo
     - rocm_smi_lib
+    - rocPRIM
+    - rocprofiler-register
     - rocRAND
+    - ROCR-Runtime
     - rocSOLVER
     - rocSPARSE
     - roctracer
-    - hipBLASLt
-    - rocprofiler-register
-    - rocm-core
-    - rocPRIM
     # below are additional dependencies not called out by build script, but throw errors during cmake
+    - composable_kernel
+    - hipBLAS-common
     - hipCUB
     - rocThrust
-    - hipBLAS-common
-    - composable_kernel
 - name: rocmTestDependencies
   type: object
   default:
+    # rocroller.so needed and is not included in the wheel
+    - hipBLASLt
     - rocminfo
 # Reference on what tests to run for torchvision found in private repo:
 # https://github.com/ROCm/rocAutomation/blob/jenkins-pipelines/pytorch/pytorch_ci/test_pytorch_test1.sh#L54
@@ -240,12 +243,6 @@ jobs:
         git clone https://github.com/pytorch/builder.git --depth=1 --recurse-submodules
         sudo ln -s $(Build.SourcesDirectory)/builder /builder
       workingDirectory: $(Build.SourcesDirectory)
-  - task: Bash@3
-    displayName: Temporarily Patch CK Submodule
-    inputs:
-      targetType: inline
-      script: git pull origin develop
-      workingDirectory: $(Build.SourcesDirectory)/pytorch/third_party/composable_kernel
   - task: Bash@3
     displayName: Install patchelf
     inputs:
@@ -267,6 +264,11 @@ jobs:
       script: |
         sudo bash pytorch/.ci/docker/common/install_rocm_magma.sh $(MAGMA_ROCM)
       workingDirectory: $(Build.SourcesDirectory)
+  - task: Bash@3
+    displayName: Install targeted typing_extensions for build
+    inputs:
+      targetType: inline
+      script: pip install --target=$(Build.SourcesDirectory)/pytorch/torch/.. typing_extensions
   - task: Bash@3
     displayName: Run ROCm Build Script
     inputs:
@@ -281,7 +283,6 @@ jobs:
         PYTORCH_ROOT=$(PYTORCH_ROOT)
         CMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
         DESIRED_DEVTOOLSET=$(DESIRED_DEVTOOLSET)
-        TORCH_PACKAGE_NAME=torch.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
         PYTORCH_BUILD_VERSION=$(cat $(Build.SourcesDirectory)/pytorch/version.txt | cut -da -f1)
         PYTORCH_BUILD_NUMBER=$(date -u +%Y%m%d)
         SKIP_ALL_TESTS=1
@@ -322,8 +323,6 @@ jobs:
       inputs:
         targetType: inline
         script: >-
-          TORCH_PACKAGE_NAME=torch.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
-          TORCHVISION_PACKAGE_NAME=torchvision.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
           PYTORCH_VERSION=$(cat $(Build.SourcesDirectory)/pytorch/version.txt | cut -da -f1)post$(date -u +%Y%m%d)
           BUILD_VERSION=$(cat $(Build.SourcesDirectory)/vision/version.txt | cut -da -f1)post$(date -u +%Y%m%d)
           python3 setup.py bdist_wheel
@@ -400,11 +399,9 @@ jobs:
   - task: DownloadPipelineArtifact@2
     displayName: 'Download Pipeline Wheel Files'
     inputs:
-      itemPattern: '**/*$(JOB_GPU_TARGET)*.whl'
+      itemPattern: '**/*.whl'
       targetPath: $(Agent.BuildDirectory)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    parameters:
-      dependencySource: staging
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
     parameters:
       dependencyList: ${{ parameters.rocmTestDependencies }}

.azuredevops/nightly/rocm-nightly.yml

@@ -3,12 +3,21 @@ parameters:
 - name: jobList
   type: object
   default:
-    - gfx942-staging:
-      target: gfx942
-      source: staging
-    - gfx90a-staging:
-      target: gfx90a
-      source: staging
+    - { os: ubuntu2204, target: gfx942, source: staging }
+    - { os: ubuntu2204, target: gfx90a, source: staging }
+    - { os: ubuntu2204, target: gfx1201, source: staging }
+    - { os: ubuntu2204, target: gfx1100, source: staging }
+    - { os: ubuntu2204, target: gfx1030, source: staging }
+    - { os: ubuntu2404, target: gfx942, source: staging }
+    - { os: ubuntu2404, target: gfx90a, source: staging }
+    - { os: ubuntu2404, target: gfx1201, source: staging }
+    - { os: ubuntu2404, target: gfx1100, source: staging }
+    - { os: ubuntu2404, target: gfx1030, source: staging }
+    - { os: almalinux8, target: gfx942, source: staging }
+    - { os: almalinux8, target: gfx90a, source: staging }
+    - { os: almalinux8, target: gfx1201, source: staging }
+    - { os: almalinux8, target: gfx1100, source: staging }
+    - { os: almalinux8, target: gfx1030, source: staging }
 - name: rocmDependencies
   type: object
   default:
@@ -16,9 +25,9 @@ parameters:
     - amdsmi
     - aomp-extras
     - aomp
+    - clr
     - composable_kernel
     - half
-    - HIP
     - hip-tests
     - hipBLAS
     - hipBLAS-common
@@ -83,7 +92,7 @@ schedules:
 
 jobs:
 - ${{ each job in parameters.jobList }}:
-  - job: rocm_nightly_${{ job.target }}_${{ job.source }}
+  - job: rocm_nightly_${{ job.os }}_${{ job.target }}_${{ job.source }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -108,9 +117,9 @@ jobs:
       parameters:
         dependencySource: ${{ job.source }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
         skipLibraryLinking: true
-        skipLlvmSymlink: true
     - script: df -h
       displayName: System disk space after ROCm
     - script: du -sh $(Agent.BuildDirectory)/rocm

.azuredevops/tag-builds/clr.yml

@@ -28,12 +28,22 @@ resources:
     endpoint: ROCm
     name: ROCm/hipother
     ref: ${{ parameters.checkoutRef }}
+  pipelines:
+  - pipeline: hip_pipeline
+    source: \experimental\HIP
+    trigger: true
+  - pipeline: hipother_pipeline
+    source: \experimental\hipother
+    trigger: true
 
 trigger: none
 pr: none
 
 jobs:
-  - template: ${{ variables.CI_COMPONENT_PATH }}/HIP.yml
-    parameters:
-      checkoutRepo: release_repo
-      checkoutRef: ${{ parameters.checkoutRef }}
+  - ${{ if eq(variables['Build.Reason'], 'ResourceTrigger') }}:
+    - template: ${{ variables.CI_COMPONENT_PATH }}/copyHIP.yml@pipelines_repo
+  - ${{ if ne(variables['Build.Reason'], 'ResourceTrigger') }}:
+    - template: ${{ variables.CI_COMPONENT_PATH }}/HIP.yml@pipelines_repo
+      parameters:
+        checkoutRepo: release_repo
+        checkoutRef: ${{ parameters.checkoutRef }}

.azuredevops/templates/steps/artifact-download.yml

@@ -19,36 +19,27 @@ parameters:
   default: false
 
 steps:
-- task: Bash@3
-  displayName: Set allowPartiallySucceededBuilds
-  inputs:
-    targetType: inline
-    script: |
-      if [[ ",$ALLOWED_PARTIAL_SUCCEED_BUILDS," == *",${{ parameters.componentName }},"* ]]; then
-        echo "##vso[task.setvariable variable=allowPartiallySucceededBuilds;]true"
-      else
-        echo "##vso[task.setvariable variable=allowPartiallySucceededBuilds;]false"
-      fi
 - task: DownloadPipelineArtifact@2
   displayName: Download ${{ parameters.componentName }}
   inputs:
-    ${{ if eq(parameters.aggregatePipeline, false) }}:
-      buildType: 'specific'
-      project: ROCm-CI
-      definition: ${{ parameters.pipelineId }}
-      specificBuildWithTriggering: true
-      itemPattern: '**/*${{ parameters.fileFilter }}*'
-      # aomp is a special case, since the trigger file is under ROCm/ROCm instead of the component repo
-      ${{ if notIn(parameters.componentName, 'aomp') }}:
-        buildVersionToDownload: latestFromBranch # default is 'latest'
-      branchName: refs/heads/${{ parameters.branchName }}
-      allowPartiallySucceededBuilds: $(allowPartiallySucceededBuilds)
-      targetPath: '$(Pipeline.Workspace)/d'
-    ${{ else }}:
+    ${{ if parameters.aggregatePipeline }}:
       buildType: 'current'
       itemPattern: '**/${{ parameters.componentName }}*${{ parameters.fileFilter }}*'
-      allowPartiallySucceededBuilds: $(allowPartiallySucceededBuilds)
+      allowPartiallySucceededBuilds: true
       targetPath: '$(Pipeline.Workspace)/d'
+    ${{ else }}:
+      buildType: 'specific'
+      project: ROCm-CI
+      specificBuildWithTriggering: true
+      allowPartiallySucceededBuilds: true
+      definition: ${{ parameters.pipelineId }}
+      itemPattern: '**/*${{ parameters.fileFilter }}*'
+      targetPath: '$(Pipeline.Workspace)/d'
+      branchName: refs/heads/${{ parameters.branchName }}
+      ${{ if eq(parameters.componentName, 'aomp') }}:
+        buildVersionToDownload: latest # aomp trigger lives in ROCm/ROCm, so cannot use ROCm/aomp branch names
+      ${{ else }}:
+        buildVersionToDownload: latestFromBranch
 - task: ExtractFiles@1
   displayName: Extract ${{ parameters.componentName }}
   inputs:

.azuredevops/templates/steps/artifact-upload.yml

@@ -3,15 +3,21 @@
 # publish can be toggled off for jobs that produce multiple tarballs
 # for those cases, only publish the last call which puts all the tarballs in one container folder
 parameters:
-- name: artifactName
+- name: componentName
   type: string
-  default: 'drop'
-- name: publish
-  type: boolean
-  default: true
+  default: $(Build.DefinitionName)
 - name: gpuTarget
   type: string
   default: ''
+- name: artifactName
+  type: string
+  default: drop
+- name: publish
+  type: boolean
+  default: true
+- name: os
+  type: string
+  default: 'ubuntu2204'
 
 steps:
 - task: ArchiveFiles@2
@@ -20,7 +26,7 @@ steps:
     includeRootFolder: false
     archiveType: 'tar'
     tarCompression: 'gz'
-    archiveFile: '$(Build.ArtifactStagingDirectory)/$(Build.DefinitionName)_$(Build.BuildId)_$(Build.BuildNumber)_ubuntu2204_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.tar.gz'
+    archiveFile: '$(Build.ArtifactStagingDirectory)/${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}_$(System.JobAttempt).tar.gz'
 - task: DeleteFiles@1
   displayName: 'Cleanup Staging Area'
   inputs:
@@ -32,7 +38,7 @@ steps:
   inputs:
     workingDirectory: $(Pipeline.Workspace)
     targetType: inline
-    script: echo "$(Build.DefinitionName)_$(Build.BuildId)_$(Build.BuildNumber)_ubuntu2204_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.tar.gz" >> pipelineArtifacts.txt
+    script: echo "${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}_$(System.JobAttempt).tar.gz" >> pipelineArtifacts.txt
 # then publish it
 - ${{ if parameters.publish }}:
   - task: PublishPipelineArtifact@1
@@ -40,4 +46,5 @@ steps:
     displayName: '${{ parameters.artifactName }} Publish'
     retryCountOnTaskFailure: 3
     inputs:
+      artifactName: ${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}_$(System.JobAttempt)
       targetPath: '$(Build.ArtifactStagingDirectory)'

.azuredevops/templates/steps/build-autotools.yml

@@ -1,4 +1,7 @@
 parameters:
+- name: os
+  type: string
+  default: 'ubuntu2204'
 - name: componentName
   type: string
   default: ''
@@ -20,17 +23,23 @@ steps:
   displayName: '${{ parameters.componentName }} configure flags'
   inputs:
     targetType: inline
-    script: ./configure --prefix=${{ parameters.installDir }} ${{ parameters.configureFlags }}
     workingDirectory: ${{ parameters.buildDir }}
+    script: |
+      ${{ iif(eq(parameters.os, 'almalinux8'), 'source /opt/rh/gcc-toolset-14/enable', '') }}
+      ./configure --prefix=${{ parameters.installDir }} ${{ parameters.configureFlags }}
 - task: Bash@3
   displayName: '${{ parameters.componentName }} make'
   inputs:
     targetType: inline
-    script: ${{ parameters.makeCallPrefix }} make -j$(nproc)
     workingDirectory: ${{ parameters.buildDir }}
+    script: |
+      ${{ iif(eq(parameters.os, 'almalinux8'), 'source /opt/rh/gcc-toolset-14/enable', '') }}
+      ${{ parameters.makeCallPrefix }} make -j$(nproc)
 - task: Bash@3
   displayName: '${{ parameters.componentName }} make install'
   inputs:
     targetType: inline
-    script: make install
     workingDirectory: ${{ parameters.buildDir }}
+    script: |
+      ${{ iif(eq(parameters.os, 'almalinux8'), 'source /opt/rh/gcc-toolset-14/enable', '') }}
+      make install

.azuredevops/templates/steps/build-cmake.yml

@@ -1,10 +1,16 @@
 parameters:
+- name: os
+  type: string
+  default: 'ubuntu2204'
 - name: componentName
   type: string
   default: ''
 - name: extraBuildFlags
   type: string
   default: ''
+- name: extraCxxFlags
+  type: string
+  default: ''
 - name: multithreadFlag
   type: string
   default: ''
@@ -32,41 +38,81 @@ parameters:
 - name: installEnabled
   type: boolean
   default: true
+# for jobs that rebuild during install step and use ninja
+# set to true to save time, only applies for almalinux8
+- name: consolidateBuildAndInstall
+  type: boolean
+  default: false
 - name: printDiskSpace
   type: boolean
   default: true
+# todo: make this control cxx and c compiler flags
+- name: useAmdclang
+  type: boolean
+  default: true
+
+# for cmake calls, set env variables for AlmaLinux 8
+# to simulate running source /opt/rh/gcc-toolset-14/enable for the session
 
 steps:
 # create workingDirectory if it does not exist and change into it
 # call cmake from within that directory using $cmakeArgs as its parameters
 - task: CMake@1
   displayName: '${{parameters.componentName }} CMake Flags'
+  ${{ if eq(parameters.os, 'almalinux8')}}:
+    env:
+      PATH: "/opt/rh/gcc-toolset-14/root/usr/bin:$(PATH)"
+      MANPATH: "/opt/rh/gcc-toolset-14/root/usr/share/man:$(MANPATH)"
+      INFOPATH: "/opt/rh/gcc-toolset-14/root/usr/share/info:$(INFOPATH)"
+      PCP_DIR: "/opt/rh/gcc-toolset-14/root"
+      LD_LIBRARY_PATH: "/opt/rh/gcc-toolset-14/root/usr/lib64:/opt/rh/gcc-toolset-14/root/usr/lib:$(LD_LIBRARY_PATH)"
+      PKG_CONFIG_PATH: "/opt/rh/gcc-toolset-14/root/usr/lib64/pkgconfig:$(PKG_CONFIG_PATH)"
   inputs:
     workingDirectory: ${{ parameters.cmakeBuildDir }}
-    ${{ if eq(parameters.customInstallPath, true) }}:
-      cmakeArgs: -DCMAKE_INSTALL_PREFIX=${{ parameters.installDir }} ${{ parameters.extraBuildFlags }} ${{ parameters.cmakeSourceDir }}
-    ${{ else }}:
-      cmakeArgs: ${{ parameters.extraBuildFlags }} ${{ parameters.cmakeSourceDir }}
+    cmakeArgs: >-
+      ${{ iif(parameters.customInstallPath, join('', format('-DCMAKE_INSTALL_PREFIX={0}', parameters.installDir)), '') }}
+      ${{ iif(eq(parameters.os, 'almalinux8'), '-DCMAKE_SHARED_LINKER_FLAGS="-L$(Agent.BuildDirectory)/rocm/lib64 -L/opt/rh/gcc-toolset-14/root/usr/lib/gcc/x86_64-redhat-linux/14/"', '') }}
+      ${{ iif(eq(parameters.os, 'almalinux8'), '-DCMAKE_EXE_LINKER_FLAGS="-L$(Agent.BuildDirectory)/rocm/lib64 -L/opt/rh/gcc-toolset-14/root/usr/lib/gcc/x86_64-redhat-linux/14/"', '') }}
+      -DCMAKE_CXX_FLAGS="${{ parameters.extraCxxFlags }} ${{ iif(and(eq(parameters.os, 'almalinux8'), parameters.useAmdclang), '--gcc-toolchain=/opt/rh/gcc-toolset-14/root', '') }}"
+      ${{ parameters.extraBuildFlags }}
+      ${{ parameters.cmakeSourceDir }}
 - ${{ if parameters.printDiskSpace }}:
   - script: df -h
     displayName: Disk space before build
 # equivalent to running make $cmakeTargetDir from $cmakeBuildDir
 # i.e., cd $cmakeBuildDir; make $cmakeTargetDir
 - task: CMake@1
-  displayName: '${{parameters.componentName }} Build'
+  ${{ if and( eq(parameters.os, 'almalinux8'), eq(parameters.consolidateBuildAndInstall , true)) }}:
+    displayName: '${{ parameters.componentName }} CMake Build and Install'
+  ${{ else }}:
+    displayName: '${{ parameters.componentName }} CMake Build'
+  ${{ if eq(parameters.os, 'almalinux8')}}:
+    env:
+      PATH: "/opt/rh/gcc-toolset-14/root/usr/bin:$(PATH)"
+      MANPATH: "/opt/rh/gcc-toolset-14/root/usr/share/man:$(MANPATH)"
+      INFOPATH: "/opt/rh/gcc-toolset-14/root/usr/share/info:$(INFOPATH)"
+      PCP_DIR: "/opt/rh/gcc-toolset-14/root"
+      LD_LIBRARY_PATH: "/opt/rh/gcc-toolset-14/root/usr/lib64:/opt/rh/gcc-toolset-14/root/usr/lib:$(LD_LIBRARY_PATH)"
+      PKG_CONFIG_PATH: "/opt/rh/gcc-toolset-14/root/usr/lib64/pkgconfig:$(PKG_CONFIG_PATH)"
   inputs:
     workingDirectory: ${{ parameters.cmakeBuildDir }}
-    ${{ if eq(parameters.customBuildTarget, '') }}:
-      cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} ${{ parameters.multithreadFlag }}'
-    ${{ else }}:
-      cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} --target ${{ parameters.customBuildTarget }} ${{ parameters.multithreadFlag }}'
-    retryCountOnTaskFailure: 10
+    ${{ if eq(parameters.os, 'almalinux8') }}:
+      cmakeArgs: >-
+        --build ${{ parameters.cmakeTargetDir }}
+        ${{ iif(and(eq(parameters.consolidateBuildAndInstall, true), ne(parameters.cmakeTarget, '')), format('--target {0}', parameters.cmakeTarget), '') }}
+        ${{ iif(and(ne(parameters.customBuildTarget, ''), ne(parameters.consolidateBuildAndInstall, true)), format('--target {0}', parameters.customBuildTarget), '') }}
+        ${{ parameters.multithreadFlag }}
+    ${{ if ne(parameters.os, 'almalinux8') }}:
+      cmakeArgs: >-
+        --build ${{ parameters.cmakeTargetDir }}
+        ${{ iif(ne(parameters.customBuildTarget, ''), format('--target {0}', parameters.customBuildTarget), '') }}
+        ${{ parameters.multithreadFlag }}
 - ${{ if parameters.printDiskSpace }}:
   - script: df -h
     displayName: Disk space after build
 # equivalent to running make $cmakeTarget from $cmakeBuildDir
 # e.g., make install
-- ${{ if eq(parameters.installEnabled, true) }}:
+- ${{ if and(eq(parameters.installEnabled, true), or(ne(parameters.os, 'almalinux8'), eq(parameters.consolidateBuildAndInstall, false))) }}:
   - task: CMake@1
     displayName: '${{parameters.componentName }} ${{ parameters.cmakeTarget }}'
     inputs:

.azuredevops/templates/steps/checkout.yml

@@ -4,9 +4,6 @@ parameters:
 - name: checkoutRepo
   type: string
   default: 'self'
-- name: sparseCheckout
-  type: boolean
-  default: false
 - name: sparseCheckoutDir
   type: string
   default: ''
@@ -22,10 +19,10 @@ steps:
     submodules: ${{ parameters.submoduleBehaviour }}
     retryCountOnTaskFailure: 3
     fetchFilter: blob:none
-    ${{ if eq(parameters.sparseCheckout, true) }}:
+    ${{ if ne(parameters.sparseCheckoutDir, '') }}:
       sparseCheckoutDirectories: ${{ parameters.sparseCheckoutDir }}
       path: sparse
-  - ${{ if eq(parameters.sparseCheckout, true) }}:
+  - ${{ if ne(parameters.sparseCheckoutDir, '') }}:
     - task: Bash@3
       displayName: Symlink sparse checkout
       inputs:

.azuredevops/templates/steps/dependencies-apt.yml

@@ -0,0 +1,42 @@
+parameters:
+- name: aptPackages
+  type: object
+  default: []
+- name: registerROCmPackages
+  type: boolean
+  default: false
+
+steps:
+- ${{ if eq(parameters.registerROCmPackages, true) }}:
+  - task: Bash@3
+    displayName: 'Register AMDGPU & ROCm repos (apt)'
+    inputs:
+      targetType: inline
+      script: |
+        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
+        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$(REPO_RADEON_VERSION)/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION) jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
+        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
+        sudo apt update
+- task: Bash@3
+  displayName: 'sudo apt-get update'
+  inputs:
+    targetType: inline
+    script: |
+      echo "deb http://archive.ubuntu.com/ubuntu/ jammy main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
+      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
+      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-backports main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
+      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-security main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
+      sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update
+- task: Bash@3
+  displayName: 'sudo apt-get fix'
+  inputs:
+    targetType: inline
+    script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-broken install
+- ${{ if gt(length(parameters.aptPackages), 0) }}:
+  - task: Bash@3
+    displayName: 'sudo apt-get install ...'
+    inputs:
+      targetType: inline
+      script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-missing install ${{ join(' ', parameters.aptPackages) }}

.azuredevops/templates/steps/dependencies-aqlprofile.yml

@@ -1,25 +1,44 @@
+parameters:
+- name: os
+  type: string
+  default: ubuntu2204
+
 steps:
 - task: Bash@3
   displayName: Get aqlprofile package name
   inputs:
     targetType: inline
-    script: |
-      export packageName=$(curl -s https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb")
-      echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
+    ${{ if eq(parameters.os, 'ubuntu2204') }}:
+      script: |
+        export packageName=$(curl -s https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb")
+        echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
+    ${{ if eq(parameters.os, 'almalinux8') }}:
+      script: |
+        export packageName=$(curl -s https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/ | grep -oP "hsa-amd-aqlprofile-[^\"]+\.rpm" | head -n1)
+        echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
 - task: Bash@3
   displayName: 'Download aqlprofile'
   inputs:
     targetType: inline
-    script: wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$(packageName)
     workingDirectory: '$(Pipeline.Workspace)'
+    ${{ if eq(parameters.os, 'ubuntu2204') }}:
+      script: wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$(packageName)
+    ${{ if eq(parameters.os, 'almalinux8') }}:
+      script: wget -nv https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/$(packageName)
 - task: Bash@3
   displayName: 'Extract aqlprofile'
   inputs:
     targetType: inline
-    script: |
-      mkdir hsa-amd-aqlprofile
-      dpkg-deb -R $(packageName) hsa-amd-aqlprofile
     workingDirectory: '$(Pipeline.Workspace)'
+    ${{ if eq(parameters.os, 'ubuntu2204') }}:
+      script: |
+        mkdir hsa-amd-aqlprofile
+        dpkg-deb -R $(packageName) hsa-amd-aqlprofile
+    ${{ if eq(parameters.os, 'almalinux8') }}:
+      script: |
+        mkdir hsa-amd-aqlprofile
+        sudo dnf -y install rpm-build cpio
+        rpm2cpio $(packageName) | (cd hsa-amd-aqlprofile && cpio -idmv)
 - task: Bash@3
   displayName: 'Copy aqlprofile files'
   inputs:

.azuredevops/templates/steps/dependencies-boost.yml

@@ -1,35 +0,0 @@
-steps:
-- task: DownloadPipelineArtifact@2
-  displayName: Download Boost
-  inputs:
-    buildType: specific
-    project: ROCm-CI
-    definition: $(BOOST_DEPENDENCY_PIPELINE_ID)
-    targetPath: $(Pipeline.Workspace)/d
-- task: ExtractFiles@1
-  displayName: Extract Boost
-  inputs:
-    archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
-    destinationFolder: $(Agent.BuildDirectory)/boost
-    cleanDestinationFolder: true
-    overwriteExistingFiles: true
-- task: DeleteFiles@1
-  displayName: Cleanup Compressed Boost
-  inputs:
-    SourceFolder: $(Pipeline.Workspace)/d
-    Contents: '**/*.tar.gz'
-    RemoveDotFiles: true
-- task: Bash@3
-  displayName: 'List Boost files'
-  inputs:
-    targetType: inline
-    script: ls -1R $(Agent.BuildDirectory)/boost
-- task: Bash@3
-  displayName: 'Link Boost shared libraries'
-  inputs:
-    targetType: inline
-    script: |
-      echo $(Agent.BuildDirectory)/boost/lib | sudo tee /etc/ld.so.conf.d/boost.conf
-      sudo cat /etc/ld.so.conf.d/boost.conf
-      sudo ldconfig -v
-      ldconfig -p

.azuredevops/templates/steps/dependencies-cmake-latest.yml

@@ -1,10 +1,23 @@
-# replace cmake from apt install with newest version using snap install
 steps:
 - task: Bash@3
-  displayName: update cmake
+  displayName: Install CMake 3.31
   inputs:
     targetType: inline
     script: |
-      sudo apt purge cmake -y
-      sudo snap install cmake --classic --channel=3.31/stable
-      hash -r
+      CMAKE_VERSION=3.31.0
+      CMAKE_ROOT="$(Pipeline.Workspace)/cmake"
+
+      echo "Downloading CMake $CMAKE_VERSION..."
+      curl -fsSL -o cmake.tar.gz https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/cmake-${CMAKE_VERSION}-linux-x86_64.tar.gz
+
+      echo "Extracting to $CMAKE_ROOT..."
+      sudo mkdir -p $CMAKE_ROOT
+      sudo tar --strip-components=1 -xz -C $CMAKE_ROOT -f cmake.tar.gz
+
+      echo "##vso[task.prependpath]$CMAKE_ROOT/bin"
+- task: Bash@3
+  displayName: cmake --version
+  inputs:
+    targetType: inline
+    script: |
+      cmake --version

.azuredevops/templates/steps/dependencies-dnf.yml

@@ -0,0 +1,157 @@
+parameters:
+- name: aptPackages
+  type: object
+  default: []
+- name: registerROCmPackages
+  type: boolean
+  default: false
+# As par of installing gcc toolset and python,
+# the environment will install this base set of dnf packages.
+- name: basePackages
+  type: object
+  default:
+    - epel-release
+    - gcc-toolset-14
+    - gcc-toolset-14-libatomic-devel
+    - git
+    - jq
+    - numactl
+    - python3.11
+    - python3.11-pip
+    - vim-common
+    - wget
+# Instead of defining multiple arrays of packages per component,
+# we define a map of apt package names to dnf package names.
+- name: aptToDnfMap
+  type: object
+  default:
+    bison: bison
+    ccache: ccache
+    cmake: cmake
+    cuda-toolkit-12-9: cuda-compiler-12-9 cuda-toolkit-12-9
+    libcudnn9-dev-cuda-12: libcudnn9-cuda-12
+    dejagnu: dejagnu
+    doxygen: doxygen
+    # note: doxygen-doc is not available in dnf
+    # libavcodec-dev, libavformat-dev, libavutil-dev come with ffmpeg-devel
+    ffmpeg: ffmpeg ffmpeg-devel
+    flex: flex
+    # note: g++ is installed by default with gcc-toolset-14
+    # note: gawk is already installed
+    # note: gcc-toolset-14-gfortran is installed by default with gcc-toolset-14
+    # note: git is in the base packages list
+    graphviz: graphviz
+    libbabeltrace-dev: libbabeltrace-devel
+    libbison-dev: bison-devel
+    libboost-program-options-dev: boost-devel
+    # note: libdrm-amdgpu1 is not available in dnf
+    libdrm-dev: libdrm-devel
+    libdrm-amdgpu-dev: libdrm-amdgpu-devel
+    libdw-dev: elfutils-devel
+    libelf-dev: elfutils-libelf-devel
+    libexpat-dev: expat-devel
+    libffi-dev: libffi-devel
+    libfftw3-dev: fftw-devel
+    libgmp-dev: gmp-devel
+    liblzma-dev: xz-devel
+    libmpfr-dev: mpfr-devel
+    libmsgpack-dev: msgpack-devel
+    libncurses5-dev: ncurses-devel
+    libnuma-dev: numactl-devel
+    libopenmpi-dev: openmpi-devel
+    libpci-dev: libpciaccess-devel
+    libssl-dev: openssl-devel
+    # note: libstdc++-devel is in the base packages list
+    libsystemd-dev: systemd-devel
+    libtool: libtool
+    # note: libudev-dev is part of systemd-devel
+    libva-amdgpu-dev: libva-amdgpu-devel
+    mesa-amdgpu-va-drivers: mesa-amdgpu-va-drivers
+    mesa-common-dev: mesa-libGL-devel
+    ncurses-dev: ncurses-devel
+    # note: llvm needs ninja-build version newer than what dnf provides
+    ocl-icd-libopencl1: ocl-icd
+    ocl-icd-opencl-dev: ocl-icd-devel
+    opencl-headers: opencl-headers
+    parallel: parallel
+    pkg-config: pkgconf-pkg-config
+    # note: python3 is the default python in AlmaLinux 8
+    python3-dev: python3.11-devel
+    # note: python3.11-pip is already installed when updating to python 3.11
+    # note: python3.11-setuptools is already installed when updating to python 3.11
+    texinfo: texinfo
+    zlib1g-dev: zlib-devel
+
+steps:
+- ${{ if eq(parameters.registerROCmPackages, true) }}:
+  - task: Bash@3
+    displayName: 'Register AMDGPU & ROCm repos (dnf)'
+    inputs:
+      targetType: inline
+      script: |
+        sudo rpm --import https://repo.radeon.com/rocm/rocm.gpg.key
+        echo '[amdgpu]' | sudo tee /etc/yum.repos.d/amdgpu.repo > /dev/null
+        echo "name=amdgpu" | sudo tee --append /etc/yum.repos.d/amdgpu.repo
+        echo "baseurl=https://repo.radeon.com/amdgpu/$(REPO_RADEON_VERSION)/rhel/8.10/main/x86_64/" | sudo tee --append /etc/yum.repos.d/amdgpu.repo
+        echo "enabled=1" | sudo tee --append /etc/yum.repos.d/amdgpu.repo
+        echo "gpgcheck=1" | sudo tee --append /etc/yum.repos.d/amdgpu.repo
+        echo "gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key" | sudo tee --append /etc/yum.repos.d/amdgpu.repo
+        echo '[rocm]' | sudo tee /etc/yum.repos.d/rocm.repo > /dev/null
+        echo "name=ROCm$(REPO_RADEON_VERSION)" | sudo tee --append /etc/yum.repos.d/rocm.repo
+        echo "baseurl=https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/" | sudo tee --append /etc/yum.repos.d/rocm.repo
+        echo "enabled=1" | sudo tee --append /etc/yum.repos.d/rocm.repo
+        echo "gpgcheck=1" | sudo tee --append /etc/yum.repos.d/rocm.repo
+        echo "gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key" | sudo tee --append /etc/yum.repos.d/rocm.repo
+        sudo dnf clean all
+        sudo dnf makecache
+- task: Bash@3
+  displayName: 'Install base dnf packages'
+  inputs:
+    targetType: inline
+    script: |
+      sudo dnf config-manager --set-enabled powertools
+      # rpm fusion free repo for some dependencies
+      sudo dnf -y install https://download1.rpmfusion.org/free/el/rpmfusion-free-release-8.noarch.rpm
+      sudo dnf -y install ${{ join(' ', parameters.basePackages) }}
+- task: Bash@3
+  displayName: 'Check gcc environment'
+  inputs:
+    targetType: inline
+    script: |
+      echo "=== Versions and sanity checks ==="
+      gcc --version
+      g++ --version
+      gcc -print-file-name=libstdc++.so
+      g++ -print-file-name=libstdc++.so
+- task: Bash@3
+  displayName: 'Set python 3.11 as default'
+  inputs:
+    targetType: inline
+    script: |
+      sudo dnf -y module disable python36
+      sudo rm -f /usr/local/bin/python3.12 /usr/local/bin/python3.13 /usr/local/bin/python3.14
+      sudo alternatives --set python /usr/bin/python3.11
+      sudo alternatives --set python3 /usr/bin/python3.11
+      python3 --version
+      python3 -m pip install --upgrade pip setuptools wheel
+- ${{ each pkg in parameters.aptPackages }}:
+  # note: llvm needs ninja-build version newer than what dnf provides
+  - ${{ if eq(pkg, 'ninja-build') }}:
+    - task: Bash@3
+      displayName: 'Install ninja 1.11.1'
+      inputs:
+        targetType: inline
+        script: |
+          curl -LO https://github.com/ninja-build/ninja/releases/download/v1.11.1/ninja-linux.zip
+          sudo dnf -y install unzip
+          unzip ninja-linux.zip
+          sudo mv ninja /usr/local/bin/ninja
+          sudo chmod +x /usr/local/bin/ninja
+          echo "##vso[task.prependpath]/usr/local/bin"
+  - ${{ if ne(parameters.aptToDnfMap[pkg], '') }}:
+    - task: Bash@3
+      displayName: 'dnf install ${{ parameters.aptToDnfMap[pkg] }}'
+      inputs:
+        targetType: inline
+        script: |
+          sudo dnf -y install ${{ parameters.aptToDnfMap[pkg] }}

.azuredevops/templates/steps/dependencies-other.yml

@@ -9,56 +9,24 @@ parameters:
 - name: registerROCmPackages
   type: boolean
   default: false
+- name: packageManager
+  type: string
+  default: apt
 
 steps:
-- ${{ if eq(parameters.registerROCmPackages, true) }}:
-  - task: Bash@3
-    displayName: 'Register AMDGPU & ROCm repos'
-    inputs:
-      targetType: inline
-      script: |
-        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
-        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$(REPO_RADEON_VERSION)/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION) jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
-        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
-        sudo apt update
-# firefox takes time to upgrade and is not needed for CI workloads, hold version
-- task: Bash@3
-  continueOnError: true
-  displayName: 'sudo apt-mark hold firefox'
-  inputs:
-    targetType: inline
-    script: sudo apt-mark hold firefox
-- task: Bash@3
-  displayName: 'sudo apt-get update'
-  inputs:
-    targetType: inline
-    script: |
-      echo "deb http://archive.ubuntu.com/ubuntu/ jammy main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-backports main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-security main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
-      sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update
-- task: Bash@3
-  displayName: 'sudo apt-get upgrade'
-  inputs:
-    targetType: inline
-    script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes upgrade
-- task: Bash@3
-  displayName: 'sudo apt-get fix'
-  inputs:
-    targetType: inline
-    script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-broken install
-- ${{ if gt(length(parameters.aptPackages), 0) }}:
-  - task: Bash@3
-    displayName: 'sudo apt-get install ...'
-    inputs:
-      targetType: inline
-      script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-missing install ${{ join(' ', parameters.aptPackages) }}
+- ${{ if eq(parameters.packageManager, 'apt') }}:
+  - template: dependencies-apt.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      registerROCmPackages: ${{ parameters.registerROCmPackages }}
+- ${{ if eq(parameters.packageManager, 'dnf') }}:
+  - template: dependencies-dnf.yml
+    parameters:
+      aptPackages: ${{ parameters.aptPackages }}
+      registerROCmPackages: ${{ parameters.registerROCmPackages }}
 - ${{ if gt(length(parameters.pipModules), 0) }}:
   - task: Bash@3
     displayName: 'pip install  ...'
     inputs:
       targetType: inline
-      script: pip install -v --force-reinstall ${{ join(' ', parameters.pipModules) }}
+      script: python3 -m pip install -v --force-reinstall ${{ join(' ', parameters.pipModules) }}

.azuredevops/templates/steps/dependencies-rocm.yml

@@ -13,6 +13,9 @@ parameters:
 - name: dependencyList
   type: object
   default: []
+- name: os
+  type: string
+  default: 'ubuntu2204'
 - name: gpuTarget
   type: string
   default: ''
@@ -36,6 +39,10 @@ parameters:
 - name: aggregatePipeline
   type: boolean
   default: false
+# monorepo related parameters
+- name: downstreamAggregateNames
+  type: string
+  default: ''
 
 - name: componentVarList
   type: object
@@ -103,7 +110,7 @@ parameters:
     hipCUB:
       pipelineId: $(HIPCUB_PIPELINE_ID)
       stagingBranch: develop
-      mainlineBranch: mainline
+      mainlineBranch: develop
       hasGpuTarget: true
     hipFFT:
       pipelineId: $(HIPFFT_PIPELINE_ID)
@@ -123,7 +130,7 @@ parameters:
     hipRAND:
       pipelineId: $(HIPRAND_PIPELINE_ID)
       stagingBranch: develop
-      mainlineBranch: mainline
+      mainlineBranch: develop
       hasGpuTarget: true
     hipSOLVER:
       pipelineId: $(HIPSOLVER_PIPELINE_ID)
@@ -258,7 +265,7 @@ parameters:
     rocPRIM:
       pipelineId: $(ROCPRIM_PIPELINE_ID)
       stagingBranch: develop
-      mainlineBranch: mainline
+      mainlineBranch: develop
       hasGpuTarget: true
     rocprofiler:
       pipelineId: $(ROCPROFILER_PIPELINE_ID)
@@ -298,7 +305,7 @@ parameters:
     rocRAND:
       pipelineId: $(ROCRAND_PIPELINE_ID)
       stagingBranch: develop
-      mainlineBranch: mainline
+      mainlineBranch: develop
       hasGpuTarget: true
     rocr_debug_agent:
       pipelineId: $(ROCR_DEBUG_AGENT_PIPELINE_ID)
@@ -323,7 +330,7 @@ parameters:
     rocThrust:
       pipelineId: $(ROCTHRUST_PIPELINE_ID)
       stagingBranch: develop
-      mainlineBranch: mainline
+      mainlineBranch: develop
       hasGpuTarget: true
     roctracer:
       pipelineId: $(ROCTRACER_PIPELINE_ID)
@@ -361,7 +368,7 @@ steps:
         pipelineId: ${{ parameters.componentVarList[split(dependency, ':')[0]].pipelineId }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         ${{ if parameters.componentVarList[split(dependency, ':')[0]].hasGpuTarget }}:
-          fileFilter: "${{ split(dependency, ':')[1] }}*${{ parameters.gpuTarget }}"
+          fileFilter: "${{ split(dependency, ':')[1] }}*_${{ parameters.os }}_${{ parameters.gpuTarget }}"
         # dependencySource = staging
         ${{ if eq(parameters.dependencySource, 'staging')}}:
           branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
@@ -384,6 +391,14 @@ steps:
         ${{ else }}:
           branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
 # no colon (:) found in this item in the list
+  - ${{ elseif containsValue(split(parameters.downstreamAggregateNames, '+'), dependency) }}:
+    - template: local-artifact-download.yml
+      parameters:
+        ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
+          gpuTarget: ${{ parameters.gpuTarget }}
+        preTargetFilter: ${{ dependency }}
+        os: ${{ parameters.os }}
+        buildType: current
   - ${{ else }}:
     - template: artifact-download.yml
       parameters:
@@ -391,7 +406,9 @@ steps:
         pipelineId: ${{ parameters.componentVarList[dependency].pipelineId }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
-          fileFilter: ${{ parameters.gpuTarget }}
+          fileFilter: ${{ parameters.os }}_${{ parameters.gpuTarget }}
+        ${{ else }}:
+          fileFilter: ${{ parameters.os }}
         # dependencySource = staging
         ${{ if eq(parameters.dependencySource, 'staging')}}:
           branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
@@ -419,14 +436,16 @@ steps:
     displayName: Symlink from rocm/llvm to rocm/lib/llvm
     inputs:
       targetType: inline
-      script: sudo ln -s $(Agent.BuildDirectory)/rocm/llvm $(Agent.BuildDirectory)/rocm/lib/llvm
+      script: |
+        sudo mkdir -p $(Agent.BuildDirectory)/rocm/lib
+        sudo ln -sr $(Agent.BuildDirectory)/rocm/llvm $(Agent.BuildDirectory)/rocm/lib/llvm
   - task: Bash@3
     displayName: Symlink executables from rocm/llvm/bin to rocm/bin
     inputs:
       targetType: inline
       script: |
         for file in amdclang amdclang++ amdclang-cl amdclang-cpp amdflang amdlld aompcc mygpu mycpu offload-arch; do
-          sudo ln -s $(Agent.BuildDirectory)/rocm/llvm/bin/$file $(Agent.BuildDirectory)/rocm/bin/$file
+          sudo ln -sr $(Agent.BuildDirectory)/rocm/llvm/bin/$file $(Agent.BuildDirectory)/rocm/bin/$file
         done
 # dlopen calls within a ctest or pytest sequence runs into issues when shared library symlink convention is not followed
 # the convention is as follows:
@@ -471,8 +490,10 @@ steps:
       targetType: inline
 # OS ignores if the ROCm lib folder shows up more than once
       script: |
-        echo $(Agent.BuildDirectory)/rocm/lib | sudo tee /etc/ld.so.conf.d/rocm-ci.conf
+        echo $(Agent.BuildDirectory)/rocm/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
         echo $(Agent.BuildDirectory)/rocm/llvm/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
+        echo $(Agent.BuildDirectory)/rocm/lib64 | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
+        echo $(Agent.BuildDirectory)/rocm/llvm/lib64 | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
         sudo cat /etc/ld.so.conf.d/rocm-ci.conf
         sudo ldconfig -v
         ldconfig -p

.azuredevops/templates/steps/dependencies-vendor.yml

@@ -0,0 +1,53 @@
+parameters:
+- name: os
+  type: string
+  default: 'ubuntu2204'
+- name: dependencyList
+  type: object
+- name: pipelineIdList
+  type: object
+  default:
+    boost: 250
+    grpc: 72
+    gtest: 73
+    half560: 68
+    lapack: 69
+
+steps:
+- ${{ each dependency in parameters.dependencyList }}:
+  - task: DownloadPipelineArtifact@2
+    displayName: Download ${{ dependency }}
+    inputs:
+      project: ROCm-CI
+      buildType: specific
+      targetPath: $(Pipeline.Workspace)/d
+      definition: ${{ parameters.pipelineIdList[dependency] }}
+      itemPattern: '**/*${{ parameters.os }}*'
+  - task: ExtractFiles@1
+    displayName: Extract ${{ dependency }}
+    inputs:
+      archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
+      destinationFolder: $(Agent.BuildDirectory)/vendor
+      cleanDestinationFolder: true
+      overwriteExistingFiles: true
+  - task: DeleteFiles@1
+    displayName: Clean up ${{ dependency }}
+    inputs:
+      SourceFolder: $(Pipeline.Workspace)/d
+      Contents: '**/*.tar.gz'
+      RemoveDotFiles: true
+- task: Bash@3
+  displayName: List vendored files
+  inputs:
+    targetType: inline
+    script: ls -la1R $(Agent.BuildDirectory)/vendor
+- task: Bash@3
+  displayName: Link vendored shared libraries
+  inputs:
+    targetType: inline
+    script: |
+      echo $(Agent.BuildDirectory)/vendor/lib | sudo tee -a /etc/ld.so.conf.d/vendor.conf
+      echo $(Agent.BuildDirectory)/vendor/lib64 | sudo tee -a /etc/ld.so.conf.d/vendor.conf
+      sudo cat /etc/ld.so.conf.d/vendor.conf
+      sudo ldconfig -v
+      ldconfig -p

.azuredevops/templates/steps/local-artifact-download.yml

@@ -2,6 +2,9 @@
 # It can be overridden to download any artifact from any pipeline, given the appropriate build/pipeline IDs
 
 parameters:
+  - name: os
+    type: string
+    default: 'ubuntu2204'
   - name: gpuTarget
     type: string
     default: ''
@@ -29,25 +32,27 @@ parameters:
 
 steps:
   - task: DownloadPipelineArtifact@2
-    displayName: 'Download Pipeline Build'
+    displayName: Download ${{ parameters.preTargetFilter}}*${{ parameters.os }}_${{ parameters.gpuTarget}}*${{ parameters.postTargetFilter}}
     inputs:
       ${{ if eq(parameters.buildType, 'specific') }}:
         buildType: specific
         buildVersionToDownload: specific
         project: ROCm-CI
-        definition: ${{ parameters.definitionId }}
-        buildId: ${{ parameters.buildId }}
-      itemPattern: '**/*${{ parameters.preTargetFilter }}*${{ parameters.gpuTarget }}*${{ parameters.postTargetFilter }}*'
+        ${{ if ne(parameters.definitionId, 0) }}:
+          definition: ${{ parameters.definitionId }}
+        ${{ if ne(parameters.buildId, 0) }}:
+          buildId: ${{ parameters.buildId }}
+      itemPattern: '**/*${{ parameters.preTargetFilter }}*${{ parameters.os }}_${{ parameters.gpuTarget }}*${{ parameters.postTargetFilter }}*'
       targetPath: $(Pipeline.Workspace)/d
   - task: ExtractFiles@1
-    displayName: 'Extract Pipeline Build'
+    displayName: Extract ${{ parameters.preTargetFilter}}*${{ parameters.os }}_${{ parameters.gpuTarget}}*${{ parameters.postTargetFilter}}
     inputs:
       archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
       destinationFolder: '$(Agent.BuildDirectory)/rocm'
       cleanDestinationFolder: false
       overwriteExistingFiles: true
   - task: DeleteFiles@1
-    displayName: 'Clean up Compressed Pipeline Build'
+    displayName: Clean up ${{ parameters.preTargetFilter}}*${{ parameters.os }}_${{ parameters.gpuTarget}}*${{ parameters.postTargetFilter}}
     inputs:
       SourceFolder: '$(Pipeline.Workspace)/d'
       Contents: '/**/*.tar.xz'

.azuredevops/templates/steps/manifest.yml

@@ -1,10 +1,19 @@
 parameters:
-- name: artifactName
+- name: componentName
   type: string
-  default: 'drop'
+  default: $(Build.DefinitionName)
+- name: sparseCheckoutDir
+  type: string
+  default: ''
 - name: gpuTarget
   type: string
   default: ''
+- name: artifactName
+  type: string
+  default: drop
+- name: os
+  type: string
+  default: 'ubuntu2204'
 
 steps:
 - task: Bash@3
@@ -25,8 +34,9 @@ steps:
 
       IS_TAG_BUILD=$(jq 'has("release_repo")' resources.repositories)
       IS_AOMP_BUILD=$(jq 'has("aomp_repo")' resources.repositories)
+      IS_MATHLIBS_BUILD=$(jq 'has("libraries_repo")' resources.repositories)
 
-      if [ "$IS_TAG_BUILD" = "true" ] || [ "$IS_AOMP_BUILD" = "true" ]; then
+      if [ "$IS_TAG_BUILD" = "true" ] || [ "$IS_AOMP_BUILD" = "true" ] || [ "$IS_MATHLIBS_BUILD" = "true" ]; then
         exclude_keys=("pipelines_repo" "self") # Triggered by a file under ROCm/ROCm
       else
         exclude_keys=("pipelines_repo") # Triggered by a file under a component repo
@@ -45,6 +55,7 @@ steps:
               buildId: "$(Build.BuildId)",
               repoId: $entry.value.id,
               repoName: $entry.value.name,
+              repoSparse: "${{ parameters.sparseCheckoutDir }}",
               repoRef: $entry.value.ref,
               repoUrl: $entry.value.url,
               repoVersion: $entry.value.version
@@ -55,7 +66,7 @@ steps:
         )
       ' resources.repositories)
 
-      manifest_json=$(Build.ArtifactStagingDirectory)/manifest_$(Build.DefinitionName)_$(Build.BuildId)_$(Build.BuildNumber)_ubuntu2204_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.json
+      manifest_json=$(Build.ArtifactStagingDirectory)/manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.json
 
       dependencies=()
       for manifest_file in $(Pipeline.Workspace)/d/**/manifest_*.json; do
@@ -81,6 +92,7 @@ steps:
           "<tr><td>" + .buildNumber + "</td>" +
           "<td><a href=\"https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=" + .buildId + "\">" + .buildId + "</a></td>" +
           "<td><a href=\"" + .repoUrl + "\">" + .repoName + "</a></td>" +
+          "<td><a href=\"" + .repoUrl + "/tree/" + .repoRef + "/" + .repoSparse + "\">" + .repoSparse + "</a></td>" +
           "<td><a href=\"" + .repoUrl + "/tree/" + .repoRef + "\">" + .repoRef + "</a></td>" +
           "<td><a href=\"" + .repoUrl + "/commit/" + .repoVersion + "\">" + .repoVersion + "</a></td></tr>"
         ')
@@ -93,6 +105,7 @@ steps:
           "<tr><td>" + .buildNumber + "</td>" +
           "<td><a href=\"https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=" + .buildId + "\">" + .buildId + "</a></td>" +
           "<td><a href=\"" + .repoUrl + "\">" + .repoName + "</a></td>" +
+          "<td><a href=\"" + .repoUrl + "/tree/" + .repoRef + "/" + .repoSparse + "\">" + .repoSparse + "</a></td>" +
           "<td><a href=\"" + .repoUrl + "/tree/" + .repoRef + "\">" + .repoRef + "</a></td>" +
           "<td><a href=\"" + .repoUrl + "/commit/" + .repoVersion + "\">" + .repoVersion + "</a></td></tr>"
         ')
@@ -107,7 +120,7 @@ steps:
   inputs:
     targetType: inline
     script: |
-      manifest_html=$(Build.ArtifactStagingDirectory)/manifest_$(Build.DefinitionName)_$(Build.BuildId)_$(Build.BuildNumber)_ubuntu2204_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html
+      manifest_html=$(Build.ArtifactStagingDirectory)/manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html
       cat <<EOF > $manifest_html
       <html>
       <h1>Manifest</h1>
@@ -117,6 +130,7 @@ steps:
         <th>Build Number</th>
         <th>Build ID</th>
         <th>Repo Name</th>
+        <th>Repo Sparse</th>
         <th>Repo Ref</th>
         <th>Repo Version</th>
       </tr>
@@ -128,6 +142,7 @@ steps:
         <th>Build Number</th>
         <th>Build ID</th>
         <th>Repo Name</th>
+        <th>Repo Sparse</th>
         <th>Repo Ref</th>
         <th>Repo Version</th>
       </tr>
@@ -148,7 +163,7 @@ steps:
   continueOnError: true
   inputs:
     tabName: Manifest
-    reportDir: $(Build.ArtifactStagingDirectory)/manifest_$(Build.DefinitionName)_$(Build.BuildId)_$(Build.BuildNumber)_ubuntu2204_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html
+    reportDir: $(Build.ArtifactStagingDirectory)/manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html
 - task: Bash@3
   displayName: Save manifest artifact file name
   condition: always()
@@ -157,5 +172,5 @@ steps:
     workingDirectory: $(Pipeline.Workspace)
     targetType: inline
     script: |
-      echo "manifest_$(Build.DefinitionName)_$(Build.BuildId)_$(Build.BuildNumber)_ubuntu2204_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html" >> pipelineArtifacts.txt
-      echo "manifest_$(Build.DefinitionName)_$(Build.BuildId)_$(Build.BuildNumber)_ubuntu2204_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.json" >> pipelineArtifacts.txt
+      echo "manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.html" >> pipelineArtifacts.txt
+      echo "manifest_${{ parameters.componentName }}_$(Build.BuildId)_$(Build.BuildNumber)_${{ parameters.os }}_${{ parameters.gpuTarget }}_${{ parameters.artifactName }}.json" >> pipelineArtifacts.txt

.azuredevops/templates/steps/miopen-get-ck-build.yml

@@ -25,7 +25,7 @@ steps:
       echo "Fetching CK build ID for commit $CK_COMMIT"
       CK_CHECKS_URL="$GH_API/composable_kernel/commits/${CK_COMMIT}/check-runs"
       CK_BUILD_ID=$(curl -s $CK_CHECKS_URL | \
-        jq '.check_runs[] | select(.name == "composable_kernel" and .app.slug == "azure-pipelines") | .details_url' | \
+        jq '.check_runs[] | select(.name == "composable_kernel" and .app.slug == "azure-pipelines" and .conclusion == "success") | .details_url' | \
         tr -d '"' | grep -oP 'buildId=\K\d+')
 
       # If none found, use latest successful CK build instead

.azuredevops/templates/steps/preamble.yml

@@ -3,10 +3,27 @@
 # also display installed components and packages
 steps:
 - task: Bash@3
-  displayName: List apt packages
+  displayName: OS Version
   inputs:
     targetType: inline
-    script: apt list --installed
+    script: cat /etc/os-release
+- task: Bash@3
+  displayName: List installed packages (apt, dnf, or yum)
+  inputs:
+    targetType: inline
+    script: |
+      if command -v apt >/dev/null 2>&1; then
+        echo "Listing installed packages with apt:"
+        apt list --installed
+      elif command -v dnf >/dev/null 2>&1; then
+        echo "Listing installed packages with dnf:"
+        dnf list installed
+      elif command -v yum >/dev/null 2>&1; then
+        echo "Listing installed packages with yum:"
+        yum list installed
+      else
+        echo "No supported package manager found (apt, dnf, yum)."
+      fi
 - task: Bash@3
   displayName: Print Python version
   inputs:
@@ -16,7 +33,7 @@ steps:
   displayName: List Python packages
   inputs:
     targetType: inline
-    script: pip list -v
+    script: python3 -m pip list -v
 # The "Azure Pipelines" agents install CMake in multiple ways, including a standalone install into /usr/local/bin:
 # https://github.com/actions/runner-images/blob/6d939a3ab352a54a021dd67b071577287b6f14a5/images/ubuntu/scripts/build/install-cmake.sh#L27
 # This standalone CMake does not have a fixed version, and is not the same version as the one installed by the package manager

.azuredevops/templates/steps/test.yml

@@ -2,21 +2,27 @@ parameters:
 - name: componentName
   type: string
   default: ''
+- name: os
+  type: string
+  default: ubuntu2204
 - name: testDir
   type: string
-  default: 'build'
+  default: build
 - name: testExecutable
   type: string
-  default: 'ctest'
+  default: ctest
 - name: testParameters
   type: string
-  default: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+  default: --output-on-failure --force-new-ctest-process --output-junit test_output.xml
+- name: extraTestParameters
+  type: string
+  default: ''
 - name: testOutputFile
   type: string
   default: test_output.xml
 - name: testOutputFormat
   type: string
-  default: 'JUnit'
+  default: JUnit
   values:
     - JUnit
     - NUnit
@@ -26,26 +32,28 @@ parameters:
 - name: testPublishResults
   type: boolean
   default: true
-- name: allowPartiallySucceededBuilds
+- name: allowComponentTestFailure
   type: object
   default:
     - amdsmi
-    - aomp
     - HIPIFY
-    - MIVisionX
     - rocm_smi_lib
-    - rocprofiler-sdk
     - roctracer
+    # the following do not use this template but allow test failures, included for completeness
+    - aomp
+    - ROCgdb
 
 steps:
 # run test, continue on failure to publish results
 # and to publish build artifacts
 - task: Bash@3
   displayName: '${{ parameters.componentName }} Test'
-  continueOnError: ${{ containsValue(parameters.allowPartiallySucceededBuilds, parameters.componentName) }}
+  continueOnError: ${{ containsValue(parameters.allowComponentTestFailure, parameters.componentName) }}
   inputs:
     targetType: inline
-    script: ${{ parameters.testExecutable }} ${{ parameters.testParameters }}
+    script: |
+      ${{ iif(eq(parameters.os, 'almalinux8'), 'source /opt/rh/gcc-toolset-14/enable', '') }}
+      ${{ parameters.testExecutable }} ${{ parameters.testParameters }} ${{ parameters.extraTestParameters }}
     workingDirectory: ${{ parameters.testDir }}
 - ${{ if parameters.testPublishResults }}:
   - task: PublishTestResults@2

.azuredevops/variables-global.yml

@@ -3,6 +3,8 @@
 variables:
 - name: RESOURCES_REPOSITORIES
   value: $[ convertToJson(resources.repositories) ]
+- name: CCACHE_DIR
+  value: $(Pipeline.Workspace)/ccache
 - name: CI_ROOT_PATH
   value: /.azuredevops
 - name: CI_COMPONENT_PATH
@@ -30,320 +32,136 @@ variables:
 - name: GFX90A_TEST_POOL
   value: gfx90a_test_pool
 - name: LATEST_RELEASE_VERSION
-  value: 6.4.0
+  value: 6.4.1
 - name: REPO_RADEON_VERSION
-  value: 6.4
+  value: 6.4.1
 - name: NEXT_RELEASE_VERSION
-  value: 6.5.0
+  value: 7.0.0
 - name: LATEST_RELEASE_TAG
-  value: rocm-6.4.0
+  value: rocm-6.4.1
 - name: DOCKER_SKIP_GFX
   value: gfx90a
-- name: AMDMIGRAPHX_GFX942_TEST_PIPELINE_ID
-  value: 197
 - name: AMDMIGRAPHX_PIPELINE_ID
   value: 113
-- name: AMDMIGRAPHX_TAGGED_PIPELINE_ID
-  value: 60
 - name: AMDSMI_PIPELINE_ID
   value: 99
-- name: AMDSMI_TAGGED_PIPELINE_ID
-  value: 33
 - name: AOMP_EXTRAS_PIPELINE_ID
   value: 111
-- name: AOMP_EXTRAS_TAGGED_PIPELINE_ID
-  value: 75
 - name: AOMP_PIPELINE_ID
   value: 115
-- name: AOMP_TAGGED_PIPELINE_ID
-  value: 76
-- name: CCACHE_DIR
-  value: $(Pipeline.Workspace)/ccache
 - name: CLR_PIPELINE_ID
   value: 145
-- name: CLR_TAGGED_PIPELINE_ID
-  value: 71
-- name: COMPOSABLE_KERNEL_GFX942_TEST_PIPELINE_ID
-  value: 179
 - name: COMPOSABLE_KERNEL_PIPELINE_ID
   value: 86
-- name: COMPOSABLE_KERNEL_TAGGED_PIPELINE_ID
-  value: 38
 - name: FLANG_LEGACY_PIPELINE_ID
   value: 77
-- name: FLANG_LEGACY_TAGGED_PIPELINE_ID
-  value: 77
 - name: HALF_PIPELINE_ID
   value: 101
-- name: HALF_TAGGED_PIPELINE_ID
-  value: 11
 - name: HALF560_PIPELINE_ID
   value: 68
 - name: HALF560_BUILD_ID
   value: 621
 - name: HIP_PIPELINE_ID
   value: 93
-- name: HIP_TAGGED_PIPELINE_ID
-  value: 31
 - name: HIP_TESTS_PIPELINE_ID
   value: 233
-- name: HIP_TESTS_TAGGED_PIPELINE_ID
-  value: 220
 - name: HIPBLAS_COMMON_PIPELINE_ID
   value: 223
-- name: HIPBLAS_COMMON_TAGGED_PIPELINE_ID
-  value: 224
-- name: HIPBLAS_GFX942_TEST_PIPELINE_ID
-  value: 202
 - name: HIPBLAS_PIPELINE_ID
   value: 87
-- name: HIPBLAS_TAGGED_PIPELINE_ID
-  value: 44
-- name: HIPBLASLT_GFX942_TEST_PIPELINE_ID
-  value: 187
 - name: HIPBLASLT_PIPELINE_ID
   value: 112
-- name: HIPBLASLT_TAGGED_PIPELINE_ID
-  value: 45
-- name: HIPCUB_GFX942_TEST_PIPELINE_ID
-  value: 186
 - name: HIPCUB_PIPELINE_ID
-  value: 97
-- name: HIPCUB_TAGGED_PIPELINE_ID
-  value: 46
-- name: HIPFFT_GFX942_TEST_PIPELINE_ID
-  value: 198
+  value: 277
 - name: HIPFFT_PIPELINE_ID
   value: 121
-- name: HIPFFT_TAGGED_PIPELINE_ID
-  value: 12
 - name: HIPFORT_PIPELINE_ID
   value: 102
-- name: HIPFORT_TAGGED_PIPELINE_ID
-  value: 34
 - name: HIPIFY_PIPELINE_ID
   value: 92
-- name: HIPIFY_TAGGED_PIPELINE_ID
-  value: 13
-- name: HIPRAND_GFX942_TEST_PIPELINE_ID
-  value: 188
 - name: HIPRAND_PIPELINE_ID
-  value: 90
-- name: HIPRAND_TAGGED_PIPELINE_ID
-  value: 42
-- name: HIPSOLVER_GFX942_TEST_PIPELINE_ID
-  value: 201
+  value: 275
 - name: HIPSOLVER_PIPELINE_ID
   value: 84
-- name: HIPSOLVER_TAGGED_PIPELINE_ID
-  value: 52
-- name: HIPSPARSE_GFX942_TEST_PIPELINE_ID
-  value: 195
 - name: HIPSPARSE_PIPELINE_ID
   value: 83
-- name: HIPSPARSE_TAGGED_PIPELINE_ID
-  value: 14
-- name: HIPSPARSELT_GFX942_TEST_PIPELINE_ID
-  value: 200
 - name: HIPSPARSELT_PIPELINE_ID
   value: 104
-- name: HIPSPARSELT_TAGGED_PIPELINE_ID
-  value: 53
-- name: HIPTENSOR_GFX942_TEST_PIPELINE_ID
-  value: 192
 - name: HIPTENSOR_PIPELINE_ID
   value: 105
-- name: HIPTENSOR_TAGGED_PIPELINE_ID
-  value: 56
 - name: LLVM_PROJECT_PIPELINE_ID
   value: 2
-- name: LLVM_PROJECT_TAGGED_PIPELINE_ID
-  value: 8
 - name: MIOPEN_PIPELINE_ID
   value: 108
-- name: MIOPEN_TAGGED_PIPELINE_ID
-  value: 58
 - name: MIVISIONX_PIPELINE_ID
   value: 80
-- name: MIVISIONX_TAGGED_PIPELINE_ID
-  value: 18
-- name: OMNIPERF_PIPELINE_ID
-  value: 241
-- name: OMNIPERF_TAGGED_PIPELINE_ID
-  value: 242
-- name: OMNITRACE_PIPELINE_ID
-  value: 253
-- name: OMNITRACE_TAGGED_PIPELINE_ID
-  value: 252
-- name: RCCL_GFX942_TEST_PIPELINE_ID
-  value: 184
 - name: RCCL_PIPELINE_ID
   value: 107
-- name: RCCL_TAGGED_PIPELINE_ID
-  value: 15
 - name: RDC_PIPELINE_ID
   value: 100
-- name: RDC_TAGGED_PIPELINE_ID
-  value: 59
 - name: ROCAL_PIPELINE_ID
   value: 151
-- name: ROCALUTION_GFX942_TEST_PIPELINE_ID
-  value: 196
 - name: ROCALUTION_PIPELINE_ID
   value: 89
-- name: ROCALUTION_TAGGED_PIPELINE_ID
-  value: 16
-- name: ROCBLAS_GFX942_TEST_PIPELINE_ID
-  value: 185
 - name: ROCBLAS_PIPELINE_ID
   value: 85
-- name: ROCBLAS_TAGGED_PIPELINE_ID
-  value: 32
 - name: ROCDBGAPI_PIPELINE_ID
   value: 135
-- name: ROCDBGAPI_TAGGED_PIPELINE_ID
-  value: 17
 - name: ROCDECODE_PIPELINE_ID
   value: 79
-- name: ROCDECODE_TAGGED_PIPELINE_ID
-  value: 21
-- name: ROCFFT_GFX942_TEST_PIPELINE_ID
-  value: 189
 - name: ROCFFT_PIPELINE_ID
   value: 120
-- name: ROCFFT_TAGGED_PIPELINE_ID
-  value: 19
 - name: ROCGDB_PIPELINE_ID
   value: 134
-- name: ROCGDB_TAGGED_PIPELINE_ID
-  value: 50
 - name: ROCJPEG_PIPELINE_ID
   value: 262
-- name: ROCJPEG_TAGGED_PIPELINE_ID
-  value: 263
 - name: ROCM_BANDWIDTH_TEST_PIPELINE_ID
   value: 88
-- name: ROCM_BANDWIDTH_TEST_TAGGED_PIPELINE_ID
-  value: 23
 - name: ROCM_CMAKE_PIPELINE_ID
   value: 6
-- name: ROCM_CMAKE_TAGGED_PIPELINE_ID
-  value: 7
 - name: ROCM_CORE_PIPELINE_ID
   value: 103
-- name: ROCM_CORE_TAGGED_PIPELINE_ID
-  value: 22
-- name: ROCM_EXAMPLES_GFX942_TEST_PIPELINE_ID
-  value: 204
 - name: ROCM_EXAMPLES_PIPELINE_ID
   value: 216
-- name: ROCM_EXAMPLES_TAGGED_PIPELINE_ID
-  value: 245
 - name: ROCM_SMI_LIB_PIPELINE_ID
   value: 96
-- name: ROCM_SMI_LIB_TAGGED_PIPELINE_ID
-  value: 47
 - name: ROCMINFO_PIPELINE_ID
   value: 91
-- name: ROCMINFO_TAGGED_PIPELINE_ID
-  value: 27
 - name: ROCMLIR_PIPELINE_ID
   value: 229
-- name: ROCMLIR_TAGGED_PIPELINE_ID
-  value: 62
 - name: ROCMVALIDATIONSUITE_PIPELINE_ID
   value: 106
-- name: ROCMVALIDATIONSUITE_TAGGED_PIPELINE_ID
-  value: 43
-- name: ROCPRIM_GFX942_TEST_PIPELINE_ID
-  value: 180
 - name: ROCPRIM_PIPELINE_ID
-  value: 82
-- name: ROCPRIM_TAGGED_PIPELINE_ID
-  value: 20
-- name: ROCPROFILER_GFX942_TEST_PIPELINE_ID
-  value: 190
+  value: 273
 - name: ROCPROFILER_COMPUTE_PIPELINE_ID
   value: 257
-- name: ROCPROFILER_COMPUTE_TAGGED_PIPELINE_ID
-  value: 258
 - name: ROCPROFILER_REGISTER_PIPELINE_ID
   value: 1
-- name: ROCPROFILER_REGISTER_TAGGED_PIPELINE_ID
-  value: 25
 - name: ROCPROFILER_SDK_PIPELINE_ID
   value: 246
-- name: ROCPROFILER_SDK_TAGGED_PIPELINE_ID
-  value: 234
 - name: ROCPROFILER_SYSTEMS_PIPELINE_ID
   value: 255
-- name: ROCPROFILER_SYSTEMS_TAGGED_PIPELINE_ID
-  value: 254
 - name: ROCPROFILER_PIPELINE_ID
   value: 143
-- name: ROCPROFILER_TAGGED_PIPELINE_ID
-  value: 28
 - name: ROCPYDECODE_PIPELINE_ID
   value: 239
-- name: ROCPYDECODE_TAGGED_PIPELINE_ID
-  value: 232
 - name: ROCR_DEBUG_AGENT_PIPELINE_ID
   value: 136
-- name: ROCR_DEBUG_AGENT_TAGGED_PIPELINE_ID
-  value: 29
 - name: ROCR_RUNTIME_PIPELINE_ID
   value: 10
-- name: ROCR_RUNTIME_TAGGED_PIPELINE_ID
-  value: 24
-- name: ROCRAND_GFX942_TEST_PIPELINE_ID
-  value: 183
 - name: ROCRAND_PIPELINE_ID
-  value: 95
-- name: ROCRAND_TAGGED_PIPELINE_ID
-  value: 41
-- name: ROCSOLVER_GFX942_TEST_PIPELINE_ID
-  value: 199
+  value: 274
 - name: ROCSOLVER_PIPELINE_ID
   value: 81
-- name: ROCSOLVER_TAGGED_PIPELINE_ID
-  value: 55
-- name: ROCSPARSE_GFX942_TEST_PIPELINE_ID
-  value: 191
 - name: ROCSPARSE_PIPELINE_ID
   value: 98
-- name: ROCSPARSE_TAGGED_PIPELINE_ID
-  value: 67
-- name: ROCT_THUNK_INTERFACE_PIPELINE_ID
-  value: 3
-- name: ROCT_THUNK_INTERFACE_TAGGED_PIPELINE_ID
-  value: 9
-- name: ROCTHRUST_GFX942_TEST_PIPELINE_ID
-  value: 194
 - name: ROCTHRUST_PIPELINE_ID
-  value: 94
-- name: ROCTHRUST_TAGGED_PIPELINE_ID
-  value: 26
-- name: ROCTRACER_GFX942_TEST_PIPELINE_ID
-  value: 181
+  value: 276
 - name: ROCTRACER_PIPELINE_ID
   value: 141
-- name: ROCTRACER_TAGGED_PIPELINE_ID
-  value: 30
-- name: ROCWMMA_GFX942_TEST_PIPELINE_ID
-  value: 193
 - name: ROCWMMA_PIPELINE_ID
   value: 109
-- name: ROCWMMA_TAGGED_PIPELINE_ID
-  value: 57
-- name: RPP_GFX942_TEST_PIPELINE_ID
-  value: 182
 - name: RPP_PIPELINE_ID
   value: 78
-- name: RPP_TAGGED_PIPELINE_ID
-  value: 39
 - name: TRANSFERBENCH_PIPELINE_ID
   value: 265
-- name: TRANSFERBENCH_TAGGED_PIPELINE_ID
-  value: 266
-- name: BOOST_DEPENDENCY_PIPELINE_ID
-  value: 250

.wordlist.txt

@@ -272,6 +272,7 @@ NBIO
 NBIOs
 NCCL
 NCF
+NFS
 NIC
 NICs
 NLI
@@ -500,6 +501,7 @@ ZenDNN
 accuracies
 activations
 addr
+ade
 ai
 alloc
 allocatable
@@ -515,6 +517,7 @@ avx
 awk
 backend
 backends
+bb
 benchmarked
 benchmarking
 bfloat
@@ -538,6 +541,7 @@ cd
 centos
 centric
 changelog
+checkpointing
 chiplet
 cmake
 cmd
@@ -578,6 +582,7 @@ de
 deallocation
 debuggability
 debian
+deepseek
 denoise
 denoised
 denoises
@@ -601,6 +606,7 @@ embeddings
 enablement
 encodings
 endfor
+endif
 endpgm
 enqueue
 env
@@ -702,6 +708,7 @@ migratable
 miopen
 miopengemm
 mivisionx
+mixtral
 mjx
 mkdir
 mlirmiopen
@@ -843,6 +850,7 @@ subfolder
 subfolders
 submodule
 submodules
+subnet
 supercomputing
 symlink
 symlinks

CHANGELOG.md

@@ -6,7 +6,7 @@ different versions of the ROCm software stack and its components.
 
 ## ROCm 6.4.1
 
-See the [ROCm 6.4.1 release notes](https://rocm-stg.amd.com/en/latest/about/release-notes.html)
+See the [ROCm 6.4.1 release notes](https://rocm.docs.amd.com/en/docs-6.4.1/about/release-notes.html)
 for a complete overview of this release.
 
 ### **AMD SMI** (25.4.2)
@@ -894,6 +894,18 @@ See the full [ROCm SMI changelog](https://github.com/ROCm/rocm_smi_lib/blob/rele
 
 - Fixed an issue where sampling multi-GPU Python workloads caused the system to stop responding.
 
+### **ROCm Validation Suite** (1.1.0)
+
+#### Added
+
+* Configuration files for MI210.
+* Support for OCP fp8 data type.
+* GPU index-based CLI execution.
+
+#### Changed
+
+* JSON logging with updated schema.
+
 ### **rocPRIM** (3.4.0)
 
 #### Added

README.md

@@ -19,142 +19,17 @@ ROCm supports programming models, such as OpenMP and OpenCL, and includes all ne
 source software compilers, debuggers, and libraries. ROCm is fully integrated into machine learning
 (ML) frameworks, such as PyTorch and TensorFlow.
 
-## Getting the ROCm Source Code
+> [!IMPORTANT]
+> A new open source build platform for ROCm is under development at
+> https://github.com/ROCm/TheRock, featuring a unified CMake build with bundled
+> dependencies, Windows support, and more.
+>
+> The instructions below describe the prior process for building from source
+> which will be replaced once TheRock is mature enough.
 
-AMD ROCm is built from open source software. It is, therefore, possible to modify the various components of ROCm by downloading the source code and rebuilding the components. The source code for ROCm components can be cloned from each of the GitHub repositories using git.  For easy access to download the correct versions of each of these tools, the ROCm repository contains a repo manifest file called [default.xml](./default.xml). You can use this manifest file to download the source code for ROCm software.
+## Getting and Building ROCm from Source
 
-### Installing the repo tool
-
-The repo tool from Google allows you to manage multiple git repositories simultaneously. Run the following commands to install the repo tool:
-
-```bash
-mkdir -p ~/bin/
-curl https://storage.googleapis.com/git-repo-downloads/repo > ~/bin/repo
-chmod a+x ~/bin/repo
-```
-
-**Note:** The ```~/bin/``` folder is used as an example. You can specify a different folder to install the repo tool into if you desire.
-
-### Installing git-lfs
-
-Some ROCm projects use the Git Large File Storage (LFS) format that may require you to install git-lfs. Refer to [Git Large File Storage](https://github.com/git-lfs/git-lfs/blob/main/INSTALLING.md) for more information. For example, to install git-lfs for Ubuntu, use the following command:
-
-```bash
-sudo apt-get install git-lfs
-```
-
-### Downloading the ROCm source code
-
-The following example shows how to use the repo tool to download the ROCm source code. If you choose a directory other than ~/bin/ to install the repo tool, you must use that chosen directory in the code as shown below:
-
-```bash
-mkdir -p ~/ROCm/
-cd ~/ROCm/
-export ROCM_VERSION=6.4.1
-~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.4.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
-~/bin/repo sync
-```
-
-**Note:** Using this sample code will cause the repo tool to download the open source code associated with the specified ROCm release. Ensure that you have ssh-keys configured on your machine for your GitHub ID prior to the download as explained at [Connecting to GitHub with SSH](https://docs.github.com/en/authentication/connecting-to-github-with-ssh).
-
-## Building the ROCm source code
-
-Each ROCm component repository contains directions for building that component, such as the rocSPARSE documentation [Installation and Building for Linux](https://rocm.docs.amd.com/projects/rocSPARSE/en/latest/install/Linux_Install_Guide.html). Refer to the specific component documentation for instructions on building the repository.
-
-Each release of the ROCm software supports specific hardware and software configurations. Refer to [System requirements (Linux)](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html) for the current supported hardware and OS.
-
-## Build ROCm from source
-
-The Build will use as many processors as it can find to build in parallel. Some of the compiles can consume as much as 10GB of RAM, so make sure you have plenty of Swap Space !
-
-By default the ROCm build will compile for all supported GPU architectures and will take approximately 500 CPU hours.
-The Build time will reduce significantly if we limit the GPU Architecture/s against which we need to build by using the environment variable GPU_ARCHS as mentioned below.
-
-```bash
-# --------------------------------------
-# Step1: clone source code
-# --------------------------------------
-
-mkdir -p ~/WORKSPACE/      # Or any folder name other than WORKSPACE
-cd ~/WORKSPACE/
-export ROCM_VERSION=6.4.1
-~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.4.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
-~/bin/repo sync
-
-# --------------------------------------
-# Step 2: Prepare build environment
-# --------------------------------------
-
-# Option 1: Start a docker container
-# Pulling required base docker images:
-# Ubuntu22.04 built from ROCm/tools/rocm-build/docker/ubuntu22/Dockerfile
-docker pull rocm/rocm-build-ubuntu-22.04:6.4
-# Ubuntu24.04 built from ROCm/tools/rocm-build/docker/ubuntu24/Dockerfile
-docker pull rocm/rocm-build-ubuntu-24.04:6.4
-
-# Start docker container and mount the source code folder:
-docker run -ti \
-    -e ROCM_VERSION=${ROCM_VERSION} \
-    -e CCACHE_DIR=$HOME/.ccache \
-    -e CCACHE_ENABLED=true \
-    -e DOCK_WORK_FOLD=/src \
-    -w /src \
-    -v $PWD:/src \
-    -v /etc/passwd:/etc/passwd \
-    -v /etc/shadow:/etc/shadow \
-    -v ${HOME}/.ccache:${HOME}/.ccache \
-    -u $(id -u):$(id -g) \
-    <replace_with_required_ubuntu_base_docker_image> bash
-
-# Option 2: Install required packages into the host machine
-# For ubuntu22.04 system
-cd ROCm/tools/rocm-build/docker/ubuntu22
-cp * /tmp && cd /tmp
-bash install-prerequisites.sh
-# For ubuntu24.04 system
-cd ROCm/tools/rocm-build/docker/ubuntu24
-cp * /tmp && cd /tmp
-bash install-prerequisites.sh
-
-# --------------------------------------
-# Step 3: Run build command line
-# --------------------------------------
-
-# Select GPU targets before building:
-# When GPU_ARCHS is not set, default GPU targets supported by ROCm6.1 will be used.
-# To build against a subset of GFX architectures you can use the below env variable.
-# Support MI300 (gfx940, gfx941, gfx942).
-export GPU_ARCHS="gfx942"               # Example
-export GPU_ARCHS="gfx940;gfx941;gfx942" # Example
-
-# Pick and run build commands in the docker container:
-# Build rocm-dev packages
-make -f ROCm/tools/rocm-build/ROCm.mk -j ${NPROC:-$(nproc)} rocm-dev
-# Build all ROCm packages
-make -f ROCm/tools/rocm-build/ROCm.mk -j ${NPROC:-$(nproc)} all
-# list all ROCm components to find required components
-make -f ROCm/tools/rocm-build/ROCm.mk list_components
-# Build a single ROCm packages
-make -f ROCm/tools/rocm-build/ROCm.mk T_rocblas
-
-# Find built packages in ubuntu22.04:
-out/ubuntu-22.04/22.04/deb/
-# Find built packages in ubuntu24.04:
-out/ubuntu-24.04/24.04/deb/
-
-# Find built logs in ubuntu22.04:
-out/ubuntu-22.04/22.04/logs/
-# Find built logs in ubuntu24.04:
-out/ubuntu-24.04/24.04/logs/
-# All logs pertaining to failed components, end with .errrors extension.
-out/ubuntu-22.04/22.04/logs/rocblas.errors      # Example
-# All logs pertaining to building components, end with .inprogress extension.
-out/ubuntu-22.04/22.04/logs/rocblas.inprogress  # Example
-# All logs pertaining to passed components, use the component names.
-out/ubuntu-22.04/22.04/logs/rocblas             # Example
-```
-
-Note: [Overview for ROCm.mk](tools/rocm-build/README.md)
+Please use [TheRock](https://github.com/ROCm/TheRock) build system to build ROCm from source.
 
 ## ROCm documentation
 

RELEASE.md

@@ -74,14 +74,14 @@ ROCm documentation continues to be updated to provide clearer and more comprehen
 
 ROCm 6.4.1 introduces support for the RDNA4 architecture-based [Radeon AI PRO
 R9700](https://www.amd.com/en/products/graphics/workstations/radeon-ai-pro/ai-9000-series/amd-radeon-ai-pro-r9700.html),
-[Radeon RX 9070 XT](https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9070xt.html), and
+[Radeon RX 9070](https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9070.html),
+[Radeon RX 9070 XT](https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9070xt.html),
+Radeon RX 9070 GRE, and
 [Radeon RX 9060 XT](https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9060xt.html) GPUs
-for compute workloads. Currently, these GPUs are only supported on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.5, and RHEL 9.4.
+for compute workloads. It also adds support for RDNA3 architecture-based [Radeon PRO W7700](https://www.amd.com/en/products/graphics/workstations/radeon-pro/w7700.html) and [Radeon RX 7800 XT](https://www.amd.com/en/products/graphics/desktops/radeon/7000-series/amd-radeon-rx-7800-xt.html) GPUs. These GPUs are supported on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.5, and RHEL 9.4.
 For details, see the full list of [Supported GPUs
 (Linux)](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html#supported-gpus).
 
-Operating system support remains unchanged in this release.
-
 See the [Compatibility
 matrix](../../docs/compatibility/compatibility-matrix.rst)
 for more information about operating system and hardware compatibility.
@@ -165,7 +165,7 @@ Click {fab}`github` to go to the component's source code on GitHub.
                 <td><a href="https://github.com/ROCm/rccl"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
             <tr>
-            <td><a href="https://github.com/ROCm/rocSHMEM">rocSHMEM</a></td>
+            <td><a href="https://rocm.docs.amd.com/projects/rocSHMEM/en/docs-6.4.1/index.html">rocSHMEM</a></td>
                 <td>2.0.0</td>
                 <td><a href="https://github.com/ROCm/rocSHMEM"><i class="fab fa-github fa-lg"></i></a></td>
             </tr>
@@ -654,4 +654,4 @@ There are a number of upcoming changes planned for HIP runtime API in an upcomin
 that are not backward compatible with prior releases. Most of these changes increase 
 alignment between HIP and CUDA APIs or behavior. Some of the upcoming changes are to 
 clean up header files, remove namespace collision, and have a clear separation between 
-`hipRTC` and HIP runtime. For more information refer to [HIP Upcoming changes](https://rocm.docs.amd.com/en/docs-6.4.0/about/release-notes.html#id15).
+`hipRTC` and HIP runtime.

docs/compatibility/compatibility-matrix-historical-6.0.csv

@@ -2,7 +2,7 @@ ROCm Version,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5,
       :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,,
       ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
       ,,,,,,,,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
-      ,"RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
+      ,"RHEL 9.6, 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
       ,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
       ,SLES 15 SP6,SLES 15 SP6,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
       ,,,,,,,,,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
@@ -17,8 +17,9 @@ ROCm Version,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5,
       ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
       ,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
       ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1201 [#RDNA4-OS-past-60]_,,,,,,,,,,,,,,,
-      ,gfx1200 [#RDNA4-OS-past-60]_,,,,,,,,,,,,,,,
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1201 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
+      ,gfx1200 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
+,gfx1101 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
       ,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
       ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
       ,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942 [#mi300_624-past-60]_,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
@@ -41,7 +42,7 @@ ROCm Version,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5,
       CUB,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
 ,,,,,,,,,,,,,,,,
       KMD & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,
-      KMD versions,"6.4.x, 6.3.x","6.4.x, 6.3.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
+      :doc:`KMD versions <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
       ,,,,,,,,,,,,,,,,
       ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,
       :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
@@ -56,7 +57,7 @@ ROCm Version,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5,
       ,,,,,,,,,,,,,,,,
       COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,
       :doc:`RCCL <rccl:index>`,2.22.3,2.22.3,2.21.5,2.21.5,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
-      `rocSHMEM <https://github.com/ROCm/rocSHMEM>`_ ,2.0.0,2.0.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`rocSHMEM <rocshmem:index>`,2.0.0,2.0.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
       ,,,,,,,,,,,,,,,,
       MATH LIBS,.. _mathlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,
       `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0

docs/compatibility/compatibility-matrix.rst

@@ -28,7 +28,7 @@ compatibility and system requirements.
 
       :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2
       ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5
-      ,"RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4"
+      ,"RHEL 9.6, 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4"
       ,RHEL 8.10,RHEL 8.10,RHEL 8.10
       ,SLES 15 SP6,SLES 15 SP6,"SLES 15 SP6, SP5"
       ,"Oracle Linux 9, 8 [#mi300x]_","Oracle Linux 9, 8 [#mi300x]_",Oracle Linux 8.10 [#mi300x]_
@@ -42,8 +42,9 @@ compatibility and system requirements.
       ,RDNA3,RDNA3,RDNA3
       ,RDNA2,RDNA2,RDNA2
       ,.. _gpu-support-compatibility-matrix:,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1201 [#RDNA4-OS]_,,
-      ,gfx1200 [#RDNA4-OS]_,,
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1201 [#RDNA-OS]_,,
+      ,gfx1200 [#RDNA-OS]_,,
+      ,gfx1101 [#RDNA-OS]_,,
       ,gfx1100,gfx1100,gfx1100
       ,gfx1030,gfx1030,gfx1030
       ,gfx942,gfx942,gfx942
@@ -65,7 +66,7 @@ compatibility and system requirements.
       CUB,2.5.0,2.5.0,2.3.2
       ,,,
       KMD & USER SPACE [#kfd_support]_,.. _kfd-userspace-support-compatibility-matrix:,,
-      KMD versions,"6.4.x, 6.3.x","6.4.x, 6.3.x","6.4.x, 6.3.x, 6.2.x, 6.1.x"
+      :doc:`KMD versions <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x"
       ,,,
       ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix:,,
       :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0
@@ -80,7 +81,7 @@ compatibility and system requirements.
       ,,,
       COMMUNICATION,.. _commlibs-support-compatibility-matrix:,,
       :doc:`RCCL <rccl:index>`,2.22.3,2.22.3,2.21.5
-      `rocSHMEM <https://github.com/ROCm/rocSHMEM>`_ ,2.0.0,2.0.0,N/A
+      :doc:`rocSHMEM <rocshmem:index>`,2.0.0,2.0.0,N/A
       ,,,
       MATH LIBS,.. _mathlibs-support-compatibility-matrix:,,
       `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0
@@ -156,7 +157,7 @@ compatibility and system requirements.
 .. [#mi300_620] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
 .. [#kfd_support] Starting from ROCm 6.4.0, forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software is provided up to a year apart (assuming hardware support is available in both). For earlier ROCm releases, the compatibility is provided for +/- 2 releases. These are the compatibility combinations that are currently supported.
 .. [#ROCT-rocr] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
-.. [#RDNA4-OS] Radeon AI PRO R9700, Radeon RX 9070 XT (gfx1201), and Radeon RX 9060 XT (gfx1200) are supported only on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.5, and RHEL 9.4.
+.. [#RDNA-OS] Radeon AI PRO R9700, Radeon RX 9070 XT (gfx1201), Radeon RX 9060 XT (gfx1200), Radeon PRO W7700 (gfx1101), and Radeon RX 7800 XT (gfx1101) are supported only on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.5, and RHEL 9.4.
 
 .. _OS-kernel-versions:
 
@@ -174,7 +175,8 @@ Use this lookup table to confirm which operating system and kernel versions are
    ,,
    `Ubuntu <https://ubuntu.com/about/release-cycle#ubuntu-kernel-release-cycle>`_, 22.04.5, "5.15 GA, 6.8 HWE", 2.35
    ,,
-   `Red Hat Enterprise Linux (RHEL 9) <https://access.redhat.com/articles/3078#RHEL9>`_, 9.5, 5.14+, 2.34
+   `Red Hat Enterprise Linux (RHEL 9) <https://access.redhat.com/articles/3078#RHEL9>`_, 9.6, 5.14+, 2.34
+   , 9.5, 5.14+, 2.34
    ,9.4, 5.14+, 2.34
    ,9.3, 5.14+, 2.34
    ,,
@@ -235,4 +237,4 @@ Expand for full historical view of:
    .. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
    .. [#kfd_support-past-60] Starting from ROCm 6.4.0, forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software is provided up to a year apart (assuming hardware support is available in both). For earlier ROCm releases, the compatibility is provided for +/- 2 releases. These are the compatibility combinations that are currently supported.
    .. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
-   .. [#RDNA4-OS-past-60] Radeon AI PRO R9700, Radeon RX 9070 XT (gfx1201), and Radeon RX 9060 XT (gfx1200) are supported only on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.5, and RHEL 9.4.
+   .. [#RDNA-OS-past-60] Radeon AI PRO R9700, Radeon RX 9070 XT (gfx1201), Radeon RX 9060 XT (gfx1200), Radeon PRO W7700 (gfx1101), and Radeon RX 7800 XT (gfx1101) are supported only on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.5, and RHEL 9.4.

docs/compatibility/ml-compatibility/jax-compatibility.rst

@@ -97,7 +97,7 @@ Docker image compatibility
 AMD validates and publishes ready-made `ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax>`_
 with ROCm backends on Docker Hub. The following Docker image tags and
 associated inventories represent the latest JAX version from the official Docker Hub and are validated for
-`ROCm 6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`_. Click the |docker-icon|
+`ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`_. Click the |docker-icon|
 icon to view the image on Docker Hub.
 
 .. list-table:: JAX Docker image components
@@ -110,19 +110,19 @@ icon to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4-jax0.4.35-py3.12/images/sha256-4069398229078f3311128b6d276c6af377c7e97d3363d020b0bf7154fae619ca"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
+           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.1-jax0.4.35-py3.12/images/sha256-7a0745a2a2758bdf86397750bac00e9086cbf67d170cfdbb08af73f7c7d18a6a"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
 
       - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
       - Ubuntu 24.04
-      - `3.12.7 <https://www.python.org/downloads/release/python-3127/>`_
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4-jax0.4.35-py3.10/images/sha256-a137f901f91ce6c13b424c40a6cf535248d4d20fd36d5daf5eee0570190a4a11"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
+           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.1-jax0.4.35-py3.10/images/sha256-5f9e8d6e6e69fdc9a1a3f2ba3b1234c3f46c53b7468538c07fd18b00899da54f"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
 
       - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
       - Ubuntu 22.04
-      - `3.10.14 <https://www.python.org/downloads/release/python-31014/>`_
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
 
 AMD publishes `Community ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax-community>`_
 with ROCm backends on Docker Hub. The following Docker image tags and

docs/compatibility/ml-compatibility/pytorch-compatibility.rst

@@ -95,7 +95,7 @@ Docker image compatibility
 
 AMD validates and publishes `PyTorch images <https://hub.docker.com/r/rocm/pytorch>`_
 with ROCm backends on Docker Hub. The following Docker image tags and associated
-inventories were tested on `ROCm 6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`_.
+inventories were tested on `ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`_.
 Click |docker-icon| to view the image on Docker Hub.
 
 .. list-table:: PyTorch Docker image components
@@ -116,137 +116,122 @@ Click |docker-icon| to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-ab1d350b818b90123cfda31363019d11c0d41a8f12a19e3cb2cb40cf0261137d"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-c76af9bfb1c25b0f40d4c29e8652105c57250bf018d23ff595b06bd79666fdd7"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.6.0 <https://github.com/ROCm/pytorch/tree/release/2.6>`_
       - 24.04
-      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
       - `1.6.0 <https://github.com/ROCm/apex/tree/release/1.6.0>`_
       - `0.21.0 <https://github.com/pytorch/vision/tree/v0.21.0>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
-      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `1.16.0 <https://github.com/openucx/ucx/tree/v1.16.0>`_
+      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`_
       - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu22.04_py3.10_pytorch_release_2.6.0/images/sha256-130536fdfceb374626a7bcb8d00b9d796ddfc3115677d51229e5b852d96b5ef4"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.6.0/images/sha256-f9d226135d51831c810dcb1251636ec61f85c65fcdda03e188c053a5d4f6585b"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.6.0 <https://github.com/ROCm/pytorch/tree/release/2.6>`_
       - 22.04
-      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
       - `1.6.0 <https://github.com/ROCm/apex/tree/release/1.6.0>`_
       - `0.21.0 <https://github.com/pytorch/vision/tree/v0.21.0>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
-      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`_
+      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`_
       - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu24.04_py3.12_pytorch_release_2.5.1/images/sha256-20a2e24b4738dc1f1a44a04f23827918b56c99f7e697e6fccb90e9c4fae8ca9b"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.5.1/images/sha256-3490e74d4f43dcdb3351dd334108d1ccd47e5a687c0523a2424ac1bcdd3dd6dd"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`_
       - 24.04
-      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
       - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`_
       - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
-      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`_
       - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu22.04_py3.11_pytorch_release_2.5.1/images/sha256-f09cb8ca39cc39222fb554060711f5c19130f7b4047aaf41fad4ba3ec470ca03"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.5.1/images/sha256-26c5dfffb4a54625884abca83166940f17dd27bc75f1b24f6e80fbcb7d4e9afb"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`_
       - 22.04
-      - `3.11.9 <https://www.python.org/downloads/release/python-3119/>`_
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
       - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`_
       - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
-      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`_
+      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`_
       - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu22.04_py3.10_pytorch_release_2.5.1/images/sha256-a91c100d1fe608dae3eb7f60a751630363d4027ac3d077d428e92945204c338e"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`_
-      - 22.04
-      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
-      - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`_
-      - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`_
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
-      - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
-      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-66a89ce6485bb887af74bb9bd76bb613ab9834a6b1374649ea7ae379883454a4"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-f378a24561fa6efc178b6dc93fc7d82e5b93653ecd59c89d4476674d29e1284d"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
       - 24.04
-      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
       - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`_
       - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
-      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`_
+      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`_
       - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-c716cf167e6e49893f11de03606ed37044153aca089e74ca615065c06877f86b"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-2308dbd0e650b7bf8d548575cbb6e2bdc021f9386384ce570da16d58ee684d22"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
       - 22.04
-      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
       - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`_
       - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
-      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`_
+      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`_
       - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu24.04_py3.12_pytorch_release_2.3.0/images/sha256-0434cbc9b07b2c26e39480d7447f676f9057a1054dcff00e0050c25a6eddbd3c"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.3.0/images/sha256-eefd2ab019728f91f94c5e6a9463cb0ea900b3011458d18fe5d88e50c0b57d86"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`_
       - 24.04
-      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
       - `1.3.0 <https://github.com/ROCm/apex/tree/release/1.3.0>`_
       - `0.18.0 <https://github.com/pytorch/vision/tree/v0.18.0>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
-      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`_
+      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`_
       - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-688b1c0073092615fb98778d78b16191e506097ee116a2d3d2628b264d5d367b"><i class="fab fa-docker fa-lg"></i></a>
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-473643226ab0e93a04720b256ed772619878abf9c42b9f84828cefed522696fd"><i class="fab fa-docker fa-lg"></i></a>
 
       - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`_
       - 22.04
-      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
       - `1.3.0 <https://github.com/ROCm/apex/tree/release/1.3.0>`_
       - `0.18.0 <https://github.com/pytorch/vision/tree/v0.18.0>`_
       - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
       - `master <https://bitbucket.org/icl/magma/src/master/>`_
-      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
-      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`_
+      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`_
       - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
 
 Key ROCm libraries for PyTorch

docs/compatibility/ml-compatibility/tensorflow-compatibility.rst

@@ -56,7 +56,7 @@ Docker image compatibility
 AMD validates and publishes ready-made `TensorFlow images
 <https://hub.docker.com/r/rocm/tensorflow>`_ with ROCm backends on
 Docker Hub. The following Docker image tags and associated inventories are
-validated for `ROCm 6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`_. Click
+validated for `ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`_. Click
 the |docker-icon| icon to view the image on Docker Hub.
 
 .. list-table:: TensorFlow Docker image components
@@ -73,82 +73,122 @@ the |docker-icon| icon to view the image on Docker Hub.
 
            <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.12-tf2.18-dev/images/sha256-fa9cf5fa6c6079a7118727531ccd0056c6e3224a42c3d6e78a49e7781daafff4"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
       - dev
       - 24.04
-      - `Python 3.12.4 <https://www.python.org/downloads/release/python-3124/>`_
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
       - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.12-tf2.18-runtime/images/sha256-14addca4b92a47c806b83ebaeed593fc6672cd99f0017ed8dad759fe72ed0309"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.18-runtime/images/sha256-d14d8c4989e7c9a60f4e72461b9e349de72347c6162dcd6897e6f4f80ffbb440"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
       - runtime
       - 24.04
-      - `Python 3.12.4 <https://www.python.org/downloads/release/python-3124/>`_
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
       - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.10-tf2.18-dev/images/sha256-f5e151060df04ff5fb59f5604b49cd371931bbe75b06aec9fe7781397c4be0ce"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.18-dev/images/sha256-081e5bd6615a5dc17247ebd2ccc26895c3feeff086720400fa39b477e60a77c0"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
       - dev
       - 22.04
-      - `Python 3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
       - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.10-tf2.18-runtime/images/sha256-5cd4c03fdb1036570c0d4929da60a65c4466998dc80f1dc8a5a0b173eae017fb"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.18-runtime/images/sha256-bf369637378264f4af6ddad5ca8b8611d3e372ffbea9ab7a06f1e122f0a0867b"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
       - runtime
       - 22.04
-      - `Python 3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
       - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.12-tf2.17-dev/images/sha256-b3add80e374a2db2d1088d746e740afa89d439aca02cacba959ad298f5cd2b3f"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.17-dev/images/sha256-5a502008c50d0b6508e6027f911bdff070a7493700ae064bed74e1d22b91ed50"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
       - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
       - dev
       - 24.04
-      - `Python 3.12.4 <https://www.python.org/downloads/release/python-3124/>`_
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
       - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.12-tf2.17-runtime/images/sha256-3a244f026c32177eff7958ffbad390de85b438b2b48b455cc39f15d70fa1270d"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.17-runtime/images/sha256-1ee5dfffceb71ac66617ada33de3a10de0cb74199cc4b82441192e5e92fa2ddf"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
       - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
       - runtime
       - 24.04
-      - `Python 3.12.4 <https://www.python.org/downloads/release/python-3124/>`_
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-3124/>`_
       - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.10-tf2.17-dev/images/sha256-e0cecdfacb59169335049983cdab6da578c209bb9f4d08aad97e184ae59171a6"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.17-dev/images/sha256-109218ad92bfae83bbd2710475f7502166e1ed54ca0b9748a9cbc3f5a1d75af1"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
       - dev
       - 22.04
-      - `Python 3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
       - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`_
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.10-tf2.17-runtime/images/sha256-6f43de12f7eb202791b698ac51d28b72098de90034dbcd48486629b0125f7707"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.17-runtime/images/sha256-5d78bd5918d394f92263daa2990e88d695d27200dd90ed83ec64d20c7661c9c1"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
 
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
+      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
       - runtime
       - 22.04
-      - `Python 3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
       - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`_
 
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.16-dev/images/sha256-b09b1ad921c09c687b7c916141051e9fcf15539a5686e5aa67c689195a522719"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - dev
+      - 24.04
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
+      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.12-tf2.16-runtime/images/sha256-20dbd824e85558abfe33fc9283cc547d88cde3c623fe95322743a5082f883a64"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - runtime
+      - 24.04
+      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
+      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-dev/images/sha256-36c4fa047c86e2470ac473ec1429aea6d4b8934b90ffeb34d1afab40e7e5b377"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.16.2 <https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-dev/images/sha256-36c4fa047c86e2470ac473ec1429aea6d4b8934b90ffeb34d1afab40e7e5b377>`__
+      - dev
+      - 22.04
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
+      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-runtime/images/sha256-a94150ffb81365234ebfa34e764db5474bc6ab7d141b56495eac349778dafcf3"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+
+      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
+      - runtime
+      - 22.04
+      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
+      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`_
+
 
 Critical ROCm libraries for TensorFlow
 ===============================================================================

docs/conf.py

@@ -71,8 +71,9 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/inference/index", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/hugging-face-models", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/llm-inference-frameworks", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/vllm-benchmark", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/pytorch-inference-benchmark", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/vllm", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250513", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/deploy-your-model", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/inference-optimization/index", "os": ["linux"]},

docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.7.3_20250325-benchmark-models.yaml

@@ -0,0 +1,159 @@
+vllm_benchmark:
+  unified_docker:
+    latest:
+      pull_tag: rocm/vllm:rocm6.3.1_instinct_vllm0.7.3_20250325
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.7.3_20250325/images/sha256-25245924f61750b19be6dcd8e787e46088a496c1fe17ee9b9e397f3d84d35640
+      rocm_version: 6.3.1
+      vllm_version: 0.7.3
+      pytorch_version: 2.7.0 (dev nightly)
+      hipblaslt_version: 0.13
+  model_groups:
+    - group: Llama
+      tag: llama
+      models:
+      - model: Llama 3.1 8B
+        mad_tag: pyt_vllm_llama-3.1-8b
+        model_repo: meta-llama/Llama-3.1-8B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: float16
+      - model: Llama 3.1 70B
+        mad_tag: pyt_vllm_llama-3.1-70b
+        model_repo: meta-llama/Llama-3.1-70B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+        precision: float16
+      - model: Llama 3.1 405B
+        mad_tag: pyt_vllm_llama-3.1-405b
+        model_repo: meta-llama/Llama-3.1-405B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
+        precision: float16
+      - model: Llama 3.2 11B Vision
+        mad_tag: pyt_vllm_llama-3.2-11b-vision-instruct
+        model_repo: meta-llama/Llama-3.2-11B-Vision-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct
+        precision: float16
+      - model: Llama 2 7B
+        mad_tag: pyt_vllm_llama-2-7b
+        model_repo: meta-llama/Llama-2-7b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
+        precision: float16
+      - model: Llama 2 70B
+        mad_tag: pyt_vllm_llama-2-70b
+        model_repo: meta-llama/Llama-2-70b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+        precision: float16
+      - model: Llama 3.1 8B FP8
+        mad_tag: pyt_vllm_llama-3.1-8b_fp8
+        model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
+        precision: float8
+      - model: Llama 3.1 70B FP8
+        mad_tag: pyt_vllm_llama-3.1-70b_fp8
+        model_repo: amd/Llama-3.1-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV
+        precision: float8
+      - model: Llama 3.1 405B FP8
+        mad_tag: pyt_vllm_llama-3.1-405b_fp8
+        model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+        precision: float8
+    - group: Mistral
+      tag: mistral
+      models:
+      - model: Mixtral MoE 8x7B
+        mad_tag: pyt_vllm_mixtral-8x7b
+        model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+        precision: float16
+      - model: Mixtral MoE 8x22B
+        mad_tag: pyt_vllm_mixtral-8x22b
+        model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
+        precision: float16
+      - model: Mistral 7B
+        mad_tag: pyt_vllm_mistral-7b
+        model_repo: mistralai/Mistral-7B-Instruct-v0.3
+        url: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
+        precision: float16
+      - model: Mixtral MoE 8x7B FP8
+        mad_tag: pyt_vllm_mixtral-8x7b_fp8
+        model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        precision: float8
+      - model: Mixtral MoE 8x22B FP8
+        mad_tag: pyt_vllm_mixtral-8x22b_fp8
+        model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        precision: float8
+      - model: Mistral 7B FP8
+        mad_tag: pyt_vllm_mistral-7b_fp8
+        model_repo: amd/Mistral-7B-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV
+        precision: float8
+    - group: Qwen
+      tag: qwen
+      models:
+      - model: Qwen2 7B
+        mad_tag: pyt_vllm_qwen2-7b
+        model_repo: Qwen/Qwen2-7B-Instruct
+        url: https://huggingface.co/Qwen/Qwen2-7B-Instruct
+        precision: float16
+      - model: Qwen2 72B
+        mad_tag: pyt_vllm_qwen2-72b
+        model_repo: Qwen/Qwen2-72B-Instruct
+        url: https://huggingface.co/Qwen/Qwen2-72B-Instruct
+        precision: float16
+    - group: JAIS
+      tag: jais
+      models:
+      - model: JAIS 13B
+        mad_tag: pyt_vllm_jais-13b
+        model_repo: core42/jais-13b-chat
+        url: https://huggingface.co/core42/jais-13b-chat
+        precision: float16
+      - model: JAIS 30B
+        mad_tag: pyt_vllm_jais-30b
+        model_repo: core42/jais-30b-chat-v3
+        url: https://huggingface.co/core42/jais-30b-chat-v3
+        precision: float16
+    - group: DBRX
+      tag: dbrx
+      models:
+      - model: DBRX Instruct
+        mad_tag: pyt_vllm_dbrx-instruct
+        model_repo: databricks/dbrx-instruct
+        url: https://huggingface.co/databricks/dbrx-instruct
+        precision: float16
+      - model: DBRX Instruct FP8
+        mad_tag: pyt_vllm_dbrx_fp8
+        model_repo: amd/dbrx-instruct-FP8-KV
+        url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
+        precision: float8
+    - group: Gemma
+      tag: gemma
+      models:
+      - model: Gemma 2 27B
+        mad_tag: pyt_vllm_gemma-2-27b
+        model_repo: google/gemma-2-27b
+        url: https://huggingface.co/google/gemma-2-27b
+        precision: float16
+    - group: Cohere
+      tag: cohere
+      models:
+      - model: C4AI Command R+ 08-2024
+        mad_tag: pyt_vllm_c4ai-command-r-plus-08-2024
+        model_repo: CohereForAI/c4ai-command-r-plus-08-2024
+        url: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024
+        precision: float16
+      - model: C4AI Command R+ 08-2024 FP8
+        mad_tag: pyt_vllm_command-r-plus_fp8
+        model_repo: amd/c4ai-command-r-plus-FP8-KV
+        url: https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV
+        precision: float8
+    - group: DeepSeek
+      tag: deepseek
+      models:
+      - model: DeepSeek MoE 16B
+        mad_tag: pyt_vllm_deepseek-moe-16b-chat
+        model_repo: deepseek-ai/deepseek-moe-16b-chat
+        url: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat
+        precision: float16

docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.8.3_20250415-benchmark-models.yaml

@@ -0,0 +1,152 @@
+vllm_benchmark:
+  unified_docker:
+    latest:
+      pull_tag: rocm/vllm:rocm6.3.1_instinct_vllm0.8.3_20250415
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.8.3_20250415/images/sha256-ad9062dea3483d59dedb17c67f7c49f30eebd6eb37c3fac0a171fb19696cc845
+      rocm_version: 6.3.1
+      vllm_version: 0.8.3
+      pytorch_version: 2.7.0 (dev nightly)
+      hipblaslt_version: 0.13
+  model_groups:
+    - group: Llama
+      tag: llama
+      models:
+      - model: Llama 3.1 8B
+        mad_tag: pyt_vllm_llama-3.1-8b
+        model_repo: meta-llama/Llama-3.1-8B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: float16
+      - model: Llama 3.1 70B
+        mad_tag: pyt_vllm_llama-3.1-70b
+        model_repo: meta-llama/Llama-3.1-70B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+        precision: float16
+      - model: Llama 3.1 405B
+        mad_tag: pyt_vllm_llama-3.1-405b
+        model_repo: meta-llama/Llama-3.1-405B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
+        precision: float16
+      - model: Llama 3.2 11B Vision
+        mad_tag: pyt_vllm_llama-3.2-11b-vision-instruct
+        model_repo: meta-llama/Llama-3.2-11B-Vision-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct
+        precision: float16
+      - model: Llama 2 7B
+        mad_tag: pyt_vllm_llama-2-7b
+        model_repo: meta-llama/Llama-2-7b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
+        precision: float16
+      - model: Llama 2 70B
+        mad_tag: pyt_vllm_llama-2-70b
+        model_repo: meta-llama/Llama-2-70b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+        precision: float16
+      - model: Llama 3.1 8B FP8
+        mad_tag: pyt_vllm_llama-3.1-8b_fp8
+        model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
+        precision: float8
+      - model: Llama 3.1 70B FP8
+        mad_tag: pyt_vllm_llama-3.1-70b_fp8
+        model_repo: amd/Llama-3.1-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV
+        precision: float8
+      - model: Llama 3.1 405B FP8
+        mad_tag: pyt_vllm_llama-3.1-405b_fp8
+        model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+        precision: float8
+    - group: Mistral
+      tag: mistral
+      models:
+      - model: Mixtral MoE 8x7B
+        mad_tag: pyt_vllm_mixtral-8x7b
+        model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+        precision: float16
+      - model: Mixtral MoE 8x22B
+        mad_tag: pyt_vllm_mixtral-8x22b
+        model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
+        precision: float16
+      - model: Mistral 7B
+        mad_tag: pyt_vllm_mistral-7b
+        model_repo: mistralai/Mistral-7B-Instruct-v0.3
+        url: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
+        precision: float16
+      - model: Mixtral MoE 8x7B FP8
+        mad_tag: pyt_vllm_mixtral-8x7b_fp8
+        model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        precision: float8
+      - model: Mixtral MoE 8x22B FP8
+        mad_tag: pyt_vllm_mixtral-8x22b_fp8
+        model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        precision: float8
+      - model: Mistral 7B FP8
+        mad_tag: pyt_vllm_mistral-7b_fp8
+        model_repo: amd/Mistral-7B-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV
+        precision: float8
+    - group: Qwen
+      tag: qwen
+      models:
+      - model: Qwen2 7B
+        mad_tag: pyt_vllm_qwen2-7b
+        model_repo: Qwen/Qwen2-7B-Instruct
+        url: https://huggingface.co/Qwen/Qwen2-7B-Instruct
+        precision: float16
+      - model: Qwen2 72B
+        mad_tag: pyt_vllm_qwen2-72b
+        model_repo: Qwen/Qwen2-72B-Instruct
+        url: https://huggingface.co/Qwen/Qwen2-72B-Instruct
+        precision: float16
+      - model: QwQ-32B
+        mad_tag: pyt_vllm_qwq-32b
+        model_repo: Qwen/QwQ-32B
+        url: https://huggingface.co/Qwen/QwQ-32B
+        precision: float16
+        tunableop: true
+    - group: DBRX
+      tag: dbrx
+      models:
+      - model: DBRX Instruct
+        mad_tag: pyt_vllm_dbrx-instruct
+        model_repo: databricks/dbrx-instruct
+        url: https://huggingface.co/databricks/dbrx-instruct
+        precision: float16
+      - model: DBRX Instruct FP8
+        mad_tag: pyt_vllm_dbrx_fp8
+        model_repo: amd/dbrx-instruct-FP8-KV
+        url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
+        precision: float8
+    - group: Gemma
+      tag: gemma
+      models:
+      - model: Gemma 2 27B
+        mad_tag: pyt_vllm_gemma-2-27b
+        model_repo: google/gemma-2-27b
+        url: https://huggingface.co/google/gemma-2-27b
+        precision: float16
+    - group: Cohere
+      tag: cohere
+      models:
+      - model: C4AI Command R+ 08-2024
+        mad_tag: pyt_vllm_c4ai-command-r-plus-08-2024
+        model_repo: CohereForAI/c4ai-command-r-plus-08-2024
+        url: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024
+        precision: float16
+      - model: C4AI Command R+ 08-2024 FP8
+        mad_tag: pyt_vllm_command-r-plus_fp8
+        model_repo: amd/c4ai-command-r-plus-FP8-KV
+        url: https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV
+        precision: float8
+    - group: DeepSeek
+      tag: deepseek
+      models:
+      - model: DeepSeek MoE 16B
+        mad_tag: pyt_vllm_deepseek-moe-16b-chat
+        model_repo: deepseek-ai/deepseek-moe-16b-chat
+        url: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat
+        precision: float16

docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.8.5_20250513-benchmark-models.yaml

@@ -0,0 +1,152 @@
+vllm_benchmark:
+  unified_docker:
+    latest:
+      pull_tag: rocm/vllm:rocm6.3.1_vllm0.8.5_20250513
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_vllm_0.8.5_20250513/images/sha256-5c8b4436dd0464119d9df2b44c745fadf81512f18ffb2f4b5dc235c71ebe26b4
+      rocm_version: 6.3.1
+      vllm_version: 0.8.5
+      pytorch_version: 2.7.0+gitf717b2a
+      hipblaslt_version: 0.15
+  model_groups:
+    - group: Meta Llama
+      tag: llama
+      models:
+      - model: Llama 3.1 8B
+        mad_tag: pyt_vllm_llama-3.1-8b
+        model_repo: meta-llama/Llama-3.1-8B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: float16
+      - model: Llama 3.1 70B
+        mad_tag: pyt_vllm_llama-3.1-70b
+        model_repo: meta-llama/Llama-3.1-70B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+        precision: float16
+      - model: Llama 3.1 405B
+        mad_tag: pyt_vllm_llama-3.1-405b
+        model_repo: meta-llama/Llama-3.1-405B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
+        precision: float16
+      - model: Llama 3.2 11B Vision
+        mad_tag: pyt_vllm_llama-3.2-11b-vision-instruct
+        model_repo: meta-llama/Llama-3.2-11B-Vision-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct
+        precision: float16
+      - model: Llama 2 7B
+        mad_tag: pyt_vllm_llama-2-7b
+        model_repo: meta-llama/Llama-2-7b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
+        precision: float16
+      - model: Llama 2 70B
+        mad_tag: pyt_vllm_llama-2-70b
+        model_repo: meta-llama/Llama-2-70b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+        precision: float16
+      - model: Llama 3.1 8B FP8
+        mad_tag: pyt_vllm_llama-3.1-8b_fp8
+        model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
+        precision: float8
+      - model: Llama 3.1 70B FP8
+        mad_tag: pyt_vllm_llama-3.1-70b_fp8
+        model_repo: amd/Llama-3.1-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV
+        precision: float8
+      - model: Llama 3.1 405B FP8
+        mad_tag: pyt_vllm_llama-3.1-405b_fp8
+        model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+        precision: float8
+    - group: Mistral AI
+      tag: mistral
+      models:
+      - model: Mixtral MoE 8x7B
+        mad_tag: pyt_vllm_mixtral-8x7b
+        model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+        precision: float16
+      - model: Mixtral MoE 8x22B
+        mad_tag: pyt_vllm_mixtral-8x22b
+        model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
+        precision: float16
+      - model: Mistral 7B
+        mad_tag: pyt_vllm_mistral-7b
+        model_repo: mistralai/Mistral-7B-Instruct-v0.3
+        url: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
+        precision: float16
+      - model: Mixtral MoE 8x7B FP8
+        mad_tag: pyt_vllm_mixtral-8x7b_fp8
+        model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        precision: float8
+      - model: Mixtral MoE 8x22B FP8
+        mad_tag: pyt_vllm_mixtral-8x22b_fp8
+        model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        precision: float8
+      - model: Mistral 7B FP8
+        mad_tag: pyt_vllm_mistral-7b_fp8
+        model_repo: amd/Mistral-7B-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV
+        precision: float8
+    - group: Qwen
+      tag: qwen
+      models:
+      - model: Qwen2 7B
+        mad_tag: pyt_vllm_qwen2-7b
+        model_repo: Qwen/Qwen2-7B-Instruct
+        url: https://huggingface.co/Qwen/Qwen2-7B-Instruct
+        precision: float16
+      - model: Qwen2 72B
+        mad_tag: pyt_vllm_qwen2-72b
+        model_repo: Qwen/Qwen2-72B-Instruct
+        url: https://huggingface.co/Qwen/Qwen2-72B-Instruct
+        precision: float16
+      - model: QwQ-32B
+        mad_tag: pyt_vllm_qwq-32b
+        model_repo: Qwen/QwQ-32B
+        url: https://huggingface.co/Qwen/QwQ-32B
+        precision: float16
+        tunableop: true
+    - group: Databricks DBRX
+      tag: dbrx
+      models:
+      - model: DBRX Instruct
+        mad_tag: pyt_vllm_dbrx-instruct
+        model_repo: databricks/dbrx-instruct
+        url: https://huggingface.co/databricks/dbrx-instruct
+        precision: float16
+      - model: DBRX Instruct FP8
+        mad_tag: pyt_vllm_dbrx_fp8
+        model_repo: amd/dbrx-instruct-FP8-KV
+        url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
+        precision: float8
+    - group: Google Gemma
+      tag: gemma
+      models:
+      - model: Gemma 2 27B
+        mad_tag: pyt_vllm_gemma-2-27b
+        model_repo: google/gemma-2-27b
+        url: https://huggingface.co/google/gemma-2-27b
+        precision: float16
+    - group: Cohere
+      tag: cohere
+      models:
+      - model: C4AI Command R+ 08-2024
+        mad_tag: pyt_vllm_c4ai-command-r-plus-08-2024
+        model_repo: CohereForAI/c4ai-command-r-plus-08-2024
+        url: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024
+        precision: float16
+      - model: C4AI Command R+ 08-2024 FP8
+        mad_tag: pyt_vllm_command-r-plus_fp8
+        model_repo: amd/c4ai-command-r-plus-FP8-KV
+        url: https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV
+        precision: float8
+    - group: DeepSeek
+      tag: deepseek
+      models:
+      - model: DeepSeek MoE 16B
+        mad_tag: pyt_vllm_deepseek-moe-16b-chat
+        model_repo: deepseek-ai/deepseek-moe-16b-chat
+        url: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat
+        precision: float16

docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.8.5_20250521-benchmark-models.yaml

@@ -0,0 +1,167 @@
+vllm_benchmark:
+  unified_docker:
+    latest:
+      pull_tag: rocm/vllm:rocm6.3.1_vllm0.8.5_20250521
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_vllm_0.8.5_20250521/images/sha256-38410c51af7208897cd8b737c9bdfc126e9bc8952d4aa6b88c85482f03092a11
+      rocm_version: 6.3.1
+      vllm_version: 0.8.5 (0.8.6.dev315+g91a560098.rocm631)
+      pytorch_version: 2.7.0+gitf717b2a
+      hipblaslt_version: 0.15
+  model_groups:
+    - group: Meta Llama
+      tag: llama
+      models:
+        - model: Llama 3.1 8B
+          mad_tag: pyt_vllm_llama-3.1-8b
+          model_repo: meta-llama/Llama-3.1-8B-Instruct
+          url: https://huggingface.co/meta-llama/Llama-3.1-8B
+          precision: float16
+        - model: Llama 3.1 70B
+          mad_tag: pyt_vllm_llama-3.1-70b
+          model_repo: meta-llama/Llama-3.1-70B-Instruct
+          url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+          precision: float16
+        - model: Llama 3.1 405B
+          mad_tag: pyt_vllm_llama-3.1-405b
+          model_repo: meta-llama/Llama-3.1-405B-Instruct
+          url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
+          precision: float16
+        - model: Llama 3.2 11B Vision
+          mad_tag: pyt_vllm_llama-3.2-11b-vision-instruct
+          model_repo: meta-llama/Llama-3.2-11B-Vision-Instruct
+          url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct
+          precision: float16
+        - model: Llama 2 7B
+          mad_tag: pyt_vllm_llama-2-7b
+          model_repo: meta-llama/Llama-2-7b-chat-hf
+          url: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
+          precision: float16
+        - model: Llama 2 70B
+          mad_tag: pyt_vllm_llama-2-70b
+          model_repo: meta-llama/Llama-2-70b-chat-hf
+          url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+          precision: float16
+        - model: Llama 3.1 8B FP8
+          mad_tag: pyt_vllm_llama-3.1-8b_fp8
+          model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
+          url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
+          precision: float8
+        - model: Llama 3.1 70B FP8
+          mad_tag: pyt_vllm_llama-3.1-70b_fp8
+          model_repo: amd/Llama-3.1-70B-Instruct-FP8-KV
+          url: https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV
+          precision: float8
+        - model: Llama 3.1 405B FP8
+          mad_tag: pyt_vllm_llama-3.1-405b_fp8
+          model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
+          url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+          precision: float8
+    - group: Mistral AI
+      tag: mistral
+      models:
+        - model: Mixtral MoE 8x7B
+          mad_tag: pyt_vllm_mixtral-8x7b
+          model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
+          url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+          precision: float16
+        - model: Mixtral MoE 8x22B
+          mad_tag: pyt_vllm_mixtral-8x22b
+          model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
+          url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
+          precision: float16
+        - model: Mistral 7B
+          mad_tag: pyt_vllm_mistral-7b
+          model_repo: mistralai/Mistral-7B-Instruct-v0.3
+          url: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
+          precision: float16
+        - model: Mixtral MoE 8x7B FP8
+          mad_tag: pyt_vllm_mixtral-8x7b_fp8
+          model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+          url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+          precision: float8
+        - model: Mixtral MoE 8x22B FP8
+          mad_tag: pyt_vllm_mixtral-8x22b_fp8
+          model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+          url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+          precision: float8
+        - model: Mistral 7B FP8
+          mad_tag: pyt_vllm_mistral-7b_fp8
+          model_repo: amd/Mistral-7B-v0.1-FP8-KV
+          url: https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV
+          precision: float8
+    - group: Qwen
+      tag: qwen
+      models:
+        - model: Qwen2 7B
+          mad_tag: pyt_vllm_qwen2-7b
+          model_repo: Qwen/Qwen2-7B-Instruct
+          url: https://huggingface.co/Qwen/Qwen2-7B-Instruct
+          precision: float16
+        - model: Qwen2 72B
+          mad_tag: pyt_vllm_qwen2-72b
+          model_repo: Qwen/Qwen2-72B-Instruct
+          url: https://huggingface.co/Qwen/Qwen2-72B-Instruct
+          precision: float16
+        - model: QwQ-32B
+          mad_tag: pyt_vllm_qwq-32b
+          model_repo: Qwen/QwQ-32B
+          url: https://huggingface.co/Qwen/QwQ-32B
+          precision: float16
+          tunableop: true
+    - group: Databricks DBRX
+      tag: dbrx
+      models:
+        - model: DBRX Instruct
+          mad_tag: pyt_vllm_dbrx-instruct
+          model_repo: databricks/dbrx-instruct
+          url: https://huggingface.co/databricks/dbrx-instruct
+          precision: float16
+        - model: DBRX Instruct FP8
+          mad_tag: pyt_vllm_dbrx_fp8
+          model_repo: amd/dbrx-instruct-FP8-KV
+          url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
+          precision: float8
+    - group: Google Gemma
+      tag: gemma
+      models:
+        - model: Gemma 2 27B
+          mad_tag: pyt_vllm_gemma-2-27b
+          model_repo: google/gemma-2-27b
+          url: https://huggingface.co/google/gemma-2-27b
+          precision: float16
+    - group: Cohere
+      tag: cohere
+      models:
+        - model: C4AI Command R+ 08-2024
+          mad_tag: pyt_vllm_c4ai-command-r-plus-08-2024
+          model_repo: CohereForAI/c4ai-command-r-plus-08-2024
+          url: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024
+          precision: float16
+        - model: C4AI Command R+ 08-2024 FP8
+          mad_tag: pyt_vllm_command-r-plus_fp8
+          model_repo: amd/c4ai-command-r-plus-FP8-KV
+          url: https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV
+          precision: float8
+    - group: DeepSeek
+      tag: deepseek
+      models:
+        - model: DeepSeek MoE 16B
+          mad_tag: pyt_vllm_deepseek-moe-16b-chat
+          model_repo: deepseek-ai/deepseek-moe-16b-chat
+          url: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat
+          precision: float16
+    - group: Microsoft Phi
+      tag: phi
+      models:
+        - model: Phi-4
+          mad_tag: pyt_vllm_phi-4
+          model_repo: microsoft/phi-4
+          url: https://huggingface.co/microsoft/phi-4
+    - group: TII Falcon
+      tag: falcon
+      models:
+        - model: Falcon 180B
+          mad_tag: pyt_vllm_falcon-180b
+          model_repo: tiiuae/falcon-180B
+          url: https://huggingface.co/tiiuae/falcon-180B
+          precision: float16

docs/data/how-to/rocm-for-ai/inference/pytorch-inference-benchmark-models.yaml

@@ -23,3 +23,11 @@ pytorch_inference_benchmark:
         model_repo: meta-llama/Llama-3.1-8B-Instruct
         url: https://huggingface.co/chaidiscovery/chai-1
         precision: float16
+    - group: Mochi Video
+      tag: mochi
+      models:
+      - model: Mochi 1
+        mad_tag: pyt_mochi_video_inference
+        model_repo: genmo/mochi-1-preview
+        url: https://huggingface.co/genmo/mochi-1-preview
+        precision: float16

docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml

@@ -1,14 +1,14 @@
 vllm_benchmark:
   unified_docker:
     latest:
-      pull_tag: rocm/vllm:rocm6.3.1_instinct_vllm0.8.3_20250415
-      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.8.3_20250415/images/sha256-ad9062dea3483d59dedb17c67f7c49f30eebd6eb37c3fac0a171fb19696cc845
-      rocm_version: 6.3.1
-      vllm_version: 0.8.3
-      pytorch_version: 2.7.0 (dev nightly)
-      hipblaslt_version: 0.13
+      pull_tag: rocm/vllm:rocm6.4.1_vllm_0.9.0.1_20250605
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.9.0.1_20250605/images/sha256-f48beeb3d72663a93c77211eb45273d564451447c097e060befa713d565fa36c
+      rocm_version: 6.4.1
+      vllm_version: 0.9.0.1 (0.9.0.2.dev108+g71faa1880.rocm641)
+      pytorch_version: 2.7.0+gitf717b2a
+      hipblaslt_version: 0.15
   model_groups:
-    - group: Llama
+    - group: Meta Llama
       tag: llama
       models:
       - model: Llama 3.1 8B
@@ -26,11 +26,6 @@ vllm_benchmark:
         model_repo: meta-llama/Llama-3.1-405B-Instruct
         url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
         precision: float16
-      - model: Llama 3.2 11B Vision
-        mad_tag: pyt_vllm_llama-3.2-11b-vision-instruct
-        model_repo: meta-llama/Llama-3.2-11B-Vision-Instruct
-        url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct
-        precision: float16
       - model: Llama 2 7B
         mad_tag: pyt_vllm_llama-2-7b
         model_repo: meta-llama/Llama-2-7b-chat-hf
@@ -56,7 +51,7 @@ vllm_benchmark:
         model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
         url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
         precision: float8
-    - group: Mistral
+    - group: Mistral AI
       tag: mistral
       models:
       - model: Mixtral MoE 8x7B
@@ -108,7 +103,7 @@ vllm_benchmark:
         url: https://huggingface.co/Qwen/QwQ-32B
         precision: float16
         tunableop: true
-    - group: DBRX
+    - group: Databricks DBRX
       tag: dbrx
       models:
       - model: DBRX Instruct
@@ -121,7 +116,7 @@ vllm_benchmark:
         model_repo: amd/dbrx-instruct-FP8-KV
         url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
         precision: float8
-    - group: Gemma
+    - group: Google Gemma
       tag: gemma
       models:
       - model: Gemma 2 27B
@@ -150,3 +145,18 @@ vllm_benchmark:
         model_repo: deepseek-ai/deepseek-moe-16b-chat
         url: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat
         precision: float16
+    - group: Microsoft Phi
+      tag: phi
+      models:
+      - model: Phi-4
+        mad_tag: pyt_vllm_phi-4
+        model_repo: microsoft/phi-4
+        url: https://huggingface.co/microsoft/phi-4
+    - group: TII Falcon
+      tag: falcon
+      models:
+      - model: Falcon 180B
+        mad_tag: pyt_vllm_falcon-180b
+        model_repo: tiiuae/falcon-180B
+        url: https://huggingface.co/tiiuae/falcon-180B
+        precision: float16

docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml

@@ -0,0 +1,29 @@
+megatron-lm_benchmark:
+  model_groups:
+    - group: Meta Llama
+      tag: llama
+      models:
+      - model: Llama 3.3 70B
+        mad_tag: pyt_megatron_lm_train_llama-3.3-70b
+      - model: Llama 3.1 8B
+        mad_tag: pyt_megatron_lm_train_llama-3.1-8b
+      - model: Llama 3.1 70B
+        mad_tag: pyt_megatron_lm_train_llama-3.1-70b
+      - model: Llama 2 7B
+        mad_tag: pyt_megatron_lm_train_llama-2-7b
+      - model: Llama 2 70B
+        mad_tag: pyt_megatron_lm_train_llama-2-70b
+    - group: DeepSeek
+      tag: deepseek
+      models:
+      - model: DeepSeek-V3
+        mad_tag: pyt_megatron_lm_train_deepseek-v3-proxy
+      - model: DeepSeek-V2-Lite
+        mad_tag: pyt_megatron_lm_train_deepseek-v2-lite-16b
+    - group: Mistral AI
+      tag: mistral
+      models:
+      - model: Mixtral 8x7B
+        mad_tag: pyt_megatron_lm_train_mixtral-8x7b
+      - model: Mixtral 8x22B
+        mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy

docs/data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml

@@ -0,0 +1,120 @@
+unified_docker:
+  latest:
+    pull_tag: rocm/pytorch-training:v25.6
+    docker_hub_url: https://hub.docker.com/r/rocm/pytorch-training/tags
+    rocm_version: 6.4.1
+    pytorch_version: 2.8.0a0+git7d205b2
+    python_version: 3.10.17
+    transformer_engine_version: 1.14.0+2f85f5f2
+    flash_attention_version: 3.0.0.post1
+    hipblaslt_version: 0.15.0-8c6919d
+    triton_version: 3.3.0
+model_groups:
+  - group: Pre-training
+    tag: pre-training
+    models:
+    - model: Llama 3.1 8B
+      mad_tag: pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+      training_modes: [pretrain]
+    - model: Llama 3.1 70B
+      mad_tag: pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+      precision: BF16
+      training_modes: [pretrain]
+    - model: FLUX.1-dev
+      mad_tag: pyt_train_flux
+      model_repo: Flux
+      url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+      precision: BF16
+      training_modes: [pretrain]
+  - group: Fine-tuning
+    tag: fine-tuning
+    models:
+    - model: Llama 4 Scout 17B-16E
+      mad_tag: pyt_train_llama-4-scout-17b-16e
+      model_repo: Llama-4-17B_16E
+      url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.3 70B
+      mad_tag: pyt_train_llama-3.3-70b
+      model_repo: Llama-3.3-70B
+      url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 3.2 1B
+      mad_tag: pyt_train_llama-3.2-1b
+      model_repo: Llama-3.2-1B
+      url: https://huggingface.co/meta-llama/Llama-3.2-1B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 3B
+      mad_tag: pyt_train_llama-3.2-3b
+      model_repo: Llama-3.2-3B
+      url: https://huggingface.co/meta-llama/Llama-3.2-3B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 Vision 11B
+      mad_tag: pyt_train_llama-3.2-vision-11b
+      model_repo: Llama-3.2-Vision-11B
+      url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.2 Vision 90B
+      mad_tag: pyt_train_llama-3.2-vision-90b
+      model_repo: Llama-3.2-Vision-90B
+      url: https://huggingface.co/meta-llama/Llama-3.2-90B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.1 8B
+      mad_tag: pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.1 70B
+      mad_tag: pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 3.1 405B
+      mad_tag: pyt_train_llama-3.1-405b
+      model_repo: Llama-3.1-405B
+      url: https://huggingface.co/meta-llama/Llama-3.1-405B
+      precision: BF16
+      training_modes: [finetune_qlora, HF_finetune_lora]
+    - model: Llama 3 8B
+      mad_tag: pyt_train_llama-3-8b
+      model_repo: Llama-3-8B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3 70B
+      mad_tag: pyt_train_llama-3-70b
+      model_repo: Llama-3-70B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-70B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 7B
+      mad_tag: pyt_train_llama-2-7b
+      model_repo: Llama-2-7B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 2 13B
+      mad_tag: pyt_train_llama-2-13b
+      model_repo: Llama-2-13B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 70B
+      mad_tag: pyt_train_llama-2-70b
+      model_repo: Llama-2-70B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_lora, finetune_qlora, HF_finetune_lora]

docs/how-to/rocm-for-ai/inference-optimization/workload.rst

@@ -678,7 +678,7 @@ To specify the quantization scaling config, use the
 ``--quantization-param-path`` parameter. If the parameter is not specified,
 the default scaling factor of ``1`` is used, which can lead to less accurate
 results. To generate ``kv-cache`` scaling JSON file, see `FP8 KV
-Cache <https://github.com/vllm-project/vllm/blob/main/examples/fp8/README.md>`__
+Cache <https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_kv_cache/README.md>`__
 in the vLLM GitHub repository.
 
 Two sample Llama scaling configuration files are in vLLM for ``llama2-70b`` and

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.4.3.rst

@@ -0,0 +1,346 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the unified
+                 ROCm Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker:
+
+The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
+a prebuilt, optimized environment designed for validating large language model
+(LLM) inference performance on the AMD Instinct™ MI300X accelerator. This
+ROCm vLLM Docker image integrates vLLM and PyTorch tailored specifically for the
+MI300X accelerator and includes the following components:
+
+* `ROCm 6.2.0 <https://github.com/ROCm/ROCm>`_
+
+* `vLLM 0.4.3 <https://docs.vllm.ai/en/latest>`_
+
+* `PyTorch 2.4.0 <https://github.com/pytorch/pytorch>`_
+
+* Tuning files (in CSV format)
+
+With this Docker image, you can quickly validate the expected inference
+performance numbers on the MI300X accelerator. This topic also provides tips on
+optimizing performance with popular AI models.
+
+.. _vllm-benchmark-vllm:
+
+.. note::
+
+   vLLM is a toolkit and library for LLM inference and
+   serving. It deploys the PagedAttention algorithm, which reduces memory
+   consumption and increases throughput by leveraging dynamic key and value
+   allocation in GPU memory. vLLM also incorporates many LLM acceleration
+   and quantization algorithms. In addition, AMD implements high-performance
+   custom kernels and modules in vLLM to enhance performance further. See
+   :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for more
+   information.
+
+Getting started
+===============
+
+Use the following procedures to reproduce the benchmark results on an
+MI300X accelerator with the prebuilt vLLM Docker image.
+
+.. _vllm-benchmark-get-started:
+
+1. Disable NUMA auto-balancing.
+
+   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+   might hang until the periodic balancing is finalized. For more information,
+   see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
+
+   .. code-block:: shell
+
+      # disable automatic NUMA balancing
+      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+      # check if NUMA balancing is disabled (returns 0 if disabled)
+      cat /proc/sys/kernel/numa_balancing
+      0
+
+2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
+
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/vllm:rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50
+
+Once setup is complete, you can choose between two options to reproduce the
+benchmark results:
+
+-  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
+
+-  :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
+
+.. _vllm-benchmark-mad:
+
+MAD-integrated benchmarking
+===========================
+
+Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+directory and install the required packages on the host machine.
+
+.. code-block:: shell
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD
+   pip install -r requirements.txt
+
+Use this command to run a performance benchmark test of the Llama 3.1 8B model
+on one GPU with ``float16`` data type in the host machine.
+
+.. code-block:: shell
+
+   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+   python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
+
+ROCm MAD launches a Docker container with the name
+``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
+model are collected in the following path: ``~/MAD/reports_float16/``
+
+Although the following eight models are pre-configured to collect latency and
+throughput performance data, users can also change the benchmarking parameters.
+Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
+
+Available models
+----------------
+
+.. hlist::
+   :columns: 3
+
+   * ``pyt_vllm_llama-3.1-8b``
+
+   * ``pyt_vllm_llama-3.1-70b``
+
+   * ``pyt_vllm_llama-3.1-405b``
+
+   * ``pyt_vllm_llama-2-7b``
+
+   * ``pyt_vllm_mistral-7b``
+
+   * ``pyt_vllm_qwen2-7b``
+
+   * ``pyt_vllm_jais-13b``
+
+   * ``pyt_vllm_jais-30b``
+
+.. _vllm-benchmark-standalone:
+
+Standalone benchmarking
+=======================
+
+You can run the vLLM benchmark tool independently by starting the
+:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
+snippet.
+
+.. code-block::
+
+   docker pull rocm/vllm:rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50
+   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name unified_docker_vllm rocm/vllm:rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50
+
+In the Docker container, clone the ROCm MAD repository and navigate to the
+benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+.. code-block::
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD/scripts/vllm
+
+Multiprocessing distributed executor
+--------------------------------------
+
+To optimize vLLM performance, add the multiprocessing API server argument ``--distributed-executor-backend mp``.
+
+Command
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+To start the benchmark, use the following command with the appropriate options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
+
+See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
+
+.. note::
+
+   The input sequence length, output sequence length, and tensor parallel (TP) are
+   already configured. You don't need to specify them with this script.
+
+.. note::
+
+   If you encounter the following error, pass your access-authorized Hugging
+   Face token to the gated models.
+
+   .. code-block:: shell
+
+      OSError: You are trying to access a gated repo.
+
+      # pass your HF_TOKEN
+      export HF_TOKEN=$your_personal_hf_token
+
+.. _vllm-benchmark-standalone-options:
+
+Options
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. list-table::
+   :header-rows: 1
+
+   * - Name
+     - Options
+     - Description
+
+   * - ``$test_option``
+     - latency
+     - Measure decoding token latency
+
+   * -
+     - throughput
+     - Measure token generation throughput
+
+   * -
+     - all
+     - Measure both throughput and latency
+
+   * - ``$model_repo``
+     - ``meta-llama/Meta-Llama-3.1-8B-Instruct``
+     - Llama 3.1 8B
+
+   * - (``float16``)
+     - ``meta-llama/Meta-Llama-3.1-70B-Instruct``
+     - Llama 3.1 70B
+
+   * -
+     - ``meta-llama/Meta-Llama-3.1-405B-Instruct``
+     - Llama 3.1 405B
+
+   * -
+     - ``meta-llama/Llama-2-7b-chat-hf``
+     - Llama 2 7B
+
+   * -
+     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
+     - Mixtral 8x7B
+
+   * -
+     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
+     - Mixtral 8x22B
+
+   * -
+     - ``mistralai/Mistral-7B-Instruct-v0.3``
+     - Mixtral 7B
+
+   * -
+     - ``Qwen/Qwen2-7B-Instruct``
+     - Qwen2 7B
+
+   * -
+     - ``core42/jais-13b-chat``
+     - JAIS 13B
+
+   * -
+     - ``core42/jais-30b-chat-v3``
+     - JAIS 30B
+
+   * - ``$num_gpu``
+     - 1 or 8
+     - Number of GPUs
+
+   * - ``$datatype``
+     - ``float16``
+     - Data type
+
+.. _vllm-benchmark-run-benchmark:
+
+Running the benchmark on the MI300X accelerator
+-----------------------------------------------
+
+Here are some examples of running the benchmark with various options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+Latency benchmark example
+^^^^^^^^^^^^^^^^^^^^^^^^^
+ 
+Use this command to benchmark the latency of the Llama 3.1 8B model on one GPU with the ``float16`` data type.
+
+.. code-block::
+
+   ./vllm_benchmark_report.sh -s latency -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
+
+Find the latency report at:
+
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_latency_report.csv``
+
+Throughput benchmark example
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Use this command to benchmark the throughput of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
+
+Find the throughput reports at:
+
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``
+
+.. raw:: html
+
+   <style>
+   mjx-container[jax="CHTML"][display="true"] {
+       text-align: left;
+       margin: 0;
+   }
+
+   </style>
+
+.. note::
+
+   Throughput is calculated as:
+
+   - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+   - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+
+Further reading
+===============
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/tuning-guides/mi300x/workload`.
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see :doc:`/how-to/system-optimization/mi300x`.
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Using ROCm for AI </how-to/rocm-for-ai/index>`.
+
+- To learn how to optimize inference on LLMs, see
+  :doc:`Fine-tuning LLMs and inference optimization </how-to/llm-fine-tuning-optimization/index>`.
+
+- For a list of other ready-made Docker images for ROCm, see the
+  :doc:`Docker image support matrix <rocm-install-on-linux:reference/docker-image-support-matrix>`.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.6.4.rst

@@ -0,0 +1,419 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the unified
+                 ROCm Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker:
+
+The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
+a prebuilt, optimized environment designed for validating large language model
+(LLM) inference performance on the AMD Instinct™ MI300X accelerator. This
+ROCm vLLM Docker image integrates vLLM and PyTorch tailored specifically for the
+MI300X accelerator and includes the following components:
+
+* `ROCm 6.2.1 <https://github.com/ROCm/ROCm>`_
+
+* `vLLM 0.6.4 <https://docs.vllm.ai/en/latest>`_
+
+* `PyTorch 2.5.0 <https://github.com/pytorch/pytorch>`_
+
+* Tuning files (in CSV format)
+
+With this Docker image, you can quickly validate the expected inference
+performance numbers on the MI300X accelerator. This topic also provides tips on
+optimizing performance with popular AI models.
+
+.. hlist::
+   :columns: 6
+
+   * Llama 3.1 8B
+
+   * Llama 3.1 70B
+
+   * Llama 3.1 405B
+
+   * Llama 2 7B
+
+   * Llama 2 70B
+
+   * Mixtral 8x7B
+
+   * Mixtral 8x22B
+
+   * Mixtral 7B
+
+   * Qwen2 7B
+
+   * Qwen2 72B
+
+   * JAIS 13B
+
+   * JAIS 30B
+
+.. _vllm-benchmark-vllm:
+
+.. note::
+
+   vLLM is a toolkit and library for LLM inference and serving. AMD implements
+   high-performance custom kernels and modules in vLLM to enhance performance.
+   See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+   more information.
+
+Getting started
+===============
+
+Use the following procedures to reproduce the benchmark results on an
+MI300X accelerator with the prebuilt vLLM Docker image.
+
+.. _vllm-benchmark-get-started:
+
+1. Disable NUMA auto-balancing.
+
+   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+   might hang until the periodic balancing is finalized. For more information,
+   see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
+
+   .. code-block:: shell
+
+      # disable automatic NUMA balancing
+      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+      # check if NUMA balancing is disabled (returns 0 if disabled)
+      cat /proc/sys/kernel/numa_balancing
+      0
+
+2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
+
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+
+Once setup is complete, you can choose between two options to reproduce the
+benchmark results:
+
+-  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
+
+-  :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
+
+.. _vllm-benchmark-mad:
+
+MAD-integrated benchmarking
+===========================
+
+Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+directory and install the required packages on the host machine.
+
+.. code-block:: shell
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD
+   pip install -r requirements.txt
+
+Use this command to run a performance benchmark test of the Llama 3.1 8B model
+on one GPU with ``float16`` data type in the host machine.
+
+.. code-block:: shell
+
+   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+   python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
+
+ROCm MAD launches a Docker container with the name
+``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
+model are collected in the following path: ``~/MAD/reports_float16/``.
+
+Although the following models are preconfigured to collect latency and
+throughput performance data, you can also change the benchmarking parameters.
+Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
+
+Available models
+----------------
+
+.. hlist::
+   :columns: 3
+
+   * ``pyt_vllm_llama-3.1-8b``
+
+   * ``pyt_vllm_llama-3.1-70b``
+
+   * ``pyt_vllm_llama-3.1-405b``
+
+   * ``pyt_vllm_llama-2-7b``
+
+   * ``pyt_vllm_llama-2-70b``
+
+   * ``pyt_vllm_mixtral-8x7b``
+
+   * ``pyt_vllm_mixtral-8x22b``
+
+   * ``pyt_vllm_mistral-7b``
+
+   * ``pyt_vllm_qwen2-7b``
+
+   * ``pyt_vllm_qwen2-72b``
+
+   * ``pyt_vllm_jais-13b``
+
+   * ``pyt_vllm_jais-30b``
+
+   * ``pyt_vllm_llama-3.1-8b_fp8``
+
+   * ``pyt_vllm_llama-3.1-70b_fp8``
+
+   * ``pyt_vllm_llama-3.1-405b_fp8``
+
+   * ``pyt_vllm_mixtral-8x7b_fp8``
+
+   * ``pyt_vllm_mixtral-8x22b_fp8``
+
+.. _vllm-benchmark-standalone:
+
+Standalone benchmarking
+=======================
+
+You can run the vLLM benchmark tool independently by starting the
+:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
+snippet.
+
+.. code-block::
+
+   docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.4 rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+
+In the Docker container, clone the ROCm MAD repository and navigate to the
+benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+.. code-block::
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD/scripts/vllm
+
+Command
+-------
+
+To start the benchmark, use the following command with the appropriate options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
+
+See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
+
+.. note::
+
+   The input sequence length, output sequence length, and tensor parallel (TP) are
+   already configured. You don't need to specify them with this script.
+
+.. note::
+
+   If you encounter the following error, pass your access-authorized Hugging
+   Face token to the gated models.
+
+   .. code-block:: shell
+
+      OSError: You are trying to access a gated repo.
+
+      # pass your HF_TOKEN
+      export HF_TOKEN=$your_personal_hf_token
+
+.. _vllm-benchmark-standalone-options:
+
+Options
+-------
+
+.. list-table::
+   :header-rows: 1
+   :align: center
+
+   * - Name
+     - Options
+     - Description
+
+   * - ``$test_option``
+     - latency
+     - Measure decoding token latency
+
+   * -
+     - throughput
+     - Measure token generation throughput
+
+   * -
+     - all
+     - Measure both throughput and latency
+
+   * - ``$model_repo``
+     - ``meta-llama/Meta-Llama-3.1-8B-Instruct``
+     - Llama 3.1 8B
+
+   * - (``float16``)
+     - ``meta-llama/Meta-Llama-3.1-70B-Instruct``
+     - Llama 3.1 70B
+
+   * -
+     - ``meta-llama/Meta-Llama-3.1-405B-Instruct``
+     - Llama 3.1 405B
+
+   * -
+     - ``meta-llama/Llama-2-7b-chat-hf``
+     - Llama 2 7B
+
+   * -
+     - ``meta-llama/Llama-2-70b-chat-hf``
+     - Llama 2 70B
+
+   * -
+     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
+     - Mixtral 8x7B
+
+   * -
+     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
+     - Mixtral 8x22B
+
+   * -
+     - ``mistralai/Mistral-7B-Instruct-v0.3``
+     - Mixtral 7B
+
+   * -
+     - ``Qwen/Qwen2-7B-Instruct``
+     - Qwen2 7B
+
+   * -
+     - ``Qwen/Qwen2-72B-Instruct``
+     - Qwen2 72B
+
+   * -
+     - ``core42/jais-13b-chat``
+     - JAIS 13B
+
+   * -
+     - ``core42/jais-30b-chat-v3``
+     - JAIS 30B
+
+   * - ``$model_repo``
+     - ``amd/Meta-Llama-3.1-8B-Instruct-FP8-KV``
+     - Llama 3.1 8B
+
+   * - (``float8``)
+     - ``amd/Meta-Llama-3.1-70B-Instruct-FP8-KV``
+     - Llama 3.1 70B
+
+   * -
+     - ``amd/Meta-Llama-3.1-405B-Instruct-FP8-KV``
+     - Llama 3.1 405B
+
+   * -
+     - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
+     - Mixtral 8x7B
+
+   * -
+     - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
+     - Mixtral 8x22B
+
+   * - ``$num_gpu``
+     - 1 or 8
+     - Number of GPUs
+
+   * - ``$datatype``
+     - ``float16`` or ``float8``
+     - Data type
+
+.. _vllm-benchmark-run-benchmark:
+
+Running the benchmark on the MI300X accelerator
+-----------------------------------------------
+
+Here are some examples of running the benchmark with various options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+Example 1: latency benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+ 
+Use this command to benchmark the latency of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
+
+.. code-block::
+
+   ./vllm_benchmark_report.sh -s latency -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
+   ./vllm_benchmark_report.sh -s latency -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
+
+Find the latency reports at:
+
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_latency_report.csv``
+
+- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_latency_report.csv``
+
+Example 2: throughput benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Use this command to benchmark the throughput of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
+   ./vllm_benchmark_report.sh -s throughput -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
+
+Find the throughput reports at:
+
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``
+
+- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_throughput_report.csv``
+
+.. raw:: html
+
+   <style>
+   mjx-container[jax="CHTML"][display="true"] {
+       text-align: left;
+       margin: 0;
+   }
+   </style>
+
+.. note::
+
+   Throughput is calculated as:
+
+   - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+   - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+
+Further reading
+===============
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/tuning-guides/mi300x/workload`.
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see :doc:`/how-to/system-optimization/mi300x`.
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Using ROCm for AI </how-to/rocm-for-ai/index>`.
+
+- To learn how to optimize inference on LLMs, see
+  :doc:`Fine-tuning LLMs and inference optimization </how-to/llm-fine-tuning-optimization/index>`.
+
+- For a list of other ready-made Docker images for ROCm, see the
+  :doc:`Docker image support matrix <rocm-install-on-linux:reference/docker-image-support-matrix>`.
+
+- To compare with the previous version of the ROCm vLLM Docker image for performance validation, refer to
+  `LLM inference performance validation on AMD Instinct MI300X (ROCm 6.2.0) <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.6.6.rst

@@ -0,0 +1,461 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+                 ROCm vLLM Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+***********************************************************
+LLM inference performance validation on AMD Instinct MI300X
+***********************************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker:
+
+The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
+a prebuilt, optimized environment for validating large language model (LLM)
+inference performance on the AMD Instinct™ MI300X accelerator. This ROCm vLLM
+Docker image integrates vLLM and PyTorch tailored specifically for the MI300X
+accelerator and includes the following components:
+
+* `ROCm 6.3.1 <https://github.com/ROCm/ROCm>`_
+
+* `vLLM 0.6.6 <https://docs.vllm.ai/en/latest>`_
+
+* `PyTorch 2.7.0 (2.7.0a0+git3a58512) <https://github.com/pytorch/pytorch>`_
+
+With this Docker image, you can quickly validate the expected inference
+performance numbers for the MI300X accelerator. This topic also provides tips on
+optimizing performance with popular AI models. For more information, see the lists of
+:ref:`available models for MAD-integrated benchmarking <vllm-benchmark-mad-models>`
+and :ref:`standalone benchmarking <vllm-benchmark-standalone-options>`.
+
+.. _vllm-benchmark-vllm:
+
+.. note::
+
+   vLLM is a toolkit and library for LLM inference and serving. AMD implements
+   high-performance custom kernels and modules in vLLM to enhance performance.
+   See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+   more information.
+
+Getting started
+===============
+
+Use the following procedures to reproduce the benchmark results on an
+MI300X accelerator with the prebuilt vLLM Docker image.
+
+.. _vllm-benchmark-get-started:
+
+1. Disable NUMA auto-balancing.
+
+   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+   might hang until the periodic balancing is finalized. For more information,
+   see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
+
+   .. code-block:: shell
+
+      # disable automatic NUMA balancing
+      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+      # check if NUMA balancing is disabled (returns 0 if disabled)
+      cat /proc/sys/kernel/numa_balancing
+      0
+
+2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
+
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+
+Once the setup is complete, choose between two options to reproduce the
+benchmark results:
+
+-  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
+
+-  :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
+
+.. _vllm-benchmark-mad:
+
+MAD-integrated benchmarking
+===========================
+
+Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+directory and install the required packages on the host machine.
+
+.. code-block:: shell
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD
+   pip install -r requirements.txt
+
+Use this command to run a performance benchmark test of the Llama 3.1 8B model
+on one GPU with ``float16`` data type in the host machine.
+
+.. code-block:: shell
+
+   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+   python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
+
+ROCm MAD launches a Docker container with the name
+``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
+model are collected in the following path: ``~/MAD/reports_float16/``.
+
+Although the following models are preconfigured to collect latency and
+throughput performance data, you can also change the benchmarking parameters.
+Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
+
+.. _vllm-benchmark-mad-models:
+
+Available models
+----------------
+
+.. list-table::
+   :header-rows: 1
+   :widths: 2, 3
+
+   * - Model name
+     - Tag
+
+   * - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
+     - ``pyt_vllm_llama-3.1-8b``
+
+   * - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
+     - ``pyt_vllm_llama-3.1-70b``
+
+   * - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
+     - ``pyt_vllm_llama-3.1-405b``
+
+   * - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
+     - ``pyt_vllm_llama-3.2-11b-vision-instruct``
+
+   * - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
+     - ``pyt_vllm_llama-2-7b``
+
+   * - `Llama 2 70B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
+     - ``pyt_vllm_llama-2-70b``
+
+   * - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
+     - ``pyt_vllm_mixtral-8x7b``
+
+   * - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
+     - ``pyt_vllm_mixtral-8x22b``
+
+   * - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
+     - ``pyt_vllm_mistral-7b``
+
+   * - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
+     - ``pyt_vllm_qwen2-7b``
+
+   * - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
+     - ``pyt_vllm_qwen2-72b``
+
+   * - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
+     - ``pyt_vllm_jais-13b``
+
+   * - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
+     - ``pyt_vllm_jais-30b``
+
+   * - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
+     - ``pyt_vllm_dbrx-instruct``
+
+   * - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
+     - ``pyt_vllm_gemma-2-27b``
+
+   * - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
+     - ``pyt_vllm_c4ai-command-r-plus-08-2024``
+
+   * - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
+     - ``pyt_vllm_deepseek-moe-16b-chat``
+
+   * - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
+     - ``pyt_vllm_llama-3.1-70b_fp8``
+
+   * - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
+     - ``pyt_vllm_llama-3.1-405b_fp8``
+
+   * - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mixtral-8x7b_fp8``
+
+   * - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mixtral-8x22b_fp8``
+
+   * - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
+     - ``pyt_vllm_mistral-7b_fp8``
+
+   * - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
+     - ``pyt_vllm_dbrx_fp8``
+
+   * - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
+     - ``pyt_vllm_command-r-plus_fp8``
+
+.. _vllm-benchmark-standalone:
+
+Standalone benchmarking
+=======================
+
+You can run the vLLM benchmark tool independently by starting the
+:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
+snippet.
+
+.. code-block::
+
+   docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.6 rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+
+In the Docker container, clone the ROCm MAD repository and navigate to the
+benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+.. code-block::
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD/scripts/vllm
+
+Command
+-------
+
+To start the benchmark, use the following command with the appropriate options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
+
+See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
+
+.. note::
+
+   The input sequence length, output sequence length, and tensor parallel (TP) are
+   already configured. You don't need to specify them with this script.
+
+.. note::
+
+   If you encounter the following error, pass your access-authorized Hugging
+   Face token to the gated models.
+
+   .. code-block:: shell
+
+      OSError: You are trying to access a gated repo.
+
+      # pass your HF_TOKEN
+      export HF_TOKEN=$your_personal_hf_token
+
+.. _vllm-benchmark-standalone-options:
+
+Options and available models
+----------------------------
+
+.. list-table::
+   :header-rows: 1
+   :align: center
+
+   * - Name
+     - Options
+     - Description
+
+   * - ``$test_option``
+     - latency
+     - Measure decoding token latency
+
+   * -
+     - throughput
+     - Measure token generation throughput
+
+   * -
+     - all
+     - Measure both throughput and latency
+
+   * - ``$model_repo``
+     - ``meta-llama/Llama-3.1-8B-Instruct``
+     - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
+
+   * - (``float16``)
+     - ``meta-llama/Llama-3.1-70B-Instruct``
+     - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
+
+   * -
+     - ``meta-llama/Llama-3.1-405B-Instruct``
+     - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
+
+   * -
+     - ``meta-llama/Llama-3.2-11B-Vision-Instruct``
+     - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
+
+   * -
+     - ``meta-llama/Llama-2-7b-chat-hf``
+     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
+
+   * -
+     - ``meta-llama/Llama-2-70b-chat-hf``
+     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
+
+   * -
+     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
+     - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
+
+   * -
+     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
+     - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
+
+   * -
+     - ``mistralai/Mistral-7B-Instruct-v0.3``
+     - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
+
+   * -
+     - ``Qwen/Qwen2-7B-Instruct``
+     - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
+
+   * -
+     - ``Qwen/Qwen2-72B-Instruct``
+     - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
+
+   * -
+     - ``core42/jais-13b-chat``
+     - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
+
+   * -
+     - ``core42/jais-30b-chat-v3``
+     - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
+
+   * -
+     - ``databricks/dbrx-instruct``
+     - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
+
+   * -
+     - ``google/gemma-2-27b``
+     - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
+
+   * -
+     - ``CohereForAI/c4ai-command-r-plus-08-2024``
+     - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
+
+   * -
+     - ``deepseek-ai/deepseek-moe-16b-chat``
+     - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
+
+   * - ``$model_repo``
+     - ``amd/Llama-3.1-70B-Instruct-FP8-KV``
+     - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
+
+   * - (``float8``)
+     - ``amd/Llama-3.1-405B-Instruct-FP8-KV``
+     - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
+
+   * -
+     - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
+     - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
+
+   * -
+     - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
+     - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
+
+   * -
+     - ``amd/Mistral-7B-v0.1-FP8-KV``
+     - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
+
+   * -
+     - ``amd/dbrx-instruct-FP8-KV``
+     - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
+
+   * -
+     - ``amd/c4ai-command-r-plus-FP8-KV``
+     - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
+
+   * - ``$num_gpu``
+     - 1 or 8
+     - Number of GPUs
+
+   * - ``$datatype``
+     - ``float16`` or ``float8``
+     - Data type
+
+.. _vllm-benchmark-run-benchmark:
+
+Running the benchmark on the MI300X accelerator
+-----------------------------------------------
+
+Here are some examples of running the benchmark with various options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+Example 1: latency benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+ 
+Use this command to benchmark the latency of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
+
+.. code-block::
+
+   ./vllm_benchmark_report.sh -s latency -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
+   ./vllm_benchmark_report.sh -s latency -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
+
+Find the latency reports at:
+
+- ``./reports_float16/summary/Llama-3.1-70B-Instruct_latency_report.csv``
+
+- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_latency_report.csv``
+
+Example 2: throughput benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Use this command to benchmark the throughput of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
+   ./vllm_benchmark_report.sh -s throughput -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
+
+Find the throughput reports at:
+
+- ``./reports_float16/summary/Llama-3.1-70B-Instruct_throughput_report.csv``
+
+- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_throughput_report.csv``
+
+.. raw:: html
+
+   <style>
+   mjx-container[jax="CHTML"][display="true"] {
+       text-align: left;
+       margin: 0;
+   }
+   </style>
+
+.. note::
+
+   Throughput is calculated as:
+
+   - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+   - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+
+Further reading
+===============
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`../inference-optimization/workload`.
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see :doc:`../../system-optimization/mi300x`.
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Running models from Hugging Face <hugging-face-models>`.
+
+- To learn how to optimize inference on LLMs, see
+  :doc:`Inference optimization <../inference-optimization/index>`.
+
+- To learn how to fine-tune LLMs, see
+  :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.7.3-20250325.rst

@@ -0,0 +1,329 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+                 ROCm vLLM Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.7.3_20250325-benchmark-models.yaml
+
+   {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
+   {% set model_groups = data.vllm_benchmark.model_groups %}
+
+   The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
+   a prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on AMD Instinct™ MI300X series accelerator. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
+   accelerators and includes the following components:
+
+   * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
+
+   * `vLLM {{ unified_docker.vllm_version }} <https://docs.vllm.ai/en/latest>`_
+
+   * `PyTorch {{ unified_docker.pytorch_version }} <https://github.com/pytorch/pytorch>`_
+
+   * `hipBLASLt {{ unified_docker.hipblaslt_version }} <https://github.com/ROCm/hipBLASLt>`_
+
+   With this Docker image, you can quickly test the :ref:`expected
+   inference performance numbers <vllm-benchmark-performance-measurements>` for
+   MI300X series accelerators.
+
+   .. _vllm-benchmark-available-models:
+
+   Available models
+   ================
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+        <div class="row">
+          <div class="col-2 me-2 model-param-head">Model</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+            <div class="col-3 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+   {% endfor %}
+          </div>
+        </div>
+
+        <div class="row mt-1">
+          <div class="col-2 me-2 model-param-head">Model variant</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+      {% set models = model_group.models %}
+      {% for model in models %}
+         {% if models|length % 3 == 0 %}
+            <div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% else %}
+            <div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+          </div>
+        </div>
+      </div>
+
+   .. _vllm-benchmark-vllm:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
+         Some models require access authorization prior to use via an external license agreement through a third party.
+
+      {% endfor %}
+   {% endfor %}
+
+   .. note::
+
+      vLLM is a toolkit and library for LLM inference and serving. AMD implements
+      high-performance custom kernels and modules in vLLM to enhance performance.
+      See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+      more information.
+
+   .. _vllm-benchmark-performance-measurements:
+
+   Performance measurements
+   ========================
+
+   To evaluate performance, the
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+   page provides reference throughput and latency measurements for inferencing
+   popular AI models.
+
+   .. important::
+
+      The performance data presented in
+      `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+      only reflects the :doc:`latest version of this inference benchmarking environment <../vllm>`_.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+
+   Advanced features and known issues
+   ==================================
+
+   For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
+   see the developer's guide at `<https://github.com/ROCm/vllm/tree/25070a1841df0dca585b7ddcb967c42aaec4b7c5/docs/dev-docker>`__.
+
+   Getting started
+   ===============
+
+   Use the following procedures to reproduce the benchmark results on an
+   MI300X accelerator with the prebuilt vLLM Docker image.
+
+   .. _vllm-benchmark-get-started:
+
+   1. Disable NUMA auto-balancing.
+
+      To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+      might hang until the periodic balancing is finalized. For more information,
+      see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
+
+      .. code-block:: shell
+
+         # disable automatic NUMA balancing
+         sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+         # check if NUMA balancing is disabled (returns 0 if disabled)
+         cat /proc/sys/kernel/numa_balancing
+         0
+
+   2. Download the `ROCm vLLM Docker image <{{ unified_docker.docker_hub_url }}>`_.
+
+      Use the following command to pull the Docker image from Docker Hub.
+
+      .. code-block:: shell
+
+         docker pull {{ unified_docker.pull_tag }}
+
+   Benchmarking
+   ============
+
+   Once the setup is complete, choose between two options to reproduce the
+   benchmark results:
+
+   .. _vllm-benchmark-mad:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+            directory and install the required packages on the host machine.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD
+               pip install -r requirements.txt
+
+            Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
+            using one GPU with the ``{{model.precision}}`` data type on the host machine.
+
+            .. code-block:: shell
+
+               export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+               python3 tools/run_models.py --tags {{model.mad_tag}} --keep-model-dir --live-output --timeout 28800
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
+            model are collected in the following path: ``~/MAD/reports_{{model.precision}}/``.
+
+            Although the :ref:`available models <vllm-benchmark-available-models>` are preconfigured
+            to collect latency and throughput performance data, you can also change the benchmarking
+            parameters. See the standalone benchmarking tab for more information.
+
+         .. tab-item:: Standalone benchmarking
+
+            Run the vLLM benchmark tool independently by starting the
+            `Docker container <{{ unified_docker.docker_hub_url }}>`_
+            as shown in the following snippet.
+
+            .. code-block::
+
+               docker pull {{ unified_docker.pull_tag }}
+               docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name test {{ unified_docker.pull_tag }}
+
+            In the Docker container, clone the ROCm MAD repository and navigate to the
+            benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+            .. code-block::
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/vllm
+
+            To start the benchmark, use the following command with the appropriate options.
+
+            .. code-block::
+
+               ./vllm_benchmark_report.sh -s $test_option -m {{model.model_repo}} -g $num_gpu -d {{model.precision}}
+
+            .. list-table::
+               :header-rows: 1
+               :align: center
+
+               * - Name
+                 - Options
+                 - Description
+
+               * - ``$test_option``
+                 - latency
+                 - Measure decoding token latency
+
+               * -
+                 - throughput
+                 - Measure token generation throughput
+
+               * -
+                 - all
+                 - Measure both throughput and latency
+
+               * - ``$num_gpu``
+                 - 1 or 8
+                 - Number of GPUs
+
+               * - ``$datatype``
+                 - ``float16`` or ``float8``
+                 - Data type
+
+            .. note::
+
+               The input sequence length, output sequence length, and tensor parallel (TP) are
+               already configured. You don't need to specify them with this script.
+
+            .. note::
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block::
+
+                  OSError: You are trying to access a gated repo.
+
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            Here are some examples of running the benchmark with various options.
+
+            * Latency benchmark
+
+              Use this command to benchmark the latency of the {{model.model}} model on eight GPUs with the ``{{model.precision}}`` data type.
+
+              .. code-block::
+
+                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
+
+              Find the latency report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_latency_report.csv``.
+
+            * Throughput benchmark
+
+              Use this command to throughput the latency of the {{model.model}} model on eight GPUs with the ``{{model.precision}}`` data type.
+
+              .. code-block:: shell
+
+                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
+
+              Find the throughput report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_throughput_report.csv``.
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`../inference-optimization/workload`.
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Running models from Hugging Face <hugging-face-models>`.
+
+- To learn how to optimize inference on LLMs, see
+  :doc:`Inference optimization <../inference-optimization/index>`.
+
+- To learn how to fine-tune LLMs, see
+  :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.3-20250415.rst

@@ -9,7 +9,7 @@ vLLM inference performance testing
 
 .. _vllm-benchmark-unified-docker:
 
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.8.3_20250415-benchmark-models.yaml
 
    {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
    {% set model_groups = data.vllm_benchmark.model_groups %}
@@ -98,18 +98,18 @@ vLLM inference performance testing
    page provides reference throughput and latency measurements for inferencing
    popular AI models.
 
-   .. note::
+   .. important::
 
       The performance data presented in
       `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
-      should not be interpreted as the peak performance achievable by AMD
-      Instinct MI325X and MI300X accelerators or ROCm software.
+      only reflects the :doc:`latest version of this inference benchmarking environment <../vllm>`_.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
 
    Advanced features and known issues
    ==================================
 
    For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
-   see the developer's guide at `<https://github.com/ROCm/vllm/blob/main/docs/dev-docker/README.md>`__.
+   see the developer's guide at `<https://github.com/ROCm/vllm/tree/7a9f58aae0e7215a5f3dccde60e35072c41656c2/docs/dev-docker>`__.
 
    System validation
    =================
@@ -339,43 +339,5 @@ Further reading
 Previous versions
 =================
 
-This table lists previous versions of the ROCm vLLM inference Docker image for
-inference performance testing. For detailed information about available models
-for benchmarking, see the version-specific documentation.
-
-.. list-table::
-   :header-rows: 1
-   :stub-columns: 1
-
-   * - ROCm version
-     - vLLM version
-     - PyTorch version
-     - Resources
-
-   * - 6.3.1
-     - 0.7.3
-     - 2.7.0
-     - 
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.3/how-to/rocm-for-ai/inference/vllm-benchmark.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.7.3_20250325/images/sha256-25245924f61750b19be6dcd8e787e46088a496c1fe17ee9b9e397f3d84d35640>`_
-
-   * - 6.3.1
-     - 0.6.6
-     - 2.7.0
-     - 
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.2/how-to/rocm-for-ai/inference/vllm-benchmark.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6/images/sha256-9a12ef62bbbeb5a4c30a01f702c8e025061f575aa129f291a49fbd02d6b4d6c9>`_
-
-   * - 6.2.1
-     - 0.6.4
-     - 2.5.0
-     - 
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4/images/sha256-ccbb74cc9e7adecb8f7bdab9555f7ac6fc73adb580836c2a35ca96ff471890d8>`_
-
-   * - 6.2.0
-     - 0.4.3
-     - 2.4.0
-     - 
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50/images/sha256-9e4dd4788a794c3d346d7d0ba452ae5e92d39b8dfac438b2af8efdc7f15d22c0>`_
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250513.rst

@@ -0,0 +1,354 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+                 ROCm vLLM Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.8.5_20250513-benchmark-models.yaml
+
+   {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
+   {% set model_groups = data.vllm_benchmark.model_groups %}
+
+   The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
+   a prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
+   accelerators and includes the following components:
+
+   * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
+
+   * `vLLM {{ unified_docker.vllm_version }} <https://docs.vllm.ai/en/latest>`_
+
+   * `PyTorch {{ unified_docker.pytorch_version }} <https://github.com/pytorch/pytorch>`_
+
+   * `hipBLASLt {{ unified_docker.hipblaslt_version }} <https://github.com/ROCm/hipBLASLt>`_
+
+   With this Docker image, you can quickly test the :ref:`expected
+   inference performance numbers <vllm-benchmark-performance-measurements>` for
+   MI300X series accelerators.
+
+   .. _vllm-benchmark-available-models:
+
+   Supported models
+   ================
+
+   The following models are supported for inference performance benchmarking
+   with vLLM and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started.
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+        <div class="row">
+          <div class="col-2 me-2 model-param-head">Model group</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+            <div class="col-3 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+   {% endfor %}
+          </div>
+        </div>
+
+        <div class="row mt-1">
+          <div class="col-2 me-2 model-param-head">Model</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+      {% set models = model_group.models %}
+      {% for model in models %}
+         {% if models|length % 3 == 0 %}
+            <div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% else %}
+            <div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+          </div>
+        </div>
+      </div>
+
+   .. _vllm-benchmark-vllm:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
+         Some models require access authorization prior to use via an external license agreement through a third party.
+
+      {% endfor %}
+   {% endfor %}
+
+   .. note::
+
+      vLLM is a toolkit and library for LLM inference and serving. AMD implements
+      high-performance custom kernels and modules in vLLM to enhance performance.
+      See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+      more information.
+
+   .. _vllm-benchmark-performance-measurements:
+
+   Performance measurements
+   ========================
+
+   To evaluate performance, the
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+   page provides reference throughput and latency measurements for inferencing
+   popular AI models.
+
+   .. important::
+
+      The performance data presented in
+      `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+      only reflects the :doc:`latest version of this inference benchmarking environment <../vllm>`_.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+
+   Advanced features and known issues
+   ==================================
+
+   For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
+   see the developer's guide at `<https://github.com/ROCm/vllm/tree/16d2b92ebcf90fe55cf73fa0b9329a6c9d3dede8/docs/dev-docker>`__.
+
+   System validation
+   =================
+
+   Before running AI workloads, it's important to validate that your AMD hardware is configured
+   correctly and performing optimally.
+
+   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+   might hang until the periodic balancing is finalized. For more information,
+   see the :ref:`system validation steps <rocm-for-ai-system-optimization>`.
+
+   .. code-block:: shell
+
+      # disable automatic NUMA balancing
+      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+      # check if NUMA balancing is disabled (returns 0 if disabled)
+      cat /proc/sys/kernel/numa_balancing
+      0
+
+   To test for optimal performance, consult the recommended :ref:`System health benchmarks
+   <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+   system's configuration.
+
+   Pull the Docker image
+   =====================
+
+   Download the `ROCm vLLM Docker image <{{ unified_docker.docker_hub_url }}>`_.
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ unified_docker.pull_tag }}
+
+   Benchmarking
+   ============
+
+   Once the setup is complete, choose between two options to reproduce the
+   benchmark results:
+
+   .. _vllm-benchmark-mad:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+            directory and install the required packages on the host machine.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD
+               pip install -r requirements.txt
+
+            Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
+            using one GPU with the ``{{model.precision}}`` data type on the host machine.
+
+            .. code-block:: shell
+
+               export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+               python3 tools/run_models.py --tags {{model.mad_tag}} --keep-model-dir --live-output --timeout 28800
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
+            model are collected in the following path: ``~/MAD/reports_{{model.precision}}/``.
+
+            Although the :ref:`available models <vllm-benchmark-available-models>` are preconfigured
+            to collect latency and throughput performance data, you can also change the benchmarking
+            parameters. See the standalone benchmarking tab for more information.
+
+            {% if model.tunableop %}
+
+            .. note::
+
+               For improved performance, consider enabling :ref:`PyTorch TunableOp <mi300x-tunableop>`.
+               TunableOp automatically explores different implementations and configurations of certain PyTorch
+               operators to find the fastest one for your hardware.
+
+               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled
+               (see
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To
+               enable it, edit the default run behavior in the ``models.json``
+               configuration before running inference -- update the model's run
+               ``args`` by changing ``--tunableop off`` to ``--tunableop on``.
+
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the performance-collection run.
+
+            {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            Run the vLLM benchmark tool independently by starting the
+            `Docker container <{{ unified_docker.docker_hub_url }}>`_
+            as shown in the following snippet.
+
+            .. code-block::
+
+               docker pull {{ unified_docker.pull_tag }}
+               docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name test {{ unified_docker.pull_tag }}
+
+            In the Docker container, clone the ROCm MAD repository and navigate to the
+            benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+            .. code-block::
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/vllm
+
+            To start the benchmark, use the following command with the appropriate options.
+
+            .. code-block::
+
+               ./vllm_benchmark_report.sh -s $test_option -m {{model.model_repo}} -g $num_gpu -d {{model.precision}}
+
+            .. list-table::
+               :header-rows: 1
+               :align: center
+
+               * - Name
+                 - Options
+                 - Description
+
+               * - ``$test_option``
+                 - latency
+                 - Measure decoding token latency
+
+               * -
+                 - throughput
+                 - Measure token generation throughput
+
+               * -
+                 - all
+                 - Measure both throughput and latency
+
+               * - ``$num_gpu``
+                 - 1 or 8
+                 - Number of GPUs
+
+               * - ``$datatype``
+                 - ``float16`` or ``float8``
+                 - Data type
+
+            .. note::
+
+               The input sequence length, output sequence length, and tensor parallel (TP) are
+               already configured. You don't need to specify them with this script.
+
+            .. note::
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block::
+
+                  OSError: You are trying to access a gated repo.
+
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            Here are some examples of running the benchmark with various options.
+
+            * Latency benchmark
+
+              Use this command to benchmark the latency of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block::
+
+                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
+
+              Find the latency report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_latency_report.csv``.
+
+            * Throughput benchmark
+
+              Use this command to benchmark the throughput of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block:: shell
+
+                 ./vllm_benchmark_report.sh -s throughput -m {{model.model_repo}} -g 8 -d {{model.precision}}
+
+              Find the throughput report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_throughput_report.csv``.
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`../../../inference-optimization/workload`.
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Running models from Hugging Face <../../hugging-face-models>`.
+
+- To learn how to optimize inference on LLMs, see
+  :doc:`Inference optimization <../../../inference-optimization/index>`.
+
+- To learn how to fine-tune LLMs, see
+  :doc:`Fine-tuning LLMs <../../../fine-tuning/index>`.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250521.rst

@@ -0,0 +1,354 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+                 ROCm vLLM Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.8.5_20250521-benchmark-models.yaml
+
+   {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
+   {% set model_groups = data.vllm_benchmark.model_groups %}
+
+   The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
+   a prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
+   accelerators and includes the following components:
+
+   * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
+
+   * `vLLM {{ unified_docker.vllm_version }} <https://docs.vllm.ai/en/latest>`_
+
+   * `PyTorch {{ unified_docker.pytorch_version }} <https://github.com/ROCm/pytorch.git>`_
+
+   * `hipBLASLt {{ unified_docker.hipblaslt_version }} <https://github.com/ROCm/hipBLASLt>`_
+
+   With this Docker image, you can quickly test the :ref:`expected
+   inference performance numbers <vllm-benchmark-performance-measurements>` for
+   MI300X series accelerators.
+
+   .. _vllm-benchmark-available-models:
+
+   Supported models
+   ================
+
+   The following models are supported for inference performance benchmarking
+   with vLLM and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started.
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+        <div class="row">
+          <div class="col-2 me-2 model-param-head">Model group</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+            <div class="col-3 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+   {% endfor %}
+          </div>
+        </div>
+
+        <div class="row mt-1">
+          <div class="col-2 me-2 model-param-head">Model</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+      {% set models = model_group.models %}
+      {% for model in models %}
+         {% if models|length % 3 == 0 %}
+            <div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% else %}
+            <div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+          </div>
+        </div>
+      </div>
+
+   .. _vllm-benchmark-vllm:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
+         Some models require access authorization prior to use via an external license agreement through a third party.
+
+      {% endfor %}
+   {% endfor %}
+
+   .. note::
+
+      vLLM is a toolkit and library for LLM inference and serving. AMD implements
+      high-performance custom kernels and modules in vLLM to enhance performance.
+      See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+      more information.
+
+   .. _vllm-benchmark-performance-measurements:
+
+   Performance measurements
+   ========================
+
+   To evaluate performance, the
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+   page provides reference throughput and latency measurements for inferencing
+   popular AI models.
+
+   .. note::
+
+      The performance data presented in
+      `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+      should not be interpreted as the peak performance achievable by AMD
+      Instinct MI325X and MI300X accelerators or ROCm software.
+
+   Advanced features and known issues
+   ==================================
+
+   For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
+   see the developer's guide at `<https://github.com/ROCm/vllm/blob/main/docs/dev-docker/README.md>`__.
+
+   System validation
+   =================
+
+   Before running AI workloads, it's important to validate that your AMD hardware is configured
+   correctly and performing optimally.
+
+   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+   might hang until the periodic balancing is finalized. For more information,
+   see the :ref:`system validation steps <rocm-for-ai-system-optimization>`.
+
+   .. code-block:: shell
+
+      # disable automatic NUMA balancing
+      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+      # check if NUMA balancing is disabled (returns 0 if disabled)
+      cat /proc/sys/kernel/numa_balancing
+      0
+
+   To test for optimal performance, consult the recommended :ref:`System health benchmarks
+   <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+   system's configuration.
+
+   Pull the Docker image
+   =====================
+
+   Download the `ROCm vLLM Docker image <{{ unified_docker.docker_hub_url }}>`_.
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ unified_docker.pull_tag }}
+
+   Benchmarking
+   ============
+
+   Once the setup is complete, choose between two options to reproduce the
+   benchmark results:
+
+   .. _vllm-benchmark-mad:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+            directory and install the required packages on the host machine.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD
+               pip install -r requirements.txt
+
+            Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
+            using one GPU with the ``{{model.precision}}`` data type on the host machine.
+
+            .. code-block:: shell
+
+               export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+               python3 tools/run_models.py --tags {{model.mad_tag}} --keep-model-dir --live-output --timeout 28800
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
+            model are collected in the following path: ``~/MAD/reports_{{model.precision}}/``.
+
+            Although the :ref:`available models <vllm-benchmark-available-models>` are preconfigured
+            to collect latency and throughput performance data, you can also change the benchmarking
+            parameters. See the standalone benchmarking tab for more information.
+
+            {% if model.tunableop %}
+
+            .. note::
+
+               For improved performance, consider enabling :ref:`PyTorch TunableOp <mi300x-tunableop>`.
+               TunableOp automatically explores different implementations and configurations of certain PyTorch
+               operators to find the fastest one for your hardware.
+
+               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled
+               (see
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To
+               enable it, edit the default run behavior in the ``models.json``
+               configuration before running inference -- update the model's run
+               ``args`` by changing ``--tunableop off`` to ``--tunableop on``.
+
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the performance-collection run.
+
+            {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            Run the vLLM benchmark tool independently by starting the
+            `Docker container <{{ unified_docker.docker_hub_url }}>`_
+            as shown in the following snippet.
+
+            .. code-block::
+
+               docker pull {{ unified_docker.pull_tag }}
+               docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name test {{ unified_docker.pull_tag }}
+
+            In the Docker container, clone the ROCm MAD repository and navigate to the
+            benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+            .. code-block::
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/vllm
+
+            To start the benchmark, use the following command with the appropriate options.
+
+            .. code-block::
+
+               ./vllm_benchmark_report.sh -s $test_option -m {{model.model_repo}} -g $num_gpu -d {{model.precision}}
+
+            .. list-table::
+               :header-rows: 1
+               :align: center
+
+               * - Name
+                 - Options
+                 - Description
+
+               * - ``$test_option``
+                 - latency
+                 - Measure decoding token latency
+
+               * -
+                 - throughput
+                 - Measure token generation throughput
+
+               * -
+                 - all
+                 - Measure both throughput and latency
+
+               * - ``$num_gpu``
+                 - 1 or 8
+                 - Number of GPUs
+
+               * - ``$datatype``
+                 - ``float16`` or ``float8``
+                 - Data type
+
+            .. note::
+
+               The input sequence length, output sequence length, and tensor parallel (TP) are
+               already configured. You don't need to specify them with this script.
+
+            .. note::
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block::
+
+                  OSError: You are trying to access a gated repo.
+
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            Here are some examples of running the benchmark with various options.
+
+            * Latency benchmark
+
+              Use this command to benchmark the latency of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block::
+
+                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
+
+              Find the latency report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_latency_report.csv``.
+
+            * Throughput benchmark
+
+              Use this command to benchmark the throughput of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block:: shell
+
+                 ./vllm_benchmark_report.sh -s throughput -m {{model.model_repo}} -g 8 -d {{model.precision}}
+
+              Find the throughput report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_throughput_report.csv``.
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`../../inference-optimization/workload`.
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Running models from Hugging Face <../hugging-face-models>`.
+
+- To learn how to optimize inference on LLMs, see
+  :doc:`Inference optimization <../../inference-optimization/index>`.
+
+- To learn how to fine-tune LLMs, see
+  :doc:`Fine-tuning LLMs <../../fine-tuning/index>`.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-history.rst

@@ -0,0 +1,75 @@
+:orphan:
+
+**************************************************
+vLLM inference performance testing version history
+**************************************************
+
+This table lists previous versions of the ROCm vLLM inference Docker image for
+inference performance testing. For detailed information about available models
+for benchmarking, see the version-specific documentation. You can find tagged
+previous releases of the ``ROCm/vllm`` Docker image on `Docker Hub <https://hub.docker.com/r/rocm/vllm/tags>`_.
+
+.. list-table::
+   :header-rows: 1
+   :stub-columns: 1
+
+   * - ROCm version
+     - vLLM version
+     - PyTorch version
+     - Resources
+
+   * - 6.4.0
+     - 0.9.0.1
+     - 2.7.0
+     - 
+       * :doc:`Documentation <../vllm>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_vllm_0.8.5_20250521/images/sha256-38410c51af7208897cd8b737c9bdfc126e9bc8952d4aa6b88c85482f03092a11>`_
+
+   * - 6.3.1
+     - 0.8.5 (0.8.6.dev)
+     - 2.7.0
+     - 
+       * :doc:`Documentation <vllm-0.8.5-20250521>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_vllm_0.8.5_20250521/images/sha256-38410c51af7208897cd8b737c9bdfc126e9bc8952d4aa6b88c85482f03092a11>`_
+
+   * - 6.3.1
+     - 0.8.5
+     - 2.7.0
+     - 
+       * :doc:`Documentation <vllm-0.8.5-20250513>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_vllm_0.8.5_20250513/images/sha256-5c8b4436dd0464119d9df2b44c745fadf81512f18ffb2f4b5dc235c71ebe26b4>`_
+
+   * - 6.3.1
+     - 0.8.3
+     - 2.7.0
+     - 
+       * :doc:`Documentation <vllm-0.8.3-20250415>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.8.3_20250415/images/sha256-ad9062dea3483d59dedb17c67f7c49f30eebd6eb37c3fac0a171fb19696cc845>`_
+
+   * - 6.3.1
+     - 0.7.3
+     - 2.7.0
+     - 
+       * :doc:`Documentation <vllm-0.7.3-20250325>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.7.3_20250325/images/sha256-25245924f61750b19be6dcd8e787e46088a496c1fe17ee9b9e397f3d84d35640>`_
+
+   * - 6.3.1
+     - 0.6.6
+     - 2.7.0
+     - 
+       * :doc:`Documentation <vllm-0.6.6>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6/images/sha256-9a12ef62bbbeb5a4c30a01f702c8e025061f575aa129f291a49fbd02d6b4d6c9>`_
+
+   * - 6.2.1
+     - 0.6.4
+     - 2.5.0
+     - 
+       * :doc:`Documentation <vllm-0.6.4>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4/images/sha256-ccbb74cc9e7adecb8f7bdab9555f7ac6fc73adb580836c2a35ca96ff471890d8>`_
+
+   * - 6.2.0
+     - 0.4.3
+     - 2.4.0
+     - 
+       * :doc:`Documentation <vllm-0.4.3>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50/images/sha256-9e4dd4788a794c3d346d7d0ba452ae5e92d39b8dfac438b2af8efdc7f15d22c0>`_

docs/how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference.rst

@@ -24,20 +24,24 @@ PyTorch inference performance testing
    Supported models
    ================
 
+   The following models are supported for inference performance benchmarking
+   with PyTorch and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started.
+
    .. raw:: html
 
       <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
         <div class="row">
-          <div class="col-2 me-2 model-param-head">Model</div>
+          <div class="col-2 me-2 model-param-head">Model group</div>
           <div class="row col-10">
    {% for model_group in model_groups %}
-            <div class="col-6 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+            <div class="col-4 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
    {% endfor %}
           </div>
         </div>
 
         <div class="row mt-1" style="display: none;">
-          <div class="col-2 me-2 model-param-head">Model variant</div>
+          <div class="col-2 me-2 model-param-head">Model</div>
           <div class="row col-10">
    {% for model_group in model_groups %}
       {% set models = model_group.models %}
@@ -99,7 +103,7 @@ PyTorch inference performance testing
 
          The Chai-1 benchmark uses a specifically selected Docker image using ROCm 6.2.3 and PyTorch 2.3.0 to address an accuracy issue.
 
-   .. container:: model-doc pyt_clip_inference
+   .. container:: model-doc pyt_clip_inference pyt_mochi_video_inference
 
       Use the following command to pull the `ROCm PyTorch Docker image <https://hub.docker.com/layers/rocm/pytorch/latest/images/sha256-05b55983e5154f46e7441897d0908d79877370adca4d1fff4899d9539d6c4969>`_ from Docker Hub.
 
@@ -162,11 +166,14 @@ Further reading
 - To learn more about system settings and management practices to configure your system for
   MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`../../inference-optimization/workload`.
+
 - To learn how to run LLM models from Hugging Face or your model, see
-  :doc:`Running models from Hugging Face <hugging-face-models>`.
+  :doc:`Running models from Hugging Face <../hugging-face-models>`.
 
 - To learn how to optimize inference on LLMs, see
-  :doc:`Inference optimization <../inference-optimization/index>`.
+  :doc:`Inference optimization <../../inference-optimization/index>`.
 
 - To learn how to fine-tune LLMs, see
-  :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
+  :doc:`Fine-tuning LLMs <../../fine-tuning/index>`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst

@@ -0,0 +1,346 @@
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+                 ROCm vLLM Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. _vllm-benchmark-unified-docker:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
+
+   {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
+   {% set model_groups = data.vllm_benchmark.model_groups %}
+
+   The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
+   a prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
+   accelerators and includes the following components:
+
+   * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
+
+   * `vLLM {{ unified_docker.vllm_version }} <https://docs.vllm.ai/en/latest>`_
+
+   * `PyTorch {{ unified_docker.pytorch_version }} <https://github.com/ROCm/pytorch.git>`_
+
+   * `hipBLASLt {{ unified_docker.hipblaslt_version }} <https://github.com/ROCm/hipBLASLt>`_
+
+   With this Docker image, you can quickly test the :ref:`expected
+   inference performance numbers <vllm-benchmark-performance-measurements>` for
+   MI300X series accelerators.
+
+   .. _vllm-benchmark-available-models:
+
+   Supported models
+   ================
+
+   The following models are supported for inference performance benchmarking
+   with vLLM and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started.
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+        <div class="row">
+          <div class="col-2 me-2 model-param-head">Model group</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+            <div class="col-3 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+   {% endfor %}
+          </div>
+        </div>
+
+        <div class="row mt-1">
+          <div class="col-2 me-2 model-param-head">Model</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+      {% set models = model_group.models %}
+      {% for model in models %}
+         {% if models|length % 3 == 0 %}
+            <div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% else %}
+            <div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+          </div>
+        </div>
+      </div>
+
+   .. _vllm-benchmark-vllm:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
+         Some models require access authorization prior to use via an external license agreement through a third party.
+
+      {% endfor %}
+   {% endfor %}
+
+   .. note::
+
+      vLLM is a toolkit and library for LLM inference and serving. AMD implements
+      high-performance custom kernels and modules in vLLM to enhance performance.
+      See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+      more information.
+
+   .. _vllm-benchmark-performance-measurements:
+
+   Performance measurements
+   ========================
+
+   To evaluate performance, the
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+   page provides reference throughput and latency measurements for inferencing popular AI models.
+
+   .. important::
+
+      The performance data presented in
+      `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+      only reflects the latest version of this inference benchmarking environment.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+
+   Advanced features and known issues
+   ==================================
+
+   For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
+   see the developer's guide at `<https://github.com/ROCm/vllm/tree/7bb0618b1fe725b7d4fad9e525aa44da12c94a8b/docs/dev-docker>`__.
+
+   System validation
+   =================
+
+   Before running AI workloads, it's important to validate that your AMD hardware is configured
+   correctly and performing optimally.
+
+   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+   might hang until the periodic balancing is finalized. For more information,
+   see the :ref:`system validation steps <rocm-for-ai-system-optimization>`.
+
+   .. code-block:: shell
+
+      # disable automatic NUMA balancing
+      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+      # check if NUMA balancing is disabled (returns 0 if disabled)
+      cat /proc/sys/kernel/numa_balancing
+      0
+
+   To test for optimal performance, consult the recommended :ref:`System health benchmarks
+   <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+   system's configuration.
+
+   Pull the Docker image
+   =====================
+
+   Download the `ROCm vLLM Docker image <{{ unified_docker.docker_hub_url }}>`_.
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ unified_docker.pull_tag }}
+
+   Benchmarking
+   ============
+
+   Once the setup is complete, choose between two options to reproduce the
+   benchmark results:
+
+   .. _vllm-benchmark-mad:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+            directory and install the required packages on the host machine.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD
+               pip install -r requirements.txt
+
+            Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
+            using one GPU with the ``{{model.precision}}`` data type on the host machine.
+
+            .. code-block:: shell
+
+               export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+               python3 tools/run_models.py --tags {{model.mad_tag}} --keep-model-dir --live-output --timeout 28800
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
+            model are collected in the following path: ``~/MAD/reports_{{model.precision}}/``.
+
+            Although the :ref:`available models <vllm-benchmark-available-models>` are preconfigured
+            to collect latency and throughput performance data, you can also change the benchmarking
+            parameters. See the standalone benchmarking tab for more information.
+
+            {% if model.tunableop %}
+
+            .. note::
+
+               For improved performance, consider enabling :ref:`PyTorch TunableOp <mi300x-tunableop>`.
+               TunableOp automatically explores different implementations and configurations of certain PyTorch
+               operators to find the fastest one for your hardware.
+
+               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled
+               (see
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To
+               enable it, edit the default run behavior in the ``models.json``
+               configuration before running inference -- update the model's run
+               ``args`` by changing ``--tunableop off`` to ``--tunableop on``.
+
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the performance-collection run.
+
+            {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            Run the vLLM benchmark tool independently by starting the
+            `Docker container <{{ unified_docker.docker_hub_url }}>`_
+            as shown in the following snippet.
+
+            .. code-block::
+
+               docker pull {{ unified_docker.pull_tag }}
+               docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name test {{ unified_docker.pull_tag }}
+
+            In the Docker container, clone the ROCm MAD repository and navigate to the
+            benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+            .. code-block::
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/vllm
+
+            To start the benchmark, use the following command with the appropriate options.
+
+            .. code-block::
+
+               ./vllm_benchmark_report.sh -s $test_option -m {{model.model_repo}} -g $num_gpu -d {{model.precision}}
+
+            .. list-table::
+               :header-rows: 1
+               :align: center
+
+               * - Name
+                 - Options
+                 - Description
+
+               * - ``$test_option``
+                 - latency
+                 - Measure decoding token latency
+
+               * -
+                 - throughput
+                 - Measure token generation throughput
+
+               * -
+                 - all
+                 - Measure both throughput and latency
+
+               * - ``$num_gpu``
+                 - 1 or 8
+                 - Number of GPUs
+
+               * - ``$datatype``
+                 - ``float16`` or ``float8``
+                 - Data type
+
+            .. note::
+
+               The input sequence length, output sequence length, and tensor parallel (TP) are
+               already configured. You don't need to specify them with this script.
+
+            .. note::
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block::
+
+                  OSError: You are trying to access a gated repo.
+
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            Here are some examples of running the benchmark with various options.
+
+            * Latency benchmark
+
+              Use this command to benchmark the latency of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block::
+
+                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
+
+              Find the latency report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_latency_report.csv``.
+
+            * Throughput benchmark
+
+              Use this command to benchmark the throughput of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block:: shell
+
+                 ./vllm_benchmark_report.sh -s throughput -m {{model.model_repo}} -g 8 -d {{model.precision}}
+
+              Find the throughput report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_throughput_report.csv``.
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`../../inference-optimization/workload`.
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Running models from Hugging Face <../hugging-face-models>`.
+
+- To learn how to optimize inference on LLMs, see
+  :doc:`Inference optimization <../../inference-optimization/index>`.
+
+- To learn how to fine-tune LLMs, see
+  :doc:`Fine-tuning LLMs <../../fine-tuning/index>`.
+
+Previous versions
+=================
+
+See :doc:`previous-versions/vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst

@@ -374,22 +374,5 @@ own cluster setup.
 Previous versions
 =================
 
-This table lists previous versions of the ROCm JAX MaxText Docker image for training
-performance testing. For detailed information about available models for
-benchmarking, see the version-specific documentation.
-
-.. list-table::
-   :header-rows: 1
-   :stub-columns: 1
-
-   * - Image version
-     - ROCm version
-     - JAX version
-     - Resources
-
-   * - 25.4
-     - 6.3.0
-     - 0.4.31
-     - 
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.3/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.4/images/sha256-fb3eb71cd74298a7b3044b7130cf84113f14d518ff05a2cd625c11ea5f6a7b01>`_
+See :doc:`previous-versions/jax-maxtext-history` to find documentation for previous releases
+of the ``ROCm/jax-training`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-history.rst

@@ -0,0 +1,34 @@
+:orphan:
+
+********************************************************
+JAX MaxText training performance testing version history
+********************************************************
+
+This table lists previous versions of the ROCm JAX MaxText Docker image for training
+performance testing. For detailed information about available models for
+benchmarking, see the version-specific documentation.
+You can find tagged
+previous releases of the ``ROCm/jax-training`` Docker image on `Docker Hub <https://hub.docker.com/r/rocm/jax-training/tags>`_.
+
+.. list-table::
+   :header-rows: 1
+   :stub-columns: 1
+
+   * - Image version
+     - ROCm version
+     - JAX version
+     - Resources
+
+   * - 25.5
+     - 6.3.4
+     - 0.4.35
+     - 
+       * :doc:`Documentation <../jax-maxtext>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.5/images/sha256-4e0516358a227cae8f552fb866ec07e2edcf244756f02e7b40212abfbab5217b>`_
+
+   * - 25.4
+     - 6.3.0
+     - 0.4.31
+     - 
+       * :doc:`Documentation <jax-maxtext-v25.4>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.4/images/sha256-fb3eb71cd74298a7b3044b7130cf84113f14d518ff05a2cd625c11ea5f6a7b01>`_

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.4.rst

@@ -0,0 +1,358 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using JAX MaxText for ROCm.
+   :keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
+
+**************************************
+Training a model with MaxText for ROCm
+**************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm JAX MaxText
+   training performance documentation. See :doc:`../jax-maxtext` for the latest version.
+
+MaxText is a high-performance, open-source framework built on the Google JAX
+machine learning library to train LLMs at scale. The MaxText framework for
+ROCm is an optimized fork of the upstream
+`<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
+on AMD MI300X series accelerators.
+
+The MaxText for ROCm training Docker (``rocm/jax-training:maxtext-v25.4``) image
+provides a prebuilt environment for training on AMD Instinct MI300X and MI325X accelerators,
+including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
+It includes the following software components:
+
++--------------------------+--------------------------------+
+| Software component       | Version                        |
++==========================+================================+
+| ROCm                     | 6.3.0                          |
++--------------------------+--------------------------------+
+| JAX                      | 0.4.31                         |
++--------------------------+--------------------------------+
+| Python                   | 3.10                           |
++--------------------------+--------------------------------+
+| Transformer Engine       | 1.12.0.dev0+f81a3eb            |
++--------------------------+--------------------------------+
+| hipBLASLt                | git78ec8622                    |
++--------------------------+--------------------------------+
+
+Supported features and models
+=============================
+
+MaxText provides the following key features to train large language models efficiently:
+
+- Transformer Engine (TE)
+
+- Flash Attention (FA) 3
+
+- GEMM tuning
+
+- Multi-node support
+
+.. _amd-maxtext-model-support:
+
+The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+
+* Llama 3.1 8B
+
+* Llama 3.1 70B
+
+* Llama 3 8B
+
+* Llama 3 70B
+
+* Llama 2 7B
+
+* Llama 2 70B
+
+* DeepSeek-V2-Lite
+
+.. note::
+
+   Some models, such as Llama 3, require an external license agreement through
+   a third party (for example, Meta).
+
+Unsupported features
+--------------------
+
+Currently, MaxText's default packed input format is not supported. Using this format
+with the current Docker image results in incorrect attention calculations
+across different input sequences. Support for packed input format is planned for a future release.
+
+System validation
+=================
+
+If you have already validated your system settings, including NUMA
+auto-balancing, skip this step. Otherwise, complete the :ref:`system validation
+and optimization steps <train-a-model-system-validation>` to set up your system
+before starting training.
+
+Environment setup
+=================
+
+This Docker image is optimized for specific model configurations outlined
+as follows. Performance can vary for other training workloads, as AMD
+doesn’t validate configurations and run conditions outside those described.
+
+.. _amd-maxtext-multi-node-setup:
+
+Multi-node setup
+----------------
+
+For multi-node environments, ensure you have all the necessary packages for
+your network device, such as, RDMA. If you're not using a multi-node setup
+with RDMA, skip ahead to :ref:`amd-maxtext-download-docker`.
+
+1. Install the following packages to build and install the RDMA driver.
+
+   .. code-block:: shell
+
+      sudo apt install iproute2 -y
+      sudo apt install -y linux-headers-"$(uname-r)" libelf-dev
+      sudo apt install -y gcc make libtool autoconf librdmacm-dev rdmacm-utils infiniband-diags ibverbs-utils perftest ethtool libibverbs-dev rdma-core strace libibmad5 libibnetdisc5 ibverbs-providers libibumad-dev libibumad3 libibverbs1 libnl-3-dev libnl-route-3-dev
+
+   Refer to your NIC manufacturer's documentation for further steps on
+   compiling and installing the RoCE driver. For example, for Broadcom,
+   see `Compiling Broadcom NIC software from source <https://docs.broadcom.com/doc/957608-AN2XX#G3.484341>`_
+   in `Ethernet networking guide for AMD Instinct MI300X GPU clusters <https://docs.broadcom.com/doc/957608-AN2XX>`_.
+
+2. Set the following environment variables.
+
+   a. Master address
+
+      Change `localhost` to the master node's resolvable hostname or IP address:
+
+      .. code-block:: bash
+
+         export MASTER_ADDR="${MASTER_ADDR:-localhost}"
+
+   b. Number of nodes
+
+      Set the number of nodes you want to train on (for example, ``2``, ``4``, or ``8``):
+
+      .. code-block:: bash
+
+         export NNODES="${NNODES:-1}"
+
+   c. Node ranks
+
+      Set the rank of each node (``0`` for master, ``1`` for the first worker node, and so on)
+      Node ranks should be unique across all nodes in the cluster.
+
+      .. code-block:: bash
+
+         export NODE_RANK="${NODE_RANK:-0}"
+
+   d. Network interface
+
+      Update the network interface in the script to match your system's network interface. To
+      find your network interface, run the following (outside of any Docker container):
+
+      .. code-block:: bash
+
+         ip a
+
+      Look for an active interface with an IP address in the same subnet as
+      your other nodes. Then, update the following variable in the script, for
+      example:
+
+      .. code-block:: bash
+
+         export NCCL_SOCKET_IFNAME=ens50f0np0
+
+      This variable specifies which network interface to use for inter-node communication.
+      Setting this variable to the incorrect interface can result in communication failures
+      or significantly reduced performance.
+
+   e. RDMA interface
+
+      Ensure the :ref:`required packages <amd-maxtext-multi-node-setup>` are installed on all nodes.
+      Then, set the RDMA interfaces to use for communication.
+
+      .. code-block:: bash
+
+         # If using Broadcom NIC
+         export NCCL_IB_HCA=rdma0,rdma1,rdma2,rdma3,rdma4,rdma5,rdma6,rdma7
+         # If using Mellanox NIC
+         export NCCL_IB_HCA=mlx5_0,mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_8,mlx5_9
+
+.. _amd-maxtext-download-docker:
+
+Download the Docker image
+-------------------------
+
+1. Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/jax-training:maxtext-v25.4
+
+2. Run the Docker container.
+
+   .. code-block:: shell
+
+      docker run -it --device /dev/dri --device /dev/kfd --network host --ipc host --group-add video --cap-add SYS_PTRACE --security-opt seccomp=unconfined --privileged -v $HOME/.ssh:/root/.ssh --shm-size 128G --name maxtext_training rocm/jax-training:maxtext-v25.4
+
+.. _amd-maxtext-get-started:
+
+Getting started
+===============
+
+The following examples demonstrate how to get started with single node
+and multi-node training using the benchmarking scripts provided at
+`<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__.
+
+.. important::
+
+   The provided scripts launch a Docker container and execute a benchmark. Ensure you run these commands outside of any existing Docker container.
+
+Before running any benchmarks, ensure the ``$HF_HOME`` environment variable is
+set correctly and points to your Hugging Face cache directory. Refer to the
+README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__
+for more detailed instructions.
+
+Single node training benchmarking examples
+------------------------------------------
+
+* Example 1: Single node training with Llama 2 7B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b.sh
+
+  Run the single node training benchmark:
+
+  IMAGE="rocm/jax-training:maxtext-v25.4" bash ./llama2_7b.sh
+
+* Example 2: Single node training with Llama 2 70B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.4" bash ./llama2_70b.sh
+
+* Example 3: Single node training with Llama 3 8B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.4" bash ./llama3_8b.sh
+
+* Example 4: Single node training with Llama 3 70B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.4" bash ./llama3_70b.sh
+
+* Example 5: Single node training with DeepSeek V2 16B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/deepseek_v2_16b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.4" bash ./deepseek_v2_16b.sh
+
+  .. note::
+
+     The reported TFLOP/s by MaxText for DeepSeek is not accurate. Use
+     the tokens/s as a performance indicator.
+
+Multi-node training benchmarking examples
+-----------------------------------------
+
+The following examples use SLURM for running on multiple nodes -- the commands might need to be adjusted for your
+own cluster setup.
+
+* Example 1: Multi-node training with Llama 2 7B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b_multinode.sh
+
+  Run the multi-node training benchmark. For example:
+
+  .. code-block:: shell
+
+     sbatch -N <num_nodes> llama2_7b_multinode.sh
+
+* Example 2: Multi-node training with Llama 2 70B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b_multinode.sh
+
+  Run the multi-node training benchmark. For example:
+
+  .. code-block:: shell
+
+     sbatch -N <num_nodes> llama2_70b_multinode.sh
+
+* Example 3: Multi-node training with Llama 3 8B model
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b_multinode.sh
+
+  Run the multi-node training benchmark. For example:
+
+  .. code-block:: shell
+
+     sbatch -N <num_nodes> llama3_8b_multinode.sh
+
+* Example 4: Multi-node training with Llama 3 70B model
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b_multinode.sh
+
+  Run the multi-node training benchmark. For example:
+
+  .. code-block:: shell
+
+     sbatch -N <num_nodes> llama3_70b_multinode.sh
+
+Previous versions
+=================
+
+See :doc:`jax-maxtext-history` to find documentation for previous releases
+of the ``ROCm/jax-training`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-history.rst

@@ -0,0 +1,47 @@
+:orphan:
+
+********************************************************
+Megatron-LM training performance testing version history
+********************************************************
+
+This table lists previous versions of the ROCm Megatron-LM training Docker image for
+inference performance testing. For detailed information about available models
+for benchmarking, see the version-specific documentation. You can find tagged
+previous releases of the ``ROCm/megatron-lm`` Docker image on `Docker Hub <https://hub.docker.com/r/rocm/megatron-lm/tags>`_.
+
+.. list-table::
+   :header-rows: 1
+   :stub-columns: 1
+
+   * - Image version
+     - ROCm version
+     - PyTorch version
+     - Resources
+
+   * - v25.5
+     - 6.3.4
+     - 2.8.0a0+gite2f9759
+     - 
+       * `Documentation <../megatron-lm>`_
+       * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/v25.5_py312/images/sha256-4506f18ba188d24189c6b1f95130b425f52c528a543bb3f420351824edceadc2>`_
+
+   * - v25.4
+     - 6.3.0
+     - 2.7.0a0+git637433 
+     - 
+       * :doc:`Documentation <megatron-lm-v25.4>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/v25.4/images/sha256-941aa5387918ea91c376c13083aa1e6c9cab40bb1875abbbb73bbb65d8736b3f>`_
+
+   * - v25.3
+     - 6.3.0
+     - 2.7.0a0+git637433 
+     - 
+       * :doc:`Documentation <megatron-lm-v25.3>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/v25.3/images/sha256-1e6ed9bdc3f4ca397300d5a9907e084ab5e8ad1519815ee1f868faf2af1e04e2>`_
+
+   * - v24.12-dev
+     - 6.1.0
+     - 2.4.0
+     - 
+       * :doc:`Documentation <megatron-lm-v24.12-dev>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/24.12-dev/images/sha256-5818c50334ce3d69deeeb8f589d83ec29003817da34158ebc9e2d112b929bf2e>`_

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev.rst

@@ -0,0 +1,515 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using ROCm Megatron-LM
+   :keywords: ROCm, AI, LLM, train, Megatron-LM, megatron, Llama, tutorial, docker, torch
+
+**************************************
+Training a model with ROCm Megatron-LM
+**************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm Megatron-LM
+   training performance documentation. See :doc:`../megatron-lm` for the latest version.
+
+.. _amd-megatron-lm:
+
+The ROCm Megatron-LM framework is a specialized fork of the robust Megatron-LM, designed to
+enable efficient training of large-scale language models on AMD GPUs. By leveraging AMD Instinct™ MI300X
+accelerators, AMD Megatron-LM delivers enhanced scalability, performance, and resource utilization for AI
+workloads. It is purpose-built to :ref:`support models <amd-megatron-lm-model-support>`
+like Meta's Llama 2, Llama 3, and Llama 3.1, enabling developers to train next-generation AI models with greater
+efficiency. See the GitHub repository at `<https://github.com/ROCm/Megatron-LM>`__.
+
+For ease of use, AMD provides a ready-to-use Docker image for MI300X accelerators containing essential
+components, including PyTorch, PyTorch Lightning, ROCm libraries, and Megatron-LM utilities. It contains the
+following software to accelerate training workloads:
+
++--------------------------+--------------------------------+
+| Software component       | Version                        |
++==========================+================================+
+| ROCm                     | 6.1                            |
++--------------------------+--------------------------------+
+| PyTorch                  | 2.4.0                          |
++--------------------------+--------------------------------+
+| PyTorch Lightning        | 2.4.0                          |
++--------------------------+--------------------------------+
+| Megatron Core            | 0.9.0                          |
++--------------------------+--------------------------------+
+| Transformer Engine       | 1.5.0                          |
++--------------------------+--------------------------------+
+| Flash Attention          | v2.6                           |
++--------------------------+--------------------------------+
+| Transformers             | 4.44.0                         |
++--------------------------+--------------------------------+
+
+Supported features and models
+=============================
+
+Megatron-LM provides the following key features to train large language models efficiently:
+
+- Transformer Engine (TE)
+
+- APEX
+
+- GEMM tuning
+
+- Torch.compile
+
+- 3D parallelism: TP + SP + CP
+
+- Distributed optimizer
+
+- Flash Attention (FA) 2
+
+- Fused kernels
+
+- Pre-training
+
+.. _amd-megatron-lm-model-support:
+
+The following models are pre-optimized for performance on the AMD Instinct MI300X accelerator.
+
+* Llama 2 7B
+
+* Llama 2 70B
+
+* Llama 3 8B
+
+* Llama 3 70B
+
+* Llama 3.1 8B
+
+* Llama 3.1 70B
+
+Prerequisite system validation steps
+====================================
+
+Complete the following system validation and optimization steps to set up your system before starting training.
+
+Disable NUMA auto-balancing
+---------------------------
+
+Generally, application performance can benefit from disabling NUMA auto-balancing. However,
+it might be detrimental to performance with certain types of workloads.
+
+Run the command ``cat /proc/sys/kernel/numa_balancing`` to check your current NUMA (Non-Uniform
+Memory Access) settings. Output ``0`` indicates this setting is disabled. If there is no output or
+the output is ``1``, run the following command to disable NUMA auto-balancing.
+
+.. code-block:: shell
+
+   sudo sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+
+See :ref:`mi300x-disable-numa` for more information.
+
+Hardware verification with ROCm
+-------------------------------
+
+Use the command ``rocm-smi --setperfdeterminism 1900`` to set the max clock speed up to 1900 MHz
+instead of the default 2100 MHz. This can reduce the chance of a PCC event lowering the attainable
+GPU clocks. This setting will not be required for new IFWI releases with the production PRC feature.
+You can restore this setting to its default value with the ``rocm-smi -r`` command.
+
+Run the command:
+
+.. code-block:: shell
+
+   rocm-smi --setperfdeterminism 1900
+
+See :ref:`mi300x-hardware-verification-with-rocm` for more information.
+
+RCCL Bandwidth Test
+-------------------
+
+ROCm Collective Communications Library (RCCL) is a standalone library of standard collective communication
+routines for GPUs. See the :doc:`RCCL documentation <rccl:index>` for more information. Before starting
+pre-training, running a RCCL bandwidth test helps ensure that the multi-GPU or multi-node setup is optimized
+for efficient distributed training.
+
+Running the RCCL bandwidth test helps verify that:
+
+- The GPUs can communicate across nodes or within a single node.
+
+- The interconnect (such as InfiniBand, Ethernet, or Infinite fabric) is functioning as expected and
+  provides adequate bandwidth for communication.
+
+- No hardware setup or cabling issues could affect the communication between GPUs
+
+Tuning and optimizing hyperparameters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+In distributed training, specific hyperparameters related to distributed communication can be tuned based on
+the results of the RCCL bandwidth test. These variables are already set in the Docker image:
+
+.. code-block:: shell
+
+   # force all RCCL streams to be high priority
+   export TORCH_NCCL_HIGH_PRIORITY=1
+
+   # specify which RDMA interfaces to use for communication
+   export NCCL_IB_HCA=rdma0,rdma1,rdma2,rdma3,rdma4,rdma5,rdma6,rdma7
+
+   # define the Global ID index used in RoCE mode
+   export NCCL_IB_GID_INDEX=3
+
+   # avoid data corruption/mismatch issue that existed in past releases
+   export RCCL_MSCCL_ENABLE=0
+
+Running the RCCL Bandwidth Test
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+It's recommended you run the RCCL bandwidth test before launching training. It ensures system
+performance is sufficient to launch training. RCCL is not included in the AMD Megatron-LM Docker
+image; follow the instructions in `<https://github.com/ROCm/rccl-tests>`__ to get started.
+See :ref:`mi300x-rccl` for more information.
+
+Run on 8 GPUs (``-g 8``), scanning from 8 bytes to 10 GB:
+
+.. code-block:: shell
+
+   ./build/all_reduce_perf -b 8 -e 10G -f 2 -g 8
+
+.. image:: ../../data/how-to/rocm-for-ai/rccl-tests-8-gpu.png
+   :width: 800
+
+Using one MPI process per GPU and ``-g 1`` for performance-oriented runs on both single-node and multi-node is
+recommended. So, a run on 8 GPUs looks something like:
+
+.. code-block:: shell
+
+   mpirun -np 8 --bind-to numa ./build/all_reduce_perf -b 8 -e 10G -f 2 -g 1
+
+.. image:: ../../data/how-to/rocm-for-ai/rccl-tests-1-mpi-process-per-gpu.png
+   :width: 800
+
+Running with one MPI process per GPU ensures a one-to-one mapping for CPUs and GPUs, which can be beneficial
+for smaller message sizes. This better represents the real-world use of RCCL in deep learning frameworks like
+PyTorch and TensorFlow.
+
+Use the following script to run the RCCL test for four MI300X GPU nodes. Modify paths and node addresses as needed.
+
+.. code-block::
+
+   /home/$USER/ompi_for_gpu/ompi/bin/mpirun -np 32 -H tw022:8,tw024:8,tw010:8, tw015:8 \
+   --mca pml ucx \
+   --mca btl ^openib \
+   -x NCCL_SOCKET_IFNAME=ens50f0np0 \
+   -x NCCL_IB_HCA=rdma0:1,rdma1:1,rdma2:1,rdma3:1,rdma4:1,rdma5:1,rdma6:1,rdma7:1 \
+   -x NCCL_IB_GID_INDEX=3 \
+   -x NCCL_MIN_NCHANNELS=40 \
+   -x NCCL_DEBUG=version \
+   $HOME/rccl-tests/build/all_reduce_perf -b 8 -e 8g -f 2 -g 1
+
+.. image:: ../../data/how-to/rocm-for-ai/rccl-tests-4-mi300x-gpu-nodes.png
+   :width: 800
+
+.. _mi300x-amd-megatron-lm-training:
+
+Start training on MI300X accelerators
+=====================================
+
+The pre-built ROCm Megatron-LM environment allows users to quickly validate system performance, conduct
+training benchmarks, and achieve superior performance for models like Llama 2 and Llama 3.1.
+
+Use the following instructions to set up the environment, configure the script to train models, and
+reproduce the benchmark results on the MI300X accelerators with the AMD Megatron-LM Docker
+image.
+
+.. _amd-megatron-lm-requirements:
+
+Download the Docker image and required packages
+-----------------------------------------------
+
+1. Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/megatron-lm:24.12-dev
+
+2. Launch the Docker container.
+
+   .. code-block:: shell
+
+      docker run -it --device /dev/dri --device /dev/kfd --network host --ipc host --group-add video --cap-add SYS_PTRACE --security-opt seccomp=unconfined --privileged -v $CACHE_DIR:/root/.cache --name megatron-dev-env rocm/megatron-lm:24.12-dev /bin/bash
+
+3. Clone the ROCm Megatron-LM repository to a local directory and install the required packages on the host machine.
+
+   .. code-block:: shell
+
+      git clone https://github.com/ROCm/Megatron-LM
+      cd Megatron-LM
+
+   .. note::
+
+      This release is validated with ``ROCm/Megatron-LM`` commit `bb93ccb <https://github.com/ROCm/Megatron-LM/tree/bb93ccbfeae6363c67b361a97a27c74ab86e7e92>`_.
+      Checking out this specific commit is recommended for a stable and reproducible environment.
+
+      .. code-block:: shell
+         
+         git checkout bb93ccbfeae6363c67b361a97a27c74ab86e7e92
+
+Prepare training datasets
+-------------------------
+
+If you already have the preprocessed data, you can skip this section.
+
+Use the following command to process datasets. We use GPT data as an example. You may change the merge table, use an
+end-of-document token, remove sentence splitting, and use the tokenizer type.
+
+.. code-block:: shell
+
+   python tools/preprocess_data.py \
+       --input my-corpus.json \
+       --output-prefix my-gpt2 \
+       --vocab-file gpt2-vocab.json \
+       --tokenizer-type GPT2BPETokenizer \
+       --merge-file gpt2-merges.txt \
+       --append-eod
+
+In this case, the automatically generated output files are named ``my-gpt2_text_document.bin`` and
+``my-gpt2_text_document.idx``.
+
+.. image:: ../../data/how-to/rocm-for-ai/prep-training-datasets-my-gpt2-text-document.png
+   :width: 800
+
+.. _amd-megatron-lm-environment-setup:
+
+Environment setup
+-----------------
+
+In the ``examples/llama`` directory of Megatron-LM, if you're working with Llama 2 7B or Llama 2 70 B, use the
+``train_llama2.sh`` configuration script. Likewise, if you're working with Llama 3 or Llama 3.1, then use
+``train_llama3.sh`` and update the configuration script accordingly.
+
+Network interface
+^^^^^^^^^^^^^^^^^
+
+To avoid connectivity issues, ensure the correct network interface is set in your training scripts.
+
+1. Run the following command to find the active network interface on your system.
+
+   .. code-block:: shell
+
+      ip a
+
+2. Update the ``NCCL_SOCKET_IFNAME`` and ``GLOO_SOCKET_IFNAME`` variables with your system’s network interface. For
+   example:
+
+   .. code-block:: shell
+
+      export NCCL_SOCKET_IFNAME=ens50f0np0
+
+      export GLOO_SOCKET_IFNAME=ens50f0np0
+
+Dataset options
+^^^^^^^^^^^^^^^
+
+You can use either mock data or real data for training.
+
+* If you're using a real dataset, update the ``DATA_PATH`` variable to point to the location of your dataset.
+
+  .. code-block:: shell
+
+     DATA_DIR="/root/.cache/data" # Change to where your dataset is stored
+
+     DATA_PATH=${DATA_DIR}/bookcorpus_text_sentence
+
+  .. code-block:: shell
+
+     --data-path $DATA_PATH
+
+  Ensure that the files are accessible inside the Docker container.
+
+* Mock data can be useful for testing and validation. If you're using mock data, replace ``--data-path $DATA_PATH`` with the ``--mock-data`` option.
+
+  .. code-block:: shell
+
+     --mock-data
+
+Tokenizer
+^^^^^^^^^
+
+Tokenization is the process of converting raw text into tokens that can be processed by the model. For Llama
+models, this typically involves sub-word tokenization, where words are broken down into smaller units based on
+a fixed vocabulary. The tokenizer is trained along with the model on a large corpus of text, and it learns a
+fixed vocabulary that can represent a wide range of text from different domains. This allows Llama models to
+handle a variety of input sequences, including unseen words or domain-specific terms.
+
+To train any of the Llama 2 models that this Docker image supports, use the ``Llama2Tokenizer``.
+
+To train any of Llama 3 and Llama 3.1 models that this Docker image supports, use the ``HuggingFaceTokenizer``.
+Set the Hugging Face model link in the ``TOKENIZER_MODEL`` variable.
+
+For example, if you're using the Llama 3.1 8B model:
+
+.. code-block:: shell
+
+   TOKENIZER_MODEL=meta-llama/Llama-3.1-8B
+
+Run benchmark tests
+-------------------
+
+.. note::
+
+   If you're running **multi node training**, update the following environment variables. They can
+   also be passed as command line arguments.
+
+   * Change ``localhost`` to the master node's hostname:
+
+     .. code-block:: shell
+
+        MASTER_ADDR="${MASTER_ADDR:-localhost}"
+
+   * Set the number of nodes you want to train on (for instance, ``2``, ``4``, ``8``):
+
+     .. code-block:: shell
+
+        NNODES="${NNODES:-1}"
+
+   * Set the rank of each node (0 for master, 1 for the first worker node, and so on):
+
+     .. code-block:: shell
+
+        NODE_RANK="${NODE_RANK:-0}"
+
+* Use this command to run a performance benchmark test of any of the Llama 2 models that this Docker image supports (see :ref:`variables <amd-megatron-lm-benchmark-test-vars>`).
+
+  .. code-block:: shell
+
+     {variables} bash examples/llama/train_llama2.sh
+
+* Use this command to run a performance benchmark test of any of the Llama 3 and Llama 3.1 models that this Docker image supports (see :ref:`variables <amd-megatron-lm-benchmark-test-vars>`).
+
+  .. code-block:: shell
+
+     {variables} bash examples/llama/train_llama3.sh
+
+.. _amd-megatron-lm-benchmark-test-vars:
+
+The benchmark tests support the same set of variables:
+
++--------------------------+-----------------------+-----------------------+
+| Name                     | Options               | Description           |
++==========================+=======================+=======================+
+| ``TEE_OUTPUT``           | 0 or 1                | 0: disable training   |
+|                          |                       | log                   |
+|                          |                       |                       |
+|                          |                       | 1: enable training    |
+|                          |                       | log                   |
++--------------------------+-----------------------+-----------------------+
+| ``MBS``                  |                       | Micro batch size      |
++--------------------------+-----------------------+-----------------------+
+| ``BS``                   |                       | Batch size            |
++--------------------------+-----------------------+-----------------------+
+| ``TP``                   | 1, 2, 4, 8            | Tensor parallel       |
++--------------------------+-----------------------+-----------------------+
+| ``TE_FP8``               | 0 or 1                | Datatype.             |
+|                          |                       | If it is set to 1,    |
+|                          |                       | FP8.                  |
+|                          |                       |                       |
+|                          |                       | If it is set to 0.    |
+|                          |                       | BP16                  |
++--------------------------+-----------------------+-----------------------+
+| ``NO_TORCH_COMPILE``     | 0 or 1                | If it is set to 1,    |
+|                          |                       | enable torch.compile. |
+|                          |                       |                       |
+|                          |                       | If it is set to 0.    |
+|                          |                       | Disable torch.compile |
+|                          |                       | (default)             |
++--------------------------+-----------------------+-----------------------+
+| ``SEQ_LENGTH``           |                       | Input sequence length |
++--------------------------+-----------------------+-----------------------+
+| ``GEMM_TUNING``          | 0 or 1                | If it is set to 1,    |
+|                          |                       | enable gemm tuning.   |
+|                          |                       |                       |
+|                          |                       | If it is set to 0,    |
+|                          |                       | disable gemm tuning   |
++--------------------------+-----------------------+-----------------------+
+| ``USE_FLASH_ATTN``       | 0 or 1                | 0: disable flash      |
+|                          |                       | attention             |
+|                          |                       |                       |
+|                          |                       | 1: enable flash       |
+|                          |                       | attention             |
++--------------------------+-----------------------+-----------------------+
+| ``ENABLE_PROFILING``     | 0 or 1                | 0: disable torch      |
+|                          |                       | profiling             |
+|                          |                       |                       |
+|                          |                       | 1: enable torch       |
+|                          |                       | profiling             |
++--------------------------+-----------------------+-----------------------+
+| ``MODEL_SIZE``           |                       | The size of the mode: |
+|                          |                       | 7B/70B, etc.          |
++--------------------------+-----------------------+-----------------------+
+| ``TOTAL_ITERS``          |                       | Total number of       |
+|                          |                       | iterations            |
++--------------------------+-----------------------+-----------------------+
+| ``transformer-impl``     | transformer_engine or | Enable transformer    |
+|                          | local                 | engine by default     |
++--------------------------+-----------------------+-----------------------+
+
+Benchmarking examples
+^^^^^^^^^^^^^^^^^^^^^
+
+.. tab-set::
+
+   .. tab-item:: Single node training
+      :sync: single
+
+      Use this command to run training with Llama 2 7B model on a single node. You can specify MBS, BS, FP,
+      datatype, and so on.
+
+      .. code-block:: bash
+
+         TEE_OUTPUT=1 MBS=5 BS=120 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+         SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+      You can find the training logs at the location defined in ``$TRAIN_LOG`` in the :ref:`configuration script <amd-megatron-lm-environment-setup>`.
+
+      See the sample output:
+
+      .. image:: ../../data/how-to/rocm-for-ai/llama2-7b-training-log-sample.png
+         :width: 800
+
+   .. tab-item:: Multi node training
+      :sync: multi
+
+      Launch the Docker container on each node.
+
+      In this example, run training with Llama 2 7B model on 2 nodes with specific MBS, BS, FP, datatype, and
+      so on.
+
+      On the master node:
+
+      .. code-block:: bash
+
+         TEE_OUTPUT=1 MBS=4 BS=64 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+         SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+      On the worker node:
+
+      .. code-block:: bash
+
+         TEE_OUTPUT=1 MBS=4 BS=64 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+         SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+      You can find the training logs at the location defined in ``$TRAIN_LOG`` in the :ref:`configuration script <amd-megatron-lm-environment-setup>`.
+
+      Sample output for 2-node training:
+
+      Master node:
+
+      .. image:: ../../data/how-to/rocm-for-ai/2-node-training-master.png
+         :width: 800
+
+      Worker node:
+
+      .. image:: ../../data/how-to/rocm-for-ai/2-node-training-worker.png
+         :width: 800
+
+Previous versions
+=================
+
+See :doc:`megatron-lm-history` to find documentation for previous releases
+of the ``ROCm/megatron-lm`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.3.rst

@@ -0,0 +1,535 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using Megatron-LM for ROCm.
+   :keywords: ROCm, AI, LLM, train, Megatron-LM, megatron, Llama, tutorial, docker, torch
+
+******************************************
+Training a model with Megatron-LM for ROCm
+******************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm Megatron-LM
+   training performance documentation. See :doc:`../megatron-lm` for the latest version.
+
+The Megatron-LM framework for ROCm is a specialized fork of the robust Megatron-LM,
+designed to enable efficient training of large-scale language models on AMD
+GPUs. By leveraging AMD Instinct™ MI300X series accelerators, Megatron-LM delivers
+enhanced scalability, performance, and resource utilization for AI workloads.
+It is purpose-built to support models like Llama 2, Llama 3, Llama 3.1, and
+DeepSeek, enabling developers to train next-generation AI models more
+efficiently. See the GitHub repository at `<https://github.com/ROCm/Megatron-LM>`__.
+
+AMD provides a ready-to-use Docker image for MI300X accelerators containing
+essential components, including PyTorch, ROCm libraries, and Megatron-LM
+utilities. It contains the following software components to accelerate training
+workloads:
+
++--------------------------+--------------------------------+
+| Software component       | Version                        |
++==========================+================================+
+| ROCm                     | 6.3.0                          |
++--------------------------+--------------------------------+
+| PyTorch                  | 2.7.0a0+git637433              |
++--------------------------+--------------------------------+
+| Python                   | 3.10                           |
++--------------------------+--------------------------------+
+| Transformer Engine       | 1.11                           |
++--------------------------+--------------------------------+
+| Flash Attention          | 3.0.0                          |
++--------------------------+--------------------------------+
+| hipBLASLt                | git258a2162                    |
++--------------------------+--------------------------------+
+| Triton                   | 3.1                            |
++--------------------------+--------------------------------+
+
+Supported features and models
+=============================
+
+Megatron-LM provides the following key features to train large language models efficiently:
+
+- Transformer Engine (TE)
+
+- APEX
+
+- GEMM tuning
+
+- Torch.compile
+
+- 3D parallelism: TP + SP + CP
+
+- Distributed optimizer
+
+- Flash Attention (FA) 3
+
+- Fused kernels
+
+- Pre-training
+
+.. _amd-megatron-lm-model-support:
+
+The following models are pre-optimized for performance on the AMD Instinct MI300X accelerator.
+
+* Llama 2 7B
+
+* Llama 2 70B
+
+* Llama 3 8B
+
+* Llama 3 70B
+
+* Llama 3.1 8B
+
+* Llama 3.1 70B
+
+* DeepSeek-V2-Lite
+
+.. note::
+
+   Some models, such as Llama 3, require an external license agreement through
+   a third party (for example, Meta).
+
+System validation
+=================
+
+If you have already validated your system settings, skip this step. Otherwise,
+complete the :ref:`system validation and optimization steps <train-a-model-system-validation>`
+to set up your system before starting training.
+
+Disable NUMA auto-balancing
+---------------------------
+
+Generally, application performance can benefit from disabling NUMA auto-balancing. However,
+it might be detrimental to performance with certain types of workloads.
+
+Run the command ``cat /proc/sys/kernel/numa_balancing`` to check your current NUMA (Non-Uniform
+Memory Access) settings. Output ``0`` indicates this setting is disabled. If there is no output or
+the output is ``1``, run the following command to disable NUMA auto-balancing.
+
+.. code-block:: shell
+
+   sudo sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+
+See :ref:`mi300x-disable-numa` for more information.
+
+.. _mi300x-amd-megatron-lm-training:
+
+Environment setup
+=================
+
+The pre-built ROCm Megatron-LM environment allows users to quickly validate system performance, conduct
+training benchmarks, and achieve superior performance for models like Llama 3.1, Llama 2, and DeepSeek V2.
+
+Use the following instructions to set up the environment, configure the script to train models, and
+reproduce the benchmark results on the MI300X accelerators with the AMD Megatron-LM Docker
+image.
+
+.. _amd-megatron-lm-requirements:
+ 
+Download the Docker image
+-------------------------
+
+1. Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/megatron-lm:v25.3
+
+2. Launch the Docker container.
+
+   .. code-block:: shell
+
+      docker run -it --device /dev/dri --device /dev/kfd --network host --ipc host --group-add video --cap-add SYS_PTRACE --security-opt seccomp=unconfined --privileged -v $HOME:$HOME -v  $HOME/.ssh:/root/.ssh --shm-size 64G --name megatron_training_env rocm/megatron-lm:v25.3
+
+3. Use these commands if you exit the ``megatron_training_env`` container and need to return to it.
+
+   .. code-block:: shell
+
+      docker start megatron_training_env
+      docker exec -it megatron_training_env bash
+
+The Docker container includes a pre-installed, verified version of Megatron-LM from the `release branch <https://github.com/ROCm/Megatron-LM/tree/megatron_release_v25.3>`_.
+
+.. _amd-megatron-lm-environment-setup:
+
+Configuration scripts
+---------------------
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      If you're working with Llama 2 7B or Llama 2 70 B, use the ``train_llama2.sh`` configuration
+      script in the ``examples/llama`` directory of
+      `<https://github.com/ROCm/Megatron-LM/tree/megatron_release_v25.3/examples/llama>`__.
+      Likewise, if you're working with Llama 3 or Llama 3.1, then use ``train_llama3.sh`` and update
+      the configuration script accordingly.
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      Use the ``train_deepseek_v2.sh`` configuration script in the ``examples/deepseek_v2``
+      directory of
+      `<https://github.com/ROCm/Megatron-LM/tree/megatron_release_v25.3/examples/deepseek_v2>`__
+      and update the configuration script accordingly.
+
+Network interface
+^^^^^^^^^^^^^^^^^
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      To avoid connectivity issues in multi-node deployments, ensure the correct network interface
+      is set in your training scripts.
+
+      1. Run the following command (outside the container) to find the active network interface on your system.
+
+         .. code-block:: shell
+
+            ip a
+
+      2. Update the ``NCCL_SOCKET_IFNAME`` and ``GLOO_SOCKET_IFNAME`` variables with your system’s network interface. For
+         example:
+
+         .. code-block:: shell
+
+            export NCCL_SOCKET_IFNAME=ens50f0np0
+
+            export GLOO_SOCKET_IFNAME=ens50f0np0
+
+Dataset options
+^^^^^^^^^^^^^^^
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      You can use either mock data or real data for training.
+
+      * Mock data can be useful for testing and validation. Use the ``MOCK_DATA`` variable to toggle between mock and real data. The default
+        value is ``1`` for enabled.
+
+        .. code-block:: bash
+
+           MOCK_DATA=1
+
+      * If you're using a real dataset, update the ``DATA_PATH`` variable to point to the location of your dataset.
+
+        .. code-block:: bash
+
+           MOCK_DATA=0
+
+           DATA_PATH=${DATA_PATH:-"/data/bookcorpus_text_sentence"}  # Change to where your dataset is stored
+
+        Ensure that the files are accessible inside the Docker container.
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      If you don't already have the dataset, download the DeepSeek dataset using the following
+      commands:
+
+      .. code-block:: shell
+
+         mkdir deepseek-datasets
+         cd deepseek-datasets
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/SlimPajama.json
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/alpaca_zh-train.json
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/alpaca_zh-valid.json
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/mmap_deepseekv2_datasets_text_document.bin
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/mmap_deepseekv2_datasets_text_document.idx
+
+      You can use either mock data or real data for training.
+
+      * Mock data can be useful for testing and validation. Use the ``MOCK_DATA`` variable to toggle between mock and real data. The default
+        value is ``1`` for enabled.
+
+        .. code-block:: bash
+
+           MOCK_DATA=1
+
+      * If you're using a real dataset, update the ``DATA_DIR`` variable to point to the location of your dataset.
+
+        .. code-block:: bash
+
+           MOCK_DATA=0
+
+           DATA_DIR="/root/data/deepseek-datasets"  # Change to where your dataset is stored
+
+        Ensure that the files are accessible inside the Docker container.
+
+Tokenizer
+^^^^^^^^^
+
+Tokenization is the process of converting raw text into tokens that can be processed by the model. For Llama
+models, this typically involves sub-word tokenization, where words are broken down into smaller units based on
+a fixed vocabulary. The tokenizer is trained along with the model on a large corpus of text, and it learns a
+fixed vocabulary that can represent a wide range of text from different domains. This allows Llama models to
+handle a variety of input sequences, including unseen words or domain-specific terms.
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      To train any of the Llama 2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support>`, use the ``Llama2Tokenizer``.
+
+      To train any of Llama 3 and Llama 3.1 models that this Docker image supports, use the ``HuggingFaceTokenizer``.
+      Set the Hugging Face model link in the ``TOKENIZER_MODEL`` variable.
+
+      For example, if you're using the Llama 3.1 8B model:
+
+      .. code-block:: shell
+
+         TOKENIZER_MODEL=meta-llama/Llama-3.1-8B
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      To train any of the DeepSeek V2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support>`, use the ``DeepSeekV2Tokenizer``.
+
+Multi-node training
+^^^^^^^^^^^^^^^^^^^
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      If you're running multi-node training, update the following environment variables. They can
+      also be passed as command line arguments.
+
+      * Change ``localhost`` to the master node's hostname:
+
+        .. code-block:: shell
+
+           MASTER_ADDR="${MASTER_ADDR:-localhost}"
+
+      * Set the number of nodes you want to train on (for instance, ``2``, ``4``, ``8``):
+
+        .. code-block:: shell
+
+           NNODES="${NNODES:-1}"
+
+      * Set the rank of each node (0 for master, 1 for the first worker node, and so on):
+
+        .. code-block:: shell
+
+           NODE_RANK="${NODE_RANK:-0}"
+
+      * Set ``DATA_CACHE_PATH`` to a common directory accessible by all the nodes (for example, an
+        NFS directory) for multi-node runs:
+
+        .. code-block:: shell
+
+           DATA_CACHE_PATH=/root/cache # Set to a common directory for multi-node runs
+
+      * For multi-node runs, make sure the correct network drivers are installed on the nodes. If
+        inside a Docker, either install the drivers inside the Docker container or pass the network
+        drivers from the host while creating the Docker container.
+
+Start training on AMD Instinct accelerators
+===========================================
+
+The prebuilt Megatron-LM with ROCm training environment allows users to quickly validate
+system performance, conduct training benchmarks, and achieve superior
+performance for models like Llama 3.1 and Llama 2. This container should not be
+expected to provide generalized performance across all training workloads. You
+can expect the container to perform in the model configurations described in
+the following section, but other configurations are not validated by AMD.
+
+Use the following instructions to set up the environment, configure the script
+to train models, and reproduce the benchmark results on MI300X series
+accelerators with the AMD Megatron-LM Docker image.
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      .. tab-set::
+
+         .. tab-item:: Single node training
+            :sync: single-node
+
+            To run training on a single node, navigate to the Megatron-LM folder and use the
+            following command:
+
+            .. code-block:: shell
+
+               TEE_OUTPUT=1 MBS=2 BS=128 TP=1 TE_FP8=1 SEQ_LENGTH=8192 MODEL_SIZE=8 bash examples/llama/train_llama3.sh
+
+         .. tab-item:: Multi-node training
+            :sync: multi-node
+
+            To run training on multiple nodes, launch the Docker container on each node. For example, for a two node setup (``NODE0`` as the master node), use these commands.
+
+            * On the master node ``NODE0``:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=2 BS=256 TP=1 TE_FP8=1 SEQ_LENGTH=8192 MODEL_SIZE=8 MASTER_ADDR=IP_NODE0 NNODES=2 NODE_RANK=0 bash examples/llama/train_llama3.sh
+
+            * On the worker node ``NODE1``:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=2 BS=256 TP=1 TE_FP8=1 SEQ_LENGTH=8192 MODEL_SIZE=8 MASTER_ADDR=IP_NODE0 NNODES=2 NODE_RANK=1 bash examples/llama/train_llama3.sh
+
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      To run the training on a single node, go to ``/Megatron-LM`` folder and use the following command:
+
+      .. code-block:: shell
+
+         cd /workspace/Megatron-LM
+         GEMM_TUNING=1 PR=bf16 MBS=4 AC=none bash examples/deepseek_v2/train_deepseekv2.sh
+
+Key options
+-----------
+
+.. _amd-megatron-lm-benchmark-test-vars:
+
+The benchmark tests support the following sets of variables:
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      ``TEE_OUTPUT``
+        ``1`` to enable training logs or ``0`` to disable.
+
+      ``TE_FP8``
+        ``0`` for BP16 (default) or ``1`` for FP8 GEMMs.
+
+      ``GEMM_TUNING``
+        ``1`` to enable GEMM tuning, which boosts performance by using the best GEMM kernels.
+
+      ``USE_FLASH_ATTN``
+        ``1`` to enable Flash Attention.
+
+      ``ENABLE_PROFILING``
+        ``1`` to enable PyTorch profiling for performance analysis.
+
+      ``transformer-impl``
+        ``transformer_engine`` to use the Transformer Engine (TE) or ``local`` to disable TE.
+
+      ``MODEL_SIZE``
+        ``8B`` or ``70B`` for Llama 3 and 3.1. ``7B`` or ``70B`` for Llama 2.
+
+      ``TOTAL_ITERS``
+        The total number of iterations -- ``10`` by default.
+
+      ``MOCK_DATA``
+        ``1`` to use mock data or ``0`` to use real data provided by you.
+
+      ``MBS``
+        Micro batch size.
+
+      ``BS``
+        Global batch size.
+
+      ``TP``
+        Tensor parallel (``1``, ``2``, ``4``, ``8``).
+
+      ``SEQ_LENGTH``
+        Input sequence length.
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      ``PR``
+        Precision for training. ``bf16`` for BF16 (default) or ``fp8`` for FP8 GEMMs.
+
+      ``GEMM_TUNING``
+        ``1`` to enable GEMM tuning, which boosts performance by using the best GEMM kernels.
+
+      ``TOTAL_ITERS``
+        The total number of iterations -- ``10`` by default.
+
+      ``MOCK_DATA``
+        ``1`` to use mock data or ``0`` to use real data provided by you.
+
+      ``MBS``
+        Micro batch size.
+
+      ``GBS``
+        Global batch size.
+
+Benchmarking examples
+---------------------
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      .. tab-set::
+
+         .. tab-item:: Single node training
+            :sync: single-node
+
+            Use this command to run training with Llama 2 7B model on a single node. You can specify MBS, BS, FP,
+            datatype, and so on.
+
+            .. code-block:: bash
+
+               TEE_OUTPUT=1 MBS=5 BS=120 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+               SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+            You can find the training logs at the location defined in ``$TRAIN_LOG`` in the :ref:`configuration script <amd-megatron-lm-environment-setup>`.
+
+            See the sample output:
+
+            .. image:: ../../../../data/how-to/rocm-for-ai/llama2-7b-training-log-sample.png
+               :width: 800
+
+         .. tab-item:: Multi-node training
+            :sync: multi-node
+
+            Launch the Docker container on each node.
+
+            In this example, run training with Llama 2 7B model on 2 nodes with specific MBS, BS, FP, datatype, and
+            so on.
+
+            On the master node:
+
+            .. code-block:: bash
+
+               TEE_OUTPUT=1 MBS=4 BS=64 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+               SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+            On the worker node:
+
+            .. code-block:: bash
+
+               TEE_OUTPUT=1 MBS=4 BS=64 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+               SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+            You can find the training logs at the location defined in ``$TRAIN_LOG`` in the :ref:`configuration script <amd-megatron-lm-environment-setup>`.
+
+            Sample output for 2-node training:
+
+            Master node:
+
+            .. image:: ../../../../data/how-to/rocm-for-ai/2-node-training-master.png
+               :width: 800
+
+            Worker node:
+
+            .. image:: ../../../../data/how-to/rocm-for-ai/2-node-training-worker.png
+               :width: 800
+
+Previous versions
+=================
+
+See :doc:`megatron-lm-history` to find documentation for previous releases
+of the ``ROCm/megatron-lm`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.4.rst

@@ -0,0 +1,618 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using Megatron-LM for ROCm.
+   :keywords: ROCm, AI, LLM, train, Megatron-LM, megatron, Llama, tutorial, docker, torch
+
+******************************************
+Training a model with Megatron-LM for ROCm
+******************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm Megatron-LM
+   training performance documentation. See :doc:`../megatron-lm` for the latest version.
+
+The Megatron-LM framework for ROCm is a specialized fork of the robust Megatron-LM,
+designed to enable efficient training of large-scale language models on AMD
+GPUs. By leveraging AMD Instinct™ MI300X series accelerators, Megatron-LM delivers
+enhanced scalability, performance, and resource utilization for AI workloads.
+It is purpose-built to support models like Llama 2, Llama 3, Llama 3.1, and
+DeepSeek, enabling developers to train next-generation AI models more
+efficiently. See the GitHub repository at `<https://github.com/ROCm/Megatron-LM>`__.
+
+AMD provides a ready-to-use Docker image for MI300X series accelerators containing
+essential components, including PyTorch, ROCm libraries, and Megatron-LM
+utilities. It contains the following software components to accelerate training
+workloads:
+
++--------------------------+--------------------------------+
+| Software component       | Version                        |
++==========================+================================+
+| ROCm                     | 6.3.0                          |
++--------------------------+--------------------------------+
+| PyTorch                  | 2.7.0a0+git637433              |
++--------------------------+--------------------------------+
+| Python                   | 3.10                           |
++--------------------------+--------------------------------+
+| Transformer Engine       | 1.11                           |
++--------------------------+--------------------------------+
+| Flash Attention          | 3.0.0                          |
++--------------------------+--------------------------------+
+| hipBLASLt                | git258a2162                    |
++--------------------------+--------------------------------+
+| Triton                   | 3.1                            |
++--------------------------+--------------------------------+
+
+Supported features and models
+=============================
+
+Megatron-LM provides the following key features to train large language models efficiently:
+
+- Transformer Engine (TE)
+
+- APEX
+
+- GEMM tuning
+
+- Torch.compile
+
+- 3D parallelism: TP + SP + CP
+
+- Distributed optimizer
+
+- Flash Attention (FA) 3
+
+- Fused kernels
+
+- Pre-training
+
+.. _amd-megatron-lm-model-support:
+
+The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+
+* Llama 3.1 8B
+
+* Llama 3.1 70B
+
+* Llama 3 8B
+
+* Llama 3 70B
+
+* Llama 2 7B
+
+* Llama 2 70B
+
+* DeepSeek-V2-Lite
+
+.. note::
+
+   Some models, such as Llama, require an external license agreement through
+   a third party (for example, Meta).
+
+.. _amd-megatron-lm-performance-measurements:
+
+Performance measurements
+========================
+
+To evaluate performance, the
+`Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
+page provides reference throughput and latency measurements for training
+popular AI models.
+
+.. important::
+
+   The performance data presented in
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+   only reflects the :doc:`latest version of this training benchmarking environment <../megatron-lm>`_.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+
+System validation
+=================
+
+If you have already validated your system settings, including NUMA
+auto-balancing, skip this step. Otherwise, complete the :ref:`system validation
+and optimization steps <train-a-model-system-validation>` to set up your system
+before starting training.
+
+.. _mi300x-amd-megatron-lm-training:
+
+Environment setup
+=================
+
+The prebuilt ROCm Megatron-LM environment allows users to quickly validate system performance, conduct
+training benchmarks, and achieve superior performance for models like Llama 3.1, Llama 2, and DeepSeek V2.
+
+Use the following instructions to set up the environment, configure the script to train models, and
+reproduce the benchmark results on MI300X series accelerators with the AMD Megatron-LM Docker
+image.
+
+.. _amd-megatron-lm-requirements:
+ 
+Download the Docker image
+-------------------------
+
+1. Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/megatron-lm:v25.4
+
+2. Launch the Docker container.
+
+   .. code-block:: shell
+
+      docker run -it --device /dev/dri --device /dev/kfd --device /dev/infiniband --network host --ipc host --group-add video --cap-add SYS_PTRACE --security-opt seccomp=unconfined --privileged -v $HOME:$HOME -v  $HOME/.ssh:/root/.ssh --shm-size 64G --name megatron_training_env rocm/megatron-lm:v25.4
+
+3. Use these commands if you exit the ``megatron_training_env`` container and need to return to it.
+
+   .. code-block:: shell
+
+      docker start megatron_training_env
+      docker exec -it megatron_training_env bash
+
+The Docker container includes a pre-installed, verified version of the ROCm Megatron-LM development branch `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev>`__
+(commit `fd6f01 <https://github.com/ROCm/Megatron-LM/tree/fd6f0d11d7f9480ace32f22eb7e4dab5314fa350>`_).
+
+.. _amd-megatron-lm-environment-setup:
+
+Configuration scripts
+---------------------
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      If you're working with Llama 2 7B or Llama 2 70 B, use the ``train_llama2.sh`` configuration
+      script in the ``examples/llama`` directory of
+      `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev/examples/llama>`__.
+      Likewise, if you're working with Llama 3 or Llama 3.1, use ``train_llama3.sh`` and update
+      the configuration script accordingly.
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      Use the ``train_deepseek_v2.sh`` configuration script in the ``examples/deepseek_v2``
+      directory of
+      `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev/examples/deepseek_v2>`__
+      and update the configuration script accordingly.
+
+Network interface
+^^^^^^^^^^^^^^^^^
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      Update the network interface in the script to match your system's network interface. To
+      find your network interface, run the following (outside of any Docker container):
+
+      .. code-block:: bash
+
+         ip a
+
+      Look for an active interface that has an IP address in the same subnet as
+      your other nodes. Then, update the following variables in the script, for
+      example:
+
+      .. code-block:: bash
+
+         export NCCL_SOCKET_IFNAME=ens50f0np0
+
+         export GLOO_SOCKET_IFNAME=ens50f0np0
+
+Dataset options
+^^^^^^^^^^^^^^^
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      You can use either mock data or real data for training.
+
+      * Mock data can be useful for testing and validation. Use the ``MOCK_DATA`` variable to toggle between mock and real data. The default
+        value is ``1`` for enabled.
+
+        .. code-block:: bash
+
+           MOCK_DATA=1
+
+      * If you're using a real dataset, update the ``DATA_PATH`` variable to point to the location of your dataset.
+
+        .. code-block:: bash
+
+           MOCK_DATA=0
+
+           DATA_PATH="/data/bookcorpus_text_sentence"  # Change to where your dataset is stored
+
+        Ensure that the files are accessible inside the Docker container.
+
+        To download the dataset, set the ``DATASET`` variable to the dataset you'd like to use. Two datasets are supported: ``DATASET=wiki`` and ``DATASET=bookcorpus``.
+        Use the following command to download the dataset.
+
+        .. code-block:: shell
+
+           DATASET=wiki bash examples/llama/prepare_dataset.sh # For wiki-en dataset
+           DATASET=bookcorpus bash examples/llama/prepare_dataset.sh # For bookcorpus dataset
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      If you don't already have the dataset, download the DeepSeek dataset using the following
+      commands:
+
+      .. code-block:: shell
+
+         mkdir deepseek-datasets
+         cd deepseek-datasets
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/SlimPajama.json
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/alpaca_zh-train.json
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/alpaca_zh-valid.json
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/mmap_deepseekv2_datasets_text_document.bin
+         wget https://atp-modelzoo-wlcb-pai.oss-cn-wulanchabu.aliyuncs.com/release/models/pai-megatron-patch/deepseek-datasets/mmap_deepseekv2_datasets_text_document.idx
+
+      You can use either mock data or real data for training.
+
+      * Mock data can be useful for testing and validation. Use the ``MOCK_DATA`` variable to toggle between mock and real data. The default
+        value is ``1`` for enabled.
+
+        .. code-block:: bash
+
+           MOCK_DATA=1
+
+      * If you're using a real dataset, update the ``DATA_DIR`` variable to point to the location of your dataset.
+
+        .. code-block:: bash
+
+           MOCK_DATA=0
+
+           DATA_DIR="/root/data/deepseek-datasets"  # Change to where your dataset is stored
+
+        Ensure that the files are accessible inside the Docker container.
+
+Tokenizer
+^^^^^^^^^
+
+Tokenization is the process of converting raw text into tokens that can be processed by the model. For Llama
+models, this typically involves sub-word tokenization, where words are broken down into smaller units based on
+a fixed vocabulary. The tokenizer is trained along with the model on a large corpus of text, and it learns a
+fixed vocabulary that can represent a wide range of text from different domains. This allows Llama models to
+handle a variety of input sequences, including unseen words or domain-specific terms.
+
+You can assign the path of an existing tokenizer to the ``TOKENIZER_MODEL`` as shown in the following examples.
+If the tokenizer is not found, it'll be downloaded to the default tokenizer model path: ``${DATA_DIR}/tokenizer_llama3``
+or ``${DATA_DIR}/tokenizer_llama2``.
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      To train any of the Llama 2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support>`, use the ``Llama2Tokenizer``
+      or the default ``HuggingFaceTokenizer``.
+
+      To train any of Llama 3 and Llama 3.1 models that this Docker image supports, use the ``HuggingFaceTokenizer``.
+      Set the Hugging Face model path in the ``TOKENIZER_MODEL`` variable.
+
+      For example, if you're using the Llama 3.1 8B model:
+
+      .. code-block:: shell
+
+         TOKENIZER_MODEL=meta-llama/Llama-3.1-8B
+
+      .. note::
+
+         If you don't already have the Llama 3.1 tokenizer locally, set your
+         personal Hugging Face access token ``HF_TOKEN`` to download the
+         tokenizer. If you encounter the following error, set ``HF_TOKEN`` to
+         your access-authorized Hugging Face token.
+
+         .. code-block:: shell
+
+            OSError: You are trying to access a gated repo.
+
+            # pass your HF_TOKEN
+            export HF_TOKEN=$your_personal_hf_token
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      To train any of the DeepSeek V2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support>`, use the ``DeepSeekV2Tokenizer``.
+
+Multi-node training
+^^^^^^^^^^^^^^^^^^^
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      If you're running multi-node training, update the following environment variables. They can
+      also be passed as command line arguments.
+
+      * Change ``localhost`` to the master node's hostname:
+
+        .. code-block:: shell
+
+           MASTER_ADDR="${MASTER_ADDR:-localhost}"
+
+      * Set the number of nodes you want to train on (for instance, ``2``, ``4``, ``8``):
+
+        .. code-block:: shell
+
+           NNODES="${NNODES:-1}"
+
+      * Set the rank of each node (0 for master, 1 for the first worker node, and so on):
+
+        .. code-block:: shell
+
+           NODE_RANK="${NODE_RANK:-0}"
+
+      * Set ``DATA_CACHE_PATH`` to a common directory accessible by all the nodes (for example, an
+        NFS directory) for multi-node runs:
+
+        .. code-block:: shell
+
+           DATA_CACHE_PATH=/root/cache # Set to a common directory for multi-node runs
+
+      * For multi-node runs, make sure the correct network drivers are installed on the nodes. If
+        inside a Docker container, either install the drivers inside the Docker container or pass the network
+        drivers from the host while creating the Docker container.
+
+        .. code-block:: shell
+
+           # Specify which RDMA interfaces to use for communication
+           export NCCL_IB_HCA=rdma0,rdma1,rdma2,rdma3,rdma4,rdma5,rdma6,rdma7
+
+Start training on AMD Instinct accelerators
+===========================================
+
+The prebuilt Megatron-LM with ROCm training environment allows users to quickly validate
+system performance, conduct training benchmarks, and achieve superior
+performance for models like Llama 3.1 and Llama 2. This container should not be
+expected to provide generalized performance across all training workloads. You
+can expect the container to perform in the model configurations described in
+the following section, but other configurations are not validated by AMD.
+
+Use the following instructions to set up the environment, configure the script
+to train models, and reproduce the benchmark results on MI300X series
+accelerators with the AMD Megatron-LM Docker image.
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      .. tab-set::
+
+         .. tab-item:: Single node training
+            :sync: single-node
+
+            To run training on a single node, navigate to the Megatron-LM folder and use one of the
+            following commands.
+
+            - For Llama 3.1 8B FP8:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=2 BS=128 TP=1 TE_FP8=1 SEQ_LENGTH=8192 MODEL_SIZE=8 TOTAL_ITERS=50 bash examples/llama/train_llama3.sh
+
+            - For Llama 3.1 8B BF16:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=2 BS=128 TP=1 TE_FP8=0 SEQ_LENGTH=8192 MODEL_SIZE=8 TOTAL_ITERS=50 bash examples/llama/train_llama3.sh
+
+            - For Llama 2 7B FP8:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=4 BS=256 TP=1 TE_FP8=1 SEQ_LENGTH=4096 MODEL_SIZE=7 TOTAL_ITERS=50 bash examples/llama/train_llama2.sh
+
+            - For Llama 2 7B BF16:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=4 BS=256 TP=1 TE_FP8=0 SEQ_LENGTH=4096 MODEL_SIZE=7 TOTAL_ITERS=50 bash examples/llama/train_llama2.sh
+
+            To run training with FSDP2 enabled, add the ``FSDP=1`` argument. For example:
+
+            - For Llama 3 70B BF16:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=3 BS=24 TP=1 TE_FP8=0 FSDP=1 RECOMPUTE=1 SEQ_LENGTH=8192 MODEL_SIZE=70 TOTAL_ITERS=50 bash examples/llama/train_llama3.sh
+
+            - For Llama 2 70B BF16:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=3 BS=56 TP=1 TE_FP8=0 FSDP=1 RECOMPUTE=1 SEQ_LENGTH=4096 MODEL_SIZE=70 TOTAL_ITERS=50 bash examples/llama/train_llama2.sh
+
+            .. note::
+
+               It's suggested to use ``TP=1`` when FSDP is enabled for higher throughput. FSDP2 is not supported with pipeline parallelism,
+               expert parallelism, MCore's distributed optimizer, gradient accumulation fusion, and ``FP16`` precision.
+
+         .. tab-item:: Multi-node training
+            :sync: multi-node
+
+            To run training on multiple nodes, launch the Docker container on each node. For example, for a two node setup (``NODE0`` as the master node), use these commands.
+
+            * On the master node ``NODE0``:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=2 BS=256 TP=1 TE_FP8=1 SEQ_LENGTH=8192 MODEL_SIZE=8 MASTER_ADDR=IP_NODE0 NNODES=2 NODE_RANK=0 bash examples/llama/train_llama3.sh
+
+            * On the worker node ``NODE1``:
+
+              .. code-block:: shell
+
+                 TEE_OUTPUT=1 MBS=2 BS=256 TP=1 TE_FP8=1 SEQ_LENGTH=8192 MODEL_SIZE=8 MASTER_ADDR=IP_NODE0 NNODES=2 NODE_RANK=1 bash examples/llama/train_llama3.sh
+
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      To run the training on a single node, go to ``/Megatron-LM`` folder and use the following command:
+
+      .. code-block:: shell
+
+         cd /workspace/Megatron-LM
+         GEMM_TUNING=1 PR=bf16 MBS=4 AC=none SEQ_LEN=4096 PAD_LEN=4096 TRAIN_ITERS=50 bash examples/deepseek_v2/train_deepseekv2.sh
+
+Key options
+-----------
+
+.. _amd-megatron-lm-benchmark-test-vars:
+
+The benchmark tests support the following sets of variables:
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      ``TEE_OUTPUT``
+        ``1`` to enable training logs or ``0`` to disable.
+
+      ``TE_FP8``
+        ``0`` for B16 or ``1`` for FP8 -- ``0`` by default.
+
+      ``GEMM_TUNING``
+        ``1`` to enable GEMM tuning, which boosts performance by using the best GEMM kernels.
+
+      ``USE_FLASH_ATTN``
+        ``1`` to enable Flash Attention.
+
+      ``FSDP``
+        ``1`` to enable PyTorch FSDP2. If FSDP is enabled, ``--use-distributed-optimizer``,
+        ``--overlap-param-gather``, and ``--sequence-parallel`` are automaticallyu disabled.
+
+      ``ENABLE_PROFILING``
+        ``1`` to enable PyTorch profiling for performance analysis.
+
+      ``transformer-impl``
+        ``transformer_engine`` to use the Transformer Engine (TE) or ``local`` to disable TE.
+
+      ``MODEL_SIZE``
+        ``8B`` or ``70B`` for Llama 3 and 3.1. ``7B`` or ``70B`` for Llama 2.
+
+      ``TOTAL_ITERS``
+        The total number of iterations -- ``10`` by default.
+
+      ``MOCK_DATA``
+        ``1`` to use mock data or ``0`` to use real data you provide.
+
+      ``MBS``
+        Micro batch size.
+
+      ``BS``
+        Global batch size.
+
+      ``TP``
+        Tensor parallel (``1``, ``2``, ``4``, ``8``). ``TP`` is disabled when ``FSDP`` is turned on.
+
+      ``SEQ_LENGTH``
+        Input sequence length.
+
+   .. tab-item:: DeepSeek V2
+      :sync: deepseek
+
+      ``PR``
+        Precision for training. ``bf16`` for BF16 (default) or ``fp8`` for FP8 GEMMs.
+
+      ``GEMM_TUNING``
+        ``1`` to enable GEMM tuning, which boosts performance by using the best GEMM kernels.
+
+      ``TRAIN_ITERS``
+        The total number of iterations.
+
+      ``MOCK_DATA``
+        ``1`` to use mock data or ``0`` to use real data you provide.
+
+      ``MBS``
+        Micro batch size.
+
+      ``GBS``
+        Global batch size.
+
+      ``SEQ_LEN``
+        Input sequence length.
+
+      ``AC``
+        Activation checkpointing (``none``, ``sel``, or ``full``) -- ``sel`` by default.
+
+Benchmarking examples
+---------------------
+
+.. tab-set::
+
+   .. tab-item:: Llama
+      :sync: llama
+
+      .. tab-set::
+
+         .. tab-item:: Single node training
+            :sync: single-node
+
+            Use this command to run training with Llama 2 7B model on a single node. You can specify MBS, BS, FP,
+            datatype, and so on.
+
+            .. code-block:: bash
+
+               TEE_OUTPUT=1 MBS=5 BS=120 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+               SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+            You can find the training logs at the location defined in ``$TRAIN_LOG`` in the :ref:`configuration script <amd-megatron-lm-environment-setup>`.
+
+            See the sample output:
+
+            .. image:: ../../../../data/how-to/rocm-for-ai/llama2-7b-training-log-sample.png
+               :width: 800
+
+         .. tab-item:: Multi-node training
+            :sync: multi-node
+
+            Launch the Docker container on each node.
+
+            In this example, run training with Llama 2 7B model on 2 nodes with specific MBS, BS, FP, datatype, and
+            so on.
+
+            On the master node:
+
+            .. code-block:: bash
+
+               TEE_OUTPUT=1 MBS=4 BS=64 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+               SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+            On the worker node:
+
+            .. code-block:: bash
+
+               TEE_OUTPUT=1 MBS=4 BS=64 TP=8 TE_FP8=0 NO_TORCH_COMPILE=1
+               SEQ_LENGTH=4096 bash examples/llama/train_llama2.sh
+
+            You can find the training logs at the location defined in ``$TRAIN_LOG`` in the :ref:`configuration script <amd-megatron-lm-environment-setup>`.
+
+            Sample output for 2-node training:
+
+            Master node:
+
+            .. image:: ../../../../data/how-to/rocm-for-ai/2-node-training-master.png
+               :width: 800
+
+            Worker node:
+
+            .. image:: ../../../../data/how-to/rocm-for-ai/2-node-training-worker.png
+               :width: 800
+
+Previous versions
+=================
+
+See :doc:`megatron-lm-history` to find documentation for previous releases
+of the ``ROCm/megatron-lm`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-history.rst

@@ -0,0 +1,47 @@
+:orphan:
+
+****************************************************
+PyTorch training performance testing version history
+****************************************************
+
+This table lists previous versions of the ROCm Megatron-LM training Docker image for
+inference performance testing. For detailed information about available models
+for benchmarking, see the version-specific documentation. You can find tagged
+previous releases of the ``ROCm/pytorch-training`` Docker image on `Docker Hub <https://hub.docker.com/r/rocm/pytorch-training/tags>`_.
+
+.. list-table::
+   :header-rows: 1
+   :stub-columns: 1
+
+   * - Image version
+     - ROCm version
+     - PyTorch version
+     - Resources
+
+   * - v25.6
+     - 6.3.4
+     - 2.8.0a0+git7d205b2
+     - 
+       * :doc:`Documentation <../pytorch-training>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.6/images/sha256-a4cea3c493a4a03d199a3e81960ac071d79a4a7a391aa9866add3b30a7842661>`_
+
+   * - v25.5
+     - 6.3.4
+     - 2.7.0a0+git637433
+     - 
+       * :doc:`Documentation <pytorch-training-v25.5>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.5/images/sha256-d47850a9b25b4a7151f796a8d24d55ea17bba545573f0d50d54d3852f96ecde5>`_
+
+   * - v25.4
+     - 6.3.0
+     - 2.7.0a0+git637433
+     - 
+       * :doc:`Documentation <pytorch-training-v25.4>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.4/images/sha256-fa98a9aa69968e654466c06f05aaa12730db79b48b113c1ab4f7a5fe6920a20b>`_
+
+   * - v25.3
+     - 6.3.0
+     - 2.7.0a0+git637433
+     - 
+       * :doc:`Documentation <pytorch-training-v25.3>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.3/images/sha256-0ffdde1b590fd2787b1c7adf5686875b100980b0f314090901387c44253e709b>`_