switch to GPU_TARGETS

Make documentation build platform-independent

.azuredevops/components/MIOpen.yml

@@ -123,7 +123,7 @@ jobs:
     - template: /.azuredevops/variables-global.yml
     - name: ROCM_PATH
       value: $(Agent.BuildDirectory)/rocm
-    pool: ${{ variables.HIGH_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
     workspace:
       clean: all
     steps:
@@ -131,6 +131,7 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+    - 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:
@@ -210,6 +211,7 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+    - 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:

.azuredevops/components/hipBLASLt.yml

@@ -36,8 +36,10 @@ parameters:
     - gfortran
     - git
     - libdrm-dev
+    - liblapack-dev
     - libmsgpack-dev
     - libnuma-dev
+    - libopenblas-dev
     - ninja-build
     - python3-pip
     - python3-venv
@@ -46,6 +48,12 @@ parameters:
   default:
     - joblib
     - "packaging>=22.0"
+    - pyyaml
+    - msgpack
+    - simplejson
+    - ujson
+    - orjson
+    - yappi
     - --upgrade
 - name: rocmDependencies
   type: object
@@ -81,12 +89,12 @@ parameters:
       - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx90a }
       - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1201 }
       - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1100 }
-      - { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1030 }
+      #- { pool: rocm-ci_medium_build_pool, os: ubuntu2204, packageManager: apt, target: gfx1030 }
       - { pool: rocm-ci_ultra_build_pool, os: almalinux8, packageManager: dnf, target: gfx942 }
       - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx90a }
       - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1201 }
       - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1100 }
-      - { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1030 }
+      #- { pool: rocm-ci_medium_build_pool, os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
@@ -169,7 +177,7 @@ jobs:
           cd $(Agent.BuildDirectory)/temp-deps
           # position-independent LAPACK is required for almalinux8 builds
           cmake -DBUILD_GTEST=OFF -DBUILD_LAPACK=ON -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/s/deps
-          make
+          make -j
           sudo make install
     - script: |
         mkdir -p $(CCACHE_DIR)
@@ -195,7 +203,11 @@ jobs:
           -DCMAKE_CXX_COMPILER_LAUNCHER=ccache
           -DCMAKE_C_COMPILER_LAUNCHER=ccache
           -DAMDGPU_TARGETS=${{ job.target }}
+          -DGPU_TARGETS=${{ job.target }}
           -DBUILD_CLIENTS_TESTS=ON
+          -DHIPBLASLT_ENABLE_ROCROLLER=ON
+          -DHIPBLASLT_ENABLE_FETCH=ON
+          -DHIPBLASLT_ENABLE_BLIS=OFF
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:

.azuredevops/components/hipSPARSE.yml

@@ -69,7 +69,7 @@ parameters:
       - { 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: gfx1030 }
       - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }

.azuredevops/components/hipSPARSELt.yml

@@ -113,7 +113,8 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
-        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        # ignore sparse checkout for monorepo case, we want access to hipblaslt directory
+        # sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
@@ -130,7 +131,10 @@ jobs:
       displayName: Create temp folder for external dependencies
   # hipSPARSELt already has a CMake script for external deps, so we can just run that
   # https://github.com/ROCm/hipSPARSELt/blob/develop/deps/CMakeLists.txt
-    - script: cmake $(Pipeline.Workspace)/s/deps
+    - ${{ if ne(parameters.sparseCheckoutDir, '') }}:
+        script: cmake $(Pipeline.Workspace)/s/projects/hipsparselt/deps
+      ${{ else }}:
+        script: cmake $(Pipeline.Workspace)/s/deps
       displayName: Configure hipSPARSELt external dependencies
       workingDirectory: $(Pipeline.Workspace)/deps
     - script: make
@@ -154,7 +158,11 @@ jobs:
           -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
           -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DBUILD_CLIENTS_TESTS=ON
+          -DBUILD_USE_LOCAL_TENSILE=OFF
           -GNinja
+        ${{ if ne(parameters.sparseCheckoutDir, '') }}:
+          cmakeSourceDir: $(Build.SourcesDirectory)/projects/hipsparselt
+          cmakeBuildDir: $(Build.SourcesDirectory)/projects/hipsparselt
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
         componentName: ${{ parameters.componentName }}

.azuredevops/components/llvm-project.yml

@@ -30,7 +30,7 @@ parameters:
   default:
     buildJobs:
       - { os: ubuntu2204, packageManager: apt }
-      - { os: ubuntu2404, packageManager: apt }
+      # - { os: ubuntu2404, packageManager: apt }
       - { os: almalinux8, packageManager: dnf }
 
 jobs:

.azuredevops/components/rccl.yml

@@ -76,7 +76,7 @@ jobs:
     - template: /.azuredevops/variables-global.yml
     - name: HIP_ROCCLR_HOME
       value: $(Build.BinariesDirectory)/rocm
-    pool: ${{ variables.HIGH_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
     workspace:
       clean: all
     steps:

.azuredevops/components/rocBLAS.yml

@@ -84,12 +84,12 @@ parameters:
       - { 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: 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 }
+      #- { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }

.azuredevops/components/rocSOLVER.yml

@@ -74,12 +74,12 @@ parameters:
       - { 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: 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 }
+      #- { os: almalinux8, packageManager: dnf, target: gfx1030 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }

.azuredevops/components/rocSPARSE.yml

@@ -73,7 +73,7 @@ parameters:
       - { 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: ubuntu2204, packageManager: apt, target: gfx1030 }
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }

.azuredevops/components/rocWMMA.yml

@@ -70,7 +70,7 @@ jobs:
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
-    pool: ${{ variables.HIGH_BUILD_POOL }}
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
     workspace:
       clean: all
     steps:

.azuredevops/components/rocm-examples.yml

@@ -14,6 +14,7 @@ parameters:
   type: object
   default:
     - cmake
+    - glslang-tools
     - libglfw3-dev
     - libmsgpack-dev
     - libtbb-dev
@@ -114,7 +115,7 @@ jobs:
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
           -DROCM_ROOT=$(Agent.BuildDirectory)/rocm
-          -DAMDGPU_TARGETS=${{ job.target }}
+          -DGPU_TARGETS=${{ job.target }}
           -DCMAKE_HIP_ARCHITECTURES=${{ job.target }}
           -DCMAKE_EXE_LINKER_FLAGS=-fgpu-rdc
           -GNinja

.azuredevops/components/rocprofiler.yml

@@ -8,6 +8,22 @@ parameters:
 - 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
@@ -70,6 +86,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - 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
@@ -94,6 +114,7 @@ jobs:
     - 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:
@@ -108,6 +129,8 @@ jobs:
         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: ${{ job.os }}
@@ -115,6 +138,7 @@ jobs:
         extraBuildFlags: >-
           -DCMAKE_MODULE_PATH=$(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"
+          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DCMAKE_POSITION_INDEPENDENT_CODE=ON
           -DENABLE_LDCONFIG=OFF
           -DUSE_PROF_API=1
@@ -122,10 +146,13 @@ jobs:
         multithreadFlag: -- -j32
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         gpuTarget: ${{ job.target }}
         os: ${{ job.os }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - 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
@@ -139,63 +166,68 @@ jobs:
             - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
             - ROCM_PATH:::/home/user/workspace/rocm
 
-- ${{ 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_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    - name: ROCM_PATH
-      value: $(Agent.BuildDirectory)/rocm
-    - name: LD_LIBRARY_PATH
-      value: $(Agent.BuildDirectory)/rocm/lib/rocprofiler:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1/test:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests
-    pool: ${{ job.target }}_test_pool
-    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/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:
-        componentName: rocprofilerV1
-        testDir: $(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1
-        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 }}
-        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_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      - name: ROCM_PATH
+        value: $(Agent.BuildDirectory)/rocm
+      - name: LD_LIBRARY_PATH
+        value: $(Agent.BuildDirectory)/rocm/lib/rocprofiler:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1/test:$(Agent.BuildDirectory)/rocm/share/rocprofiler/tests
+      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
+        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 }}
+          ${{ 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: rocprofilerV1
+          testDir: $(Agent.BuildDirectory)/rocm/share/rocprofiler/tests-v1
+          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 }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}

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

@@ -54,11 +54,13 @@ parameters:
     libfftw3-dev: fftw-devel
     libfmt-dev: fmt-devel
     libgmp-dev: gmp-devel
+    liblapack-dev: lapack-devel
     liblzma-dev: xz-devel
     libmpfr-dev: mpfr-devel
     libmsgpack-dev: msgpack-devel
     libncurses5-dev: ncurses-devel
     libnuma-dev: numactl-devel
+    libopenblas-dev: openblas-devel
     libopenmpi-dev: openmpi-devel
     libpci-dev: libpciaccess-devel
     libssl-dev: openssl-devel

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

@@ -203,8 +203,8 @@ parameters:
       developBranch: develop
       hasGpuTarget: true
     rocprofiler:
-      pipelineId: 143
-      developBranch: amd-staging
+      pipelineId: 329
+      developBranch: develop
       hasGpuTarget: true
     rocprofiler-compute:
       pipelineId: 257

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

@@ -69,20 +69,29 @@ steps:
 
       RETRIES=0
       MAX_RETRIES=5
-      until wget -nv $ARTIFACT_URL -O $(System.ArtifactsDirectory)/ck.zip; do
-        RETRIES=$((RETRIES+1))
-        if [[ $RETRIES -ge $MAX_RETRIES ]]; then
-          echo "Failed to download CK artifact after $MAX_RETRIES attempts."
-          exit 1
+      SUCCESS=false
+      while [ $RETRIES -lt $MAX_RETRIES ]; do
+        wget -nv $ARTIFACT_URL -O $(System.ArtifactsDirectory)/ck.zip && \
+          unzip $(System.ArtifactsDirectory)/ck.zip -d $(System.ArtifactsDirectory) && \
+          mkdir -p $(Agent.BuildDirectory)/rocm && \
+          tar -zxvf $(System.ArtifactsDirectory)/composable_kernel*/*.tar.gz -C $(Agent.BuildDirectory)/rocm && \
+          rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/composable_kernel*
+
+        if [ $? -eq 0 ]; then
+          SUCCESS=true
+          echo "Successfully downloaded CK."
+          break
+        else
+          RETRIES=$((RETRIES + 1))
+          echo "Failed to download CK on attempt $RETRIES/$MAX_RETRIES, retrying..."
+          sleep 1
         fi
-        echo "Download failed, retrying ($RETRIES/$MAX_RETRIES)..."
-        sleep 5
       done
 
-      unzip $(System.ArtifactsDirectory)/ck.zip -d $(System.ArtifactsDirectory)
-      mkdir -p $(Agent.BuildDirectory)/rocm
-      tar -zxvf $(System.ArtifactsDirectory)/composable_kernel*/*.tar.gz -C $(Agent.BuildDirectory)/rocm
-      rm -r $(System.ArtifactsDirectory)/ck.zip $(System.ArtifactsDirectory)/composable_kernel*
+      if [ "$SUCCESS" = false ]; then
+        echo "ERROR: failed to download CK after $MAX_RETRIES attempts."
+        exit 1
+      fi
 
       if [[ $EXIT_CODE -ne 0 ]]; then
         BUILD_COMMIT=$(curl -s $AZ_API/build/builds/$CK_BUILD_ID | jq '.sourceVersion' | tr -d '"')

.azuredevops/variables-global.yml

@@ -28,13 +28,13 @@ variables:
 - name: GFX90A_TEST_POOL
   value: gfx90a_test_pool
 - name: LATEST_RELEASE_VERSION
-  value: 6.4.2
+  value: 6.4.3
 - name: REPO_RADEON_VERSION
-  value: 6.4.2
+  value: 6.4.3
 - name: NEXT_RELEASE_VERSION
   value: 7.0.0
 - name: LATEST_RELEASE_TAG
-  value: rocm-6.4.2
+  value: rocm-6.4.3
 - name: DOCKER_SKIP_GFX
   value: gfx90a
 - name: COMPOSABLE_KERNEL_PIPELINE_ID

.wordlist.txt

@@ -5,6 +5,7 @@ ACEs
 ACS
 AccVGPR
 AccVGPRs
+AITER
 ALU
 AllReduce
 AMD

default.xml

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.4.2"
+    <default revision="refs/tags/rocm-6.4.3"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />

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

@@ -31,9 +31,9 @@ ROCm Version,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6
       :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
       :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
       :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A
-      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,N/A,N/A,85f95ae,85f95ae,85f95ae,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
       :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,N/A,2.4.0,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,
-      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`,N/A,N/A,N/A,N/A,0.7.0,0.7.0,0.7.0,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
       :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat]_,N/A,N/A,N/A,N/A,N/A,1.8.0b1,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.2,1.2,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
 ,,,,,,,,,,,,,,,,,,

docs/compatibility/compatibility-matrix.rst

@@ -242,7 +242,9 @@ Expand for full historical view of:
    .. [#mi300_602-past-60] **For ROCm 6.0.2** - 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.
    .. [#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.
    .. [#verl_compat] verl is only supported on ROCm 6.2.0.
+   .. [#stanford-megatron-lm_compat] Stanford Megatron-LM is only supported on ROCm 6.3.0.
    .. [#dgl_compat] DGL is only supported on ROCm 6.4.0.
+   .. [#megablocks_compat] Megablocks is only supported on ROCm 6.3.0.
    .. [#taichi_compat] Taichi is only supported on ROCm 6.3.2.
    .. [#kfd_support-past-60] As of 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. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
    .. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.

docs/conf.py

@@ -9,17 +9,21 @@ import shutil
 import sys
 from pathlib import Path
 
-shutil.copy2("../RELEASE.md", "./about/release-notes.md")
-shutil.copy2("../CHANGELOG.md", "./release/changelog.md")
+gh_release_path = os.path.join("..", "RELEASE.md")
+gh_changelog_path = os.path.join("..", "CHANGELOG.md")
+sphinx_release_path = os.path.join("about", "release-notes.md")
+sphinx_changelog_path = os.path.join("release", "changelog.md")
+shutil.copy2(gh_release_path, sphinx_release_path)
+shutil.copy2(gh_changelog_path, sphinx_changelog_path)
 
 # Mark the consolidated changelog as orphan to prevent Sphinx from warning about missing toctree entries
-with open("./release/changelog.md", "r+") as file:
+with open(sphinx_changelog_path, "r+", encoding="utf-8") as file:
     content = file.read()
     file.seek(0)
     file.write(":orphan:\n" + content)
 
 # Replace GitHub-style [!ADMONITION]s with Sphinx-compatible ```{admonition} blocks
-with open("./release/changelog.md", "r") as file:
+with open(sphinx_changelog_path, "r", encoding="utf-8") as file:
     lines = file.readlines()
 
     modified_lines = []
@@ -57,11 +61,14 @@ with open("./release/changelog.md", "r") as file:
 
     file.close()
 
-    with open("./release/changelog.md", 'w') as file:
+    with open(sphinx_changelog_path, "w", encoding="utf-8") as file:
         file.writelines(modified_lines)
 
-os.system("mkdir -p ../_readthedocs/html/downloads")
-os.system("cp compatibility/compatibility-matrix-historical-6.0.csv ../_readthedocs/html/downloads/compatibility-matrix-historical-6.0.csv")
+matrix_path = os.path.join("compatibility", "compatibility-matrix-historical-6.0.csv")
+rtd_path = os.path.join("..", "_readthedocs", "html", "downloads")
+if not os.path.exists(rtd_path):
+    os.makedirs(rtd_path)
+shutil.copy2(matrix_path, rtd_path)
 
 latex_engine = "xelatex"
 latex_elements = {
@@ -147,6 +154,8 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250521", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.0.1-20250605", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.0.1-20250702", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.1-20250702", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.1-20250715", "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"]},
 

docs/contribute/building.md

@@ -28,13 +28,31 @@ See the [Python requirements file](https://github.com/ROCm/ROCm/blob/develop/doc
 
 Use the Python Virtual Environment (`venv`) and run the following commands from the project root:
 
+::::{tab-set}
+:::{tab-item} Linux and WSL
+:sync: linux
+
 ```sh
 python3 -mvenv .venv
 
-.venv/bin/python     -m pip install -r docs/sphinx/requirements.txt
-.venv/bin/python     -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
+.venv/bin/python -m pip install -r docs/sphinx/requirements.txt
+.venv/bin/python -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
 ```
 
+:::
+:::{tab-item} Windows
+:sync: windows
+
+```powershell
+python -mvenv .venv
+
+.venv\Scripts\python.exe -m pip install -r docs/sphinx/requirements.txt
+.venv\Scripts\python.exe -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
+```
+
+:::
+::::
+
 Navigate to `_build/html/index.html` and open this file in a web browser.
 
 ## Visual Studio Code

docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.9.1_20250715-benchmark_models.yaml

@@ -0,0 +1,163 @@
+vllm_benchmark:
+  unified_docker:
+    latest:
+      # TODO: update me
+      pull_tag: rocm/vllm:rocm6.4.1_vllm_0.9.1_20250715
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.9.1_20250715/images/sha256-4a429705fa95a58f6d20aceab43b1b76fa769d57f32d5d28bd3f4e030e2a78ea
+      rocm_version: 6.4.1
+      vllm_version: 0.9.1 (0.9.2.dev364+gb432b7a28.rocm641)
+      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 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

@@ -39,7 +39,7 @@ pytorch_inference_benchmark:
         model_repo: Wan-AI/Wan2.1-T2V-14B
         url: https://huggingface.co/Wan-AI/Wan2.1-T2V-14B
         precision: bfloat16
-    - group: Janus-Pro
+    - group: Janus Pro
       tag: janus-pro
       models:
       - model: Janus Pro 7B
@@ -47,3 +47,11 @@ pytorch_inference_benchmark:
         model_repo: deepseek-ai/Janus-Pro-7B
         url: https://huggingface.co/deepseek-ai/Janus-Pro-7B
         precision: bfloat16
+    - group: Hunyuan Video
+      tag: hunyuan
+      models:
+      - model: Hunyuan Video
+        mad_tag: pyt_hy_video
+        model_repo: tencent/HunyuanVideo
+        url: https://huggingface.co/tencent/HunyuanVideo
+        precision: float16

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

@@ -2,11 +2,11 @@ vllm_benchmark:
   unified_docker:
     latest:
       # TODO: update me
-      pull_tag: rocm/vllm:rocm6.4.1_vllm_0.9.1_20250715
-      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.9.1_20250715/images/sha256-4a429705fa95a58f6d20aceab43b1b76fa769d57f32d5d28bd3f4e030e2a78ea
+      pull_tag: rocm/vllm:rocm6.4.1_vllm_0.10.0_20250812
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.10.0_20250812/images/sha256-4c277ad39af3a8c9feac9b30bf78d439c74d9b4728e788a419d3f1d0c30cacaa
       rocm_version: 6.4.1
-      vllm_version: 0.9.1 (0.9.2.dev364+gb432b7a28.rocm641)
-      pytorch_version: 2.7.0+gitf717b2a
+      vllm_version: 0.10.0 (0.10.1.dev395+g340ea86df.rocm641)
+      pytorch_version: 2.7.0+gitf717b2a (2.7.0+gitf717b2a)
       hipblaslt_version: 0.15
   model_groups:
     - group: Meta Llama
@@ -27,11 +27,6 @@ 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 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
@@ -65,11 +60,6 @@ vllm_benchmark:
         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
@@ -80,72 +70,15 @@ vllm_benchmark:
         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:
@@ -153,11 +86,3 @@ vllm_benchmark:
         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/how-to/build-rocm.rst

@@ -19,5 +19,6 @@ The general steps to build ROCm are:
 #. Run the build command
 
 Because the ROCm stack is constantly evolving, the most current instructions are stored with the source code in GitHub.  
-For detailed build instructions, see `Getting and Building ROCm from Source <https://github.com/ROCm/ROCm?tab=readme-ov-file#getting-and-building-rocm-from-source>`.
+For detailed build instructions, see `Getting and Building ROCm from Source <https://github.com/ROCm/ROCm?tab=readme-ov-file#getting-and-building-rocm-from-source>`_.
+
 

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.1-20250702.rst

@@ -14,7 +14,7 @@ vLLM inference performance testing
    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:
+.. _vllm-benchmark-unified-docker-702:
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.9.1_20250702-benchmark-models.yaml
 
@@ -77,7 +77,7 @@ vLLM inference performance testing
         </div>
       </div>
 
-   .. _vllm-benchmark-vllm:
+   .. _vllm-benchmark-vllm-702:
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
@@ -159,7 +159,7 @@ vLLM inference performance testing
    Once the setup is complete, choose between two options to reproduce the
    benchmark results:
 
-   .. _vllm-benchmark-mad:
+   .. _vllm-benchmark-mad-702:
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.1-20250715.rst

@@ -0,0 +1,450 @@
+: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-715:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.9.1_20250715-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:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      * - `ROCm <https://github.com/ROCm/ROCm>`__
+        - {{ unified_docker.rocm_version }}
+
+      * - `vLLM <https://docs.vllm.ai/en/latest>`__
+        - {{ unified_docker.vllm_version }}
+
+      * - `PyTorch <https://github.com/ROCm/pytorch>`__
+        - {{ unified_docker.pytorch_version }}
+
+      * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`__
+        - {{ unified_docker.hipblaslt_version }}
+
+With this Docker image, you can quickly test the :ref:`expected
+inference performance numbers <vllm-benchmark-performance-measurements>` for
+MI300X series accelerators.
+
+What's new
+==========
+
+The following is summary of notable changes since the :doc:`previous ROCm/vLLM Docker release <vllm-history>`.
+
+* The ``--compilation-config-parameter`` is no longer required as its options are now enabled by default.
+  This parameter has been removed from the benchmarking script.
+
+* Resolved Llama 3.1 405 B custom all-reduce issue, eliminating the need for ``--disable-custom-all-reduce``.
+  This parameter has been removed from the benchmarking script.
+
+* Fixed a ``+rms_norm`` custom kernel issue.
+
+* Added quick reduce functionality. Set ``VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=FP`` to enable; supported modes are ``FP``, ``INT8``, ``INT6``, ``INT4``.
+
+* Implemented a workaround to potentially mitigate GPU crashes experienced with the Command R+ model, pending a driver fix.
+
+Supported models
+================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.9.1_20250715-benchmark_models.yaml
+
+   {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
+   {% set model_groups = data.vllm_benchmark.model_groups %}
+
+   .. _vllm-benchmark-available-models-715:
+
+   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-715:
+
+   {% 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-715:
+
+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.
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+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.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.9.1_20250715-benchmark_models.yaml
+
+   {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
+   {% set model_groups = data.vllm_benchmark.model_groups %}
+
+   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-715:
+
+   {% 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
+
+            1. 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
+
+            2. Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
+               using one GPU with the :literal:`{{model.precision}}` data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --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, include the ``--tunableop on`` argument in your
+               run.
+
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed
+               by the performance-collection run.
+
+            {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            .. rubric:: Download the Docker image and required scripts
+
+            1. Run the vLLM benchmark tool independently by starting the
+               `Docker container <{{ unified_docker.docker_hub_url }}>`_
+               as shown in the following snippet.
+
+               .. code-block:: shell
+
+                  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 $(pwd):/workspace \
+                      --env HUGGINGFACE_HUB_CACHE=/workspace \
+                      --name test \
+                      {{ unified_docker.pull_tag }}
+
+            2. In the Docker container, clone the ROCm MAD repository and navigate to the
+               benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD/scripts/vllm
+
+            3. To start the benchmark, use the following command with the appropriate options.
+
+               .. dropdown:: Benchmark options
+                  :open:
+
+                  .. list-table::
+                     :header-rows: 1
+                     :align: center
+
+                     * - Name
+                       - Options
+                       - Description
+
+                     * - ``$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
+
+                  The input sequence length, output sequence length, and tensor parallel (TP) are
+                  already configured. You don't need to specify them with this script.
+
+               Command:
+
+               .. code-block::
+
+                  ./vllm_benchmark_report.sh \
+                      -s $test_option \
+                      -m {{model.model_repo}} \
+                      -g $num_gpu \
+                      -d {{model.precision}}
+
+               .. note::
+
+                  For best performance, it's recommend to run with ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``.
+
+                  If you encounter the following error, pass your access-authorized Hugging
+                  Face token to the gated models.
+
+                  .. code-block::
+
+                     OSError: You are trying to access a gated repo.
+
+                     # pass your HF_TOKEN
+                     export HF_TOKEN=$your_personal_hf_token
+
+            .. rubric:: Benchmarking examples
+
+            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 :literal:`{{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 :literal:`{{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 %}
+
+Advanced usage
+==============
+
+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/f94ec9beeca1071cc34f9d1e206d8c7f3ac76129/docs/dev-docker>`__.
+
+Reproducing the Docker image
+----------------------------
+
+To reproduce this ROCm/vLLM Docker image release, follow these steps:
+
+1. Clone the `vLLM repository <https://github.com/ROCm/vllm>`__.
+
+   .. code-block:: shell
+
+      git clone https://github.com/ROCm/vllm.git
+
+2. Checkout the specific release commit.
+
+   .. code-block:: shell
+
+      cd vllm
+      git checkout b432b7a285aa0dcb9677380936ffa74931bb6d6f
+
+3. Build the Docker image. Replace ``vllm-rocm`` with your desired image tag.
+
+   .. code-block:: shell
+
+      docker build -f docker/Dockerfile.rocm -t vllm-rocm .
+
+Known issues and workarounds
+============================
+
+AITER does not support FP8 KV cache yet.
+
+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 MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series 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:`/how-to/rocm-for-ai/inference-optimization/workload`.
+
+- To learn how to run community models from Hugging Face on AMD GPUs, see
+  :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.
+
+- To learn how to fine-tune LLMs and optimize inference, see
+  :doc:`Fine-tuning LLMs and inference optimization </how-to/rocm-for-ai/fine-tuning/fine-tuning-and-inference>`.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+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

@@ -16,14 +16,23 @@ previous releases of the ``ROCm/vllm`` Docker image on `Docker Hub <https://hub.
      - Components
      - Resources
 
-   * - ``rocm/vllm:rocm6.4.1_vllm_0.9.1_20250715``
+   * - ``rocm/vllm:rocm6.4.1_vllm_0.10.0_20250812``
        (latest)
+     - 
+       * ROCm 6.4.1
+       * vLLM 0.10.0
+       * PyTorch 2.7.0
+     - 
+       * :doc:`Documentation <../vllm>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.10.0_20250812/images/sha256-4c277ad39af3a8c9feac9b30bf78d439c74d9b4728e788a419d3f1d0c30cacaa>`__
+
+   * - ``rocm/vllm:rocm6.4.1_vllm_0.9.1_20250715``
      - 
        * ROCm 6.4.1
        * vLLM 0.9.1
        * PyTorch 2.7.0
      - 
-       * :doc:`Documentation <../vllm>`
+       * :doc:`Documentation <vllm-0.9.1-20250715>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.4.1_vllm_0.9.1_20250715/images/sha256-4a429705fa95a58f6d20aceab43b1b76fa769d57f32d5d28bd3f4e030e2a78ea>`__
 
    * - ``rocm/vllm:rocm6.4.1_vllm_0.9.1_20250702``

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

@@ -103,7 +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 pyt_mochi_video_inference pyt_wan2.1_inference pyt_janus_pro_inference
+   .. container:: model-doc pyt_clip_inference pyt_mochi_video_inference pyt_wan2.1_inference pyt_janus_pro_inference pyt_hy_video
 
       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.
 

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

@@ -7,7 +7,7 @@
 vLLM inference performance testing
 **********************************
 
-.. _vllm-benchmark-unified-docker:
+.. _vllm-benchmark-unified-docker-812:
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
 
@@ -47,17 +47,11 @@ What's new
 
 The following is summary of notable changes since the :doc:`previous ROCm/vLLM Docker release <previous-versions/vllm-history>`.
 
-* The ``--compilation-config-parameter`` is no longer required as its options are now enabled by default.
-  This parameter has been removed from the benchmarking script.
+* Upgraded to vLLM v0.10.
 
-* Resolved Llama 3.1 405 B custom all-reduce issue, eliminating the need for ``--disable-custom-all-reduce``.
-  This parameter has been removed from the benchmarking script.
+* FP8 KV cache support via AITER.
 
-* Fixed a ``+rms_norm`` custom kernel issue.
-
-* Added quick reduce functionality. Set ``VLLM_ROCM_QUICK_REDUCE_QUANTIZATION=FP`` to enable; supported modes are ``FP``, ``INT8``, ``INT6``, ``INT4``.
-
-* Implemented a workaround to potentially mitigate GPU crashes experienced with the Command R+ model, pending a driver fix.
+* Full graph capture support via AITER.
 
 Supported models
 ================
@@ -67,7 +61,7 @@ Supported models
    {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
    {% set model_groups = data.vllm_benchmark.model_groups %}
 
-   .. _vllm-benchmark-available-models:
+   .. _vllm-benchmark-available-models-812:
 
    The following models are supported for inference performance benchmarking
    with vLLM and ROCm. Some instructions, commands, and recommendations in this
@@ -102,7 +96,7 @@ Supported models
       </div>
       </div>
 
-   .. _vllm-benchmark-vllm:
+   .. _vllm-benchmark-vllm-812:
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
@@ -124,14 +118,14 @@ Supported models
    See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
    more information.
 
-.. _vllm-benchmark-performance-measurements:
+.. _vllm-benchmark-performance-measurements-812:
 
 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.
+page provides reference throughput and serving measurements for inferencing popular AI models.
 
 .. important::
 
@@ -176,7 +170,7 @@ system's configuration.
    Once the setup is complete, choose between two options to reproduce the
    benchmark results:
 
-   .. _vllm-benchmark-mad:
+   .. _vllm-benchmark-mad-812:
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
@@ -209,12 +203,15 @@ system's configuration.
                       --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}}/``.
+            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
+            model are collected in the following paths: ``{{ model.mad_tag }}_throughput.csv``
+            and ``{{ model.mad_tag }}_serving.csv``.
 
-            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.
+            Although the :ref:`available models
+            <vllm-benchmark-available-models>` are preconfigured to collect
+            offline throughput and online serving performance data, you can
+            also change the benchmarking parameters. See the standalone
+            benchmarking tab for more information.
 
             {% if model.tunableop %}
 
@@ -224,14 +221,12 @@ system's configuration.
                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, include the ``--tunableop on`` argument in your
-               run.
+               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled (see
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To enable it, include
+               the ``--tunableop on`` argument in your run.
 
-               Enabling TunableOp triggers a two-pass run -- a warm-up followed
-               by the performance-collection run.
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the
+               performance-collection run.
 
             {% endif %}
 
@@ -269,6 +264,13 @@ system's configuration.
 
             3. To start the benchmark, use the following command with the appropriate options.
 
+               .. code-block::
+
+                  ./run.sh \
+                      --config $CONFIG_CSV \
+                      --model_repo {{ model.model_repo }} \
+                      <overrides>
+
                .. dropdown:: Benchmark options
                   :open:
 
@@ -280,42 +282,40 @@ system's configuration.
                        - Options
                        - Description
 
-                     * - ``$test_option``
-                       - latency
-                       - Measure decoding token latency
+                     * - ``--config``
+                       - ``configs/default.csv``
+                       - Run configs from the CSV for the chosen model repo and benchmark.
 
                      * -
-                       - throughput
-                       - Measure token generation throughput
+                       - ``configs/extended.csv``
+                       - 
 
                      * -
-                       - all
-                       - Measure both throughput and latency
+                       - ``configs/performance.csv``
+                       - 
 
-                     * - ``$num_gpu``
-                       - 1 or 8
-                       - Number of GPUs
+                     * - ``--benchmark``
+                       - ``throughput``
+                       - Measure offline end-to-end throughput.
 
-                     * - ``$datatype``
-                       - ``float16`` or ``float8``
-                       - Data type
+                     * - 
+                       - ``serving``
+                       - Measure online serving performance.
+
+                     * - 
+                       - ``all``
+                       - Measure both throughput and serving.
+
+                     * - `<overrides>`
+                       - See `run.sh <https://github.com/ROCm/MAD/blob/develop/scripts/vllm/run.sh>`__ for more info.
+                       - Additional overrides to the config CSV.
 
                   The input sequence length, output sequence length, and tensor parallel (TP) are
                   already configured. You don't need to specify them with this script.
 
-               Command:
-
-               .. code-block::
-
-                  ./vllm_benchmark_report.sh \
-                      -s $test_option \
-                      -m {{model.model_repo}} \
-                      -g $num_gpu \
-                      -d {{model.precision}}
-
                .. note::
 
-                  For best performance, it's recommend to run with ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``.
+                  For best performance, it's recommended to run with ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``.
 
                   If you encounter the following error, pass your access-authorized Hugging
                   Face token to the gated models.
@@ -331,33 +331,33 @@ system's configuration.
 
             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 :literal:`{{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 :literal:`{{model.precision}}` precision.
 
               .. code-block:: shell
 
-                 ./vllm_benchmark_report.sh \
-                     -s throughput \
-                     -m {{model.model_repo}} \
-                     -g 8 \
-                     -d {{model.precision}}
+                 export MAD_MODEL_NAME={{ model.mad_tag }}
+                 ./run.sh \
+                     --config configs/default.csv \
+                     --model_repo {{model.model_repo}} \
+                     --benchmark throughput
 
-              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``.
+              Find the throughput benchmark report at ``./{{ model.mad_tag }}_throughput.csv``.
+
+            * Serving benchmark
+
+              Use this command to benchmark the serving performance of the {{model.model}} model on eight GPUs with :literal:`{{model.precision}}` precision.
+
+              .. code-block::
+
+                 export MAD_MODEL_NAME={{ model.mad_tag }}
+                 ./run.sh \
+                     --config configs/default.csv \
+                     --model_repo {{model.model_repo}} \
+                     --benchmark serving
+
+              Find the serving benchmark report at ``./{{ model.mad_tag }}_serving.csv``.
 
             .. raw:: html
 
@@ -400,7 +400,7 @@ To reproduce this ROCm/vLLM Docker image release, follow these steps:
    .. code-block:: shell
 
       cd vllm
-      git checkout b432b7a285aa0dcb9677380936ffa74931bb6d6f
+      git checkout 340ea86dfe5955d6f9a9e767d6abab5aacf2c978
 
 3. Build the Docker image. Replace ``vllm-rocm`` with your desired image tag.
 
@@ -408,11 +408,6 @@ To reproduce this ROCm/vLLM Docker image release, follow these steps:
 
       docker build -f docker/Dockerfile.rocm -t vllm-rocm .
 
-Known issues and workarounds
-============================
-
-AITER does not support FP8 KV cache yet.
-
 Further reading
 ===============
 

docs/reference/gpu-arch-specs.rst

@@ -285,7 +285,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
           - Radeon AI PRO R9700
           - RDNA4
           - gfx1201
-          - 16
+          - 32
           - 64
           - 32 or 64
           - 128

docs/sphinx/requirements.txt

@@ -234,7 +234,7 @@ sphinx-notfound-page==1.1.0
     # via rocm-docs-core
 sphinx-reredirects==0.1.6
     # via -r requirements.in
-sphinx-sitemap==2.7.2
+sphinx-sitemap==2.8.0
     # via -r requirements.in
 sphinxcontrib-applehelp==2.0.0
     # via sphinx

tools/autotag/components.xml

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.4.2"
+    <default revision="refs/tags/rocm-6.4.3"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />

tools/rocm-build/rocm-6.4.3.xml

@@ -0,0 +1,79 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest>
+    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
+    <default revision="refs/tags/rocm-6.4.3"
+     remote="rocm-org"
+     sync-c="true"
+     sync-j="4" />
+<!--list of projects for ROCm-->
+    <project name="ROCm" revision="roc-6.4.x" />
+    <project name="ROCK-Kernel-Driver" />
+    <project name="ROCR-Runtime" />
+    <project name="amdsmi" />
+    <project name="rdc" />
+    <project name="rocm_bandwidth_test" />
+    <project name="rocm_smi_lib" />
+    <project name="rocm-core" />
+    <project name="rocm-examples" />
+    <project name="rocminfo" />
+    <project name="rocprofiler" />
+    <project name="rocprofiler-register" />
+    <project name="rocprofiler-sdk" />
+    <project name="rocprofiler-compute" />
+    <project name="rocprofiler-systems" />
+    <project name="roctracer" />
+<!--HIP Projects-->
+    <project name="hip" />
+    <project name="hip-tests" />
+    <project name="HIPIFY" />
+    <project name="clr" />
+    <project name="hipother" />
+<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
+    <project name="half" />
+    <project name="llvm-project" />
+    <project name="spirv-llvm-translator" />
+<!-- gdb projects -->
+    <project name="ROCdbgapi" />
+    <project name="ROCgdb" />
+    <project name="rocr_debug_agent" />
+<!-- ROCm Libraries -->
+    <project groups="mathlibs" name="AMDMIGraphX" />
+    <project groups="mathlibs" name="MIOpen" />
+    <project groups="mathlibs" name="MIVisionX" />
+    <project groups="mathlibs" name="ROCmValidationSuite" />
+    <project groups="mathlibs" name="Tensile" />
+    <project groups="mathlibs" name="composable_kernel" />
+    <project groups="mathlibs" name="hipBLAS-common" />
+    <project groups="mathlibs" name="hipBLAS" />
+    <project groups="mathlibs" name="hipBLASLt" />
+    <project groups="mathlibs" name="hipCUB" />
+    <project groups="mathlibs" name="hipFFT" />
+    <project groups="mathlibs" name="hipRAND" />
+    <project groups="mathlibs" name="hipSOLVER" />
+    <project groups="mathlibs" name="hipSPARSE" />
+    <project groups="mathlibs" name="hipSPARSELt" />
+    <project groups="mathlibs" name="hipTensor" />
+    <project groups="mathlibs" name="hipfort" />
+    <project groups="mathlibs" name="rccl" />
+    <project groups="mathlibs" name="rocAL" />
+    <project groups="mathlibs" name="rocALUTION" />
+    <project groups="mathlibs" name="rocBLAS" />
+    <project groups="mathlibs" name="rocDecode" />
+    <project groups="mathlibs" name="rocJPEG" />
+    <project groups="mathlibs" name="rocPyDecode" />
+    <project groups="mathlibs" name="rocFFT" />
+    <project groups="mathlibs" name="rocPRIM" />
+    <project groups="mathlibs" name="rocRAND" />
+    <project groups="mathlibs" name="rocSHMEM" />
+    <project groups="mathlibs" name="rocSOLVER" />
+    <project groups="mathlibs" name="rocSPARSE" />
+    <project groups="mathlibs" name="rocThrust" />
+    <project groups="mathlibs" name="rocWMMA" />
+    <project groups="mathlibs" name="rocm-cmake" />
+    <project groups="mathlibs" name="rpp" />
+    <project groups="mathlibs" name="TransferBench" />
+<!-- Projects for OpenMP-Extras -->
+    <project name="aomp" path="openmp-extras/aomp" />
+    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
+    <project name="flang" path="openmp-extras/flang" />
+</manifest>