Docs: Ray release 25.12 and compatibility version format standardization (#5845)

Bumps [urllib3](https://github.com/urllib3/urllib3) from 2.5.0 to 2.6.3.
- [Release notes](https://github.com/urllib3/urllib3/releases)
- [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst)
- [Commits](https://github.com/urllib3/urllib3/compare/2.5.0...2.6.3)

---
updated-dependencies:
- dependency-name: urllib3
  dependency-version: 2.6.3
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.azuredevops/components/AMDMIGraphX.yml

@@ -128,6 +128,9 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.28.6'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
@@ -152,6 +155,7 @@ jobs:
           -DCMAKE_BUILD_TYPE=Release
           -DGPU_TARGETS=${{ job.target }}
           -DAMDGPU_TARGETS=${{ job.target }}
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
           -DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include
@@ -192,6 +196,9 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.28.6'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
@@ -217,6 +224,7 @@ jobs:
           -DCMAKE_BUILD_TYPE=Release
           -DGPU_TARGETS=${{ job.target }}
           -DAMDGPU_TARGETS=${{ job.target }}
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
           -DHALF_INCLUDE_DIR=$(Agent.BuildDirectory)/rocm/include

.azuredevops/components/HIP.yml

@@ -34,6 +34,7 @@ parameters:
   default:
     - cmake
     - libnuma-dev
+    - libsimde-dev
     - mesa-common-dev
     - ninja-build
     - ocl-icd-libopencl1

.azuredevops/components/ROCR-Runtime.yml

@@ -37,6 +37,7 @@ parameters:
     - libdrm-dev
     - libelf-dev
     - libnuma-dev
+    - libsimde-dev
     - ninja-build
     - pkg-config
 - name: rocmDependencies

.azuredevops/components/amdsmi.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: amdsmi
 - 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
@@ -31,7 +50,7 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: amdsmi_build_${{ job.os }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}
     pool:
       ${{ if eq(job.os, 'ubuntu2404') }}:
         vmImage: 'ubuntu-24.04'
@@ -55,6 +74,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}
@@ -65,50 +85,54 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
         os: ${{ job.os }}
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - 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 }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: amdsmi_test_${{ job.os }}_${{ job.target }}
-    dependsOn: amdsmi_build_${{ job.os }}
-    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 }}
-        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
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: amdsmi
-        testDir: '$(Agent.BuildDirectory)'
-        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 }}
-        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 }}
+      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 }}
+          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
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)'
+          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 }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/hipTensor.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipTensor
 - 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
@@ -51,7 +70,7 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipTensor_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -66,12 +85,15 @@ 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: >-
@@ -85,9 +107,12 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         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
@@ -95,44 +120,47 @@ jobs:
         aptPackages: ${{ parameters.aptPackages }}
         gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipTensor_test_${{ job.target }}
-    timeoutInMinutes: 90
-    dependsOn: hipTensor_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: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipTensor
-        testDir: '$(Agent.BuildDirectory)/rocm/bin/hiptensor'
-        testParameters: '-E ".*-extended" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
-    - 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.target }}
+      timeoutInMinutes: 90
+      dependsOn: ${{ parameters.componentName }}_build_${{ 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:
+          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 }}
+          ${{ 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/hiptensor'
+          testParameters: '-E ".*-extended" --extra-verbose --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/origami.yml

@@ -39,6 +39,7 @@ parameters:
     - python3
     - python3-dev
     - python3-pip
+    - python3-venv
     - libgtest-dev
     - libboost-filesystem-dev
     - libboost-program-options-dev
@@ -46,6 +47,8 @@ parameters:
   type: object
   default:
     - nanobind>=2.0.0
+    - pytest
+    - pytest-cov
 - name: rocmDependencies
   type: object
   default:
@@ -72,8 +75,10 @@ parameters:
       - { os: ubuntu2204, packageManager: apt }
       - { os: almalinux8, packageManager: dnf }
     testJobs:
-      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1151 }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
 - name: downstreamComponentMatrix
   type: object
   default:
@@ -116,6 +121,11 @@ jobs:
       parameters:
         dependencyList:
           - gtest
+    - ${{ if ne(job.os, 'almalinux8') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+        parameters:
+          dependencyList:
+            - catch2
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
@@ -137,6 +147,7 @@ jobs:
           -DORIGAMI_BUILD_SHARED_LIBS=ON
           -DORIGAMI_ENABLE_PYTHON=ON
           -DORIGAMI_BUILD_TESTING=ON
+          -DORIGAMI_ENABLE_FETCH=ON
           -GNinja
     - ${{ if ne(job.os, 'almalinux8') }}:
       - task: PublishPipelineArtifact@1
@@ -169,7 +180,6 @@ jobs:
       dependsOn: origami_build_${{ job.os }}
       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)
         )
@@ -180,30 +190,30 @@ jobs:
       workspace:
         clean: all
       steps:
-      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-        parameters:
-          checkoutRepo: ${{ parameters.checkoutRepo }}
-          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
       - 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-custom.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-vendor.yml
+        parameters:
+          dependencyList:
+            - gtest
+      - ${{ if ne(job.os, 'almalinux8') }}:
+        - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+          parameters:
+            dependencyList:
+              - catch2
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
         parameters:
           preTargetFilter: ${{ parameters.componentName }}
           os: ${{ job.os }}
-      - task: DownloadPipelineArtifact@2
-        displayName: 'Download Build Directory Artifact'
-        inputs:
-          artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
-          path: '$(Agent.BuildDirectory)/s/build'
-      - task: DownloadPipelineArtifact@2
-        displayName: 'Download Python Source Artifact'
-        inputs:
-          artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
-          path: '$(Agent.BuildDirectory)/s/python'
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
         parameters:
           checkoutRef: ${{ parameters.checkoutRef }}
@@ -212,25 +222,72 @@ jobs:
           gpuTarget: ${{ job.target }}
           ${{ if parameters.triggerDownstreamJobs }}:
             downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - task: CMake@1
+        displayName: 'Origami Test CMake Configuration'
+        inputs:
+          cmakeArgs: >-
+            -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
+            -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+            -DORIGAMI_BUILD_SHARED_LIBS=ON
+            -DORIGAMI_ENABLE_PYTHON=ON
+            -DORIGAMI_BUILD_TESTING=ON
+            -GNinja
+            $(Agent.BuildDirectory)/s
+      - task: Bash@3
+        displayName: 'Build Origami Tests and Python Bindings'
+        inputs:
+          targetType: inline
+          workingDirectory: build
+          script: |
+            cmake --build . --target origami-tests origami_python -- -j$(nproc)
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      # Run tests using CTest (discovers and runs both C++ and Python tests)
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
         parameters:
           componentName: ${{ parameters.componentName }}
           os: ${{ job.os }}
-          testDir: '$(Agent.BuildDirectory)/rocm/bin'
-          testExecutable: './origami-tests'
-          testParameters: '--yaml origami-tests.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
-      - script: |
-          set -e
-          export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH
-
-          echo "--- Running origami_test.py ---"
-          python3 $(Agent.BuildDirectory)/s/python/origami_test.py
-          
-          echo "--- Running origami_grid_test.py ---"
-          python3 $(Agent.BuildDirectory)/s/python/origami_grid_test.py
-        displayName: 'Run Python Binding Tests'
-        condition: succeeded()
+          testDir: 'build'
+          testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+      # Test pip install workflow
+      # - task: Bash@3
+      #   displayName: 'Test Pip Install'
+      #   inputs:
+      #     targetType: inline
+      #     script: |
+      #       set -e
+            
+      #       echo "==================================================================="
+      #       echo "Testing pip install workflow (pip install -e .)"
+      #       echo "==================================================================="
+            
+      #       # Set environment variables for pip install CMake build
+      #       export ROCM_PATH=$(Agent.BuildDirectory)/rocm
+      #       export CMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm:$(Agent.BuildDirectory)/vendor
+      #       export CMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+            
+      #       echo "ROCM_PATH: $ROCM_PATH"
+      #       echo "CMAKE_PREFIX_PATH: $CMAKE_PREFIX_PATH"
+      #       echo "CMAKE_CXX_COMPILER: $CMAKE_CXX_COMPILER"
+      #       echo ""
+            
+      #       # Install from source directory
+      #       cd "$(Agent.BuildDirectory)/s/python"
+      #       pip install -e .
+            
+      #       # Verify import works
+      #       echo ""
+      #       echo "Verifying origami can be imported..."
+      #       python3 -c "import origami; print('✓ Successfully imported origami')"
+            
+      #       # Run pytest on installed package
+      #       echo ""
+      #       echo "Running pytest tests..."
+      #       python3 -m pytest tests/ -v -m "not slow" --tb=short
+            
+      #       echo ""
+      #       echo "==================================================================="
+      #       echo "Pip install test completed successfully"
+      #       echo "==================================================================="
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
         parameters:
           aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rccl.yml

@@ -1,10 +1,35 @@
 parameters:
+- name: componentName
+  type: string
+  default: rccl
 - name: checkoutRepo
   type: string
   default: 'self'
 - name: checkoutRef
   type: string
   default: ''
+- name: systemsRepo
+  type: string
+  default: systems_repo
+- name: systemsSparseCheckoutDir
+  type: string
+  default: 'projects/rocprofiler-sdk'
+# 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
@@ -57,37 +82,52 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocprofiler-sdk:
+      name: rocprofiler-sdk
+      sparseCheckoutDir: ''
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rccl_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rccl_build_${{ job.target }}
-    timeoutInMinutes: 90
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}_${{ job.target }}
+    timeoutInMinutes: 120
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
     - name: HIP_ROCCLR_HOME
       value: $(Build.BinariesDirectory)/rocm
     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/dependencies-cmake-custom.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         submoduleBehaviour: recursive
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
       parameters:
@@ -97,10 +137,14 @@ 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:
+        os: ${{ job.os }}
         extraBuildFlags: >-
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
@@ -112,58 +156,87 @@ 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 }}
-        extraEnvVars:
-          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-        installLatestCMake: true
+    - ${{ 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
+          installLatestCMake: true
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rccl_test_${{ job.target }}
-    timeoutInMinutes: 120
-    dependsOn: rccl_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: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rccl
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        testExecutable: './rccl-UnitTests'
-        testParameters: '--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 }}
+      timeoutInMinutes: 120
+      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
+      - 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: './rccl-UnitTests'
+          testParameters: '--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 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.systemsRepo }}
+          sparseCheckoutDir: ${{ parameters.systemsSparseCheckoutDir }}
+          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/rocWMMA.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocWMMA
 - 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
@@ -66,7 +85,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocWMMA_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -81,6 +104,7 @@ 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 }}
@@ -102,9 +126,12 @@ jobs:
   # gfx1030 not supported in documentation
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         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
@@ -112,43 +139,45 @@ jobs:
         aptPackages: ${{ parameters.aptPackages }}
         gpuTarget: ${{ job.target }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocWMMA_test_${{ job.target }}
-    timeoutInMinutes: 270
-    dependsOn: rocWMMA_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: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocWMMA
-        testDir: '$(Agent.BuildDirectory)/rocm/bin/rocwmma'
-    - 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.target }}
+      timeoutInMinutes: 350
+      dependsOn: ${{ parameters.componentName }}_build_${{ 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 }}
+          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: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin/rocwmma'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/rocm-cmake.yml

@@ -81,7 +81,7 @@ jobs:
     - 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'
+        testParameters: '-E "pass-version-parent" --extra-verbose --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:

.azuredevops/components/rocm-examples.yml

@@ -17,15 +17,39 @@ parameters:
     - libdw-dev
     - libglfw3-dev
     - libmsgpack-dev
+    - libopencv-dev
     - libtbb-dev
+    - libtiff-dev
     - libva-amdgpu-dev
+    - libva2-amdgpu
+    - mesa-amdgpu-va-drivers
+    - libavcodec-dev
+    - libavformat-dev
+    - libavutil-dev
     - ninja-build
     - python3-pip
+    - protobuf-compiler
+    - libprotoc-dev
+    - libopencv-dev
+- name: pipModules
+  type: object
+  default:
+    - future==1.0.0
+    - pytz==2022.1
+    - numpy==1.23
+    - google==3.0.0
+    - protobuf==3.12.4
+    - onnx==1.12.0
+    - nnef==1.0.7
 - name: rocmDependencies
   type: object
   default:
     - AMDMIGraphX
+    - aomp
+    - aomp-extras
     - clr
+    - half
+    - composable_kernel
     - hipBLAS
     - hipBLAS-common
     - hipBLASLt
@@ -38,7 +62,13 @@ parameters:
     - hipTensor
     - llvm-project
     - MIOpen
+    - MIVisionX
+    - rocm_smi_lib
+    - rccl
+    - rocAL
+    - rocALUTION
     - rocBLAS
+    - rocDecode
     - rocFFT
     - rocJPEG
     - rocPRIM
@@ -50,11 +80,16 @@ parameters:
     - rocSPARSE
     - rocThrust
     - rocWMMA
+    - rpp
 - name: rocmTestDependencies
   type: object
   default:
     - AMDMIGraphX
+    - aomp
+    - aomp-extras
     - clr
+    - half
+    - composable_kernel
     - hipBLAS
     - hipBLAS-common
     - hipBLASLt
@@ -66,7 +101,14 @@ parameters:
     - hipSPARSE
     - hipTensor
     - llvm-project
+    - MIOpen
+    - MIVisionX
+    - rocm_smi_lib
+    - rccl
+    - rocAL
+    - rocALUTION
     - rocBLAS
+    - rocDecode
     - rocFFT
     - rocminfo
     - rocPRIM
@@ -80,6 +122,7 @@ parameters:
     - rocThrust
     - roctracer
     - rocWMMA
+    - rpp
 
 - name: jobMatrix
   type: object
@@ -108,6 +151,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
       parameters:
@@ -207,5 +251,6 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
         environment: test
         gpuTarget: ${{ job.target }}

.azuredevops/components/rocm-libraries.yml

@@ -43,9 +43,14 @@ parameters:
     - ninja-build
     - python3-pip
     - python3-venv
+    - googletest
+    - libgtest-dev
+    - libgmock-dev
+    - libboost-filesystem-dev
 - name: pipModules
   type: object
   default:
+    - msgpack
     - joblib
     - "packaging>=22.0"
     - pytest
@@ -147,6 +152,13 @@ jobs:
           echo "##vso[task.prependpath]$USER_BASE/bin"
           echo "##vso[task.setvariable variable=PytestCmakePath]$USER_BASE/share/Pytest/cmake"
         displayName: Set cmake configure paths
+    - task: Bash@3
+      displayName: Add ROCm binaries to PATH
+      inputs:
+        targetType: inline
+        script: |
+          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}

.azuredevops/components/rocprofiler-compute.yml

@@ -65,6 +65,13 @@ parameters:
     - pytest
     - pytest-cov
     - pytest-xdist
+- name: rocmDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - ROCR-Runtime
+    - rocprofiler-sdk
 - name: rocmTestDependencies
   type: object
   default:
@@ -101,10 +108,12 @@ jobs:
     ${{ if parameters.buildDependsOn }}:
       dependsOn:
         - ${{ each build in parameters.buildDependsOn }}:
-          - ${{ build }}_${{ job.os }}_${{ job.target }}
+          - ${{ build }}_${{ job.target }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
+    - name: ROCM_PATH
+      value: $(Agent.BuildDirectory)/rocm
     pool:
       vmImage: ${{ variables.BASE_BUILD_POOL }}
     workspace:
@@ -119,6 +128,14 @@ jobs:
       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: >-

.azuredevops/components/rocprofiler-sdk.yml

@@ -79,27 +79,27 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocprofiler_sdk_build_${{ job.target }}
+  - job: rocprofiler_sdk_build_${{ job.os }}_${{ job.target }}
     ${{ if parameters.buildDependsOn }}:
       dependsOn:
         - ${{ each build in parameters.buildDependsOn }}:
-          - ${{ build }}_${{ job.target }}
+          - ${{ build }}_${{ 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:
@@ -107,6 +107,7 @@ 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
@@ -118,6 +119,7 @@ jobs:
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         ${{ if parameters.triggerDownstreamJobs }}:
@@ -132,6 +134,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
         extraBuildFlags: >-
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
           -DROCPROFILER_BUILD_TESTS=ON
@@ -143,6 +146,7 @@ jobs:
       parameters:
         componentName: ${{ parameters.componentName }}
         sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
         gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
@@ -158,8 +162,8 @@ jobs:
 
 - ${{ if eq(parameters.unifiedBuild, False) }}:
   - ${{ each job in parameters.jobMatrix.testJobs }}:
-    - job: rocprofiler_sdk_test_${{ job.target }}
-      dependsOn: rocprofiler_sdk_build_${{ job.target }}
+    - job: rocprofiler_sdk_test_${{ job.os }}_${{ job.target }}
+      dependsOn: rocprofiler_sdk_build_${{ job.os }}_${{ job.target }}
       condition:
         and(succeeded(),
           eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -177,6 +181,7 @@ 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
@@ -188,6 +193,7 @@ jobs:
         parameters:
           checkoutRef: ${{ parameters.checkoutRef }}
           dependencyList: ${{ parameters.rocmDependencies }}
+          os: ${{ job.os }}
           gpuTarget: ${{ job.target }}
           ${{ if parameters.triggerDownstreamJobs }}:
               downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
@@ -202,6 +208,7 @@ jobs:
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
         parameters:
           componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
           extraBuildFlags: >-
             -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
             -DROCPROFILER_BUILD_TESTS=ON
@@ -213,7 +220,8 @@ jobs:
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
         parameters:
           componentName: ${{ parameters.componentName }}
-          testDir: $(Agent.BuildDirectory)/s/build
+          os: ${{ job.os }}
+          testDir: $(Agent.BuildDirectory)/build
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
         parameters:
           aptPackages: ${{ parameters.aptPackages }}

.azuredevops/dependencies/cli11.yml

@@ -0,0 +1,63 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: cli11Version
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: cli11_${{ 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 cli11 ${{ parameters.cli11Version }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/CLIUtils/CLI11.git -b ${{ parameters.cli11Version }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/CLI11/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/CLI11
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/dependencies/yamlcpp.yml

@@ -0,0 +1,66 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: yamlcppVersion
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: yamlcpp_${{ 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 yaml-cpp ${{ parameters.yamlcppVersion }}
+      inputs:
+        targetType: inline
+        script: git clone  https://github.com/jbeder/yaml-cpp.git -b ${{ parameters.yamlcppVersion }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/yaml-cpp/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/yaml-cpp
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -DYAML_CPP_BUILD_TOOLS=OFF
+          -DYAML_BUILD_SHARED_LIBS=OFF
+          -DYAML_CPP_INSTALL=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/tag-builds/cli11.yml

@@ -0,0 +1,23 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: cli11Version
+  type: string
+  default: "main"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/cli11.yml
+    parameters:
+      cli11Version: ${{ parameters.cli11Version }}

.azuredevops/tag-builds/yaml-cpp.yml

@@ -0,0 +1,24 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: yamlcppVersion
+  type: string
+  default: "0.8.0"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/yamlcpp.yml
+    parameters:
+      yamlcppVersion: ${{ parameters.yamlcppVersion }}
+      

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

@@ -63,6 +63,7 @@ parameters:
     libopenblas-dev: openblas-devel
     libopenmpi-dev: openmpi-devel
     libpci-dev: libpciaccess-devel
+    libsimde-dev: simde-devel
     libssl-dev: openssl-devel
     # note: libstdc++-devel is in the base packages list
     libsystemd-dev: systemd-devel

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

@@ -35,8 +35,8 @@ parameters:
       developBranch: develop
       hasGpuTarget: true
     amdsmi:
-      pipelineId: 99
-      developBranch: amd-staging
+      pipelineId: 376
+      developBranch: develop
       hasGpuTarget: false
     aomp-extras:
       pipelineId: 111
@@ -115,7 +115,7 @@ parameters:
       developBranch: develop
       hasGpuTarget: true
     hipTensor:
-      pipelineId: 105
+      pipelineId: 374
       developBranch: develop
       hasGpuTarget: true
     llvm-project:
@@ -263,7 +263,7 @@ parameters:
       developBranch: develop
       hasGpuTarget: true
     rocWMMA:
-      pipelineId: 109
+      pipelineId: 370
       developBranch: develop
       hasGpuTarget: true
     rpp:

.azuredevops/templates/steps/test.yml

@@ -13,7 +13,7 @@ parameters:
   default: ctest
 - name: testParameters
   type: string
-  default: --output-on-failure --force-new-ctest-process --output-junit test_output.xml
+  default: --extra-verbose --output-on-failure --force-new-ctest-process --output-junit test_output.xml
 - name: extraTestParameters
   type: string
   default: ''

.gitignore

@@ -1,6 +1,7 @@
 .venv
 .vscode
 build
+__pycache__
 
 # documentation artifacts
 _build/

.wordlist.txt

@@ -3,8 +3,11 @@ ABI
 ACE
 ACEs
 ACS
+AccVGPR
+AccVGPRs
 AITER
 ALU
+AllReduce
 AMD
 AMDGPU
 AMDGPUs
@@ -19,32 +22,29 @@ APIC
 APIs
 APU
 APUs
-ASAN
 ASIC
 ASICs
 ASan
+ASAN
 ASm
+Async
 ATI
-AccVGPR
-AccVGPRs
+atomicRMW
 AddressSanitizer
 AlexNet
-AllReduce
 Andrej
 Arb
 Autocast
+autograd
 BARs
-BKC
+BatchNorm
 BLAS
 BMC
 BabelStream
-BatchNorm
-Bitwise
 Blit
 Blockwise
 Bluefield
 Bootloader
-BrainFloat
 Broadcom
 CAS
 CCD
@@ -63,6 +63,7 @@ CPF
 CPP
 CPU
 CPUs
+Cron
 CSC
 CSDATA
 CSE
@@ -73,46 +74,51 @@ CTests
 CU
 CUDA
 CUs
-CX
 CXX
+CX
 Cavium
 CentOS
 ChatGPT
+Cholesky
 CoRR
 Codespaces
-ComfyUI
 Commitizen
 CommonMark
 Concretized
 Conda
 ConnectX
 CountOnes
-Cron
 CuPy
+customizable
+da
+Dashboarding
+Dataloading
+dataflows
 DBRX
 DDR
 DF
 DGEMM
 DGL
 DGLGraph
+dGPU
+dGPUs
 DIMM
 DKMS
 DL
 DMA
+DOMContentLoaded
 DNN
 DNNL
-DOMContentLoaded
 DPM
 DRI
 DW
 DWORD
-Dashboarding
 Dask
 DataFrame
 DataLoader
 DataParallel
-Dataloading
 Debian
+decompositions
 DeepSeek
 DeepSpeed
 Dependabot
@@ -120,20 +126,27 @@ Deprecations
 DevCap
 DirectX
 Disaggregated
+disaggregated
 Dockerfile
 Dockerized
 Doxygen
+dropless
 ELMo
 ENDPGM
 EPYC
 ESXi
+EP
 EoS
+etcd
+equalto
+fas
 FBGEMM
+FiLM
+FIFOs
 FFT
 FFTs
 FFmpeg
 FHS
-FIFOs
 FIXME
 FMA
 FP
@@ -142,17 +155,19 @@ Filesystem
 FindDb
 Flang
 FlashAttention
-FlashInfer
 FlashInfer’s
+FlashInfer
 FluxBenchmark
 Fortran
 Fuyu
 GALB
 GAT
+GATNE
 GCC
 GCD
 GCDs
 GCN
+GCNN
 GDB
 GDDR
 GDR
@@ -160,39 +175,43 @@ GDS
 GEMM
 GEMMs
 GFLOPS
-GFXIP
 GFortran
+GFXIP
 GGUF
+Gemma
+GiB
 GIM
 GL
+Glibc
 GLXT
+Gloo
 GMI
+GNN
+GNNs
 GPG
-GPGPU
 GPR
 GPT
 GPU
 GPU's
+GPUDirect
 GPUs
+GraphBolt
+GraphSage
 GRBM
 GRE
-Gemma
 GenAI
 GenZ
-GiB
 GitHub
 Gitpod
-Glibc
-Gloo
-GraphSage
-Graphbolt
 HBM
 HCA
 HGX
 HIPCC
+hipDataType
 HIPExtension
 HIPIFY
 HIPification
+hipification
 HIPify
 HPC
 HPCG
@@ -202,12 +221,14 @@ HSA
 HW
 HWE
 HWS
-HX
 Haswell
 Higgs
-Huggingface
-HunyuanVideo
+href
 Hyperparameters
+HybridEngine
+Huggingface
+Hunyuan
+HunyuanVideo
 IB
 ICD
 ICT
@@ -216,10 +237,13 @@ IDE
 IDEs
 IFWI
 IMDb
+IncDec
+instrSize
+interpolators
 IOMMU
 IOP
-IOPM
 IOPS
+IOPM
 IOV
 IRQ
 ISA
@@ -227,7 +251,6 @@ ISV
 ISVs
 ITL
 ImageNet
-IncDec
 InfiniBand
 Inlines
 IntelliSense
@@ -236,8 +259,10 @@ Intersphinx
 Intra
 Ioffe
 JAX's
-JSON
+JAXLIB
 Jinja
+js
+JSON
 Jupyter
 KFD
 KFDTest
@@ -245,10 +270,10 @@ KMD
 KV
 KVM
 Karpathy's
-Keras
-Khronos
 KiB
 Kineto
+Keras
+Khronos
 LAPACK
 LCLK
 LDS
@@ -256,22 +281,24 @@ LLM
 LLMs
 LLVM
 LM
+logsumexp
 LRU
 LSAN
-LSTMs
 LSan
 LTS
+LSTMs
+LteAll
 LanguageCrossEntropy
 LoRA
-LteAll
 MECO
 MEM
 MERCHANTABILITY
 MFMA
+MiB
 MIGraphX
 MIOpen
-MIOpen's
 MIOpenGEMM
+MIOpen's
 MIVisionX
 MLM
 MMA
@@ -282,31 +309,33 @@ MNIST
 MPI
 MPT
 MSVC
+mul
 MVAPICH
 MVFFR
-MXFP
 Makefile
 Makefiles
-ManyLinux
 Matplotlib
 Matrox
 MaxText
+MBT
 Megablocks
 Megatrends
 Megatron
 Mellanox
 Mellanox's
 Meta's
-MiB
 Miniconda
 MirroredStrategy
 Mixtral
+MLA
+MosaicML
 MoEs
 Mooncake
-MosaicML
 Mpops
 Multicore
 Multithreaded
+mx
+MXFP
 MyEnvironment
 MyST
 NANOO
@@ -314,27 +343,24 @@ NBIO
 NBIOs
 NCCL
 NCF
-NCS
 NFS
 NIC
 NICs
 NLI
 NLP
 NN
-NOP
 NPKit
 NPS
 NSP
 NUMA
 NVCC
 NVIDIA
-NVLink
 NVPTX
 NaN
 Nano
 Navi
-NoReturn
 Noncoherently
+NoReturn
 NousResearch's
 NumPy
 OAM
@@ -345,6 +371,7 @@ OFED
 OMM
 OMP
 OMPI
+OOM
 OMPT
 OMPX
 ONNX
@@ -361,21 +388,22 @@ OpenVX
 OpenXLA
 Optim
 Oversubscription
+PagedAttention
+Pallas
 PCC
 PCI
 PCIe
 PEFT
+perf
 PEQT
 PIL
 PILImage
-PLDM
+PJRT
 POR
 PRNG
 PRs
 PaLM
 Pageable
-PagedAttention
-Pallas
 PeerDirect
 PerfDb
 Perfetto
@@ -388,8 +416,9 @@ Pretraining
 Primus
 Profiler's
 PyPi
-PyTorch
 Pytest
+PyTorch
+QPS
 Qcycles
 Qwen
 RAII
@@ -400,16 +429,16 @@ RDC's
 RDMA
 RDNA
 README
+Recomputation
 RHEL
-RLHF
 RMW
 RNN
 RNNs
 ROC
 ROCProfiler
 ROCT
-ROCTracer
 ROCTx
+ROCTracer
 ROCclr
 ROCdbgapi
 ROCgdb
@@ -424,10 +453,8 @@ RPP
 RST
 RW
 Radeon
-Recomputation
 RelWithDebInfo
 Req
-ResNet
 Rickle
 RoCE
 Runfile
@@ -435,8 +462,8 @@ Ryzen
 SALU
 SBIOS
 SCA
+ScaledGEMM
 SDK
-SDKs
 SDMA
 SDPA
 SDRAM
@@ -453,6 +480,7 @@ SKU
 SKUs
 SLES
 SLURM
+Slurm
 SMEM
 SMFMA
 SMI
@@ -463,17 +491,17 @@ SRAM
 SRAMECC
 SVD
 SWE
-ScaledGEMM
 SerDes
 ShareGPT
 Shlens
+simd
 Skylake
-Slurm
 Softmax
 Spack
 SplitK
 Supermicro
 Szegedy
+TagRAM
 TCA
 TCC
 TCCs
@@ -481,33 +509,34 @@ TCI
 TCIU
 TCP
 TCR
+TVM
+THREADGROUPS
+threadgroups
+TensorRT
+TensorFloat
 TF
 TFLOPS
-THREADGROUPS
 TP
 TPS
 TPU
 TPUs
 TSME
-TVM
-TagRAM
 Tagram
-Taichi
-Taichi's
 TensileLite
 TensorBoard
-TensorFloat
 TensorFlow
 TensorParallel
-TensorRT
 TheRock
 ToC
-TopK
 TorchAudio
+torchaudio
 TorchElastic
 TorchMIGraphX
+torchrec
 TorchScript
 TorchServe
+torchserve
+torchtext
 TorchVision
 TransferBench
 TrapStatus
@@ -515,22 +544,22 @@ UAC
 UC
 UCC
 UCX
+ud
 UE
 UIF
 UMC
 USM
-USM
 UTCL
-UTCL
-UTIL
 UTIL
 UltraChat
 Uncached
-Unhandled
 Unittests
+Unhandled
+unwindowed
 VALU
 VBIOS
 VCN
+verl's
 VGPR
 VGPRs
 VM
@@ -541,7 +570,6 @@ VSIX
 VSkipped
 Vanhoucke
 Vulkan
-WDAG
 WGP
 WGPs
 WR
@@ -550,6 +578,7 @@ WikiText
 Wojna
 Workgroups
 Writebacks
+xcc
 XCD
 XCDs
 XGBoost
@@ -569,8 +598,8 @@ ZeRO
 ZenDNN
 accuracies
 activations
-addEventListener
 addr
+addEventListener
 ade
 ai
 alloc
@@ -581,7 +610,6 @@ amdgpu
 api
 aten
 atmi
-atomicRMW
 atomics
 autogenerated
 autotune
@@ -598,16 +626,17 @@ bilinear
 bitcode
 bitsandbytes
 bitwise
+Bitwise
 blit
 bootloader
 boson
 bosons
 br
+BrainFloat
 btn
 buildable
 bursty
 bzip
-cTDP
 cacheable
 carveout
 cd
@@ -622,7 +651,6 @@ cmd
 coalescable
 codename
 collater
-comfyui
 comgr
 compat
 completers
@@ -639,18 +667,16 @@ copyable
 cpp
 csn
 cuBLAS
+cuda
 cuDNN
+cudnn
 cuFFT
 cuLIB
 cuRAND
 cuSOLVER
 cuSPARSE
-cuda
-cudnn
 customizations
-dGPU
-dGPUs
-da
+cTDP
 dataset
 datasets
 dataspace
@@ -660,15 +686,15 @@ datatypes
 dbgapi
 de
 deallocation
-debian
 debuggability
-decompositions
+debian
 deepseek
 denoise
 denoised
 denoises
 denormalize
 dequantization
+dequantized
 dequantizes
 deserializers
 detections
@@ -677,12 +703,10 @@ devicelibs
 devsel
 dgl
 dimensionality
-disaggregated
 disambiguates
 distro
 distros
 dkms
-dropless
 dtype
 eb
 el
@@ -695,14 +719,10 @@ endpgm
 enqueue
 env
 epilog
-etcd
 etcetera
 ethernet
 exascale
 executables
-fam
-fam
-fas
 ffmpeg
 filesystem
 forEach
@@ -729,8 +749,8 @@ heterogenous
 hipBLAS
 hipBLASLt
 hipBLASLt's
+hipblaslt
 hipCUB
-hipDataType
 hipFFT
 hipFORT
 hipLIB
@@ -741,12 +761,10 @@ hipSPARSELt
 hipTensor
 hipamd
 hipblas
-hipblaslt
 hipcc
 hipcub
 hipfft
 hipfort
-hipification
 hipify
 hipsolver
 hipsparse
@@ -755,7 +773,6 @@ hostname
 hotspotting
 hpc
 hpp
-href
 hsa
 hsakmt
 hyperparameter
@@ -771,9 +788,7 @@ init
 initializer
 inlining
 installable
-instrSize
 interop
-interpolators
 interprocedural
 intra
 intrinsics
@@ -795,6 +810,7 @@ linalg
 linearized
 linter
 linux
+llm
 llvm
 lm
 localscratch
@@ -816,21 +832,23 @@ mjx
 mkdir
 mlirmiopen
 mtypes
-mul
 mutex
 mvffr
 namespace
 namespaces
 nanoGPT
+NCS
+NOP
+NVLink
 num
 numref
 ocl
-ol
 opencl
 opencv
 openmp
 openssl
 optimizers
+ol
 os
 oversubscription
 pageable
@@ -838,12 +856,13 @@ pallas
 parallelization
 parallelizing
 param
+params
 parameterization
 passthrough
 pe
-perf
 perfcounter
 performant
+piecewise
 perl
 pragma
 pre
@@ -874,6 +893,8 @@ pseudorandom
 px
 py
 pytorch
+recommender
+recommenders
 quantile
 quantizer
 quasirandom
@@ -882,13 +903,11 @@ querySelectorAll
 queueing
 qwen
 radeon
+rc
 rccl
 rdc
 rdma
 reStructuredText
-recommender
-recommenders
-redhat
 redirections
 refactorization
 reformats
@@ -902,6 +921,7 @@ rescaling
 reusability
 rhel
 rl
+RLHF
 roadmap
 roc
 rocAL
@@ -928,8 +948,8 @@ rocm
 rocminfo
 rocprim
 rocprof
-rocprofiler
 rocprofv
+rocprofiler
 rocr
 rocrand
 rocsolver
@@ -939,12 +959,13 @@ roctracer
 rst
 runtime
 runtimes
-ryzen
+ResNet
 sL
 scalability
 scalable
 scipy
 seealso
+selectattr
 selectedTag
 sendmsg
 seqs
@@ -954,7 +975,6 @@ sglang
 shader
 sharding
 sigmoid
-simd
 sles
 sm
 smi
@@ -975,7 +995,6 @@ submodule
 submodules
 subnet
 supercomputing
-suse
 symlink
 symlinks
 sys
@@ -985,7 +1004,6 @@ td
 tensorfloat
 tf
 th
-threadgroups
 tokenization
 tokenize
 tokenized
@@ -993,23 +1011,19 @@ tokenizer
 tokenizes
 toolchain
 toolchains
+topk
 toolset
 toolsets
-torchaudio
-torchrec
-torchserve
-torchtext
 torchtitan
 torchvision
 tp
 tqdm
 tracebacks
 txt
+TopK
 uarch
-ubuntu
-udev
-uncacheable
 uncached
+uncacheable
 uncorrectable
 underoptimized
 unhandled
@@ -1018,12 +1032,14 @@ unmapped
 unsqueeze
 unstacking
 unswitching
-untar
 untrusted
 untuned
-unwindowed
 upvote
+USM
+UTCL
+UTIL
 utils
+UX
 vL
 variational
 vdi
@@ -1034,7 +1050,6 @@ vectorized
 vectorizer
 vectorizes
 verl
-verl's
 virtualize
 virtualized
 vjxb
@@ -1053,12 +1068,11 @@ writeback
 writebacks
 wrreq
 wzo
+xargs
+xdit
 xDiT
 xGMI
 xPacked
-xargs
-xcc
-xdit
 xz
 yaml
 ysvmadyb

default.xml

@@ -1,33 +1,17 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-7.0.2"
+    <default revision="refs/tags/rocm-7.1.1"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />
 <!--list of projects for ROCm-->
     <project name="ROCK-Kernel-Driver" />
-    <project name="ROCR-Runtime" />
     <project name="amdsmi" />
-    <project name="aqlprofile" />
-    <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" />
@@ -41,6 +25,7 @@
     <project groups="mathlibs" name="MIVisionX" />
     <project groups="mathlibs" name="ROCmValidationSuite" />
     <project groups="mathlibs" name="composable_kernel" />
+    <project groups="mathlibs" name="hipSOLVER" />
     <project groups="mathlibs" name="hipTensor" />
     <project groups="mathlibs" name="hipfort" />
     <project groups="mathlibs" name="rccl" />
@@ -54,7 +39,14 @@
         MIOpen rocBLAS rocFFT rocPRIM rocRAND
         rocSPARSE rocThrust Tensile -->
     <project groups="mathlibs" name="rocm-libraries" />
+    <!-- The following components have been migrated to rocm-systems:
+        aqlprofile clr hip hip-tests hipother
+        rdc rocm-core rocm_smi_lib rocminfo rocprofiler-compute 
+        rocprofiler-register rocprofiler-sdk rocprofiler-systems 
+        rocprofiler rocr-runtime roctracer -->
+    <project groups="mathlibs" name="rocm-systems" />
     <project groups="mathlibs" name="rocPyDecode" />
+    <project groups="mathlibs" name="rocSOLVER" />
     <project groups="mathlibs" name="rocSHMEM" />
     <project groups="mathlibs" name="rocWMMA" />
     <project groups="mathlibs" name="rocm-cmake" />

docs/about/license.md

@@ -25,69 +25,69 @@ additional licenses. Please review individual repositories for more information.
 <!-- spellcheck-disable -->
 | Component | License |
 |:---------------------|:-------------------------|
-| [AMD Compute Language Runtime (CLR)](https://github.com/ROCm/clr) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/LICENSE.txt) |
+| [AMD Compute Language Runtime (CLR)](https://github.com/ROCm/rocm-systems/tree/develop/projects/clr) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/clr/LICENSE.md) |
 | [AMD SMI](https://github.com/ROCm/amdsmi) | [MIT](https://github.com/ROCm/amdsmi/blob/amd-staging/LICENSE) |
 | [aomp](https://github.com/ROCm/aomp/) | [Apache 2.0](https://github.com/ROCm/aomp/blob/aomp-dev/LICENSE) |
 | [aomp-extras](https://github.com/ROCm/aomp-extras/) | [MIT](https://github.com/ROCm/aomp-extras/blob/aomp-dev/LICENSE) |
-| [AQLprofile](https://github.com/rocm/aqlprofile/) | [MIT](https://github.com/ROCm/aqlprofile/blob/amd-staging/LICENSE.md) |
+| [AQLprofile](https://github.com/ROCm/rocm-systems/tree/develop/projects/aqlprofile/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/aqlprofile/LICENSE.md) |
 | [Code Object Manager (Comgr)](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/comgr) | [The University of Illinois/NCSA](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/comgr/LICENSE.txt) |
 | [Composable Kernel](https://github.com/ROCm/composable_kernel) | [MIT](https://github.com/ROCm/composable_kernel/blob/develop/LICENSE) |
 | [half](https://github.com/ROCm/half/) | [MIT](https://github.com/ROCm/half/blob/rocm/LICENSE.txt) |
-| [HIP](https://github.com/ROCm/HIP/) | [MIT](https://github.com/ROCm/HIP/blob/amd-staging/LICENSE.txt) |
-| [hipamd](https://github.com/ROCm/clr/tree/amd-staging/hipamd) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/hipamd/LICENSE.txt) |
-| [hipBLAS](https://github.com/ROCm/hipBLAS/) | [MIT](https://github.com/ROCm/hipBLAS/blob/develop/LICENSE.md) |
-| [hipBLASLt](https://github.com/ROCm/hipBLASLt/) | [MIT](https://github.com/ROCm/hipBLASLt/blob/develop/LICENSE.md) |
+| [HIP](https://github.com/ROCm/rocm-systems/tree/develop/projects/hip/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/hip/LICENSE.md) |
+| [hipamd](https://github.com/ROCm/rocm-systems/tree/develop/projects/clr/hipamd/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/clr/hipamd/LICENSE.md) |
+| [hipBLAS](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipblas/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hipblas/LICENSE.md) |
+| [hipBLASLt](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipblaslt/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hipblaslt/LICENSE.md) |
 | [HIPCC](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/hipcc) | [MIT](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/hipcc/LICENSE.txt) |
-| [hipCUB](https://github.com/ROCm/hipCUB/) | [Custom](https://github.com/ROCm/hipCUB/blob/develop/LICENSE.txt) |
-| [hipFFT](https://github.com/ROCm/hipFFT/) | [MIT](https://github.com/ROCm/hipFFT/blob/develop/LICENSE.md) |
+| [hipCUB](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipcub/) | [Custom](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hipcub/LICENSE.txt) |
+| [hipFFT](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipfft/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hipfft/LICENSE.md) |
 | [hipfort](https://github.com/ROCm/hipfort/) | [MIT](https://github.com/ROCm/hipfort/blob/develop/LICENSE) |
 | [HIPIFY](https://github.com/ROCm/HIPIFY/) | [MIT](https://github.com/ROCm/HIPIFY/blob/amd-staging/LICENSE.txt) |
-| [hipRAND](https://github.com/ROCm/hipRAND/) | [MIT](https://github.com/ROCm/hipRAND/blob/develop/LICENSE.txt) |
-| [hipSOLVER](https://github.com/ROCm/hipSOLVER/) | [MIT](https://github.com/ROCm/hipSOLVER/blob/develop/LICENSE.md) |
-| [hipSPARSE](https://github.com/ROCm/hipSPARSE/) | [MIT](https://github.com/ROCm/hipSPARSE/blob/develop/LICENSE.md) |
-| [hipSPARSELt](https://github.com/ROCm/hipSPARSELt/) | [MIT](https://github.com/ROCm/hipSPARSELt/blob/develop/LICENSE.md) |
-| [hipTensor](https://github.com/ROCm/hipTensor) | [MIT](https://github.com/ROCm/hipTensor/blob/develop/LICENSE) |
+| [hipRAND](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hiprand/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hiprand/LICENSE.md) |
+| [hipSOLVER](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipsolver/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hipsolver/LICENSE.md) |
+| [hipSPARSE](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipsparse/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hipsparse/LICENSE.md) |
+| [hipSPARSELt](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipsparselt/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hipsparselt/LICENSE.md) |
+| [hipTensor](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hiptensor/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/hiptensor/LICENSE) |
 | [llvm-project](https://github.com/ROCm/llvm-project/) | [Apache](https://github.com/ROCm/llvm-project/blob/amd-staging/LICENSE.TXT) |
 | [llvm-project/flang](https://github.com/ROCm/llvm-project/tree/amd-staging/flang) | [Apache 2.0](https://github.com/ROCm/llvm-project/blob/amd-staging/flang/LICENSE.TXT) |
 | [MIGraphX](https://github.com/ROCm/AMDMIGraphX/) | [MIT](https://github.com/ROCm/AMDMIGraphX/blob/develop/LICENSE) |
-| [MIOpen](https://github.com/ROCm/MIOpen/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/miopen/LICENSE.md) |
+| [MIOpen](https://github.com/ROCm/rocm-libraries/tree/develop/projects/miopen/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/miopen/LICENSE.md) |
 | [MIVisionX](https://github.com/ROCm/MIVisionX/) | [MIT](https://github.com/ROCm/MIVisionX/blob/develop/LICENSE.txt) |
 | [rocAL](https://github.com/ROCm/rocAL) | [MIT](https://github.com/ROCm/rocAL/blob/develop/LICENSE.txt) |
 | [rocALUTION](https://github.com/ROCm/rocALUTION/) | [MIT](https://github.com/ROCm/rocALUTION/blob/develop/LICENSE.md) |
-| [rocBLAS](https://github.com/ROCm/rocBLAS/) | [MIT](https://github.com/ROCm/rocBLAS/blob/develop/LICENSE.md) |
+| [rocBLAS](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocblas/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocblas/LICENSE.md) |
 | [ROCdbgapi](https://github.com/ROCm/ROCdbgapi/) | [MIT](https://github.com/ROCm/ROCdbgapi/blob/amd-staging/LICENSE.txt) |
 | [rocDecode](https://github.com/ROCm/rocDecode) | [MIT](https://github.com/ROCm/rocDecode/blob/develop/LICENSE) |
-| [rocFFT](https://github.com/ROCm/rocFFT/) | [MIT](https://github.com/ROCm/rocFFT/blob/develop/LICENSE.md) |
+| [rocFFT](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocfft/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocfft/LICENSE.md) |
 | [ROCgdb](https://github.com/ROCm/ROCgdb/) | [GNU General Public License v3.0](https://github.com/ROCm/ROCgdb/blob/amd-staging/COPYING3) |
 | [rocJPEG](https://github.com/ROCm/rocJPEG/) | [MIT](https://github.com/ROCm/rocJPEG/blob/develop/LICENSE) |
 | [ROCK-Kernel-Driver](https://github.com/ROCm/ROCK-Kernel-Driver/) | [GPL 2.0 WITH Linux-syscall-note](https://github.com/ROCm/ROCK-Kernel-Driver/blob/master/COPYING) |
-| [rocminfo](https://github.com/ROCm/rocminfo/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocminfo/blob/amd-staging/License.txt) |
+| [rocminfo](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocminfo/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocminfo/License.txt) |
 | [ROCm Bandwidth Test](https://github.com/ROCm/rocm_bandwidth_test/) | [MIT](https://github.com/ROCm/rocm_bandwidth_test/blob/master/LICENSE.txt) |
 | [ROCm CMake](https://github.com/ROCm/rocm-cmake/) | [MIT](https://github.com/ROCm/rocm-cmake/blob/develop/LICENSE) |
 | [ROCm Communication Collectives Library (RCCL)](https://github.com/ROCm/rccl/) | [Custom](https://github.com/ROCm/rccl/blob/develop/LICENSE.txt) |
-| [ROCm-Core](https://github.com/ROCm/rocm-core) | [MIT](https://github.com/ROCm/rocm-core/blob/master/copyright) |
-| [ROCm Compute Profiler](https://github.com/ROCm/rocprofiler-compute) | [MIT](https://github.com/ROCm/rocprofiler-compute/blob/amd-staging/LICENSE) |
-| [ROCm Data Center (RDC)](https://github.com/ROCm/rdc/) | [MIT](https://github.com/ROCm/rdc/blob/amd-staging/LICENSE.md) |
+| [ROCm-Core](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocm-core/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocm-core/LICENSE.md) |
+| [ROCm Compute Profiler](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-compute/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocprofiler-compute/LICENSE.md) |
+| [ROCm Data Center (RDC)](https://github.com/ROCm/rocm-systems/tree/develop/projects/rdc/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/rdc/LICENSE.md) |
 | [ROCm-Device-Libs](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/device-libs) | [The University of Illinois/NCSA](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/device-libs/LICENSE.TXT) |
-| [ROCm-OpenCL-Runtime](https://github.com/ROCm/clr/tree/amd-staging/opencl) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/opencl/LICENSE.txt) |
+| [ROCm-OpenCL-Runtime](https://github.com/ROCm/rocm-systems/tree/develop/projects/clr/opencl/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/clr/opencl/LICENSE.md) |
 | [ROCm Performance Primitives (RPP)](https://github.com/ROCm/rpp) | [MIT](https://github.com/ROCm/rpp/blob/develop/LICENSE) |
-| [ROCm SMI Lib](https://github.com/ROCm/rocm_smi_lib/) | [MIT](https://github.com/ROCm/rocm_smi_lib/blob/amd-staging/LICENSE.md) |
-| [ROCm Systems Profiler](https://github.com/ROCm/rocprofiler-systems) | [MIT](https://github.com/ROCm/rocprofiler-systems/blob/amd-staging/LICENSE.md) |
+| [ROCm SMI Lib](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocm-smi-lib/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocm-smi-lib/LICENSE.md) |
+| [ROCm Systems Profiler](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-systems/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocprofiler-systems/LICENSE.md) |
 | [ROCm Validation Suite](https://github.com/ROCm/ROCmValidationSuite/) | [MIT](https://github.com/ROCm/ROCmValidationSuite/blob/master/LICENSE) |
-| [rocPRIM](https://github.com/ROCm/rocPRIM/) | [MIT](https://github.com/ROCm/rocPRIM/blob/develop/LICENSE.txt) |
-| [ROCProfiler](https://github.com/ROCm/rocprofiler/) | [MIT](https://github.com/ROCm/rocprofiler/blob/amd-staging/LICENSE.md) |
-| [ROCprofiler-SDK](https://github.com/ROCm/rocprofiler-sdk) | [MIT](https://github.com/ROCm/rocprofiler-sdk/blob/amd-mainline/LICENSE) |
+| [rocPRIM](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocprim/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocprim/LICENSE.md) |
+| [ROCProfiler](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocprofiler/LICENSE.md) |
+| [ROCprofiler-SDK](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-sdk/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocprofiler-sdk/LICENSE.md) |
 | [rocPyDecode](https://github.com/ROCm/rocPyDecode) | [MIT](https://github.com/ROCm/rocPyDecode/blob/develop/LICENSE.txt) |
-| [rocRAND](https://github.com/ROCm/rocRAND/) | [MIT](https://github.com/ROCm/rocRAND/blob/develop/LICENSE.txt) |
+| [rocRAND](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocrand/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocrand/LICENSE.md) |
 | [ROCr Debug Agent](https://github.com/ROCm/rocr_debug_agent/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocr_debug_agent/blob/amd-staging/LICENSE.txt) |
-| [ROCR-Runtime](https://github.com/ROCm/ROCR-Runtime/) | [The University of Illinois/NCSA](https://github.com/ROCm/ROCR-Runtime/blob/amd-staging/LICENSE.txt) |
+| [ROCR-Runtime](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocr-runtime/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocr-runtime/LICENSE.txt) |
 | [rocSHMEM](https://github.com/ROCm/rocSHMEM/) | [MIT](https://github.com/ROCm/rocSHMEM/blob/develop/LICENSE.md) |
-| [rocSOLVER](https://github.com/ROCm/rocSOLVER/) | [BSD-2-Clause](https://github.com/ROCm/rocSOLVER/blob/develop/LICENSE.md) |
-| [rocSPARSE](https://github.com/ROCm/rocSPARSE/) | [MIT](https://github.com/ROCm/rocSPARSE/blob/develop/LICENSE.md) |
-| [rocThrust](https://github.com/ROCm/rocThrust/) | [Apache 2.0](https://github.com/ROCm/rocThrust/blob/develop/LICENSE) |
-| [ROCTracer](https://github.com/ROCm/roctracer/) | [MIT](https://github.com/ROCm/roctracer/blob/amd-master/LICENSE) |
-| [rocWMMA](https://github.com/ROCm/rocWMMA/) | [MIT](https://github.com/ROCm/rocWMMA/blob/develop/LICENSE.md) |
-| [Tensile](https://github.com/ROCm/Tensile/) | [MIT](https://github.com/ROCm/Tensile/blob/develop/LICENSE.md) |
+| [rocSOLVER](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocsolver/) | [BSD-2-Clause](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocsolver/LICENSE.md) |
+| [rocSPARSE](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocsparse/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocsparse/LICENSE.md) |
+| [rocThrust](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocthrust/) | [Apache 2.0](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocthrust/LICENSE) |
+| [ROCTracer](https://github.com/ROCm/rocm-systems/tree/develop/projects/roctracer/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/roctracer/LICENSE.md) |
+| [rocWMMA](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocwmma/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocwmma/LICENSE.md) |
+| [Tensile](https://github.com/ROCm/rocm-libraries/tree/develop/shared/tensile/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/shared/tensile/LICENSE.md) |
 | [TransferBench](https://github.com/ROCm/TransferBench) | [MIT](https://github.com/ROCm/TransferBench/blob/develop/LICENSE.md) |
 
 Open sourced ROCm components are released via public GitHub

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

@@ -0,0 +1,136 @@
+ROCm Version,7.1.1,7.1.0,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
+      :ref:`Operating systems & kernels <OS-kernel-versions>` [#os-compatibility-past-60]_,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.3,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 24.04.2,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,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 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 10.0, 9.6, 9.4","RHEL 10.0, 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.4","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,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 SP7,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,"SLES 15 SP7, SP6","SLES 15 SP7, SP6",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
+      ,"Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8",Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,,,
+      ,"Debian 13, 12","Debian 13, 12","Debian 13, 12",Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,,,,,,,,,,,
+      ,,,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,,,,,,,,,,,,
+      ,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,,,,,,,,,,,,,,,,,,
+      ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,CDNA4,CDNA4,CDNA4,,,,,,,,,,,,,,,,,,
+      ,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
+      ,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
+      ,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
+      ,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,,,,,,,,,,,,,,,
+      ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,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,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
+      ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`  [#gpu-compatibility-past-60]_,gfx950,gfx950,gfx950,gfx950,,,,,,,,,,,,,,,,,,
+      ,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,,,,,,,,,,,,,,,
+      ,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,,,,,,,,,,,,,,,
+      ,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,,,,,,,,,,,,,,,
+      ,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,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,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
+      ,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942, gfx942, gfx942, gfx942, gfx942, gfx942, gfx942
+      ,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
+      ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
+      ,,,,,,,,,,,,,,,,,,,,,,
+      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.9, 2.8, 2.7","2.8, 2.7, 2.6","2.8, 2.7, 2.6","2.7, 2.6, 2.5","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
+      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","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>`,0.7.1,0.7.1,0.6.0,0.6.0,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
+      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat-past-60]_,N/A,N/A,N/A,0.6.0,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,N/A
+      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat-past-60]_,N/A,N/A,N/A,N/A,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,N/A
+      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat-past-60]_,N/A,N/A,N/A,2.4.0,2.4.0,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,N/A
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat-past-60]_,N/A,N/A,N/A,N/A,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,N/A
+      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,N/A,2.51.1,N/A,N/A,2.48.0.post0,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,N/A
+      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat-past-60]_,N/A,N/A,N/A,b6652,b6356,b6356,b6356,b5997,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:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>` [#flashinfer_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,v0.2.5,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,N/A
+      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.1,1.22.0,1.22.0,1.22.0,1.20.0,1.20.0,1.20.0,1.20.0,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
+      ,,,,,,,,,,,,,,,,,,,,,,
+      ,,,,,,,,,,,,,,,,,,,,,,
+      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      `UCC <https://github.com/ROCm/ucc>`_,>=1.4.0,>=1.4.0,>=1.4.0,>=1.4.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
+      `UCX <https://github.com/ROCm/ucx>`_,>=1.17.0,>=1.17.0,>=1.17.0,>=1.17.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
+      ,,,,,,,,,,,,,,,,,,,,,,
+      THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      Thrust,2.8.5,2.8.5,2.6.0,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      CUB,2.8.5,2.8.5,2.6.0,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      ,,,,,,,,,,,,,,,,,,,,,,
+     DRIVER & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.20.1, 30.20.0 [#mi325x_KVM-past-60]_, 30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x","30.20.0 [#mi325x_KVM-past-60]_, 30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x","30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x, 6.3.x","30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x, 6.3.x, 6.2.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","6.4.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>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
+      :doc:`MIGraphX <amdmigraphx:index>`,2.14.0,2.14.0,2.13.0,2.13.0,2.12.0,2.12.0,2.12.0,2.12.0,2.11.0,2.11.0,2.11.0,2.11.0,2.10.0,2.10.0,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
+      :doc:`MIOpen <miopen:index>`,3.5.1,3.5.1,3.5.0,3.5.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`MIVisionX <mivisionx:index>`,3.4.0,3.4.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
+      :doc:`rocAL <rocal:index>`,2.4.0,2.4.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      :doc:`rocDecode <rocdecode:index>`,1.4.0,1.4.0,1.0.0,1.0.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
+      :doc:`rocJPEG <rocjpeg:index>`,1.2.0,1.2.0,1.1.0,1.1.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`rocPyDecode <rocpydecode:index>`,0.7.0,0.7.0,0.6.0,0.6.0,0.3.1,0.3.1,0.3.1,0.3.1,0.2.0,0.2.0,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`RPP <rpp:index>`,2.1.0,2.1.0,2.0.0,2.0.0,1.9.10,1.9.10,1.9.10,1.9.10,1.9.1,1.9.1,1.9.1,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
+      ,,,,,,,,,,,,,,,,,,,,,,
+      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      :doc:`RCCL <rccl:index>`,2.27.7,2.27.7,2.26.6,2.26.6,2.22.3,2.22.3,2.22.3,2.22.3,2.21.5,2.21.5,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
+      :doc:`rocSHMEM <rocshmem:index>`,3.1.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.0,2.0.0,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>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
+      :doc:`hipBLAS <hipblas:index>`,3.1.0,3.1.0,3.0.2,3.0.0,2.4.0,2.4.0,2.4.0,2.4.0,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
+      :doc:`hipBLASLt <hipblaslt:index>`,1.1.0,1.1.0,1.0.0,1.0.0,0.12.1,0.12.1,0.12.1,0.12.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
+      :doc:`hipFFT <hipfft:index>`,1.0.21,1.0.21,1.0.20,1.0.20,1.0.18,1.0.18,1.0.18,1.0.18,1.0.17,1.0.17,1.0.17,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
+      :doc:`hipfort <hipfort:index>`,0.7.1,0.7.1,0.7.0,0.7.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.1,0.5.1,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
+      :doc:`hipRAND <hiprand:index>`,3.1.0,3.1.0,3.0.0,3.0.0,2.12.0,2.12.0,2.12.0,2.12.0,2.11.1,2.11.1,2.11.1,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
+      :doc:`hipSOLVER <hipsolver:index>`,3.1.0,3.1.0,3.0.0,3.0.0,2.4.0,2.4.0,2.4.0,2.4.0,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
+      :doc:`hipSPARSE <hipsparse:index>`,4.1.0,4.1.0,4.0.1,4.0.1,3.2.0,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.5,0.2.5,0.2.4,0.2.4,0.2.3,0.2.3,0.2.3,0.2.3,0.2.2,0.2.2,0.2.2,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
+      :doc:`rocALUTION <rocalution:index>`,4.0.1,4.0.1,4.0.0,4.0.0,3.2.3,3.2.3,3.2.3,3.2.2,3.2.1,3.2.1,3.2.1,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
+      :doc:`rocBLAS <rocblas:index>`,5.1.1,5.1.0,5.0.2,5.0.0,4.4.1,4.4.1,4.4.0,4.4.0,4.3.0,4.3.0,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
+      :doc:`rocFFT <rocfft:index>`,1.0.35,1.0.35,1.0.34,1.0.34,1.0.32,1.0.32,1.0.32,1.0.32,1.0.31,1.0.31,1.0.31,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
+      :doc:`rocRAND <rocrand:index>`,4.1.0,4.1.0,4.0.0,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
+      :doc:`rocSOLVER <rocsolver:index>`,3.31.0,3.31.0,3.30.1,3.30.0,3.28.2,3.28.2,3.28.0,3.28.0,3.27.0,3.27.0,3.27.0,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
+      :doc:`rocSPARSE <rocsparse:index>`,4.1.0,4.1.0,4.0.2,4.0.2,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
+      :doc:`rocWMMA <rocwmma:index>`,2.1.0,2.0.0,2.0.0,2.0.0,1.7.0,1.7.0,1.7.0,1.7.0,1.6.0,1.6.0,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
+      :doc:`Tensile <tensile:src/index>`,4.44.0,4.44.0,4.44.0,4.44.0,4.43.0,4.43.0,4.43.0,4.43.0,4.42.0,4.42.0,4.42.0,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
+      ,,,,,,,,,,,,,,,,,,,,,,
+      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      :doc:`hipCUB <hipcub:index>`,4.1.0,4.1.0,4.0.0,4.0.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`hipTensor <hiptensor:index>`,2.0.0,2.0.0,2.0.0,2.0.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
+      :doc:`rocPRIM <rocprim:index>`,4.1.0,4.1.0,4.0.1,4.0.0,3.4.1,3.4.1,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`rocThrust <rocthrust:index>`,4.1.0,4.1.0,4.0.0,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      ,,,,,,,,,,,,,,,,,,,,,,
+      SUPPORT LIBS,,,,,,,,,,,,,,,,,,,,,,
+      `hipother <https://github.com/ROCm/hipother>`_,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43483,6.4.43483,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.1.1,7.1.0,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
+      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,20240607.5.7,20240607.5.7,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
+      ,,,,,,,,,,,,,,,,,,,,,,
+      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      :doc:`AMD SMI <amdsmi:index>`,26.2.0,26.1.0,26.0.2,26.0.0,25.5.1,25.5.1,25.4.2,25.3.0,24.7.1,24.7.1,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
+      :doc:`ROCm Data Center Tool <rdc:index>`,1.2.0,1.2.0,1.1.0,1.1.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
+      :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.8.0,7.8.0,7.8.0,7.8.0,7.7.0,7.5.0,7.5.0,7.5.0,7.4.0,7.4.0,7.4.0,7.4.0,7.3.0,7.3.0,7.3.0,7.3.0,7.2.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
+      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.3.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60105,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
+      ,,,,,,,,,,,,,,,,,,,,,,
+      PERFORMANCE TOOLS,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,2.6.0,2.6.0,2.6.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
+      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.3.1,3.3.0,3.2.3,3.2.3,3.1.1,3.1.1,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.2.1,1.2.0,1.1.1,1.1.0,1.0.2,1.0.2,1.0.1,1.0.0,0.1.2,0.1.1,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70101,2.0.70100,2.0.70002,2.0.70000,2.0.60403,2.0.60402,2.0.60401,2.0.60400,2.0.60303,2.0.60302,2.0.60301,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
+      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.0.0,1.0.0,1.0.0,1.0.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCTracer <roctracer:index>`,4.1.70101,4.1.70100,4.1.70002,4.1.70000,4.1.60403,4.1.60402,4.1.60401,4.1.60400,4.1.60303,4.1.60302,4.1.60301,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
+      ,,,,,,,,,,,,,,,,,,,,,,
+      DEVELOPMENT TOOLS,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`HIPIFY <hipify:index>`,20.0.0,20.0.0,20.0.0,20.0.0,19.0.0,19.0.0,19.0.0,19.0.0,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.4,0.77.4,0.77.4,0.77.3,0.77.2,0.77.2,0.77.2,0.77.2,0.77.0,0.77.0,0.77.0,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,16.3.0,16.3.0,16.3.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
+      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
+      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.1.0,2.1.0,2.1.0,2.0.4,2.0.4,2.0.4,2.0.4,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
+      ,,,,,,,,,,,,,,,,,,,,,,
+      COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,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,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
+      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      `Flang <https://github.com/ROCm/flang>`_,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`llvm-project <llvm-project:index>`,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      ,,,,,,,,,,,,,,,,,,,,,,
+      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,
+      :doc:`AMD CLR <hip:understand/amd_clr>`,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      :doc:`HIP <hip:index>`,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
+      :doc:`ROCr Runtime <rocr-runtime:index>`,1.18.0,1.18.0,1.18.0,1.18.0,1.15.0,1.15.0,1.15.0,1.15.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0

docs/compatibility/compatibility-matrix.rst

@@ -1,111 +1,218 @@
-****************************************
-ROCm |ROCM_VERSION| compatibility matrix
-****************************************
+.. meta::
+    :description: ROCm compatibility matrix
+    :keywords: GPU, architecture, hardware, compatibility, system, requirements, components, libraries
 
-To plan your ROCm |ROCM_VERSION| installation, use the following selector to
-view ROCm compatibility and system requirements information for your AMD
-hardware configuration. For installation instructions, see
-:doc:`/install/rocm`.
+**************************************************************************************
+Compatibility matrix
+**************************************************************************************
 
-.. include:: ./includes/selector.rst
+Use this matrix to view the ROCm compatibility and system requirements across successive major and minor releases.
 
-----
+You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-rocm-compatibility-matrix>`.
 
-Hardware, software, and firmware requirements
-=============================================
+GPUs listed in the following table support compute workloads (no display
+information or graphics). If you’re using ROCm with AMD Radeon GPUs or Ryzen APUs for graphics
+workloads, see the :doc:`Use ROCm on Radeon and Ryzen <radeon:index>` to verify
+compatibility and system requirements.
 
-ROCm depends on a coordinated stack of compatible firmware, driver, and user
-space components. Maintaining version alignment between these layers ensures
-expected GPU operation and performance, especially for AMD data center products.
-Future preview releases will expand hardware and operating system coverage.
+.. |br| raw:: html
 
-ROCm 7.10.0 enables support for primarily compute workloads. Future releases
-will support mixed workloads (compute and graphics).
+   <br/>
 
-.. selected:: os=ubuntu os=rhel os=sles
+.. container:: format-big-table
 
-   .. selected:: fam=radeon-pro fam=radeon
+  .. csv-table::
+      :header: "ROCm Version", "7.1.1", "7.1.0", "6.4.0"
+      :stub-columns: 1
 
-      If you’re interested in testing AMD Radeon™ GPUs with preview support for
-      graphics use cases with AMD ROCm 7.10.0, install Radeon Software for Linux
-      version 25.30.1 from `Linux Drivers for AMD Radeon and Radeon PRO
-      Graphics <https://www.amd.com/en/support/download/linux-drivers.html>`__.
+      :ref:`Operating systems & kernels <OS-kernel-versions>` [#os-compatibility]_,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.2
+      ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5
+      ,"RHEL 10.1, 10.0,  9.7, |br| 9.6, 9.4","RHEL 10.0, 9.6, 9.4","RHEL 9.5, 9.4"
+      ,RHEL 8.10,RHEL 8.10,RHEL 8.10
+      ,SLES 15 SP7,SLES 15 SP7,SLES 15 SP6
+      ,"Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 9, 8"
+      ,"Debian 13, 12","Debian 13, 12",Debian 12
+      ,,,Azure Linux 3.0
+      ,Rocky Linux 9,Rocky Linux 9,
+      ,.. _architecture-support-compatibility-matrix:,,
+      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,CDNA4,
+      ,CDNA3,CDNA3,CDNA3
+      ,CDNA2,CDNA2,CDNA2
+      ,CDNA,CDNA,CDNA
+      ,RDNA4,RDNA4,
+      ,RDNA3,RDNA3,RDNA3
+      ,RDNA2,RDNA2,RDNA2
+      ,.. _gpu-support-compatibility-matrix:,,
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>` [#gpu-compatibility]_,gfx950,gfx950,
+      ,gfx1201,gfx1201,
+      ,gfx1200,gfx1200,
+      ,gfx1101,gfx1101,
+      ,gfx1100,gfx1100,gfx1100
+      ,gfx1030,gfx1030,gfx1030
+      ,gfx942,gfx942,gfx942
+      ,gfx90a,gfx90a,gfx90a
+      ,gfx908,gfx908,gfx908
+      ,,,
+      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix:,,
+      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.9, 2.8, 2.7","2.8, 2.7, 2.6","2.6, 2.5, 2.4, 2.3"
+      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.18.1, 2.17.1, 2.16.2"
+      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.7.1,0.7.1,0.4.35
+      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,2.4.0
+      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat]_,N/A,N/A,b5997
+      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.1,1.22.0,1.20.0
+      ,,,
+      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
+      `UCC <https://github.com/ROCm/ucc>`_,>=1.4.0,>=1.4.0,>=1.3.0
+      `UCX <https://github.com/ROCm/ucx>`_,>=1.17.0,>=1.17.0,>=1.15.0
+      ,,,
+      THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix:,,
+      Thrust,2.8.5,2.8.5,2.5.0
+      CUB,2.8.5,2.8.5,2.5.0
+      ,,,
+      DRIVER & USER SPACE [#kfd_support]_,.. _kfd-userspace-support-compatibility-matrix:,,
+      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.20.1, 30.20.0 [#mi325x_KVM]_, |br| 30.10.2, 30.10.1 [#driver_patch]_, |br| 30.10, 6.4.x","30.20.0 [#mi325x_KVM]_, 30.10.2, |br| 30.10.1 [#driver_patch]_, 30.10, 6.4.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
+      :doc:`MIGraphX <amdmigraphx:index>`,2.14.0,2.14.0,2.12.0
+      :doc:`MIOpen <miopen:index>`,3.5.1,3.5.1,3.4.0
+      :doc:`MIVisionX <mivisionx:index>`,3.4.0,3.4.0,3.2.0
+      :doc:`rocAL <rocal:index>`,2.4.0,2.4.0,2.2.0
+      :doc:`rocDecode <rocdecode:index>`,1.4.0,1.4.0,0.10.0
+      :doc:`rocJPEG <rocjpeg:index>`,1.2.0,1.2.0,0.8.0
+      :doc:`rocPyDecode <rocpydecode:index>`,0.7.0,0.7.0,0.3.1
+      :doc:`RPP <rpp:index>`,2.1.0,2.1.0,1.9.10
+      ,,,
+      COMMUNICATION,.. _commlibs-support-compatibility-matrix:,,
+      :doc:`RCCL <rccl:index>`,2.27.7,2.27.7,2.22.3
+      :doc:`rocSHMEM <rocshmem:index>`,3.1.0,3.0.0,2.0.0
+      ,,,
+      MATH LIBS,.. _mathlibs-support-compatibility-matrix:,,
+      `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0
+      :doc:`hipBLAS <hipblas:index>`,3.1.0,3.1.0,2.4.0
+      :doc:`hipBLASLt <hipblaslt:index>`,1.1.0,1.1.0,0.12.0
+      :doc:`hipFFT <hipfft:index>`,1.0.21,1.0.21,1.0.18
+      :doc:`hipfort <hipfort:index>`,0.7.1,0.7.1,0.6.0
+      :doc:`hipRAND <hiprand:index>`,3.1.0,3.1.0,2.12.0
+      :doc:`hipSOLVER <hipsolver:index>`,3.1.0,3.1.0,2.4.0
+      :doc:`hipSPARSE <hipsparse:index>`,4.1.0,4.1.0,3.2.0
+      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.5,0.2.5,0.2.3
+      :doc:`rocALUTION <rocalution:index>`,4.0.1,4.0.1,3.2.2
+      :doc:`rocBLAS <rocblas:index>`,5.1.1,5.1.0,4.4.0
+      :doc:`rocFFT <rocfft:index>`,1.0.35,1.0.35,1.0.32
+      :doc:`rocRAND <rocrand:index>`,4.1.0,4.1.0,3.3.0
+      :doc:`rocSOLVER <rocsolver:index>`,3.31.0,3.31.0,3.28.0
+      :doc:`rocSPARSE <rocsparse:index>`,4.1.0,4.1.0,3.4.0
+      :doc:`rocWMMA <rocwmma:index>`,2.1.0,2.0.0,1.7.0
+      :doc:`Tensile <tensile:src/index>`,4.44.0,4.44.0,4.43.0
+      ,,,
+      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix:,,
+      :doc:`hipCUB <hipcub:index>`,4.1.0,4.1.0,3.4.0
+      :doc:`hipTensor <hiptensor:index>`,2.0.0,2.0.0,1.5.0
+      :doc:`rocPRIM <rocprim:index>`,4.1.0,4.1.0,3.4.0
+      :doc:`rocThrust <rocthrust:index>`,4.1.0,4.1.0,3.3.0
+      ,,,
+      SUPPORT LIBS,,,
+      `hipother <https://github.com/ROCm/hipother>`_,7.1.52802,7.1.25424,6.4.43482
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.1.1,7.1.0,6.4.0
+      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr]_,N/A [#ROCT-rocr]_,N/A [#ROCT-rocr]_
+      ,,,
+      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix:,,
+      :doc:`AMD SMI <amdsmi:index>`,26.2.0,26.1.0,25.3.0
+      :doc:`ROCm Data Center Tool <rdc:index>`,1.2.0,1.2.0,0.3.0
+      :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.8.0,7.8.0,7.5.0
+      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.3.0,1.2.0,1.1.0
+      ,,,
+      PERFORMANCE TOOLS,,,
+      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,2.6.0,1.4.0
+      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.3.1,3.3.0,3.1.0
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.2.1,1.2.0,1.0.0
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70101,2.0.70100,2.0.60400
+      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.0.0,1.0.0,0.6.0
+      :doc:`ROCTracer <roctracer:index>`,4.1.70101,4.1.70100,4.1.60400
+      ,,,
+      DEVELOPMENT TOOLS,,,
+      :doc:`HIPIFY <hipify:index>`,20.0.0,20.0.0,19.0.0
+      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.4,0.77.4,0.77.2
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,16.3.0,15.2.0
+      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.5.0,0.4.0
+      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.1.0,2.0.4
+      ,,,
+      COMPILERS,.. _compilers-support-compatibility-matrix:,,
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A
+      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1
+      `Flang <https://github.com/ROCm/flang>`_,20.0.025444,20.0.025425,19.0.0.25133
+      :doc:`llvm-project <llvm-project:index>`,20.0.025444,20.0.025425,19.0.0.25133
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,20.0.025444,20.0.025425,19.0.0.25133
+      ,,,
+      RUNTIMES,.. _runtime-support-compatibility-matrix:,,
+      :doc:`AMD CLR <hip:understand/amd_clr>`,7.1.52802,7.1.25424,6.4.43482
+      :doc:`HIP <hip:index>`,7.1.52802,7.1.25424,6.4.43482
+      `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0
+      :doc:`ROCr Runtime <rocr-runtime:index>`,1.18.0,1.18.0,1.15.0
 
-   .. selected:: fam=ryzen
+.. rubric:: Footnotes
 
-      If you're interested in testing AMD Ryzen™ APUs with preview support for
-      graphics use cases with AMD ROCm 7.10.0, use the inbox graphics drivers of
-      Ubuntu 24.04.3.
+.. [#os-compatibility] Some operating systems are supported on limited GPUs. For detailed information, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-operating-systems>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-operating-systems>`__.
+.. [#gpu-compatibility] Some GPUs have limited operating system support. For detailed information, see the latest :ref:`supported_GPUs`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-gpus>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-gpus>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-gpus>`__.
+.. [#dgl_compat] DGL is only supported on ROCm 7.0.0, ROCm 6.4.3 and ROCm 6.4.0.
+.. [#llama-cpp_compat] llama.cpp is only supported on ROCm 7.0.0 and ROCm 6.4.x.
+.. [#mi325x_KVM] For AMD Instinct MI325X KVM SR-IOV users, do not use AMD GPU Driver (amdgpu) 30.20.0.
+.. [#driver_patch] AMD GPU Driver (amdgpu) 30.10.1 is a quality release that resolves an issue identified in the 30.10 release. There are no other significant changes or feature additions in ROCm 7.0.1 from ROCm 7.0.0. AMD GPU Driver (amdgpu) 30.10.1 is compatible with ROCm 7.0.1 and ROCm 7.0.0.
+.. [#kfd_support] As of ROCm 6.4.0, forward and backward compatibility between the AMD GPU Driver (amdgpu) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported 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 AMD GPU Driver support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
+.. [#ROCT-rocr] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
 
-.. include:: ./includes/system-instinct.rst
+.. _OS-kernel-versions:
 
-.. include:: ./includes/system-radeon-pro.rst
+Operating systems, kernel and Glibc versions
+*********************************************
 
-.. include:: ./includes/system-radeon.rst
-
-.. include:: ./includes/system-ryzen.rst
-
-----
-
-.. _rocm-compat-frameworks:
-
-Deep learning frameworks
-========================
-
-ROCm |ROCM_VERSION| provides optimized support for popular deep learning
-frameworks. The following table lists supported frameworks and their supported
-versions.
-
-.. _rocm-compat-pytorch:
-
-.. matrix::
-
-   .. matrix-head::
-
-      .. matrix-row::
-
-         .. matrix-cell:: Framework
-            :header:
-
-         .. matrix-cell:: Supported versions
-            :header:
-
-   .. matrix-row::
-      :show-when: fam=instinct fam=ryzen
-
-      .. matrix-cell:: PyTorch
-
-      .. matrix-cell:: 2.9.1, 2.8.0, 2.7.1
-         :show-when: os=ubuntu os=rhel os=sles
-
-      .. matrix-cell:: 2.9.1
-         :show-when: os=windows
-
-   .. matrix-row::
-      :show-when: fam=radeon fam=radeon-pro
-
-      .. matrix-cell:: PyTorch
-
-      .. matrix-cell:: 2.9.1
-
-For installation instructions, see :ref:`pip-install-pytorch`.
-
-.. _rocm-compat-python:
+For detailed information on operating system supported on ROCm 7.1.1 and associated Kernel and Glibc version, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-operating-systems>`__.
 
 .. note::
 
-   ROCm |ROCM_VERSION| is compatible with Python versions **3.11**, **3.12**,
-   and **3.13**.
+  * See `Red Hat Enterprise Linux Release Dates <https://access.redhat.com/articles/3078>`_ to learn about the specific kernel versions supported on Red Hat Enterprise Linux (RHEL).
+  * See `List of SUSE Linux Enterprise Server kernel <https://www.suse.com/support/kb/doc/?id=000019587>`_ to learn about the specific kernel version supported on SUSE Linux Enterprise Server (SLES).
+..
+   Footnotes and ref anchors in below historical tables should be appended with "-past-60", to differentiate from the
+   footnote references in the above, latest, compatibility matrix.  It also allows to easily find & replace.
+   An easy way to work is to download the historical.CSV file, and update open it in excel. Then when content is ready,
+   delete the columns you don't need, to build the current compatibility matrix to use in above table.  Find & replace all
+   instances of "-past-60" to make it ready for above table.
 
-----
 
-ROCm Core SDK components
-========================
+.. _past-rocm-compatibility-matrix:
 
-The following table lists core components included in the ROCm |ROCM_VERSION|
-release. Expect future releases in this stream to expand the list of
-components.
+Past versions of ROCm compatibility matrix
+***************************************************
 
-.. include:: ./includes/core-sdk-components-linux.rst
+Expand for full historical view of:
 
-.. include:: ./includes/core-sdk-components-windows.rst
+.. dropdown:: ROCm 6.0 - Present
+
+   You can `download the entire .csv <../downloads/compatibility-matrix-historical-6.0.csv>`_ for offline reference.
+
+   .. csv-table::
+      :file: compatibility-matrix-historical-6.0.csv
+      :header-rows: 1
+      :stub-columns: 1
+
+   .. rubric:: Footnotes
+
+   .. [#os-compatibility-past-60] Some operating systems are supported on limited GPUs. For detailed information, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-operating-systems>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-operating-systems>`__.
+   .. [#gpu-compatibility-past-60] Some GPUs have limited operating system support. For detailed information, see the latest :ref:`supported_GPUs`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-gpus>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-gpus>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-gpus>`__.
+   .. [#tf-mi350-past-60] TensorFlow 2.17.1 is not supported on AMD Instinct MI350 Series GPUs. Use TensorFlow 2.19.1 or 2.18.1 with MI350 Series GPUs instead.
+   .. [#verl_compat-past-60] verl is only supported on ROCm 7.0.0 and 6.2.0.
+   .. [#stanford-megatron-lm_compat-past-60] Stanford Megatron-LM is only supported on ROCm 6.3.0.
+   .. [#dgl_compat-past-60] DGL is only supported on ROCm 7.0.0, ROCm 6.4.3 and ROCm 6.4.0.
+   .. [#megablocks_compat-past-60] Megablocks is only supported on ROCm 6.3.0.
+   .. [#ray_compat-past-60] Ray is only supported on ROCm 7.0.0 and 6.4.1.
+   .. [#llama-cpp_compat-past-60] llama.cpp is only supported on ROCm 7.0.0 and 6.4.x.
+   .. [#flashinfer_compat-past-60] FlashInfer is only supported on ROCm 6.4.1.
+   .. [#mi325x_KVM-past-60] For AMD Instinct MI325X KVM SR-IOV users, do not use AMD GPU Driver (amdgpu) 30.20.0.
+   .. [#driver_patch-past-60] AMD GPU Driver (amdgpu) 30.10.1 is a quality release that resolves an issue identified in the 30.10 release. There are no other significant changes or feature additions in ROCm 7.0.1 from ROCm 7.0.0. AMD GPU Driver (amdgpu) 30.10.1 is compatible with ROCm 7.0.1 and ROCm 7.0.0.
+   .. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD GPU Driver (amdgpu) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported 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 AMD GPU Driver 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/compatibility/includes/core-sdk-components-linux.rst

@@ -1,214 +0,0 @@
-.. matrix::
-   :show-when: os=ubuntu os=rhel os=sles
-
-   .. matrix-head::
-
-      .. matrix-row::
-         :header:
-
-         .. matrix-cell:: Component group
-
-         .. matrix-cell:: Component name
-
-   .. matrix-row::
-
-      .. matrix-cell:: Runtimes and compilers
-         :rowspan: 5
-
-      .. matrix-cell::
-
-         `HIP <https://github.com/ROCm/rocm-systems/tree/therock-7.10/projects/hip>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `HIPIFY <https://github.com/ROCm/HIPIFY/tree/therock-7.10>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `LLVM <https://github.com/ROCm/llvm-project/tree/therock-7.10>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `ROCr Runtime <https://github.com/ROCm/rocm-systems/tree/therock-7.10/projects/rocr-runtime>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `SPIRV-LLVM-Translator <https://github.com/ROCm/SPIRV-LLVM-Translator/tree/therock-7.10>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Control and monitoring tools
-         :rowspan: 2
-
-      .. matrix-cell::
-
-         `AMD SMI <https://github.com/ROCm/amdsmi/tree/release/therock-7.10>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocminfo <https://github.com/ROCm/rocm-systems/tree/therock-7.10/projects/rocminfo>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Profiling and debugging tools
-         :rowspan: 3
-         :show-when: fam=instinct
-
-      .. matrix-cell:: Profiling and debugging tools
-         :rowspan: 2
-         :show-when: fam=radeon-pro fam=radeon fam=ryzen
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `ROCm Compute Profiler (rocprofiler-compute) <https://github.com/ROCm/rocm-systems/tree/therock-7.10/projects/rocprofiler-compute>`__
-
-   .. matrix-row::
-      :show-when: fam=instinct
-
-      .. matrix-cell::
-
-         `ROCprofiler-SDK <https://github.com/ROCm/rocm-systems/tree/therock-7.10/projects/rocprofiler-sdk>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Math and compute libraries
-         :rowspan: 18
-         :show-when: fam=instinct
-
-      .. matrix-cell:: Math and compute libraries
-         :rowspan: 17
-         :show-when: fam=radeon-pro fam=radeon fam=ryzen
-
-      .. matrix-cell::
-
-         `rocBLAS <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocblas>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipBLAS <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipblas>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipBLASLt <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipblaslt>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocFFT <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocfft>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipFFT <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipfft>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocRAND <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocrand>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipRAND <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hiprand>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocSOLVER <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocsolver>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipSOLVER <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipsolver>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocSPARSE <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocsparse>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipSPARSE <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipsparse>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipSPARSELt <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipsparselt>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocPRIM <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocprim>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocThrust <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocthrust>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipCUB <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipcub>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocWMMA <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocwmma>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `Composable Kernel <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/composablekernel>`__ (partial, limited support)
-
-   .. matrix-row::
-      :show-when: fam=instinct
-
-      .. matrix-cell::
-
-         `MIOpen <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/miopen>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Communication librarires
-
-      .. matrix-cell::
-
-         `RCCL <https://github.com/ROCm/rccl/tree/release/therock-7.10>`__
-   .. matrix-row::
-
-      .. matrix-cell:: Support libraries
-
-      .. matrix-cell::
-
-         `ROCm CMake <https://github.com/ROCm/rocm-cmake/tree/therock-7.10>`__

docs/compatibility/includes/core-sdk-components-windows.rst

@@ -1,139 +0,0 @@
-.. matrix::
-   :show-when: os=windows
-
-   .. matrix-head::
-
-      .. matrix-row::
-         :header:
-
-         .. matrix-cell:: Component group
-
-         .. matrix-cell:: Component name
-
-   .. matrix-row::
-
-      .. matrix-cell:: Runtimes and compilers
-         :rowspan: 3
-
-      .. matrix-cell::
-
-         `HIP <https://github.com/ROCm/rocm-systems/tree/therock-7.10/projects/hip>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `HIPIFY <https://github.com/ROCm/HIPIFY/tree/therock-7.10>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `LLVM <https://github.com/ROCm/llvm-project/tree/therock-7.10>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Control and monitoring tools
-
-      .. matrix-cell:: hipinfo
-
-   .. matrix-row::
-
-      .. matrix-cell:: Math and compute libraries
-         :rowspan: 15
-
-      .. matrix-cell::
-
-         `rocBLAS <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocblas>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipBLAS <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipblas>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipBLASLt <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipblaslt>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocFFT <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocfft>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipFFT <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipfft>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocRAND <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocrand>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipRAND <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocsolver>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocSOLVER <https://github.com/ROCm/rocm-libraries/tree/therock-7.9.0/projects/rocsolver>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipSOLVER <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipsolver>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocSPARSE <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocsparse>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipSPARSE <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipsparse>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocPRIM <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocprim>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocThrust <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocthrust>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `hipCUB <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/hipcub>`__
-
-   .. matrix-row::
-
-      .. matrix-cell::
-
-         `rocWMMA <https://github.com/ROCm/rocm-libraries/tree/therock-7.10/projects/rocwmma>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Support libraries
-
-      .. matrix-cell::
-
-         `ROCm CMake <https://github.com/ROCm/rocm-cmake/tree/therock-7.10>`__

docs/compatibility/includes/selector.rst

@@ -1,128 +0,0 @@
-.. selector:: AMD device family
-   :key: fam
-
-   .. selector-option:: Instinct
-      :value: instinct
-      :width: 3
-
-   .. selector-option:: Radeon PRO
-      :value: radeon-pro
-      :width: 3
-
-   .. selector-option:: Radeon RX
-      :value: radeon
-      :width: 3
-
-   .. selector-option:: Ryzen AI
-      :value: ryzen
-      :width: 3
-
-.. selector:: Instinct GPU
-   :key: gfx
-   :show-when: fam=instinct
-
-   .. selector-info:: https://www.amd.com/en/products/accelerators/instinct.html
-
-   .. selector-option:: Instinct MI355X<br>Instinct MI350X
-      :value: 950
-      :width: 4
-
-   .. selector-option:: Instinct MI325X<br>Instinct MI300X<br>Instinct MI300A
-      :value: 942
-      :width: 4
-
-   .. selector-option:: Instinct MI250X<br>Instinct MI250<br>Instinct MI210
-      :value: 90a
-      :width: 4
-
-.. selector:: Radeon PRO GPU
-   :key: gfx
-   :show-when: fam=radeon-pro
-
-   .. selector-info:: https://www.amd.com/en/products/graphics/workstations.html
-
-   .. selector-option:: Radeon PRO W7900D<br>Radeon PRO W7900<br>Radeon PRO W7800 48GB<br>Radeon PRO W7800
-      :value: 1100
-      :width: 6
-
-   .. selector-option:: Radeon PRO W7700
-      :value: 1101
-      :width: 6
-
-.. selector:: Radeon RX GPU
-   :key: gfx
-   :show-when: fam=radeon
-
-   .. selector-info:: https://www.amd.com/en/products/graphics/desktops/radeon.html
-
-   .. selector-option:: Radeon RX 7900 XTX<br>Radeon RX 7900 XT<br>Radeon RX 7900 GRE
-      :value: 1100
-
-   .. selector-option:: Radeon RX 7800 XT<br>Radeon RX 7700 XT
-      :value: 1101
-
-.. selector:: Ryzen AI APU
-   :key: gfx
-   :show-when: fam=ryzen
-
-   .. selector-info:: https://www.amd.com/en/products/processors/workstations/mobile.html
-
-   .. selector-option:: Ryzen AI Max+ PRO 395<br>Ryzen AI Max PRO 390, 385, 380<br>Ryzen AI Max+ 395<br>Ryzen AI Max 390, 385
-      :value: 1151
-      :width: 6
-
-   .. selector-option:: Ryzen AI 9 HX 375<br>Ryzen AI 9 HX 370<br>Ryzen AI 9 365
-      :value: 1150
-      :width: 6
-
-.. selector:: Operating system
-   :key: os
-   :show-when: fam=instinct
-
-   .. selector-option:: Ubuntu
-      :value: ubuntu
-      :icon: fab fa-ubuntu fa-lg
-      :width: 4
-
-   .. selector-option:: RHEL
-      :value: rhel
-      :icon: fab fa-redhat fa-lg
-      :width: 4
-
-   .. selector-option:: SLES
-      :value: sles
-      :icon: fab fa-suse fa-lg
-      :width: 4
-
-.. selector:: Operating system
-   :key: os
-   :show-when: fam=radeon-pro fam=radeon
-
-   .. selector-option:: Ubuntu
-      :value: ubuntu
-      :icon: fab fa-ubuntu fa-lg
-      :width: 4
-
-   .. selector-option:: RHEL
-      :value: rhel
-      :icon: fab fa-redhat fa-lg
-      :width: 4
-
-   .. selector-option:: Windows
-      :value: windows
-      :icon: fab fa-windows fa-lg
-      :width: 4
-
-.. selector:: Operating system
-   :key: os
-   :show-when: fam=ryzen
-
-   .. selector-option:: Ubuntu
-      :value: ubuntu
-      :icon: fab fa-ubuntu fa-lg
-      :width: 6
-
-   .. selector-option:: Windows
-      :value: windows
-      :icon: fab fa-windows fa-lg
-      :width: 6

docs/compatibility/includes/system-instinct.rst

@@ -1,147 +0,0 @@
-.. matrix::
-   :show-when: fam=instinct
-
-   .. matrix-row::
-      :show-when: gfx=950
-
-      .. matrix-cell:: AMD Instinct MI350 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Instinct MI355X <https://www.amd.com/en/products/accelerators/instinct/mi350/mi355x.html>`__
-
-         `Instinct MI350X <https://www.amd.com/en/products/accelerators/instinct/mi350/mi350x.html>`__
-
-   .. matrix-row::
-      :show-when: gfx=942
-
-      .. matrix-cell:: AMD Instinct MI300 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Instinct MI325X <https://www.amd.com/en/products/accelerators/instinct/mi300/mi325x.html>`__
-
-         `Instinct MI300X <https://www.amd.com/en/products/accelerators/instinct/mi300/mi300x.html>`__
-
-         `Instinct MI300A <https://www.amd.com/en/products/accelerators/instinct/mi300/mi300a.html>`__
-
-   .. matrix-row::
-      :show-when: gfx=90a
-
-      .. matrix-cell:: AMD Instinct MI200 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Instinct MI250X <https://www.amd.com/en/products/accelerators/instinct/mi200/mi250x.html>`__
-
-         `Instinct MI250 <https://www.amd.com/en/products/accelerators/instinct/mi200/mi250.html>`__
-
-         `Instinct MI210 <https://www.amd.com/en/products/accelerators/instinct/mi200/mi210.html>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Architecture
-         :header:
-
-      .. matrix-cell:: CDNA 4
-         :show-when: gfx=950
-
-      .. matrix-cell:: CDNA 3
-         :show-when: gfx=942
-
-      .. matrix-cell:: CDNA 2
-         :show-when: gfx=90a
-
-   .. matrix-row::
-
-      .. matrix-cell:: LLVM target
-         :header:
-
-      .. matrix-cell:: gfx950
-         :show-when: gfx=950
-
-      .. matrix-cell:: gfx942
-         :show-when: gfx=942
-
-      .. matrix-cell:: gfx90a
-         :show-when: gfx=90a
-
-   .. matrix-row::
-      :show-when: os=ubuntu
-
-      .. matrix-cell:: Supported Ubuntu versions
-         :header:
-
-      .. matrix-cell::
-
-         Ubuntu 24.04.3 (GA kernel: 6.8)
-
-         Ubuntu 22.04.5 (GA kernel: 5.15)
-
-   .. matrix-row::
-      :show-when: os=rhel
-
-      .. matrix-cell:: Supported Red Hat Enterprise Linux versions
-         :header:
-
-      .. matrix-cell::
-
-	 RHEL 10.1 (kernel: 6.12.0-124)
-
-	 RHEL 10.0 (kernel: 6.12.0-55)
-
-	 RHEL 9.7 (kernel: 5.14.0-611)
-
-	 RHEL 9.6 (kernel: 5.14.0-570)
-
-	 RHEL 8.10 (kernel: 4.18.0-553)
-
-   .. matrix-row::
-      :show-when: os=sles
-
-      .. matrix-cell:: Supported SUSE Linux Enterprise Server version
-         :header:
-
-      .. matrix-cell:: SLES 15.7 (kernel: 6.4.0-150700.51)
-
-   .. matrix-row::
-
-      .. matrix-cell:: Supported AMD GPU Driver (amdgpu) versions
-         :header:
-
-      .. matrix-cell:: 
-
-         `30.20.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.20.0/>`__,
-         `30.10.2 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10.2/>`__,
-         `30.10.1 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10.1/>`__,
-         `30.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10/>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Supported PLDM bundle (firmware) versions
-         :header:
-
-      .. matrix-cell:: 01.25.15.04, 01.25.13.09
-         :show-when: gfx=950
-
-      .. matrix-cell::
-         :show-when: gfx=942
-
-         **MI325X** 01.25.04.02, 01.25.03.03
-
-         **MI300X** 01.25.05.00 (or later), 01.25.03.12
-
-         **MI300A** BKC 26, 25
-
-      .. matrix-cell::
-         :show-when: gfx=90a
-
-         **MI250X** IFWI 47 (or later)
-
-         **MI250** Maintenance update 5 with IFWI 75 (or later)
-
-         **MI210** Maintenance update 5 with IFWI 75 (or later)
-

docs/compatibility/includes/system-radeon-pro.rst

@@ -1,111 +0,0 @@
-.. matrix::
-   :show-when: fam=radeon-pro
-
-   .. matrix-row::
-      :show-when: gfx=1100
-
-      .. matrix-cell:: AMD Radeon PRO W7000 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Radeon PRO W7900D <https://www.amd.com/en/support/downloads/drivers.html/graphics/radeon-pro/radeon-pro-w7000-series/amd-radeon-pro-w7900d.html>`__
-
-         `Radeon PRO W7900 <https://www.amd.com/en/products/graphics/workstations/radeon-pro/w7900.html>`__
-
-         `Radeon PRO W7800 48GB <https://www.amd.com/en/products/graphics/workstations/radeon-pro/w7800-48gb.html>`__
-
-         `Radeon PRO W7800 <https://www.amd.com/en/products/graphics/workstations/radeon-pro/w7800.html>`__
-
-   .. matrix-row::
-      :show-when: gfx=1101
-
-      .. matrix-cell:: AMD Radeon PRO W7000 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Radeon PRO W7700 <https://www.amd.com/en/products/graphics/workstations/radeon-pro/w7700.html>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Architecture
-         :header:
-
-      .. matrix-cell:: RDNA 3
-
-   .. matrix-row::
-
-      .. matrix-cell:: LLVM target
-         :header:
-
-      .. matrix-cell:: gfx1101
-         :show-when: gfx=1101
-
-      .. matrix-cell:: gfx1100
-         :show-when: gfx=1100
-
-   .. matrix-row::
-      :show-when: os=ubuntu
-
-      .. matrix-cell:: Supported Ubuntu versions
-         :header:
-
-      .. matrix-cell::
-
-         24.04.3 (GA kernel: 6.8)
-
-         22.04.5 (GA kernel: 5.15)
-
-   .. matrix-row::
-      :show-when: os=rhel
-
-      .. matrix-cell:: Supported RHEL versions
-         :header:
-
-      .. matrix-cell:: 10.1, 10.0
-
-   .. matrix-row::
-      :show-when: os=windows
-
-      .. matrix-cell:: Supported Windows version
-         :header:
-
-      .. matrix-cell:: Windows 11 25H2
-
-   .. matrix-row::
-
-      .. matrix-cell:: Supported AMD GPU Driver (amdgpu) versions
-         :header:
-
-      .. matrix-cell:: 
-
-         `30.20.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.20.0/>`__,
-         `30.10.2 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10.2/>`__,
-         `30.10.1 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10.1/>`__,
-         `30.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10/>`__
-
-   .. matrix-row::
-      :show-when: os=ubuntu os=rhel os=sles
-
-      .. matrix-cell:: Supported Radeon Software for Linux version
-         :header:
-
-      .. matrix-cell::
-
-         `25.30.1 <https://www.amd.com/en/support/download/linux-drivers.html#linux-for-radeon-pro>`__
-
-   .. matrix-row::
-      :show-when: os=windows
-
-      .. matrix-cell:: Supported Adrenalin Driver version
-         :header:
-
-      .. matrix-cell::
-
-         `25.11.1 <https://www.amd.com/en/resources/support-articles/release-notes/RN-RAD-WIN-25-11-1.html>`__
-         (generally recommended)
-
-         `25.20.01.17 <https://www.amd.com/en/resources/support-articles/release-notes/RN-AMDGPU-WINDOWS-PYTORCH-7-1-1.html>`__
-         (recommended for ComfyUI)
-

docs/compatibility/includes/system-radeon.rst

@@ -1,112 +0,0 @@
-.. matrix::
-   :show-when: fam=radeon
-
-   .. matrix-row::
-      :show-when: gfx=1100
-
-      .. matrix-cell:: AMD Radeon RX 7000 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Radeon RX 7900 XTX <https://www.amd.com/en/products/graphics/desktops/radeon/7000-series/amd-radeon-rx-7900xtx.html>`__
-
-         `Radeon RX 7900 XT <https://www.amd.com/en/products/graphics/desktops/radeon/7000-series/amd-radeon-rx-7900xt.html>`__
-
-         `Radeon RX 7900 GRE <https://www.amd.com/en/products/graphics/desktops/radeon/7000-series/amd-radeon-rx-7900-gre.html>`__
-
-   .. matrix-row::
-      :show-when: gfx=1101
-
-      .. matrix-cell:: AMD Radeon RX 7000 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Radeon RX 7800 XT <https://www.amd.com/en/products/graphics/desktops/radeon/7000-series/amd-radeon-rx-7800-xt.html>`__
-
-         `Radeon RX 7700 XT <https://www.amd.com/en/products/graphics/desktops/radeon/7000-series/amd-radeon-rx-7700-xt.html>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Architecture
-         :header:
-
-      .. matrix-cell:: RDNA 3
-         :show-when: gfx=1101 gfx=1100
-
-   .. matrix-row::
-
-      .. matrix-cell:: LLVM target
-         :header:
-
-      .. matrix-cell:: gfx1100
-         :show-when: gfx=1100
-
-      .. matrix-cell:: gfx1101
-         :show-when: gfx=1101
-
-   .. matrix-row::
-      :show-when: os=ubuntu
-
-      .. matrix-cell:: Supported Ubuntu versions
-         :header:
-
-      .. matrix-cell::
-
-         24.04.3 (GA kernel: 6.8)
-
-         22.04.5 (GA kernel: 5.15)
-
-   .. matrix-row::
-      :show-when: os=rhel
-
-      .. matrix-cell:: Supported RHEL versions
-         :header:
-
-      .. matrix-cell:: 10.1, 10.0
-
-   .. matrix-row::
-      :show-when: os=windows
-
-      .. matrix-cell:: Supported Windows version
-         :header:
-
-      .. matrix-cell:: Windows 11 25H2
-
-   .. matrix-row::
-
-      .. matrix-cell:: Supported AMD GPU Driver (amdgpu) versions
-         :header:
-
-      .. matrix-cell:: 
-
-         `30.20.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.20.0/>`__,
-         `30.10.2 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10.2/>`__,
-         `30.10.1 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10.1/>`__,
-         `30.10.0 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/docs-30.10/>`__
-
-   .. matrix-row::
-      :show-when: os=ubuntu os=rhel os=sles
-
-      .. matrix-cell:: Supported Radeon Software for Linux version
-         :header:
-
-      .. matrix-cell::
-
-         `25.30.1 <https://www.amd.com/en/support/download/linux-drivers.html#linux-for-radeon-pro>`__
-
-   .. matrix-row::
-      :show-when: os=windows
-
-      .. matrix-cell:: Supported Adrenalin Driver version
-         :header:
-
-      .. matrix-cell::
-
-         `25.11.1 <https://www.amd.com/en/resources/support-articles/release-notes/RN-RAD-WIN-25-11-1.html>`__
-         (generally recommended)
-
-         `25.20.01.17 <https://www.amd.com/en/resources/support-articles/release-notes/RN-AMDGPU-WINDOWS-PYTORCH-7-1-1.html>`__
-         (recommended for ComfyUI)
-

docs/compatibility/includes/system-ryzen.rst

@@ -1,103 +0,0 @@
-.. matrix::
-   :show-when: fam=ryzen
-
-   .. matrix-row::
-      :show-when: gfx=1151
-
-      .. matrix-cell:: AMD Ryzen AI Max PRO 300 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Ryzen AI Max+ PRO 395 <https://www.amd.com/en/products/processors/laptop/ryzen-pro/ai-max-pro-300-series/amd-ryzen-ai-max-plus-pro-395.html>`__
-
-         `Ryzen AI Max PRO 390 <https://www.amd.com/en/products/processors/laptop/ryzen-pro/ai-max-pro-300-series/amd-ryzen-ai-max-pro-390.html>`__
-
-         `Ryzen AI Max PRO 385 <https://www.amd.com/en/products/processors/laptop/ryzen-pro/ai-max-pro-300-series/amd-ryzen-ai-max-pro-385.html>`__
-
-         `Ryzen AI Max PRO 380 <https://www.amd.com/en/products/processors/laptop/ryzen-pro/ai-max-pro-300-series/amd-ryzen-ai-max-pro-380.html>`__
-
-   .. matrix-row::
-      :show-when: gfx=1151
-
-      .. matrix-cell:: AMD Ryzen AI Max 300 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Ryzen AI Max+ 395 <https://www.amd.com/en/products/processors/laptop/ryzen/ai-300-series/amd-ryzen-ai-max-plus-395.html>`__
-
-         `Ryzen AI Max 390 <https://www.amd.com/en/products/processors/laptop/ryzen/ai-300-series/amd-ryzen-ai-max-390.html>`__
-
-         `Ryzen AI Max 385 <https://www.amd.com/en/products/processors/laptop/ryzen/ai-300-series/amd-ryzen-ai-max-385.html>`__
-
-   .. matrix-row::
-      :show-when: gfx=1150
-
-      .. matrix-cell:: AMD Ryzen AI 300 Series
-         :header:
-
-      .. matrix-cell::
-
-         `Ryzen AI 9 HX 375 <https://www.amd.com/en/products/processors/laptop/ryzen/ai-300-series/amd-ryzen-ai-9-hx-375.html>`__
-
-         `Ryzen AI 9 HX 370 <https://www.amd.com/en/products/processors/laptop/ryzen/ai-300-series/amd-ryzen-ai-9-hx-370.html>`__
-
-         `Ryzen AI 9 365 <https://www.amd.com/en/products/processors/laptop/ryzen/ai-300-series/amd-ryzen-ai-9-365.html>`__
-
-   .. matrix-row::
-
-      .. matrix-cell:: Architecture
-         :header:
-
-      .. matrix-cell:: RDNA 3.5
-
-   .. matrix-row::
-
-      .. matrix-cell:: LLVM target
-         :header:
-
-      .. matrix-cell:: gfx1151
-         :show-when: gfx=1151
-
-      .. matrix-cell:: gfx1150
-         :show-when: gfx=1150
-
-   .. matrix-row::
-      :show-when: os=ubuntu
-
-      .. matrix-cell:: Supported Ubuntu versions
-         :header:
-
-      .. matrix-cell:: 24.04.3 (HWE kernel: 6.14)
-
-   .. matrix-row::
-      :show-when: os=windows
-
-      .. matrix-cell:: Supported Windows version
-         :header:
-
-      .. matrix-cell:: Windows 11 25H2
-
-   .. matrix-row::
-      :show-when: os=ubuntu
-
-      .. matrix-cell:: Supported kernel driver version
-         :header:
-
-      .. matrix-cell:: Inbox kernel driver in Ubuntu 24.04.3
-
-   .. matrix-row::
-      :show-when: os=windows
-
-      .. matrix-cell:: Supported Adrenalin Driver version
-         :header:
-
-      .. matrix-cell::
-
-         `25.11.1 <https://www.amd.com/en/resources/support-articles/release-notes/RN-RAD-WIN-25-11-1.html>`__
-         (generally recommended)
-
-         `25.20.01.17 <https://www.amd.com/en/resources/support-articles/release-notes/RN-AMDGPU-WINDOWS-PYTORCH-7-1-1.html>`__
-         (recommended for ComfyUI)
-

docs/compatibility/ml-compatibility/dgl-compatibility.rst

@@ -0,0 +1,364 @@
+:orphan:
+
+.. meta::
+    :description: Deep Graph Library (DGL) compatibility
+    :keywords: GPU, CPU, deep graph library, DGL, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+DGL compatibility
+********************************************************************************
+
+Deep Graph Library (`DGL <https://www.dgl.ai/>`__) is an easy-to-use, high-performance, and scalable 
+Python package for deep learning on graphs. DGL is framework agnostic, meaning 
+that if a deep graph model is a component in an end-to-end application, the rest of 
+the logic is implemented using PyTorch.  
+
+DGL provides a high-performance graph object that can reside on either CPUs or GPUs. 
+It bundles structural data features for better control and provides a variety of functions 
+for computing with graph objects, including efficient and customizable message passing 
+primitives for Graph Neural Networks.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of DGL is maintained in the official `https://github.com/ROCm/dgl 
+  <https://github.com/ROCm/dgl>`__ repository, which differs from the 
+  `https://github.com/dmlc/dgl <https://github.com/dmlc/dgl>`__ upstream repository.
+
+- To get started and install DGL on ROCm, use the prebuilt :ref:`Docker images <dgl-docker-compat>`, 
+  which include ROCm, DGL, and all required dependencies.
+
+  - See the :doc:`ROCm DGL installation guide <rocm-install-on-linux:install/3rd-party/dgl-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://www.dgl.ai/pages/start.html>`__ 
+    for additional context.
+
+.. _dgl-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `DGL images <https://hub.docker.com/r/rocm/dgl/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest available DGL version from the official Docker Hub. 
+Click the |docker-icon| to view the image on Docker Hub.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - DGL
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/dgl/dgl-2.4.0.amd0_rocm7.0.0_ubuntu24.04_py3.12_pytorch_2.8.0/images/sha256-943698ddf54c22a7bcad2e5b4ff467752e29e4ba6d0c926789ae7b242cbd92dd"><i class="fab fa-docker fa-lg"></i> rocm/dgl</a>
+
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
+      - `2.8.0 <https://github.com/pytorch/pytorch/releases/tag/v2.8.0>`__
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/dgl/dgl-2.4.0.amd0_rocm7.0.0_ubuntu24.04_py3.12_pytorch_2.6.0/images/sha256-b2ec286a035eb7d0a6aab069561914d21a3cac462281e9c024501ba5ccedfbf7"><i class="fab fa-docker fa-lg"></i> rocm/dgl</a>
+
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
+      - `2.6.0 <https://github.com/pytorch/pytorch/releases/tag/v2.6.0>`__
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/dgl/dgl-2.4.0.amd0_rocm7.0.0_ubuntu22.04_py3.10_pytorch_2.7.1/images/sha256-d27aee16df922ccf0bcd9107bfcb6d20d34235445d456c637e33ca6f19d11a51"><i class="fab fa-docker fa-lg"></i> rocm/dgl</a>
+
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
+      - `2.7.1 <https://github.com/pytorch/pytorch/releases/tag/v2.7.1>`__
+      - 22.04
+      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`__
+      - MI300X, MI250X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/dgl/dgl-2.4.0.amd0_rocm6.4.3_ubuntu24.04_py3.12_pytorch_2.6.0/images/sha256-f3ba6a3c9ec9f6c1cde28449dc9780e0c4c16c4140f4b23f158565fbfd422d6b"><i class="fab fa-docker fa-lg"></i> rocm/dgl</a>
+
+      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
+      - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
+      - `2.6.0 <https://github.com/pytorch/pytorch/releases/tag/v2.6.0>`__
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/dgl/dgl-2.4_rocm6.4_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-8ce2c3bcfaa137ab94a75f9e2ea711894748980f57417739138402a542dd5564"><i class="fab fa-docker fa-lg"></i> rocm/dgl</a>
+
+      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__
+      - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
+      - `2.6.0 <https://github.com/pytorch/pytorch/releases/tag/v2.6.0>`__
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/dgl/dgl-2.4_rocm6.4_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-cf1683283b8eeda867b690229c8091c5bbf1edb9f52e8fb3da437c49a612ebe4"><i class="fab fa-docker fa-lg"></i> rocm/dgl</a>
+
+      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__
+      - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
+      - `2.4.1 <https://github.com/pytorch/pytorch/releases/tag/v2.4.1>`__
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/dgl/dgl-2.4_rocm6.4_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-4834f178c3614e2d09e89e32041db8984c456d45dfd20286e377ca8635686554"><i class="fab fa-docker fa-lg"></i> rocm/dgl</a>
+
+      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__
+      - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
+      - `2.4.1 <https://github.com/pytorch/pytorch/releases/tag/v2.4.1>`__
+      - 22.04
+      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`__
+      - MI300X, MI250X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/dgl/dgl-2.4_rocm6.4_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-88740a2c8ab4084b42b10c3c6ba984cab33dd3a044f479c6d7618e2b2cb05e69"><i class="fab fa-docker fa-lg"></i> rocm/dgl</a>
+
+      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__
+      - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
+      - `2.3.0 <https://github.com/pytorch/pytorch/releases/tag/v2.3.0>`__
+      - 22.04
+      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`__
+      - MI300X, MI250X
+
+
+.. _dgl-key-rocm-libraries:
+
+Key ROCm libraries for DGL
+================================================================================
+
+DGL on ROCm depends on specific libraries that affect its features and performance.
+Using the DGL Docker container or building it with the provided Docker file or a ROCm base image is recommended.
+If you prefer to build it yourself, ensure the following dependencies are installed:
+
+.. list-table:: 
+    :header-rows: 1
+
+    * - ROCm library
+      - ROCm 7.0.0 Version
+      - ROCm 6.4.x Version
+      - Purpose
+    * - `Composable Kernel <https://github.com/ROCm/composable_kernel>`_
+      - 1.1.0
+      - 1.1.0
+      - Enables faster execution of core operations like matrix multiplication
+        (GEMM), convolutions and transformations.
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
+      - 3.0.0
+      - 2.4.0
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
+      - 1.0.0
+      - 0.12.0
+      - hipBLASLt is an extension of the hipBLAS library, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+    * - `hipCUB <https://github.com/ROCm/hipCUB>`_
+      - 4.0.0
+      - 3.4.0
+      - Provides a C++ template library for parallel algorithms for reduction,
+        scan, sort and select.
+    * - `hipFFT <https://github.com/ROCm/hipFFT>`_
+      - 1.0.20
+      - 1.0.18
+      - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
+    * - `hipRAND <https://github.com/ROCm/hipRAND>`_
+      - 3.0.0
+      - 2.12.0
+      - Provides fast random number generation for GPUs.
+    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
+      - 3.0.0
+      - 2.4.0
+      - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
+        singular value decompositions (SVD).
+    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
+      - 4.0.1
+      - 3.2.0
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+    * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
+      - 0.2.4
+      - 0.2.3
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+    * - `hipTensor <https://github.com/ROCm/hipTensor>`_
+      - 2.0.0
+      - 1.5.0
+      - Optimizes for high-performance tensor operations, such as contractions.
+    * - `MIOpen <https://github.com/ROCm/MIOpen>`_
+      - 3.5.0
+      - 3.4.0
+      - Optimizes deep learning primitives such as convolutions, pooling,
+        normalization, and activation functions.
+    * - `MIGraphX <https://github.com/ROCm/AMDMIGraphX>`_
+      - 2.13.0
+      - 2.12.0
+      - Adds graph-level optimizations, ONNX models and mixed precision support
+        and enable Ahead-of-Time (AOT) Compilation.
+    * - `MIVisionX <https://github.com/ROCm/MIVisionX>`_
+      - 3.3.0
+      - 3.2.0
+      - Optimizes acceleration for computer vision and AI workloads like
+        preprocessing, augmentation, and inferencing.
+    * - `rocAL <https://github.com/ROCm/rocAL>`_
+      - 3.3.0
+      - 2.2.0
+      - Accelerates the data pipeline by offloading intensive preprocessing and
+        augmentation tasks. rocAL is part of MIVisionX.
+    * - `RCCL <https://github.com/ROCm/rccl>`_
+      - 2.26.6
+      - 2.22.3
+      - Optimizes for multi-GPU communication for operations like AllReduce and
+        Broadcast.
+    * - `rocDecode <https://github.com/ROCm/rocDecode>`_
+      - 1.0.0
+      - 0.10.0
+      - Provides hardware-accelerated data decoding capabilities, particularly
+        for image, video, and other dataset formats.
+    * - `rocJPEG <https://github.com/ROCm/rocJPEG>`_
+      - 1.1.0
+      - 0.8.0
+      - Provides hardware-accelerated JPEG image decoding and encoding.
+    * - `RPP <https://github.com/ROCm/RPP>`_
+      - 2.0.0
+      - 1.9.10
+      - Speeds up data augmentation, transformation, and other preprocessing steps.
+    * - `rocThrust <https://github.com/ROCm/rocThrust>`_
+      - 4.0.0
+      - 3.3.0
+      - Provides a C++ template library for parallel algorithms like sorting,
+        reduction, and scanning.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
+      - 2.0.0
+      - 1.7.0
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+
+.. _dgl-supported-features-latest:
+
+Supported features with ROCm 7.0.0
+================================================================================
+
+Many functions and methods available upstream are also supported in DGL on ROCm.
+Instead of listing them all, support is grouped into the following categories to provide a general overview. 
+
+* DGL Base
+* DGL Backend 
+* DGL Data
+* DGL Dataloading
+* DGL Graph
+* DGL Function
+* DGL Ops
+* DGL Sampling
+* DGL Transforms
+* DGL Utils
+* DGL Distributed
+* DGL Geometry
+* DGL Mpops
+* DGL NN
+* DGL Optim
+* DGL Sparse
+* GraphBolt
+
+.. _dgl-unsupported-features-latest:
+
+Unsupported features with ROCm 7.0.0
+================================================================================
+
+* TF32 Support (only supported for PyTorch 2.7 and above)
+* Kineto/ROCTracer integration
+
+.. _dgl-unsupported-functions:
+
+Unsupported functions with ROCm 7.0.0
+================================================================================
+
+* ``bfs``
+* ``format``
+* ``multiprocess_sparse_adam_state_dict``
+* ``half_spmm``
+* ``segment_mm`` 
+* ``gather_mm_idx_b``
+* ``sample_labors_prob``
+* ``sample_labors_noprob``
+* ``sparse_admin``
+
+.. _dgl-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+DGL can be used for Graph Learning, and building popular graph models like  
+GAT, GCN, and GraphSage. Using these models, a variety of use cases are supported:
+
+- Recommender systems
+- Network Optimization and Analysis
+- 1D (Temporal) and 2D (Image) Classification
+- Drug Discovery
+
+For use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for DGL examples and best practices to optimize your workloads on AMD GPUs.
+
+* Although multiple use cases of DGL have been tested and verified, a few have been  
+  outlined in the `DGL in the Real World: Running GNNs on Real Use Cases 
+  <https://rocm.blogs.amd.com/artificial-intelligence/dgl_blog2/README.html>`__ blog 
+  post, which walks through four real-world graph neural network (GNN) workloads 
+  implemented with the Deep Graph Library on ROCm. It covers tasks ranging from 
+  heterogeneous e-commerce graphs and multiplex networks (GATNE) to molecular graph 
+  regression (GNN-FiLM) and EEG-based neurological diagnosis (EEG-GCNN). For each use 
+  case, the authors detail: the dataset and task, how DGL is used, and their experience 
+  porting to ROCm. It is shown that DGL codebases often run without modification, with 
+  seamless integration of graph operations, message passing, sampling, and convolution. 
+
+* The `Graph Neural Networks (GNNs) at Scale: DGL with ROCm on AMD Hardware 
+  <https://rocm.blogs.amd.com/artificial-intelligence/why-graph-neural/README.html>`__ 
+  blog post introduces the Deep Graph Library (DGL) and its enablement on the AMD ROCm platform, 
+  bringing high-performance graph neural network (GNN) training to AMD GPUs. DGL bridges 
+  the gap between dense tensor frameworks and the irregular nature of graph data through a 
+  graph-first, message-passing abstraction. Its design ensures scalability, flexibility, and 
+  interoperability across frameworks like PyTorch and TensorFlow. AMD’s ROCm integration 
+  enables DGL to run efficiently on HIP-based GPUs, supported by prebuilt Docker containers 
+  and open-source repositories. This marks a major step in AMD's mission to advance open, 
+  scalable AI ecosystems beyond traditional architectures.
+
+You can pre-process datasets and begin training on AMD GPUs through:
+
+* Single-GPU training/inference
+* Multi-GPU training
+
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/dgl-history` to find documentation for previous releases
+of the ``ROCm/dgl`` Docker image.

docs/compatibility/ml-compatibility/flashinfer-compatibility.rst

@@ -0,0 +1,98 @@
+:orphan:
+
+.. meta::
+    :description: FlashInfer compatibility
+    :keywords: GPU, LLM, FlashInfer, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+FlashInfer compatibility
+********************************************************************************
+
+`FlashInfer <https://docs.flashinfer.ai/index.html>`__ is a library and kernel generator 
+for Large Language Models (LLMs) that provides a high-performance implementation of graphics 
+processing units (GPUs) kernels. FlashInfer focuses on LLM serving and inference, as well 
+as advanced performance across diverse scenarios.
+
+FlashInfer features highly efficient attention kernels, load-balanced scheduling, and memory-optimized 
+techniques, while supporting customized attention variants. It’s compatible with ``torch.compile``, and 
+offers high-performance LLM-specific operators, with easy integration through PyTorch, and C++ APIs.
+
+.. note::
+
+  The ROCm port of FlashInfer is under active development, and some features are not yet available. 
+  For the latest feature compatibility matrix, refer to the ``README`` of the 
+  `https://github.com/ROCm/flashinfer <https://github.com/ROCm/flashinfer>`__ repository.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of FlashInfer is maintained in the official `https://github.com/ROCm/flashinfer 
+  <https://github.com/ROCm/flashinfer>`__ repository, which differs from the 
+  `https://github.com/flashinfer-ai/flashinfer <https://github.com/flashinfer-ai/flashinfer>`__ 
+  upstream repository.
+
+- To get started and install FlashInfer on ROCm, use the prebuilt :ref:`Docker images <flashinfer-docker-compat>`, 
+  which include ROCm, FlashInfer, and all required dependencies.
+
+  - See the :doc:`ROCm FlashInfer installation guide <rocm-install-on-linux:install/3rd-party/flashinfer-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://docs.flashinfer.ai/installation.html>`__ 
+    for additional context.
+
+.. _flashinfer-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `FlashInfer images <https://hub.docker.com/r/rocm/flashinfer/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tag and associated
+inventories represent the latest available FlashInfer version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - FlashInfer
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/flashinfer/flashinfer-0.2.5_rocm6.4_ubuntu24.04_py3.12_pytorch2.7/images/sha256-558914838821c88c557fb6d42cfbc1bdb67d79d19759f37c764a9ee801f93313"><i class="fab fa-docker fa-lg"></i> rocm/flashinfer</a>
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - `v0.2.5 <https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.2.5>`__
+      - `2.7.1 <https://github.com/ROCm/pytorch/releases/tag/v2.7.1>`__
+      - 24.04
+      - `3.12 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X
+
+.. _flashinfer-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+The release of FlashInfer on ROCm provides the decode functionality for LLM inferencing.
+In the decode phase, tokens are generated sequentially, with the model predicting each new 
+token based on the previously generated tokens and the input context.
+
+FlashInfer on ROCm brings over upstream features such as load balancing, sparse and dense 
+attention optimizations, and batching support, enabling efficient execution on AMD Instinct™ MI300X GPUs.
+
+Because large LLMs often require substantial KV caches or long context windows, FlashInfer on ROCm 
+also implements cascade attention from upstream to reduce memory usage. 
+
+For currently supported use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for examples and best practices to optimize your workloads on AMD GPUs.
+

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

@@ -0,0 +1,319 @@
+:orphan:
+
+.. meta::
+   :description: JAX compatibility
+   :keywords: GPU, JAX, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+JAX compatibility
+*******************************************************************************
+
+`JAX <https://docs.jax.dev/en/latest/notebooks/thinking_in_jax.html>`__ is a library 
+for array-oriented numerical computation (similar to NumPy), with automatic differentiation 
+and just-in-time (JIT) compilation to enable high-performance machine learning research.
+
+JAX provides an API that combines automatic differentiation and the 
+Accelerated Linear Algebra (XLA) compiler to achieve high-performance machine 
+learning at scale. JAX uses composable transformations of Python and NumPy through 
+JIT compilation, automatic vectorization, and parallelization.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of JAX is maintained in the official `https://github.com/ROCm/rocm-jax 
+  <https://github.com/ROCm/rocm-jax>`__ repository, which differs from the 
+  `https://github.com/jax-ml/jax <https://github.com/jax-ml/jax>`__ upstream repository.
+
+- To get started and install JAX on ROCm, use the prebuilt :ref:`Docker images <jax-docker-compat>`, 
+  which include ROCm, JAX, and all required dependencies.
+
+  - See the :doc:`ROCm JAX installation guide <rocm-install-on-linux:install/3rd-party/jax-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://jax.readthedocs.io/en/latest/installation.html#amd-gpu-linux>`__ 
+    for additional context.
+
+Version support
+--------------------------------------------------------------------------------
+
+AMD releases official `ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax/tags>`_
+quarterly alongside new ROCm releases. These images undergo full AMD testing.
+`Community ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax-community/tags>`_
+follow upstream JAX releases and use the latest available ROCm version.
+
+JAX Plugin-PJRT with JAX/JAXLIB compatibility
+================================================================================
+
+Portable JIT Runtime (PJRT) is an open, stable interface for device runtime and
+compiler. The following table details the ROCm version compatibility matrix
+between JAX Plugin–PJRT and JAX/JAXLIB.
+
+.. list-table::
+    :header-rows: 1
+
+    * - JAX Plugin-PJRT
+      - JAX/JAXLIB
+      - ROCm
+    * - 0.7.1
+      - 0.7.1
+      - 7.1.1, 7.1.0
+    * - 0.6.0
+      - 0.6.2, 0.6.0
+      - 7.0.2, 7.0.1, 7.0.0
+
+Use cases and recommendations
+================================================================================
+
+* The `nanoGPT in JAX <https://rocm.blogs.amd.com/artificial-intelligence/nanoGPT-JAX/README.html>`_
+  blog explores the implementation and training of a Generative Pre-trained
+  Transformer (GPT) model in JAX, inspired by Andrej Karpathy’s JAX-based
+  nanoGPT. Comparing how essential GPT components—such as self-attention
+  mechanisms and optimizers—are realized in JAX and JAX, also highlights
+  JAX’s unique features.
+
+* The `Optimize GPT Training: Enabling Mixed Precision Training in JAX using
+  ROCm on AMD GPUs <https://rocm.blogs.amd.com/artificial-intelligence/jax-mixed-precision/README.html>`_
+  blog post provides a comprehensive guide on enhancing the training efficiency
+  of GPT models by implementing mixed precision techniques in JAX, specifically
+  tailored for AMD GPUs utilizing the ROCm platform.
+
+* The `Supercharging JAX with Triton Kernels on AMD GPUs <https://rocm.blogs.amd.com/artificial-intelligence/jax-triton/README.html>`_
+  blog demonstrates how to develop a custom fused dropout-activation kernel for
+  matrices using Triton, integrate it with JAX, and benchmark its performance
+  using ROCm.
+
+* The `Distributed fine-tuning with JAX on AMD GPUs <https://rocm.blogs.amd.com/artificial-intelligence/distributed-sft-jax/README.html>`_
+  outlines the process of fine-tuning a Bidirectional Encoder Representations
+  from Transformers (BERT)-based large language model (LLM) using JAX for a text
+  classification task. The blog post discusses techniques for parallelizing the
+  fine-tuning across multiple AMD GPUs and assess the model's performance on a
+  holdout dataset. During the fine-tuning, a BERT-base-cased transformer model
+  and the General Language Understanding Evaluation (GLUE) benchmark dataset was
+  used on a multi-GPU setup.
+
+* The `MI300X workload optimization guide <https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/workload.html>`_
+  provides detailed guidance on optimizing workloads for the AMD Instinct MI300X
+  GPU using ROCm. The page is aimed at helping users achieve optimal
+  performance for deep learning and other high-performance computing tasks on
+  the MI300X GPU.
+
+For more use cases and recommendations, see `ROCm JAX blog posts <https://rocm.blogs.amd.com/blog/tag/jax.html>`_.
+
+.. _jax-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+AMD validates and publishes `JAX images <https://hub.docker.com/r/rocm/jax/tags>`__
+with ROCm backends on Docker Hub.
+
+For ``jax-community`` images, see `rocm/jax-community
+<https://hub.docker.com/r/rocm/jax-community/tags>`__ on Docker Hub.
+
+To find the right image tag, see the :ref:`JAX on ROCm installation
+documentation <rocm-install-on-linux:jax-docker-support>` for a list of
+available ``rocm/jax`` images.
+
+.. _key_rocm_libraries:
+
+Key ROCm libraries for JAX
+================================================================================
+
+The following ROCm libraries represent potential targets that could be utilized
+by JAX on ROCm for various computational tasks. The actual libraries used will
+depend on the specific implementation and operations performed.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - Version
+      - Purpose
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
+      - :version-ref:`hipBLAS rocm_version`
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
+      - :version-ref:`hipBLASLt rocm_version`
+      - hipBLASLt is an extension of hipBLAS, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+    * - `hipCUB <https://github.com/ROCm/hipCUB>`_
+      - :version-ref:`hipCUB rocm_version`
+      - Provides a C++ template library for parallel algorithms for reduction,
+        scan, sort and select.
+    * - `hipFFT <https://github.com/ROCm/hipFFT>`_
+      - :version-ref:`hipFFT rocm_version`
+      - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
+    * - `hipRAND <https://github.com/ROCm/hipRAND>`_
+      - :version-ref:`hipRAND rocm_version`
+      - Provides fast random number generation for GPUs.
+    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
+      - :version-ref:`hipSOLVER rocm_version`
+      - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
+        singular value decompositions (SVD).
+    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
+      - :version-ref:`hipSPARSE rocm_version`
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+    * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
+      - :version-ref:`hipSPARSELt rocm_version`
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+    * - `MIOpen <https://github.com/ROCm/MIOpen>`_
+      - :version-ref:`MIOpen rocm_version`
+      - Optimized for deep learning primitives such as convolutions, pooling,
+        normalization, and activation functions.
+    * - `RCCL <https://github.com/ROCm/rccl>`_
+      - :version-ref:`RCCL rocm_version`
+      - Optimized for multi-GPU communication for operations like  all-reduce,
+        broadcast, and scatter.
+    * - `rocThrust <https://github.com/ROCm/rocThrust>`_
+      - :version-ref:`rocThrust rocm_version`
+      - Provides a C++ template library for parallel algorithms like sorting,
+        reduction, and scanning.
+
+.. note::
+
+    This table shows ROCm libraries that could potentially be utilized by JAX. Not
+    all libraries may be used in every configuration, and the actual library usage
+    will depend on the specific operations and implementation details.
+
+Supported data types and modules
+===============================================================================
+
+The following tables lists the supported public JAX API data types and modules.
+
+Supported data types
+--------------------------------------------------------------------------------
+
+ROCm supports all the JAX data types of `jax.dtypes <https://docs.jax.dev/en/latest/jax.dtypes.html>`_
+module, `jax.numpy.dtype <https://docs.jax.dev/en/latest/_autosummary/jax.numpy.dtype.html>`_
+and `default_dtype <https://docs.jax.dev/en/latest/default_dtypes.html>`_ .
+The ROCm supported data types in JAX are collected in the following table.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+
+    * - ``bfloat16``
+      - 16-bit bfloat (brain floating point).
+
+    * - ``bool``
+      - Boolean.
+
+    * - ``complex128``
+      - 128-bit complex.
+
+    * - ``complex64``
+      - 64-bit complex.
+
+    * - ``float16``
+      - 16-bit (half precision) floating-point.
+
+    * - ``float32``
+      - 32-bit (single precision) floating-point.
+
+    * - ``float64``
+      - 64-bit (double precision) floating-point.
+
+    * - ``half``
+      - 16-bit (half precision) floating-point.
+
+    * - ``int16``
+      - Signed 16-bit integer.
+
+    * - ``int32``
+      - Signed 32-bit integer.
+
+    * - ``int64``
+      - Signed 64-bit integer.
+
+    * - ``int8``
+      - Signed 8-bit integer.
+
+    * - ``uint16``
+      - Unsigned 16-bit (word) integer.
+
+    * - ``uint32``
+      - Unsigned 32-bit (dword) integer.
+
+    * - ``uint64``
+      - Unsigned 64-bit (qword) integer.
+
+    * - ``uint8``
+      - Unsigned 8-bit (byte) integer.
+
+.. note::
+
+  JAX data type support is affected by the :ref:`key_rocm_libraries` and it's
+  collected on :doc:`ROCm data types and precision support <rocm:reference/precision-support>`
+  page.
+
+Supported modules
+--------------------------------------------------------------------------------
+
+For a complete and up-to-date list of JAX public modules (for example, ``jax.numpy``,
+``jax.scipy``, ``jax.lax``), their descriptions, and usage, please refer directly to the
+`official JAX API documentation <https://jax.readthedocs.io/en/latest/jax.html>`_.
+
+.. note::
+
+  Since version 0.1.56, JAX has full support for ROCm, and the
+  :ref:`Known issues and important notes <jax_comp_known_issues>` section
+  contains details about limitations specific to the ROCm backend. The list of
+  JAX API modules are maintained by the JAX project and is subject to change.
+  Refer to the official Jax documentation for the most up-to-date information.
+
+Key features and enhancements for ROCm 7.0
+===============================================================================
+
+- Upgraded XLA backend: Integrates a newer XLA version, enabling better
+  optimizations, broader operator support, and potential performance gains.
+
+- RNN support: Native RNN support (including LSTMs via ``jax.experimental.rnn``)
+  now available on ROCm, aiding sequence model development.
+
+- Comprehensive linear algebra capabilities: Offers robust ``jax.linalg``
+  operations, essential for scientific and machine learning tasks.
+
+- Expanded AMD GPU architecture support: Provides ongoing support for gfx1101
+  GPUs and introduces support for gfx950 and gfx12xx GPUs.
+
+- Mixed FP8 precision support: Enables ``lax.dot_general`` operations with mixed FP8
+  types, offering pathways for memory and compute efficiency.
+
+- Streamlined PyPi packaging: Provides reliable PyPi wheels for JAX on ROCm,
+  simplifying the installation process.
+
+- Pallas experimental kernel development: Continued Pallas framework
+  enhancements for custom GPU kernels, including new intrinsics (specific
+  kernel behaviors under review).
+
+- Improved build system and CI: Enhanced ROCm build system and CI for greater
+  reliability and maintainability.
+
+- Enhanced distributed computing setup: Improved JAX setup in multi-GPU
+  distributed environments.
+
+.. _jax_comp_known_issues:
+
+Known issues and notes for ROCm 7.0
+===============================================================================
+
+- ``nn.dot_product_attention``: Certain configurations of ``jax.nn.dot_product_attention``
+  may cause segmentation faults, though the majority of use cases work correctly.
+
+- SVD with dynamic shapes: SVD on inputs with dynamic/symbolic shapes might result in an error.
+  SVD with static shapes is unaffected.
+
+- QR decomposition with symbolic shapes: QR decomposition operations may fail when using
+  symbolic/dynamic shapes in shape polymorphic contexts.
+
+- Pallas kernels: Specific advanced Pallas kernels may exhibit variations in
+  numerical output or resource usage. These are actively reviewed as part of
+  Pallas's experimental development.

docs/compatibility/ml-compatibility/llama-cpp-compatibility.rst

@@ -0,0 +1,275 @@
+:orphan:
+
+.. meta::
+    :description: llama.cpp compatibility
+    :keywords: GPU, GGML, llama.cpp, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+llama.cpp compatibility
+********************************************************************************
+
+`llama.cpp <https://github.com/ggml-org/llama.cpp>`__ is an open-source framework 
+for Large Language Model (LLM) inference that runs on both central processing units 
+(CPUs) and graphics processing units (GPUs). It is written in plain C/C++, providing 
+a simple, dependency-free setup. 
+
+The framework supports multiple quantization options, from 1.5-bit to 8-bit integers, 
+to accelerate inference and reduce memory usage. Originally built as a CPU-first library, 
+llama.cpp is easy to integrate with other programming environments and is widely 
+adopted across diverse platforms, including consumer devices. 
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of llama.cpp is maintained in the official `https://github.com/ROCm/llama.cpp 
+  <https://github.com/ROCm/llama.cpp>`__ repository, which differs from the 
+  `https://github.com/ggml-org/llama.cpp <https://github.com/ggml-org/llama.cpp>`__ upstream repository.
+
+- To get started and install llama.cpp on ROCm, use the prebuilt :ref:`Docker images <llama-cpp-docker-compat>`, 
+  which include ROCm, llama.cpp, and all required dependencies.
+
+  - See the :doc:`ROCm llama.cpp installation guide <rocm-install-on-linux:install/3rd-party/llama-cpp-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md>`__ 
+    for additional context.
+
+.. _llama-cpp-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `llama.cpp images <https://hub.docker.com/r/rocm/llama.cpp/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest available llama.cpp versions from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. important::
+
+   Tag endings of ``_full``, ``_server``, and ``_light`` serve different purposes for entrypoints as follows:
+
+   - Full: This image includes both the main executable file and the tools to convert ``LLaMA`` models into ``ggml`` and convert into 4-bit quantization.
+   - Server: This image only includes the server executable file.
+   - Light: This image only includes the main executable file.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Full Docker
+      - Server Docker
+      - Light Docker
+      - llama.cpp
+      - ROCm
+      - Ubuntu
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_full/images/sha256-a94f0c7a598cc6504ff9e8371c016d7a2f93e69bf54a36c870f9522567201f10g"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_server/images/sha256-be175932c3c96e882dfbc7e20e0e834f58c89c2925f48b222837ee929dfc47ee"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_light/images/sha256-d8ba0c70603da502c879b1f8010b439c8e7fa9f6cbdac8bbbbbba97cb41ebc9e"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6652 <https://github.com/ROCm/llama.cpp/tree/release/b6652>`__
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_full/images/sha256-37582168984f25dce636cc7288298e06d94472ea35f65346b3541e6422b678ee"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_server/images/sha256-7e70578e6c3530c6591cc2c26da24a9ee68a20d318e12241de93c83224f83720"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_light/images/sha256-9a5231acf88b4a229677bc2c636ea3fe78a7a80f558bd80910b919855de93ad5"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6652 <https://github.com/ROCm/llama.cpp/tree/release/b6652>`__
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_full/images/sha256-5960fc850024a8a76451f9eaadd89b7e59981ae9f393b407310c1ddf18892577"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_server/images/sha256-1b79775d9f546065a6aaf9ca426e1dd4ed4de0b8f6ee83687758cc05af6538e6"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_light/images/sha256-8f863c4c2857ae42bebd64e4f1a0a1e7cc3ec4503f243e32b4a4dcad070ec361"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_full/images/sha256-888879b3ee208f9247076d7984524b8d1701ac72611689e89854a1588bec9867"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_server/images/sha256-90e4ff99a66743e33fd00728cd71a768588e5f5ef355aaa196669fe65ac70672"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_light/images/sha256-bd447a049939cb99054f8fbf3f2352870fe906a75e2dc3339c845c08b9c53f9b"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_full/images/sha256-5b3a1bc4889c1fcade434b937fbf9cc1c22ff7dc0317c130339b0c9238bc88c4"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_server/images/sha256-5228ff99d0f627a9032d668f4381b2e80dc1e301adc3e0821f26d8354b175271"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_light/images/sha256-b12723b332a826a89b7252dddf868cbe4d1a869562fc4aa4032f59e1a683b968"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_full/images/sha256-cd6e21a6a73f59b35dd5309b09dd77654a94d783bf13a55c14eb8dbf8e9c2615"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_server/images/sha256-c2b4689ab2c47e6626e8fea22d7a63eb03d47c0fde9f5ef8c9f158d15c423e58"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_light/images/sha256-1acc28f29ed87db9cbda629cb29e1989b8219884afe05f9105522be929e94da4"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_full/images/sha256-2f8ae8a44510d96d52dea6cb398b224f7edeb7802df7ec488c6f63d206b3cdc9"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_server/images/sha256-fece497ff9f4a28b12f645de52766941da8ead8471aa1ea84b61d4b4568e51f2"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_light/images/sha256-3e14352fa6f8c6128b23cf9342531c20dbfb522550b626e09d83b260a1947022"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_full/images/sha256-80763062ef0bec15038c35fd01267f1fc99a5dd171d4b48583cc668b15efad69"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_server/images/sha256-db2a6c957555ed83b819bbc54aea884a93192da0fb512dae63d32e0dc4e8ab8f"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_light/images/sha256-c6dbb07cc655fb079d5216e4b77451cb64a9daa0585d23b6fb8b32cb22021197"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_full/images/sha256-f78f6c81ab2f8e957469415fe2370a1334fe969c381d1fe46050c85effaee9d5"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_server/images/sha256-275ad9e18f292c26a00a2de840c37917e98737a88a3520bdc35fd3fc5c9a6a9b"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_light/images/sha256-cc324e6faeedf0e400011f07b49d2dc41a16bae257b2b7befa0f4e2e97231320"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b5997 <https://github.com/ROCm/llama.cpp/tree/release/b5997>`__
+      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__
+      - 24.04
+      - MI300X, MI210
+
+.. _llama-cpp-key-rocm-libraries:
+
+Key ROCm libraries for llama.cpp
+================================================================================
+
+llama.cpp functionality on ROCm is determined by its underlying library
+dependencies. These ROCm components affect the capabilities, performance, and
+feature set available to developers. Ensure you have the required libraries for 
+your corresponding ROCm version.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - ROCm 7.0.0 version
+      - ROCm 6.4.x version
+      - Purpose
+      - Usage
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`__
+      - 3.0.0
+      - 2.4.0
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Supports operations such as matrix multiplication, matrix-vector
+        products, and tensor contractions. Utilized in both dense and batched
+        linear algebra operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`__
+      - 1.0.0
+      - 0.12.0
+      - hipBLASLt is an extension of the hipBLAS library, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+      - By setting the flag ``ROCBLAS_USE_HIPBLASLT``, you can dispatch hipblasLt
+        kernels where possible.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`__
+      - 2.0.0
+      - 1.7.0
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+      - Can be used to enhance the flash attention performance on AMD compute, by enabling
+        the flag during compile time.
+
+.. _llama-cpp-uses-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+llama.cpp can be applied in a variety of scenarios, particularly when you need to meet one or more of the following requirements:
+
+- Plain C/C++ implementation with no external dependencies
+- Support for 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory usage
+- Custom HIP (Heterogeneous-compute Interface for Portability) kernels for running large language models (LLMs) on AMD GPUs (graphics processing units)
+- CPU (central processing unit) + GPU (graphics processing unit) hybrid inference for partially accelerating models larger than the total available VRAM (video random-access memory)
+
+llama.cpp is also used in a range of real-world applications, including:
+
+- Games such as `Lucy's Labyrinth <https://github.com/MorganRO8/Lucys_Labyrinth>`__:
+  A simple maze game where AI-controlled agents attempt to trick the player.
+- Tools such as `Styled Lines <https://marketplace.unity.com/packages/tools/ai-ml-integration/style-text-webgl-ios-stand-alone-llm-llama-cpp-wrapper-292902>`__:
+  A proprietary, asynchronous inference wrapper for Unity3D game development, including pre-built mobile and web platform wrappers and a model example.
+- Various other AI applications use llama.cpp as their inference engine;  
+  for a detailed list, see the `user interfaces (UIs) section <https://github.com/ggml-org/llama.cpp?tab=readme-ov-file#description>`__.
+
+For more use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for llama.cpp examples and best practices to optimize your workloads on AMD GPUs.
+
+- The `Llama.cpp Meets Instinct: A New Era of Open-Source AI Acceleration <https://rocm.blogs.amd.com/ecosystems-and-partners/llama-cpp/README.html>`__ 
+  blog post outlines how the open-source llama.cpp framework enables efficient LLM inference—including interactive inference with ``llama-cli``, 
+  server deployment with ``llama-server``, GGUF model preparation and quantization, performance benchmarking, and optimizations tailored for 
+  AMD Instinct GPUs within the ROCm ecosystem. 
+
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/llama-cpp-history` to find documentation for previous releases
+of the ``ROCm/llama.cpp`` Docker image.

docs/compatibility/ml-compatibility/megablocks-compatibility.rst

@@ -0,0 +1,104 @@
+:orphan:
+
+.. meta::
+    :description: Megablocks compatibility
+    :keywords: GPU, megablocks, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+Megablocks compatibility
+********************************************************************************
+
+`Megablocks <https://github.com/databricks/megablocks>`__ is a lightweight library 
+for mixture-of-experts `(MoE) <https://huggingface.co/blog/moe>`__ training. 
+The core of the system is efficient "dropless-MoE" and standard MoE layers. 
+Megablocks is integrated with `https://github.com/stanford-futuredata/Megatron-LM 
+<https://github.com/stanford-futuredata/Megatron-LM>`__, 
+where data and pipeline parallel training of MoEs is supported.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Megablocks is maintained in the official `https://github.com/ROCm/megablocks 
+  <https://github.com/ROCm/megablocks>`__ repository, which differs from the 
+  `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`__ upstream repository.
+
+- To get started and install Megablocks on ROCm, use the prebuilt :ref:`Docker image <megablocks-docker-compat>`, 
+  which includes ROCm, Megablocks, and all required dependencies.
+
+  - See the :doc:`ROCm Megablocks installation guide <rocm-install-on-linux:install/3rd-party/megablocks-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/databricks/megablocks>`__ 
+    for additional context.
+
+.. _megablocks-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `Megablocks images <https://hub.docker.com/r/rocm/megablocks/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tag and associated
+inventories represent the latest available Megablocks version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Megablocks
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/megablocks/megablocks-0.7.0_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-372ff89b96599019b8f5f9db469c84add2529b713456781fa62eb9a148659ab4"><i class="fab fa-docker fa-lg"></i> rocm/megablocks</a>
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `0.7.0 <https://github.com/databricks/megablocks/releases/tag/v0.7.0>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - MI300X
+
+Supported models and features with ROCm 6.3.0
+================================================================================
+
+This section summarizes the Megablocks features supported by ROCm.
+
+* Distributed Pre-training
+* Activation Checkpointing and Recomputation
+* Distributed Optimizer
+* Mixture-of-Experts
+* dropless-Mixture-of-Experts
+
+.. _megablocks-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+* The `Efficient MoE training on AMD ROCm: How-to use Megablocks on AMD GPUs 
+  <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`__ 
+  blog post guides how to leverage the ROCm platform for pre-training using the 
+  Megablocks framework. It introduces a streamlined approach for training Mixture-of-Experts 
+  (MoE) models using the Megablocks library on AMD hardware. Focusing on GPT-2, it 
+  demonstrates how block-sparse computations can enhance scalability and efficiency in MoE 
+  training. The guide provides step-by-step instructions for setting up the environment, 
+  including cloning the repository, building the Docker image, and running the training container. 
+  Additionally, it offers insights into utilizing the ``oscar-1GB.json`` dataset for pre-training 
+  language models. By leveraging Megablocks and the ROCm platform, you can optimize your MoE 
+  training workflows for large-scale transformer models.
+
+It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
+
+* Single-GPU pre-training
+* Multi-GPU pre-training
+

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

@@ -0,0 +1,498 @@
+:orphan:
+
+.. meta::
+    :description: PyTorch compatibility
+    :keywords: GPU, PyTorch, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+PyTorch compatibility
+********************************************************************************
+
+`PyTorch <https://pytorch.org/>`__ is an open-source tensor library designed for
+deep learning. PyTorch on ROCm provides mixed-precision and large-scale training
+using `MIOpen <https://github.com/ROCm/MIOpen>`__ and
+`RCCL <https://github.com/ROCm/rccl>`__ libraries.
+
+PyTorch provides two high-level features:
+
+- Tensor computation (like NumPy) with strong GPU acceleration
+
+- Deep neural networks built on a tape-based autograd system (rapid computation 
+  of multiple partial derivatives or gradients)
+
+Support overview
+================================================================================
+
+ROCm support for PyTorch is upstreamed into the official PyTorch repository. 
+ROCm development is aligned with the stable release of PyTorch, while upstream 
+PyTorch testing uses the stable release of ROCm to maintain consistency:
+
+- The ROCm-supported version of PyTorch is maintained in the official `https://github.com/ROCm/pytorch 
+  <https://github.com/ROCm/pytorch>`__ repository, which differs from the 
+  `https://github.com/pytorch/pytorch <https://github.com/pytorch/pytorch>`__ upstream repository.
+
+- To get started and install PyTorch on ROCm, use the prebuilt :ref:`Docker images <pytorch-docker-compat>`, 
+  which include ROCm, PyTorch, and all required dependencies.
+
+  - See the :doc:`ROCm PyTorch installation guide <rocm-install-on-linux:install/3rd-party/pytorch-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://pytorch.org/get-started/locally/>`__ or 
+    `Previous versions <https://pytorch.org/get-started/previous-versions/>`__ for additional context.
+
+PyTorch includes tooling that generates HIP source code from the CUDA backend.
+This approach allows PyTorch to support ROCm without requiring manual code
+modifications. For more information, see :doc:`HIPIFY <hipify:index>`.
+
+Version support
+--------------------------------------------------------------------------------
+
+AMD releases official `ROCm PyTorch Docker images <https://hub.docker.com/r/rocm/pytorch/tags>`_
+quarterly alongside new ROCm releases. These images undergo full AMD testing.
+
+.. _pytorch-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+* :doc:`Using ROCm for AI: training a model </how-to/rocm-for-ai/training/benchmark-docker/pytorch-training>`
+  guides how to leverage the ROCm platform for training AI models. It covers the
+  steps, tools, and best practices for optimizing training workflows on AMD GPUs
+  using PyTorch features.
+
+* :doc:`Single-GPU fine-tuning and inference </how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference>`
+  describes and demonstrates how to use the ROCm platform for the fine-tuning
+  and inference of machine learning models, particularly large language models
+  (LLMs), on systems with a single GPU. This topic provides a detailed guide for
+  setting up, optimizing, and executing fine-tuning and inference workflows in
+  such environments.
+
+* :doc:`Multi-GPU fine-tuning and inference optimization </how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference>`
+  describes and demonstrates the fine-tuning and inference of machine learning
+  models on systems with multiple GPUs.
+
+* The :doc:`Instinct MI300X workload optimization guide </how-to/rocm-for-ai/inference-optimization/workload>`
+  provides detailed guidance on optimizing workloads for the AMD Instinct MI300X
+  GPU using ROCm. This guide helps users achieve optimal performance for
+  deep learning and other high-performance computing tasks on the MI300X
+  GPU.
+
+* The :doc:`Inception with PyTorch documentation </conceptual/ai-pytorch-inception>`
+  describes how PyTorch integrates with ROCm for AI workloads. It outlines the
+  use of PyTorch on the ROCm platform and focuses on efficiently leveraging AMD
+  GPU hardware for training and inference tasks in AI applications.
+
+For more use cases and recommendations, see `ROCm PyTorch blog posts <https://rocm.blogs.amd.com/blog/tag/pytorch.html>`__.
+
+.. _pytorch-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+AMD validates and publishes `PyTorch images <https://hub.docker.com/r/rocm/pytorch/tags>`__
+with ROCm backends on Docker Hub.
+
+To find the right image tag, see the :ref:`PyTorch on ROCm installation
+documentation <rocm-install-on-linux:pytorch-docker-support>` for a list of
+available ``rocm/pytorch`` images.
+
+Key ROCm libraries for PyTorch
+================================================================================
+
+PyTorch functionality on ROCm is determined by its underlying library
+dependencies. These ROCm components affect the capabilities, performance, and
+feature set available to developers.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - Version
+      - Purpose
+      - Used in
+    * - `Composable Kernel <https://github.com/ROCm/composable_kernel>`__
+      - :version-ref:`"Composable Kernel" rocm_version`
+      - Enables faster execution of core operations like matrix multiplication
+        (GEMM), convolutions and transformations.
+      - Speeds up ``torch.permute``, ``torch.view``, ``torch.matmul``,
+        ``torch.mm``, ``torch.bmm``, ``torch.nn.Conv2d``, ``torch.nn.Conv3d``
+        and ``torch.nn.MultiheadAttention``.
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`__
+      - :version-ref:`hipBLAS rocm_version`
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Supports operations such as matrix multiplication, matrix-vector
+        products, and tensor contractions. Utilized in both dense and batched
+        linear algebra operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`__
+      - :version-ref:`hipBLASLt rocm_version`
+      - hipBLASLt is an extension of the hipBLAS library, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+      - Accelerates operations such as ``torch.matmul``, ``torch.mm``, and the
+        matrix multiplications used in convolutional and linear layers.
+    * - `hipCUB <https://github.com/ROCm/hipCUB>`__
+      - :version-ref:`hipCUB rocm_version`
+      - Provides a C++ template library for parallel algorithms for reduction,
+        scan, sort and select.
+      - Supports operations such as ``torch.sum``, ``torch.cumsum``,
+        ``torch.sort`` irregular shapes often involve scanning, sorting, and
+        filtering, which hipCUB handles efficiently.
+    * - `hipFFT <https://github.com/ROCm/hipFFT>`__
+      - :version-ref:`hipFFT rocm_version`
+      - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
+      - Used in functions like the ``torch.fft`` module.
+    * - `hipRAND <https://github.com/ROCm/hipRAND>`__
+      - :version-ref:`hipRAND rocm_version`
+      - Provides fast random number generation for GPUs.
+      - The ``torch.rand``, ``torch.randn``, and stochastic layers like
+        ``torch.nn.Dropout`` rely on hipRAND.
+    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`__
+      - :version-ref:`hipSOLVER rocm_version`
+      - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
+        singular value decompositions (SVD).
+      - Supports functions like ``torch.linalg.solve``,
+        ``torch.linalg.eig``, and ``torch.linalg.svd``.
+    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`__
+      - :version-ref:`hipSPARSE rocm_version`
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+      - Sparse tensor operations ``torch.sparse``.
+    * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`__
+      - :version-ref:`hipSPARSELt rocm_version`
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+      - Sparse tensor operations ``torch.sparse``.
+    * - `hipTensor <https://github.com/ROCm/hipTensor>`__
+      - :version-ref:`hipTensor rocm_version`
+      - Optimizes for high-performance tensor operations, such as contractions.
+      - Accelerates tensor algebra, especially in deep learning and scientific
+        computing.
+    * - `MIOpen <https://github.com/ROCm/MIOpen>`__
+      - :version-ref:`MIOpen rocm_version`
+      - Optimizes deep learning primitives such as convolutions, pooling,
+        normalization, and activation functions.
+      - Speeds up convolutional neural networks (CNNs), recurrent neural
+        networks (RNNs), and other layers. Used in operations like
+        ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
+    * - `MIGraphX <https://github.com/ROCm/AMDMIGraphX>`__
+      - :version-ref:`MIGraphX rocm_version`
+      - Adds graph-level optimizations, ONNX models and mixed precision support
+        and enable Ahead-of-Time (AOT) Compilation.
+      - Speeds up inference models and executes ONNX models for
+        compatibility with other frameworks.
+        ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
+    * - `MIVisionX <https://github.com/ROCm/MIVisionX>`__
+      - :version-ref:`MIVisionX rocm_version`
+      - Optimizes acceleration for computer vision and AI workloads like
+        preprocessing, augmentation, and inferencing.
+      - Faster data preprocessing and augmentation pipelines for datasets like
+        ImageNet or COCO and easy to integrate into PyTorch's ``torch.utils.data``
+        and ``torchvision`` workflows.
+    * - `rocAL <https://github.com/ROCm/rocAL>`__
+      - :version-ref:`rocAL rocm_version`
+      - Accelerates the data pipeline by offloading intensive preprocessing and
+        augmentation tasks. rocAL is part of MIVisionX.
+      - Easy to integrate into PyTorch's ``torch.utils.data`` and
+        ``torchvision`` data load workloads.
+    * - `RCCL <https://github.com/ROCm/rccl>`__
+      - :version-ref:`RCCL rocm_version`
+      - Optimizes for multi-GPU communication for operations like AllReduce and
+        Broadcast.
+      - Distributed data parallel training (``torch.nn.parallel.DistributedDataParallel``).
+        Handles communication in multi-GPU setups.
+    * - `rocDecode <https://github.com/ROCm/rocDecode>`__
+      - :version-ref:`rocDecode rocm_version`
+      - Provides hardware-accelerated data decoding capabilities, particularly
+        for image, video, and other dataset formats.
+      - Can be integrated in ``torch.utils.data``, ``torchvision.transforms``
+        and ``torch.distributed``.
+    * - `rocJPEG <https://github.com/ROCm/rocJPEG>`__
+      - :version-ref:`rocJPEG rocm_version`
+      - Provides hardware-accelerated JPEG image decoding and encoding.
+      - GPU accelerated ``torchvision.io.decode_jpeg`` and
+        ``torchvision.io.encode_jpeg`` and can be integrated in
+        ``torch.utils.data`` and ``torchvision``.
+    * - `RPP <https://github.com/ROCm/RPP>`__
+      - :version-ref:`RPP rocm_version`
+      - Speeds up data augmentation, transformation, and other preprocessing steps.
+      - Easy to integrate into PyTorch's ``torch.utils.data`` and
+        ``torchvision`` data load workloads to speed up data processing.
+    * - `rocThrust <https://github.com/ROCm/rocThrust>`__
+      - :version-ref:`rocThrust rocm_version`
+      - Provides a C++ template library for parallel algorithms like sorting,
+        reduction, and scanning.
+      - Utilized in backend operations for tensor computations requiring
+        parallel processing.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`__
+      - :version-ref:`rocWMMA rocm_version`
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+      - Linear layers (``torch.nn.Linear``), convolutional layers
+        (``torch.nn.Conv2d``), attention layers, general tensor operations that
+        involve matrix products, such as ``torch.matmul``, ``torch.bmm``, and
+        more.
+
+Supported modules and data types
+================================================================================
+
+The following section outlines the supported data types, modules, and domain
+libraries available in PyTorch on ROCm.
+
+Supported data types
+--------------------------------------------------------------------------------
+
+The tensor data type is specified using the ``dtype`` attribute or argument.
+PyTorch supports many data types for different use cases.
+
+The following table lists `torch.Tensor <https://pytorch.org/docs/stable/tensors.html>`__
+single data types:
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+    * - ``torch.float8_e4m3fn``
+      - 8-bit floating point, e4m3
+    * - ``torch.float8_e5m2``
+      - 8-bit floating point, e5m2
+    * - ``torch.float16`` or ``torch.half``
+      - 16-bit floating point
+    * - ``torch.bfloat16``
+      - 16-bit floating point
+    * - ``torch.float32`` or ``torch.float``
+      - 32-bit floating point
+    * - ``torch.float64`` or ``torch.double``
+      - 64-bit floating point
+    * - ``torch.complex32`` or ``torch.chalf``
+      - 32-bit complex numbers
+    * - ``torch.complex64`` or ``torch.cfloat``
+      - 64-bit complex numbers
+    * - ``torch.complex128`` or ``torch.cdouble``
+      - 128-bit complex numbers
+    * - ``torch.uint8``
+      - 8-bit integer (unsigned)
+    * - ``torch.uint16``
+      - 16-bit integer (unsigned);
+        Not natively supported in ROCm
+    * - ``torch.uint32``
+      - 32-bit integer (unsigned);
+        Not natively supported in ROCm
+    * - ``torch.uint64``
+      - 64-bit integer (unsigned);
+        Not natively supported in ROCm
+    * - ``torch.int8``
+      - 8-bit integer (signed)
+    * - ``torch.int16`` or ``torch.short``
+      - 16-bit integer (signed)
+    * - ``torch.int32`` or ``torch.int``
+      - 32-bit integer (signed)
+    * - ``torch.int64`` or ``torch.long``
+      - 64-bit integer (signed)
+    * - ``torch.bool``
+      - Boolean
+    * - ``torch.quint8``
+      - Quantized 8-bit integer (unsigned)
+    * - ``torch.qint8``
+      - Quantized 8-bit integer (signed)
+    * - ``torch.qint32``
+      - Quantized 32-bit integer (signed)
+    * - ``torch.quint4x2``
+      - Quantized 4-bit integer (unsigned)
+
+.. note::
+
+  Unsigned types, except ``uint8``, have limited support in eager mode. They
+  primarily exist to assist usage with ``torch.compile``.
+
+  See :doc:`ROCm precision support <rocm:reference/precision-support>` for the
+  native hardware support of data types.
+
+Supported modules
+--------------------------------------------------------------------------------
+
+For a complete and up-to-date list of PyTorch core modules (for example., ``torch``,
+``torch.nn``, ``torch.cuda``, ``torch.backends.cuda`` and
+``torch.backends.cudnn``), their descriptions, and usage, please refer directly
+to the `official PyTorch documentation <https://pytorch.org/docs/stable/index.html>`_.
+
+Core PyTorch functionality on ROCm includes tensor operations, neural network
+layers, automatic differentiation, distributed training, mixed-precision
+training, compilation features, and domain-specific libraries for audio, vision,
+text processing, and more.
+
+Supported domain libraries
+--------------------------------------------------------------------------------
+
+PyTorch offers specialized `domain libraries <https://pytorch.org/domains/>`_ with
+GPU acceleration that build on its core features to support specific application
+areas. The table below lists the PyTorch domain libraries that are compatible
+with ROCm.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Library
+      - Description
+
+    * - `torchaudio <https://docs.pytorch.org/audio/stable/index.html>`_
+      - Audio and signal processing library for PyTorch. Provides utilities for
+        audio I/O, signal and data processing functions, datasets, model
+        implementations, and application components for audio and speech
+        processing tasks.
+
+        **Note:** To ensure GPU-acceleration with ``torchaudio.transforms``,
+        you need to explicitly move audio data (waveform tensor) to GPU using
+        ``.to('cuda')``.
+
+    * - `torchtune <https://meta-pytorch.org/torchtune/stable/index.html>`_
+      - PyTorch-native library designed for fine-tuning large language models
+        (LLMs). Provides supports the full fine-tuning workflow and offers
+        compatibility with popular production inference systems.
+
+        **Note:** Only official release exists.
+
+    * - `torchvision <https://docs.pytorch.org/vision/stable/index.html>`_
+      - Computer vision library that is part of the PyTorch project. Provides
+        popular datasets, model architectures, and common image transformations
+        for computer vision applications.
+
+    * - `torchdata <https://meta-pytorch.org/data/beta/index.html#torchdata>`_
+      - Beta library of common modular data loading primitives for easily
+        constructing flexible and performant data pipelines, with features still
+        in prototype stage.
+
+    * - `torchrec <https://meta-pytorch.org/torchrec/>`_
+      - PyTorch domain library for common sparsity and parallelism primitives
+        needed for large-scale recommender systems, enabling authors to train
+        models with large embedding tables shared across many GPUs.
+
+        **Note:** ``torchrec`` does not implement ROCm-specific kernels. ROCm
+        acceleration is provided through the underlying PyTorch framework and
+        ROCm library integration.
+
+    * - `torchserve <https://docs.pytorch.org/serve/>`_
+      - Performant, flexible and easy-to-use tool for serving PyTorch models in
+        production, providing features for model management, batch processing,
+        and scalable deployment.
+
+        **Note:** `torchserve <https://docs.pytorch.org/serve/>`_ is no longer
+        actively maintained. Last official release is sent out with PyTorch 2.4.
+
+    * - `torchrl <https://docs.pytorch.org/rl/stable/index.html>`_
+      - Open-source, Python-first Reinforcement Learning library for PyTorch
+        with a focus on high modularity and good runtime performance, providing
+        low and high-level RL abstractions and reusable functionals for cost
+        functions, returns, and data processing.
+
+        **Note:** Only official release exists.
+
+    * - `tensordict <https://docs.pytorch.org/tensordict/stable/index.html>`_
+      - Dictionary-like class that simplifies operations on batches of tensors,
+        enhancing code readability, compactness, and modularity by abstracting
+        tailored operations and reducing errors through automatic operation
+        dispatching.
+
+        **Note:** Only official release exists.
+
+Key features and enhancements for PyTorch 2.9 with ROCm 7.1.1
+================================================================================
+- Scaled Dot Product Attention (SDPA) upgraded to use AOTriton version 0.11b.
+
+- Default hipBLASLt support enabled for gfx908 architecture on ROCm 6.3 and later.
+
+- MIOpen now supports channels last memory format for 3D convolutions and batch normalization.
+
+- NHWC convolution operations in MIOpen optimized by eliminating unnecessary transpose operations.
+
+- Improved tensor.item() performance by removing redundant synchronization.
+
+- Enhanced performance for element-wise operations and reduction kernels.
+
+- Added support for grouped GEMM operations through fbgemm_gpu generative AI components.
+
+- Resolved device error in Inductor when using CUDA graph trees with HIP.
+
+- Corrected logsumexp scaling in AOTriton-based SDPA implementation.
+
+- Added stream graph capture status validation in memory copy synchronization functions.
+
+Key features and enhancements for PyTorch 2.8 with ROCm 7.1
+================================================================================
+
+- MIOpen deep learning optimizations: Further optimized NHWC BatchNorm feature.
+
+- Added float8 support for the DeepSpeed extension, allowing for decreased
+  memory footprint and increased throughput in training and inference workloads.
+
+- ``torch.nn.functional.scaled_dot_product_attention`` now calling optimized
+  flash attention kernel automatically.
+
+Key features and enhancements for PyTorch 2.7/2.8 with ROCm 7.0
+================================================================================
+
+- Enhanced TunableOp framework: Introduces ``tensorfloat32`` support for
+  TunableOp operations, improved offline tuning for ScaledGEMM operations,
+  submatrix offline tuning capabilities, and better logging for BLAS operations
+  without bias vectors.
+
+- Expanded GPU architecture support: Provides optimized support for newer GPU
+  architectures, including gfx1200 and gfx1201 with preferred hipBLASLt backend
+  selection, along with improvements for gfx950 and gfx1100 Series GPUs.
+
+- Advanced Triton Integration: AOTriton 0.10b introduces official support for
+  gfx950 and gfx1201, along with experimental support for gfx1101, gfx1151,
+  gfx1150, and gfx1200.
+
+- Improved element-wise kernel performance: Delivers enhanced vectorized
+  element-wise kernels with better support for heterogeneous tensor types and
+  optimized input vectorization for tensors with mixed data types.
+
+- MIOpen deep learning optimizations: Enables NHWC BatchNorm by default on
+  ROCm 7.0+, provides ``maxpool`` forward and backward performance improvements
+  targeting ResNet scenarios, and includes updated launch configurations for
+  better performance.
+
+- Enhanced memory and tensor operations: Features fixes for in-place ``aten``
+  sum operations with specialized templated kernels, improved 3D tensor
+  performance with NHWC format, and better handling of memory-bound matrix
+  multiplication operations.
+
+- Robust testing and quality improvements: Includes comprehensive test suite
+  updates with improved tolerance handling for Navi3x architectures, generalized
+  ROCm-specific test conditions, and enhanced unit test coverage for Flash
+  Attention and Memory Efficient operations.
+
+- Composable Kernel (CK) updates: Features updated CK submodule integration with
+  the latest optimizations and performance improvements for core mathematical
+  operations.
+
+- Development and debugging enhancements: Includes improved source handling for
+  dynamic compilation, better error handling for atomic operations, and enhanced
+  state checking for trace operations.
+
+- Integrate APEX fused layer normalization, which can have positive impact on
+  text-to-video models.
+
+- Integrate APEX distributed fused LAMB and distributed fused ADAM, which can
+  have positive impact on BERT-L and Llama2-SFT.
+
+- FlashAttention v3 has been integrated for AMD GPUs.
+
+- `Pytorch C++ extensions <https://pytorch.org/tutorials/advanced/cpp_extension.html>`_
+  provide a mechanism for compiling custom operations that can be used during
+  network training or inference. For AMD platforms, ``amdclang++`` has been
+  validated as the supported compiler for building these extensions.
+
+Known issues and notes for PyTorch 2.7/2.8 with ROCm 7.0 and ROCm 7.1
+================================================================================
+
+- The ``matmul.allow_fp16_reduced_precision_reduction`` and
+  ``matmul.allow_bf16_reduced_precision_reduction`` options under
+  ``torch.backends.cuda`` are not supported. As a result,
+  reduced-precision reductions using FP16 or BF16 accumulation types are not
+  available.

docs/compatibility/ml-compatibility/ray-compatibility.rst

@@ -0,0 +1,114 @@
+:orphan:
+
+.. meta::
+    :description: Ray compatibility
+    :keywords: GPU, Ray, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+Ray compatibility
+*******************************************************************************
+
+Ray is a unified framework for scaling AI and Python applications from your laptop 
+to a full cluster, without changing your code. Ray consists of `a core distributed 
+runtime  <https://docs.ray.io/en/latest/ray-core/walkthrough.html>`__ and a set of 
+`AI libraries <https://docs.ray.io/en/latest/ray-air/getting-started.html>`__ for 
+simplifying machine learning computations.
+
+Ray is a general-purpose framework that runs many types of workloads efficiently. 
+Any Python application can be scaled with Ray, without extra infrastructure.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Ray is maintained in the official `https://github.com/ROCm/ray 
+  <https://github.com/ROCm/ray>`__ repository, which differs from the 
+  `https://github.com/ray-project/ray <https://github.com/ray-project/ray>`__ upstream repository.
+
+- To get started and install Ray on ROCm, use the prebuilt :ref:`Docker image <ray-docker-compat>`, 
+  which includes ROCm, Ray, and all required dependencies.
+
+  - See the :doc:`ROCm Ray installation guide <rocm-install-on-linux:install/3rd-party/ray-install>`
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://docs.ray.io/en/latest/ray-overview/installation.html>`__ 
+    for additional context.
+
+.. _ray-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `ROCm Ray Docker images <https://hub.docker.com/r/rocm/ray/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and
+associated inventories represent the latest Ray version from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Ray
+      - Pytorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.51.1_rocm7.0.0_ubuntu22.04_py3.12_pytorch2.9.0/images/sha256-a02f6766b4ba406f88fd7e85707ec86c04b569834d869a08043ec9bcbd672168"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - `2.51.1 <https://github.com/ROCm/ray/tree/release/2.51.1>`__
+      - 2.9.0a0+git1c57644
+      - 22.04
+      - `3.12.12 <https://www.python.org/downloads/release/python-31212/>`__
+      - MI300X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.48.0.post0_rocm6.4.1_ubuntu24.04_py3.12_pytorch2.6.0/images/sha256-0d166fe6bdced38338c78eedfb96eff92655fb797da3478a62dd636365133cc0"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - `2.48.0.post0 <https://github.com/ROCm/ray/tree/release/2.48.0.post0>`__
+      - 2.6.0+git684f6f2
+      - 24.04
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - MI300X, MI210
+
+Use cases and recommendations
+================================================================================
+
+* The `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm 
+  Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__  
+  blog provides an overview of Volcano Engine Reinforcement Learning (verl) 
+  for large language models (LLMs) and discusses its benefits in large-scale 
+  reinforcement learning from human feedback (RLHF). It uses Ray as part of a 
+  hybrid orchestration engine to schedule and coordinate training and inference 
+  tasks in parallel, enabling optimized resource utilization and potential overlap 
+  between these phases. This dynamic resource allocation strategy significantly 
+  improves overall system efficiency. The blog presents verl’s performance results, 
+  focusing on throughput and convergence accuracy achieved on AMD Instinct™ MI300X 
+  GPUs. Follow this guide to get started with verl on AMD Instinct GPUs and 
+  accelerate your RLHF training with ROCm-optimized performance.
+
+* The `Exploring Use Cases for Scalable AI: Implementing Ray with ROCm Support for Efficient ML Workflows 
+  <https://rocm.blogs.amd.com/artificial-intelligence/rocm-ray/README.html>`__
+  blog post describes key use cases such as training and inference for large language models (LLMs), 
+  model serving, hyperparameter tuning, reinforcement learning, and the orchestration of large-scale 
+  workloads using Ray in the ROCm environment.
+
+For more use cases and recommendations, see the AMD GPU tabs in the `Accelerator Support 
+topic <https://docs.ray.io/en/latest/ray-core/scheduling/accelerators.html#accelerator-support>`__ 
+of the Ray core documentation and refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for Ray examples and best practices to optimize your workloads on AMD GPUs.
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/ray-history` to find documentation for previous releases
+of the ``ROCm/ray`` Docker image.

docs/compatibility/ml-compatibility/stanford-megatron-lm-compatibility.rst

@@ -0,0 +1,116 @@
+:orphan:
+
+.. meta::
+    :description: Stanford Megatron-LM compatibility
+    :keywords: Stanford, Megatron-LM, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+Stanford Megatron-LM compatibility
+********************************************************************************
+
+Stanford Megatron-LM is a large-scale language model training framework developed 
+by NVIDIA at `https://github.com/NVIDIA/Megatron-LM <https://github.com/NVIDIA/Megatron-LM>`_. 
+It is designed to train massive transformer-based language models efficiently by model 
+and data parallelism. 
+
+It provides efficient tensor, pipeline, and sequence-based model parallelism for 
+pre-training transformer-based language models such as GPT (Decoder Only), BERT 
+(Encoder Only), and T5 (Encoder-Decoder). 
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Stanford Megatron-LM is maintained in the official `https://github.com/ROCm/Stanford-Megatron-LM 
+  <https://github.com/ROCm/Stanford-Megatron-LM>`__ repository, which differs from the 
+  `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`__ upstream repository.
+
+- To get started and install Stanford Megatron-LM on ROCm, use the prebuilt :ref:`Docker image <megatron-lm-docker-compat>`, 
+  which includes ROCm, Stanford Megatron-LM, and all required dependencies.
+
+  - See the :doc:`ROCm Stanford Megatron-LM installation guide <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/NVIDIA/Megatron-LM>`__ 
+    for additional context.
+
+.. _megatron-lm-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `Stanford Megatron-LM images <https://hub.docker.com/r/rocm/stanford-megatron-lm/tags>`_
+with ROCm and Pytorch backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest Stanford Megatron-LM version from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Stanford Megatron-LM
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/stanford-megatron-lm/stanford-megatron-lm85f95ae_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-070556f078be10888a1421a2cb4f48c29f28b02bfeddae02588d1f7fc02a96a6"><i class="fab fa-docker fa-lg"></i> rocm/stanford-megatron-lm</a>
+
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `85f95ae <https://github.com/stanford-futuredata/Megatron-LM/commit/85f95aef3b648075fe6f291c86714fdcbd9cd1f5>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - MI300X
+
+Supported models and features with ROCm 6.3.0
+================================================================================
+
+This section details models & features that are supported by the ROCm version on Stanford Megatron-LM.
+
+Models:
+
+* BERT
+* GPT
+* T5
+* ICT
+
+Features:
+
+* Distributed Pre-training
+* Activation Checkpointing and Recomputation
+* Distributed Optimizer
+* Mixture-of-Experts
+
+.. _megatron-lm-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+The following blog post mentions Megablocks, but you can run Stanford Megatron-LM with the same steps to pre-process datasets on AMD GPUs:
+
+* The `Efficient MoE training on AMD ROCm: How-to use Megablocks on AMD GPUs 
+  <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`__ 
+  blog post guides how to leverage the ROCm platform for pre-training using the 
+  Megablocks framework. It introduces a streamlined approach for training Mixture-of-Experts 
+  (MoE) models using the Megablocks library on AMD hardware. Focusing on GPT-2, it 
+  demonstrates how block-sparse computations can enhance scalability and efficiency in MoE 
+  training. The guide provides step-by-step instructions for setting up the environment, 
+  including cloning the repository, building the Docker image, and running the training container. 
+  Additionally, it offers insights into utilizing the ``oscar-1GB.json`` dataset for pre-training 
+  language models. By leveraging Megablocks and the ROCm platform, you can optimize your MoE 
+  training workflows for large-scale transformer models.
+
+It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
+
+* Single-GPU pre-training
+* Multi-GPU pre-training

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

@@ -0,0 +1,435 @@
+:orphan:
+
+.. meta::
+    :description: TensorFlow compatibility
+    :keywords: GPU, TensorFlow, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+TensorFlow compatibility
+*******************************************************************************
+
+`TensorFlow <https://www.tensorflow.org/>`__ is an open-source library for
+solving machine learning, deep learning, and AI problems. It can solve many
+problems across different sectors and industries, but primarily focuses on
+neural network training and inference. It is one of the most popular deep 
+learning frameworks and is very active in open-source development.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of TensorFlow is maintained in the official `https://github.com/ROCm/tensorflow-upstream 
+  <https://github.com/ROCm/tensorflow-upstream>`__ repository, which differs from the 
+  `https://github.com/tensorflow/tensorflow <https://github.com/tensorflow/tensorflow>`__ upstream repository.
+
+- To get started and install TensorFlow on ROCm, use the prebuilt :ref:`Docker images <tensorflow-docker-compat>`, 
+  which include ROCm, TensorFlow, and all required dependencies.
+
+  - See the :doc:`ROCm TensorFlow installation guide <rocm-install-on-linux:install/3rd-party/tensorflow-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the `TensorFlow API versions <https://www.tensorflow.org/versions>`__ list 
+    for additional context.
+
+Version support
+--------------------------------------------------------------------------------
+
+The `official TensorFlow repository <http://github.com/tensorflow/tensorflow>`__
+includes full ROCm support. AMD maintains a TensorFlow `ROCm repository
+<http://github.com/rocm/tensorflow-upstream>`__ in order to quickly add bug
+fixes, updates, and support for the latest ROCm versions.
+
+.. _tensorflow-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+AMD provides preconfigured Docker images with TensorFlow and the ROCm backend.
+These images are published on `Docker Hub <https://hub.docker.com/r/rocm/tensorflow>`__ and are the
+recommended way to get started with deep learning with TensorFlow on ROCm.
+
+To find the right image tag, see the :ref:`TensorFlow on ROCm installation
+documentation <rocm-install-on-linux:tensorflow-docker-support>` for a list of
+available ``rocm/tensorflow`` images.
+
+
+Critical ROCm libraries for TensorFlow
+===============================================================================
+
+TensorFlow depends on multiple components and the supported features of those
+components can affect the TensorFlow ROCm supported feature set. The versions
+in the following table refer to the first TensorFlow version where the ROCm
+library was introduced as a dependency. The versions described
+are available in ROCm :version:`rocm_version`.
+
+.. list-table::
+    :widths: 25, 10, 35, 30
+    :header-rows: 1
+
+    * - ROCm library
+      - Version
+      - Purpose
+      - Used in
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`__
+      - :version-ref:`hipBLAS rocm_version`
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Accelerates operations like ``tf.matmul``, ``tf.linalg.matmul``, and
+        other matrix multiplications commonly used in neural network layers.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`__
+      - :version-ref:`hipBLASLt rocm_version`
+      - Extends hipBLAS with additional optimizations like fused kernels and
+        integer tensor cores.
+      - Optimizes matrix multiplications and linear algebra operations used in
+        layers like dense, convolutional, and RNNs in TensorFlow.
+    * - `hipCUB <https://github.com/ROCm/hipCUB>`__
+      - :version-ref:`hipCUB rocm_version`
+      - Provides a C++ template library for parallel algorithms for reduction,
+        scan, sort and select.
+      - Supports operations like ``tf.reduce_sum``, ``tf.cumsum``, ``tf.sort``
+        and other tensor operations in TensorFlow, especially those involving
+        scanning, sorting, and filtering.
+    * - `hipFFT <https://github.com/ROCm/hipFFT>`__
+      - :version-ref:`hipFFT rocm_version`
+      - Accelerates Fast Fourier Transforms (FFT) for signal processing tasks.
+      - Used for operations like signal processing, image filtering, and
+        certain types of neural networks requiring FFT-based transformations.
+    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`__
+      - :version-ref:`hipSOLVER rocm_version`
+      - Provides GPU-accelerated direct linear solvers for dense and sparse
+        systems.
+      - Optimizes linear algebra functions such as solving systems of linear
+        equations, often used in optimization and training tasks.
+    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`__
+      - :version-ref:`hipSPARSE rocm_version`
+      - Optimizes sparse matrix operations for efficient computations on sparse
+        data.
+      - Accelerates sparse matrix operations in models with sparse weight
+        matrices or activations, commonly used in neural networks.
+    * - `MIOpen <https://github.com/ROCm/MIOpen>`__
+      - :version-ref:`MIOpen rocm_version`
+      - Provides optimized deep learning primitives such as convolutions,
+        pooling,
+        normalization, and activation functions.
+      - Speeds up convolutional neural networks (CNNs) and other layers. Used
+        in TensorFlow for layers like ``tf.nn.conv2d``, ``tf.nn.relu``, and
+        ``tf.nn.lstm_cell``.
+    * - `RCCL <https://github.com/ROCm/rccl>`__
+      - :version-ref:`RCCL rocm_version`
+      - Optimizes for multi-GPU communication for operations like AllReduce and
+        Broadcast.
+      - Distributed data parallel training (``tf.distribute.MirroredStrategy``).
+        Handles communication in multi-GPU setups.
+    * - `rocThrust <https://github.com/ROCm/rocThrust>`__
+      - :version-ref:`rocThrust rocm_version`
+      - Provides a C++ template library for parallel algorithms like sorting,
+        reduction, and scanning.
+      - Reduction operations like ``tf.reduce_sum``, ``tf.cumsum`` for computing
+        the cumulative sum of elements along a given axis or ``tf.unique`` to
+        finds unique elements in a tensor can use rocThrust.
+
+Supported and unsupported features
+===============================================================================
+
+The following section maps supported data types and GPU-accelerated TensorFlow
+features to their minimum supported ROCm and TensorFlow versions.
+
+Data types
+---------------
+
+The data type of a tensor is specified using the ``dtype`` attribute or
+argument, and TensorFlow supports a wide range of data types for different use
+cases.
+
+The basic, single data types of `tf.dtypes <https://www.tensorflow.org/api_docs/python/tf/dtypes>`__
+are as follows:
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since TensorFlow
+      - Since ROCm
+    * - ``bfloat16``
+      - 16-bit bfloat (brain floating point).
+      - 1.0.0
+      - 1.7
+    * - ``bool``
+      - Boolean.
+      - 1.0.0
+      - 1.7
+    * - ``complex128``
+      - 128-bit complex.
+      - 1.0.0
+      - 1.7
+    * - ``complex64``
+      - 64-bit complex.
+      - 1.0.0
+      - 1.7
+    * - ``double``
+      - 64-bit (double precision) floating-point.
+      - 1.0.0
+      - 1.7
+    * - ``float16``
+      - 16-bit (half precision) floating-point.
+      - 1.0.0
+      - 1.7
+    * - ``float32``
+      - 32-bit (single precision) floating-point.
+      - 1.0.0
+      - 1.7
+    * - ``float64``
+      - 64-bit (double precision) floating-point.
+      - 1.0.0
+      - 1.7
+    * - ``half``
+      - 16-bit (half precision) floating-point.
+      - 2.0.0
+      - 2.0
+    * - ``int16``
+      - Signed 16-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``int32``
+      - Signed 32-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``int64``
+      - Signed 64-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``int8``
+      - Signed 8-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``qint16``
+      - Signed quantized 16-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``qint32``
+      - Signed quantized 32-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``qint8``
+      - Signed quantized 8-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``quint16``
+      - Unsigned quantized 16-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``quint8``
+      - Unsigned quantized 8-bit integer.
+      - 1.0.0
+      - 1.7
+    * - ``resource``
+      - Handle to a mutable, dynamically allocated resource.
+      - 1.0.0
+      - 1.7
+    * - ``string``
+      - Variable-length string, represented as byte array.
+      - 1.0.0
+      - 1.7
+    * - ``uint16``
+      - Unsigned 16-bit (word) integer.
+      - 1.0.0
+      - 1.7
+    * - ``uint32``
+      - Unsigned 32-bit (dword) integer.
+      - 1.5.0
+      - 1.7
+    * - ``uint64``
+      - Unsigned 64-bit (qword) integer.
+      - 1.5.0
+      - 1.7
+    * - ``uint8``
+      - Unsigned 8-bit (byte) integer.
+      - 1.0.0
+      - 1.7
+    * - ``variant``
+      - Data of arbitrary type (known at runtime).
+      - 1.4.0
+      - 1.7
+
+Features
+---------------
+
+This table provides an overview of key features in TensorFlow and their
+availability in ROCm.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Module
+      - Description
+      - Since TensorFlow
+      - Since ROCm
+    * - ``tf.linalg`` (Linear Algebra)
+      - Operations for matrix and tensor computations, such as
+        ``tf.linalg.matmul`` (matrix multiplication), ``tf.linalg.inv``
+        (matrix inversion) and ``tf.linalg.cholesky`` (Cholesky decomposition).
+        These leverage GPUs for high-performance linear algebra operations.
+      - 1.4
+      - 1.8.2
+    * - ``tf.nn`` (Neural Network Operations)
+      - GPU-accelerated building blocks for deep learning models, such as 2D
+        convolutions with ``tf.nn.conv2d``, max pooling operations with
+        ``tf.nn.max_pool``, activation functions like ``tf.nn.relu`` or softmax
+        for output layers with ``tf.nn.softmax``.
+      - 1.0
+      - 1.8.2
+    * - ``tf.image`` (Image Processing)
+      - GPU-accelerated functions for image preprocessing and augmentations,
+        such as resize images with ``tf.image.resize``, flip images horizontally
+        with ``tf.image.flip_left_right`` and adjust image brightness randomly
+        with ``tf.image.random_brightness``.
+      - 1.1
+      - 1.8.2
+    * - ``tf.keras`` (High-Level API)
+      - GPU acceleration for Keras layers and models, including dense layers
+        (``tf.keras.layers.Dense``), convolutional layers
+        (``tf.keras.layers.Conv2D``) and recurrent layers
+        (``tf.keras.layers.LSTM``).
+      - 1.4
+      - 1.8.2
+    * - ``tf.math`` (Mathematical Operations)
+      - GPU-accelerated mathematical operations, such as sum across dimensions
+        with ``tf.math.reduce_sum``, elementwise exponentiation with
+        ``tf.math.exp`` and sigmoid activation (``tf.math.sigmoid``).
+      - 1.5
+      - 1.8.2
+    * - ``tf.signal`` (Signal Processing)
+      - Functions for spectral analysis and signal transformations.
+      - 1.13
+      - 2.1
+    * - ``tf.data`` (Data Input Pipeline)
+      - GPU-accelerated data preprocessing for efficient input pipelines,
+        Prefetching with ``tf.data.experimental.AUTOTUNE``. GPU-enabled
+        transformations like map and batch.
+      - 1.4
+      - 1.8.2
+    * - ``tf.distribute`` (Distributed Training)
+      - Enabling to scale computations across multiple devices on a single
+        machine or across multiple machines.
+      - 1.13
+      - 2.1
+    * - ``tf.random`` (Random Number Generation)
+      - GPU-accelerated random number generation
+      - 1.12
+      - 1.9.2
+    * - ``tf.TensorArray`` (Dynamic Array Operations)
+      - Enables dynamic tensor manipulation on GPUs.
+      - 1.0
+      - 1.8.2
+    * - ``tf.sparse`` (Sparse Tensor Operations)
+      - GPU-accelerated sparse matrix manipulations.
+      - 1.9
+      - 1.9.0
+    * - ``tf.experimental.numpy``
+      - GPU-accelerated NumPy-like API for numerical computations.
+      - 2.4
+      - 4.1.1
+    * - ``tf.RaggedTensor``
+      - Handling of variable-length sequences and ragged tensors with GPU
+        support.
+      - 1.13
+      - 2.1
+    * - ``tf.function`` with XLA (Accelerated Linear Algebra)
+      - Enable GPU-accelerated functions in optimization.
+      - 1.14
+      - 2.4
+    * - ``tf.quantization``
+      - Quantized operations for inference, accelerated on GPUs.
+      - 1.12
+      - 1.9.2
+
+Distributed library features
+-----------------------------------
+
+Enables developers to scale computations across multiple devices on a single machine or
+across multiple machines.
+
+.. list-table::
+   :header-rows: 1
+
+   * - Feature
+     - Description
+     - Since TensorFlow
+     - Since ROCm
+   * - ``MultiWorkerMirroredStrategy``
+     - Synchronous training across multiple workers using mirrored variables.
+     - 2.0
+     - 3.0
+   * - ``MirroredStrategy``
+     - Synchronous training across multiple GPUs on one machine.
+     - 1.5
+     - 2.5
+   * - ``TPUStrategy``
+     - Efficiently trains models on Google TPUs.
+     - 1.9
+     - ❌
+   * - ``ParameterServerStrategy``
+     - Asynchronous training using parameter servers for variable management.
+     - 2.1
+     - 4.0
+   * - ``CentralStorageStrategy``
+     - Keeps variables on a single device and performs computation on multiple
+       devices.
+     - 2.3
+     - 4.1
+   * - ``CollectiveAllReduceStrategy``
+     - Synchronous training across multiple devices and hosts.
+     - 1.14
+     - 3.5
+   * - Distribution Strategies API
+     - High-level API to simplify distributed training configuration and
+       execution.
+     - 1.10
+     - 3.0
+
+Unsupported TensorFlow features
+===============================================================================
+
+The following are GPU-accelerated TensorFlow features not currently supported by
+ROCm.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Feature
+      - Description
+      - Since TensorFlow
+    * - Mixed Precision with TF32
+      - Mixed precision with TF32 is used for matrix multiplications,
+        convolutions, and other linear algebra operations, particularly in
+        deep learning workloads like CNNs and transformers.
+      - 2.4
+    * - ``tf.distribute.TPUStrategy``
+      - Efficiently trains models on Google TPUs.
+      - 1.9
+
+Use cases and recommendations
+===============================================================================
+
+* The `Training a Neural Collaborative Filtering (NCF) Recommender on an AMD
+  GPU <https://rocm.blogs.amd.com/artificial-intelligence/ncf/README.html>`__
+  blog post discusses training an NCF recommender system using TensorFlow. It
+  explains how NCF improves traditional collaborative filtering methods by
+  leveraging neural networks to model non-linear user-item interactions. The
+  post outlines the implementation using the recommenders library, focusing on
+  the use of implicit data (for example, user interactions like viewing or
+  purchasing) and how it addresses challenges like the lack of negative values.
+
+* The `Creating a PyTorch/TensorFlow code environment on AMD GPUs
+  <https://rocm.blogs.amd.com/software-tools-optimization/pytorch-tensorflow-env/README.html>`__
+  blog post provides instructions for creating a machine learning environment
+  for PyTorch and TensorFlow on AMD GPUs using ROCm. It covers steps like
+  installing the libraries, cloning code repositories, installing dependencies,
+  and troubleshooting potential issues with CUDA-based code. Additionally, it
+  explains how to HIPify code (port CUDA code to HIP) and manage Docker images
+  for a better experience on AMD GPUs. This guide aims to help data scientists
+  and ML practitioners adapt their code for AMD GPUs.
+
+For more use cases and recommendations, see the `ROCm Tensorflow blog posts <https://rocm.blogs.amd.com/blog/tag/tensorflow.html>`__.

docs/compatibility/ml-compatibility/verl-compatibility.rst

@@ -0,0 +1,118 @@
+:orphan:
+
+.. meta::
+   :description: verl compatibility
+   :keywords: GPU, verl, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+verl compatibility
+*******************************************************************************
+
+Volcano Engine Reinforcement Learning for LLMs (`verl <https://verl.readthedocs.io/en/latest/>`__)  
+is a reinforcement learning framework designed for large language models (LLMs). 
+verl offers a scalable, open-source fine-tuning solution by using a hybrid programming model 
+that makes it easy to define and run complex post-training dataflows efficiently. 
+
+Its modular APIs separate computation from data, allowing smooth integration with other frameworks. 
+It also supports flexible model placement across GPUs for efficient scaling on different cluster sizes.
+verl achieves high training and generation throughput by building on existing LLM frameworks. 
+Its 3D-HybridEngine reduces memory use and communication overhead when switching between training 
+and inference, improving overall performance.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of verl is maintained in the official `https://github.com/ROCm/verl 
+  <https://github.com/ROCm/verl>`__ repository, which differs from the 
+  `https://github.com/volcengine/verl <https://github.com/volcengine/verl>`__ upstream repository.
+
+- To get started and install verl on ROCm, use the prebuilt :ref:`Docker image <verl-docker-compat>`, 
+  which includes ROCm, verl, and all required dependencies.
+
+  - See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>`
+    for installation and setup instructions.
+
+  - You can also consult the upstream `verl documentation <https://verl.readthedocs.io/en/latest/>`__ 
+    for additional context.
+
+.. _verl-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `verl Docker images <https://hub.docker.com/r/rocm/verl/tags>`_
+with ROCm backends on Docker Hub. The following Docker image tag and associated inventories 
+represent the latest verl version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table::
+   :header-rows: 1
+   :class: docker-image-compatibility
+
+   * - Docker image
+     - ROCm
+     - verl
+     - Ubuntu
+     - PyTorch
+     - Python
+     - vllm
+     - GPU
+
+   * - .. raw:: html
+
+        <a href="https://hub.docker.com/layers/rocm/verl/verl-0.6.0.amd0_rocm7.0_vllm0.11.0.dev/images/sha256-f70a3ebc94c1f66de42a2fcc3f8a6a8d6d0881eb0e65b6958d7d6d24b3eecb0d"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+     - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+     - `0.6.0 <https://github.com/volcengine/verl/releases/tag/v0.6.0>`__
+     - 22.04
+     - `2.9.0 <https://github.com/ROCm/pytorch/tree/release/2.9-rocm7.x-gfx115x>`__
+     - `3.12.11 <https://www.python.org/downloads/release/python-31211/>`__
+     - `0.11.0 <https://github.com/vllm-project/vllm/releases/tag/v0.11.0>`__
+     - MI300X
+
+   * - .. raw:: html
+
+        <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+     - `6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`__
+     - `0.3.0.post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`__
+     - 20.04
+     - `2.5.0 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
+     - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`__
+     - `0.6.3 <https://github.com/vllm-project/vllm/releases/tag/v0.6.3>`__
+     - MI300X
+
+.. _verl-supported_features:
+
+Supported modules with verl on ROCm
+===============================================================================
+
+The following GPU-accelerated modules are supported with verl on ROCm:
+
+- ``FSDP``: Training engine
+- ``vllm``: Inference engine
+
+.. _verl-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+* The benefits of verl in large-scale reinforcement learning from human feedback 
+  (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD 
+  GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__ 
+  blog. The blog post outlines how the Volcano Engine Reinforcement Learning 
+  (verl) framework integrates with the AMD ROCm platform to optimize training on 
+  AMD Instinct™ GPUs. The guide details the process of building a Docker image, 
+  setting up single-node and multi-node training environments, and highlights 
+  performance benchmarks demonstrating improved throughput and convergence accuracy. 
+  This resource serves as a comprehensive starting point for deploying verl on AMD GPUs, 
+  facilitating efficient RLHF training workflows.
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/verl-history` to find documentation for previous releases
+of the ``ROCm/verl`` Docker image.

docs/conceptual/cmake-packages.rst

@@ -0,0 +1,407 @@
+.. meta::
+   :description: Using CMake
+   :keywords: CMake, dependencies, HIP, C++, AMD, ROCm
+
+*********************************
+Using CMake
+*********************************
+
+Most components in ROCm support CMake. Projects depending on header-only or
+library components typically require CMake 3.5 or higher whereas those wanting
+to make use of the CMake HIP language support will require CMake 3.21 or higher.
+
+Finding dependencies
+====================
+
+.. note::
+
+  For a complete
+  reference on how to deal with dependencies in CMake, refer to the CMake docs
+  on `find_package
+  <https://cmake.org/cmake/help/latest/command/find_package.html>`_ and the
+  `Using Dependencies Guide
+  <https://cmake.org/cmake/help/latest/guide/using-dependencies/index.html>`_
+  to get an overview of CMake related facilities.
+
+In short, CMake supports finding dependencies in two ways:
+
+* In Module mode, it consults a file ``Find<PackageName>.cmake`` which tries to find the component
+  in typical install locations and layouts. CMake ships a few dozen such scripts, but users and projects
+  may ship them as well.
+
+* In Config mode, it locates a file named ``<packagename>-config.cmake`` or
+  ``<PackageName>Config.cmake`` which describes the installed component in all regards needed to
+  consume it.
+
+ROCm predominantly relies on Config mode, one notable exception being the Module
+driving the compilation of HIP programs on NVIDIA runtimes. As such, when
+dependencies are not found in standard system locations, one either has to
+instruct CMake to search for package config files in additional folders using
+the ``CMAKE_PREFIX_PATH`` variable (a semi-colon separated list of file system
+paths), or using ``<PackageName>_ROOT`` variable on a project-specific basis.
+
+There are nearly a dozen ways to set these variables. One may be more convenient
+over the other depending on your workflow. Conceptually the simplest is adding
+it to your CMake configuration command on the command line via
+``-D CMAKE_PREFIX_PATH=....`` . AMD packaged ROCm installs can typically be
+added to the config file search paths such as:
+
+*  Windows: ``-D CMAKE_PREFIX_PATH=${env:HIP_PATH}``
+
+*  Linux: ``-D CMAKE_PREFIX_PATH=/opt/rocm``
+
+ROCm provides the respective *config-file* packages, and this enables
+``find_package`` to be used directly. ROCm does not require any Find module as
+the *config-file* packages are shipped with the upstream projects, such as
+rocPRIM and other ROCm libraries.
+
+For a complete guide on where and how ROCm may be installed on a system, refer
+to the installation guides for
+`Linux <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html>`_
+and
+`Windows <https://rocm.docs.amd.com/projects/install-on-windows/en/latest/index.html>`_.
+
+Using HIP in CMake
+==================
+
+ROCm components providing a C/C++ interface support consumption via any
+C/C++ toolchain that CMake knows how to drive. ROCm also supports the CMake HIP
+language features, allowing users to program using the HIP single-source
+programming model. When a program (or translation-unit) uses the HIP API without
+compiling any GPU device code, HIP can be treated in CMake as a simple C/C++
+library.
+
+Using the HIP single-source programming model
+---------------------------------------------
+
+Source code written in the HIP dialect of C++ typically uses the `.hip`
+extension. When the HIP CMake language is enabled, it will automatically
+associate such source files with the HIP toolchain being used.
+
+.. code-block:: cmake
+
+  cmake_minimum_required(VERSION 3.21) # HIP language support requires 3.21
+  cmake_policy(VERSION 3.21.3...3.27)
+  project(MyProj LANGUAGES HIP)
+  add_executable(MyApp Main.hip)
+
+Should you have existing CUDA code that is from the source compatible subset of
+HIP, you can tell CMake that despite their `.cu` extension, they're HIP sources.
+Do note that this mostly facilitates compiling kernel code-only source files,
+as host-side CUDA API won't compile in this fashion.
+
+.. code-block:: cmake
+
+  add_library(MyLib MyLib.cu)
+  set_source_files_properties(MyLib.cu PROPERTIES LANGUAGE HIP)
+
+CMake itself only hosts part of the HIP language support, such as defining
+HIP-specific properties, etc. while the other half ships with the HIP
+implementation, such as ROCm. CMake will search for a file
+`hip-lang-config.cmake` describing how the the properties defined by CMake
+translate to toolchain invocations. If one installs ROCm using non-standard
+methods or layouts and CMake can't locate this file or detect parts of the SDK,
+there's a catch-all, last resort variable consulted locating this file,
+``-D CMAKE_HIP_COMPILER_ROCM_ROOT:PATH=`` which should be set the root of the
+ROCm installation.
+
+.. note::
+    Imported targets defined by `hip-lang-config.cmake` are for internal use
+    only.
+
+If the user doesn't provide a semi-colon delimited list of device architectures
+via ``CMAKE_HIP_ARCHITECTURES``, CMake will select some sensible default. It is
+advised though that if a user knows what devices they wish to target, then set
+this variable explicitly.
+
+Consuming ROCm C/C++ libraries
+------------------------------
+
+Libraries such as rocBLAS, rocFFT, MIOpen, etc. behave as C/C++ libraries.
+Illustrated in the example below is a C++ application using MIOpen from CMake.
+It calls ``find_package(miopen)``, which provides the ``MIOpen`` imported
+target. This can be linked with ``target_link_libraries``
+
+.. code-block:: cmake
+
+  cmake_minimum_required(VERSION 3.5) # find_package(miopen) requires 3.5
+  cmake_policy(VERSION 3.5...3.27)
+  project(MyProj LANGUAGES CXX)
+  find_package(miopen)
+  add_library(MyLib ...)
+  target_link_libraries(MyLib PUBLIC MIOpen)
+
+.. note::
+
+  Most libraries are designed as host-only API, so using a GPU device
+  compiler is not necessary for downstream projects unless they use GPU device
+  code.
+
+Consuming the HIP API in C++ code
+---------------------------------
+
+Consuming the HIP API without compiling single-source GPU device code can be
+done using any C++ compiler. The ``find_package(hip)`` provides the
+``hip::host`` imported target to use HIP in this scenario.
+
+.. code-block:: cmake
+
+  cmake_minimum_required(VERSION 3.5) # find_package(hip) requires 3.5
+  cmake_policy(VERSION 3.5...3.27)
+  project(MyProj LANGUAGES CXX)
+  find_package(hip REQUIRED)
+  add_executable(MyApp ...)
+  target_link_libraries(MyApp PRIVATE hip::host)
+
+When mixing such ``CXX`` sources with ``HIP`` sources holding device-code, link
+only to `hip::host`. If HIP sources don't have `.hip` as their extension, use
+`set_source_files_properties(<hip_sources>... PROPERTIES LANGUAGE HIP)` on them.
+Linking to `hip::host` will set all the necessary flags for the ``CXX`` sources
+while ``HIP`` sources inherit all flags from the built-in language support.
+Having HIP sources in a target will turn the |LINK_LANG|_ into ``HIP``.
+
+.. |LINK_LANG| replace:: ``LINKER_LANGUAGE``
+.. _LINK_LANG: https://cmake.org/cmake/help/latest/prop_tgt/LINKER_LANGUAGE.html
+
+Compiling device code in C++ language mode
+------------------------------------------
+
+.. attention::
+
+  The workflow detailed here is considered legacy and is shown for
+  understanding's sake. It pre-dates the existence of HIP language support in
+  CMake. If source code has HIP device code in it, it is a HIP source file
+  and should be compiled as such. Only resort to the method below if your
+  HIP-enabled CMake code path can't mandate CMake version 3.21.
+
+If code uses the HIP API and compiles GPU device code, it requires using a
+device compiler. The compiler for CMake can be set using either the
+``CMAKE_C_COMPILER`` and ``CMAKE_CXX_COMPILER`` variable or using the ``CC``
+and ``CXX`` environment variables. This can be set when configuring CMake or
+put into a CMake toolchain file. The device compiler must be set to a
+compiler that supports AMD GPU targets, which is usually Clang.
+
+The ``find_package(hip)`` provides the ``hip::device`` imported target to add
+all the flags necessary for device compilation.
+
+.. code-block:: cmake
+
+  cmake_minimum_required(VERSION 3.8) # cxx_std_11 requires 3.8
+  cmake_policy(VERSION 3.8...3.27)
+  project(MyProj LANGUAGES CXX)
+  find_package(hip REQUIRED)
+  add_library(MyLib ...)
+  target_link_libraries(MyLib PRIVATE hip::device)
+  target_compile_features(MyLib PRIVATE cxx_std_11)
+
+.. note::
+
+  Compiling for the GPU device requires at least C++11.
+
+This project can then be configured with the following CMake commands:
+
+*  Windows: ``cmake -D CMAKE_CXX_COMPILER:PATH=${env:HIP_PATH}\bin\clang++.exe``
+*  Linux: ``cmake -D CMAKE_CXX_COMPILER:PATH=/opt/rocm/bin/amdclang++``
+
+Which use the device compiler provided from the binary packages of
+`ROCm HIP SDK <https://www.amd.com/en/developer/resources/rocm-hub/hip-sdk.html>`_ and
+`repo.radeon.com <https://repo.radeon.com>`_ respectively.
+
+When using the ``CXX`` language support to compile HIP device code, selecting the
+target GPU architectures is done via setting the ``GPU_TARGETS`` variable.
+``CMAKE_HIP_ARCHITECTURES`` only exists when the HIP language is enabled. By
+default, this is set to some subset of the currently supported architectures of
+AMD ROCm. It can be set to the CMake option ``-D GPU_TARGETS="gfx1032;gfx1035"``.
+
+ROCm CMake packages
+-------------------
+
++-----------+----------+--------------------------------------------------------+
+| Component | Package  | Targets                                                |
++===========+==========+========================================================+
+| HIP       | hip      | ``hip::host``, ``hip::device``                         |
++-----------+----------+--------------------------------------------------------+
+| rocPRIM   | rocprim  | ``roc::rocprim``                                       |
++-----------+----------+--------------------------------------------------------+
+| rocThrust | rocthrust| ``roc::rocthrust``                                     |
++-----------+----------+--------------------------------------------------------+
+| hipCUB    | hipcub   | ``hip::hipcub``                                        |
++-----------+----------+--------------------------------------------------------+
+| rocRAND   | rocrand  | ``roc::rocrand``                                       |
++-----------+----------+--------------------------------------------------------+
+| rocBLAS   | rocblas  | ``roc::rocblas``                                       |
++-----------+----------+--------------------------------------------------------+
+| rocSOLVER | rocsolver| ``roc::rocsolver``                                     |
++-----------+----------+--------------------------------------------------------+
+| hipBLAS   | hipblas  | ``roc::hipblas``                                       |
++-----------+----------+--------------------------------------------------------+
+| rocFFT    | rocfft   | ``roc::rocfft``                                        |
++-----------+----------+--------------------------------------------------------+
+| hipFFT    | hipfft   | ``hip::hipfft``                                        |
++-----------+----------+--------------------------------------------------------+
+| rocSPARSE | rocsparse| ``roc::rocsparse``                                     |
++-----------+----------+--------------------------------------------------------+
+| hipSPARSE | hipsparse| ``roc::hipsparse``                                     |
++-----------+----------+--------------------------------------------------------+
+| rocALUTION|rocalution| ``roc::rocalution``                                    |
++-----------+----------+--------------------------------------------------------+
+| RCCL      | rccl     | ``rccl``                                               |
++-----------+----------+--------------------------------------------------------+
+| MIOpen    | miopen   | ``MIOpen``                                             |
++-----------+----------+--------------------------------------------------------+
+| MIGraphX  | migraphx | ``migraphx::migraphx``, ``migraphx::migraphx_c``,      |
+|           |          | ``migraphx::migraphx_cpu``, ``migraphx::migraphx_gpu``,|
+|           |          | ``migraphx::migraphx_onnx``, ``migraphx::migraphx_tf`` |
++-----------+----------+--------------------------------------------------------+
+
+Using CMake presets
+===================
+
+CMake command lines depending on how specific users like to be when compiling
+code can grow to unwieldy lengths. This is the primary reason why projects tend
+to bake script snippets into their build definitions controlling compiler
+warning levels, changing CMake defaults (``CMAKE_BUILD_TYPE`` or
+``BUILD_SHARED_LIBS`` just to name a few) and all sorts anti-patterns, all in
+the name of convenience.
+
+Load on the command-line interface (CLI) starts immediately by selecting a
+toolchain, the set of utilities used to compile programs. To ease some of the
+toolchain related pains, CMake does consult the ``CC`` and ``CXX`` environmental
+variables when setting a default ``CMAKE_C[XX]_COMPILER`` respectively, but that
+is just the tip of the iceberg. There's a fair number of variables related to
+just the toolchain itself (typically supplied using
+`toolchain files <https://cmake.org/cmake/help/latest/manual/cmake-toolchains.7.html>`_
+), and then we still haven't talked about user preference or project-specific
+options.
+
+IDEs supporting CMake (Visual Studio, Visual Studio Code, CLion, etc.) all came
+up with their own way to register command-line fragments of different purpose in
+a setup-and-forget fashion for quick assembly using graphical front-ends. This is
+all nice, but configurations aren't portable, nor can they be reused in
+Continuous Integration (CI) pipelines. CMake has condensed existing practice
+into a portable JSON format that works in all IDEs and can be invoked from any
+command line. This is
+`CMake Presets <https://cmake.org/cmake/help/latest/manual/cmake-presets.7.html>`_.
+
+There are two types of preset files: one supplied by the project, called
+``CMakePresets.json`` which is meant to be committed to version control,
+typically used to drive CI; and one meant for the user to provide, called
+``CMakeUserPresets.json``, typically used to house user preference and adapting
+the build to the user's environment. These JSON files are allowed to include
+other JSON files and the user presets always implicitly includes the non-user
+variant.
+
+Using HIP with presets
+----------------------
+
+Following is an example ``CMakeUserPresets.json`` file which actually compiles
+the `amd/rocm-examples <https://github.com/amd/rocm-examples>`_ suite of sample
+applications on a typical ROCm installation:
+
+.. code-block:: json
+
+  {
+    "version": 3,
+    "cmakeMinimumRequired": {
+      "major": 3,
+      "minor": 21,
+      "patch": 0
+    },
+    "configurePresets": [
+      {
+        "name": "layout",
+        "hidden": true,
+        "binaryDir": "${sourceDir}/build/${presetName}",
+        "installDir": "${sourceDir}/install/${presetName}"
+      },
+      {
+        "name": "generator-ninja-multi-config",
+        "hidden": true,
+        "generator": "Ninja Multi-Config"
+      },
+      {
+        "name": "toolchain-makefiles-c/c++-amdclang",
+        "hidden": true,
+        "cacheVariables": {
+          "CMAKE_C_COMPILER": "/opt/rocm/bin/amdclang",
+          "CMAKE_CXX_COMPILER": "/opt/rocm/bin/amdclang++",
+          "CMAKE_HIP_COMPILER": "/opt/rocm/bin/amdclang++"
+        }
+      },
+      {
+        "name": "clang-strict-iso-high-warn",
+        "hidden": true,
+        "cacheVariables": {
+          "CMAKE_C_FLAGS": "-Wall -Wextra -pedantic",
+          "CMAKE_CXX_FLAGS": "-Wall -Wextra -pedantic",
+          "CMAKE_HIP_FLAGS": "-Wall -Wextra -pedantic"
+        }
+      },
+      {
+        "name": "ninja-mc-rocm",
+        "displayName": "Ninja Multi-Config ROCm",
+        "inherits": [
+          "layout",
+          "generator-ninja-multi-config",
+          "toolchain-makefiles-c/c++-amdclang",
+          "clang-strict-iso-high-warn"
+        ]
+      }
+    ],
+    "buildPresets": [
+      {
+        "name": "ninja-mc-rocm-debug",
+        "displayName": "Debug",
+        "configuration": "Debug",
+        "configurePreset": "ninja-mc-rocm"
+      },
+      {
+        "name": "ninja-mc-rocm-release",
+        "displayName": "Release",
+        "configuration": "Release",
+        "configurePreset": "ninja-mc-rocm"
+      },
+      {
+        "name": "ninja-mc-rocm-debug-verbose",
+        "displayName": "Debug (verbose)",
+        "configuration": "Debug",
+        "configurePreset": "ninja-mc-rocm",
+        "verbose": true
+      },
+      {
+        "name": "ninja-mc-rocm-release-verbose",
+        "displayName": "Release (verbose)",
+        "configuration": "Release",
+        "configurePreset": "ninja-mc-rocm",
+        "verbose": true
+      }
+    ],
+    "testPresets": [
+      {
+        "name": "ninja-mc-rocm-debug",
+        "displayName": "Debug",
+        "configuration": "Debug",
+        "configurePreset": "ninja-mc-rocm",
+        "execution": {
+          "jobs": 0
+        }
+      },
+      {
+        "name": "ninja-mc-rocm-release",
+        "displayName": "Release",
+        "configuration": "Release",
+        "configurePreset": "ninja-mc-rocm",
+        "execution": {
+          "jobs": 0
+        }
+      }
+    ]
+  }
+
+.. note::
+
+  Getting presets to work reliably on Windows requires some CMake improvements
+  and/or support from compiler vendors. (Refer to
+  `Add support to the Visual Studio generators <https://gitlab.kitware.com/cmake/cmake/-/issues/24245>`_
+  and `Sourcing environment scripts <https://gitlab.kitware.com/cmake/cmake/-/issues/21619>`_
+  .)

docs/conceptual/compiler-topics.md

@@ -0,0 +1,14 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="AMD ROCm documentation">
+  <meta name="keywords" content="documentation, guides, installation, compatibility, support,
+  reference, ROCm, AMD">
+</head>
+
+# Using compiler features
+
+The following topics describe using specific features of the compilation tools:
+
+* [ROCm compiler infrastructure](https://rocm.docs.amd.com/projects/llvm-project/en/latest/index.html)
+* [Using AddressSanitizer](https://rocm.docs.amd.com/projects/llvm-project/en/latest/conceptual/using-gpu-sanitizer.html)
+* [OpenMP support](https://rocm.docs.amd.com/projects/llvm-project/en/latest/conceptual/openmp.html)

docs/conceptual/file-reorg.md

@@ -0,0 +1,172 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="ROCm Linux Filesystem Hierarchy Standard reorganization">
+  <meta name="keywords" content="FHS, Linux Filesystem Hierarchy Standard, directory structure,
+  AMD, ROCm">
+</head>
+
+# ROCm Linux Filesystem Hierarchy Standard reorganization
+
+## Introduction
+
+The ROCm Software has adopted the Linux Filesystem Hierarchy Standard (FHS) [https://refspecs.linuxfoundation.org/FHS_3.0/fhs/index.html](https://refspecs.linuxfoundation.org/FHS_3.0/fhs/index.html) in order to to ensure ROCm is consistent with standard open source conventions. The following sections specify how current and future releases of ROCm adhere to FHS, how the previous ROCm file system is supported, and how improved versioning specifications are applied to ROCm.
+
+## Adopting the FHS
+
+In order to standardize ROCm directory structure and directory content layout ROCm has adopted the [FHS](https://refspecs.linuxfoundation.org/FHS_3.0/fhs/index.html), adhering to open source conventions for Linux-based distribution. FHS ensures internal consistency within the ROCm stack, as well as external consistency with other systems and distributions. The ROCm proposed file structure is outlined below:
+
+```none
+/opt/rocm-<ver>
+    | -- bin
+         | -- all public binaries
+    | -- lib
+         | -- lib<soname>.so->lib<soname>.so.major->lib<soname>.so.major.minor.patch
+              (public libaries to link with applications)
+         | -- <component>
+              | -- architecture dependent libraries and binaries used internally by components
+         | -- cmake
+              | -- <component>
+                   | --<component>-config.cmake
+    | -- libexec
+         | -- <component>
+              | -- non ISA/architecture independent executables used internally by components
+    | -- include
+         | -- <component>
+              | -- public header files
+    | -- share
+         | -- html
+              | -- <component>
+                   | -- html documentation
+         | -- info
+              | -- <component>
+                   | -- info files
+         | -- man
+              | -- <component>
+                   | -- man pages
+         | -- doc
+              | -- <component>
+                   | -- license files
+         | -- <component>
+              | -- samples
+              | -- architecture independent misc files
+```
+
+## Changes from earlier ROCm versions
+
+The following table provides a brief overview of the new ROCm FHS layout, compared to the layout of earlier ROCm versions. Note that /opt/ is used to denote the default rocm-installation-path and should be replaced in case of a non-standard installation location of the ROCm distribution.
+
+```none
+ ______________________________________________________
+|  New ROCm Layout            |  Previous ROCm Layout  |
+|_____________________________|________________________|
+| /opt/rocm-<ver>             | /opt/rocm-<ver>        |
+|     | -- bin                |     | -- bin           |
+|     | -- lib                |     | -- lib           |
+|          | -- cmake         |     | -- include       |
+|     | -- libexec            |     | -- <component_1> |
+|     | -- include            |          | -- bin      |
+|          | -- <component_1> |          | -- cmake    |
+|     | -- share              |          | -- doc      |
+|          | -- html          |          | -- lib      |
+|          | -- info          |          | -- include  |
+|          | -- man           |          | -- samples  |
+|          | -- doc           |     | -- <component_n> |
+|          | -- <component_1> |          | -- bin      |
+|               | -- samples  |          | -- cmake    |
+|               | -- ..       |          | -- doc      |
+|          | -- <component_n> |          | -- lib      |
+|               | -- samples  |          | -- include  |
+|               | -- ..       |          | -- samples  |
+|______________________________________________________|
+```
+
+## ROCm FHS reorganization: backward compatibility
+
+The FHS file organization for ROCm was first introduced in the release of ROCm 5.2 . Backward compatibility was implemented to make sure users could still run their ROCm applications while transitioning to the new FHS. ROCm has moved header files and libraries to their new locations as indicated in the above structure, and included symbolic-links and wrapper header files in their old location for backward compatibility. The following sections detail ROCm backward compatibility implementation for wrapper header files, executable files, library files and CMake config files.
+
+### Wrapper header files
+
+Wrapper header files are placed in the old location (
+`/opt/rocm-<ver>/<component>/include`) with a warning message to include files
+from the new location (`/opt/rocm-<ver>/include`) as shown in the example below.
+
+```cpp
+#pragma message "This file is deprecated. Use file from include path /opt/rocm-ver/include/ and prefix with hip."
+#include <hip/hip_runtime.h>
+```
+
+* Starting at ROCm 5.2 release, the deprecation for backward compatibility wrapper header files is: `#pragma` message announcing `#warning`.
+* Starting from ROCm 6.0 (tentatively) backward compatibility for wrapper header files will be removed, and the `#pragma` message will be announcing `#error`.
+
+### Executable files
+
+Executable files are available in the `/opt/rocm-<ver>/bin` folder. For backward
+compatibility, the old library location (`/opt/rocm-<ver>/<component>/bin`) has a
+soft link to the library at the new location. Soft links will be removed in a
+future release, tentatively ROCm v6.0.
+
+```bash
+$ ls -l /opt/rocm/hip/bin/
+lrwxrwxrwx 1 root root   24 Jan 1 23:32 hipcc -> ../../bin/hipcc
+```
+
+### Library files
+
+Library files are available in the `/opt/rocm-<ver>/lib` folder. For backward
+compatibility, the old library location (`/opt/rocm-<ver>/<component>/lib`) has a
+soft link to the library at the new location. Soft links will be removed in a
+future release, tentatively ROCm v6.0.
+
+```shell
+$ ls -l /opt/rocm/hip/lib/
+drwxr-xr-x 4 root root 4096 Jan 1 10:45 cmake
+lrwxrwxrwx 1 root root   24 Jan 1 23:32 libamdhip64.so -> ../../lib/libamdhip64.so
+```
+
+### CMake config files
+
+All CMake configuration files are available in the
+`/opt/rocm-<ver>/lib/cmake/<component>` folder. For backward compatibility, the
+old CMake locations (`/opt/rocm-<ver>/<component>/lib/cmake`) consist of a soft
+link to the new CMake config. Soft links will be removed in a future release,
+tentatively ROCm v6.0.
+
+```shell
+$ ls -l /opt/rocm/hip/lib/cmake/hip/
+lrwxrwxrwx 1 root root 42 Jan 1 23:32 hip-config.cmake -> ../../../../lib/cmake/hip/hip-config.cmake
+```
+
+## Changes required in applications using ROCm
+
+Applications using ROCm are advised to use the new file paths. As the old files
+will be deprecated in a future release. Applications have to make sure to include
+correct header file and use correct search paths.
+
+1. `#include<header_file.h>` needs to be changed to
+   `#include <component/header_file.h>`
+
+   For example: `#include <hip.h>` needs to change
+   to `#include <hip/hip.h>`
+
+2. Any variable in CMake or Makefiles pointing to component folder needs to
+   changed.
+
+   For example: `VAR1=/opt/rocm/hip` needs to be changed to `VAR1=/opt/rocm`
+   `VAR2=/opt/rocm/hsa` needs to be changed to `VAR2=/opt/rocm`
+
+3. Any reference to `/opt/rocm/<component>/bin` or `/opt/rocm/<component>/lib`
+   needs to be changed to `/opt/rocm/bin` and `/opt/rocm/lib/`, respectively.
+
+## Changes in versioning specifications
+
+In order to better manage ROCm dependencies specification and allow smoother releases of ROCm while avoiding dependency conflicts, ROCm software shall adhere to the following scheme when numbering and incrementing ROCm files versions:
+
+rocm-\<ver\>, where \<ver\> = \<x.y.z\>
+
+x.y.z denote: MAJOR.MINOR.PATCH
+
+z: PATCH - increment z when implementing backward compatible bug fixes.
+
+y: MINOR - increment y when implementing minor changes that add functionality but are still backward compatible.
+
+x: MAJOR - increment x when implementing major changes that are not backward compatible.

docs/conceptual/gpu-arch.md

@@ -0,0 +1,73 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="GPU architecture">
+  <meta name="keywords" content="GPU architecture, architecture support, MI200, MI250, RDNA,
+  MI100, AMD Instinct">
+</head>
+
+(gpu-arch-documentation)=
+
+# GPU architecture documentation
+
+:::::{grid} 1 1 2 2
+:gutter: 1
+
+:::{grid-item-card}
+**AMD Instinct MI300 Series**
+
+Review hardware aspects of the AMD Instinct™ MI300 Series GPUs and the CDNA™ 3
+architecture.
+
+* [AMD Instinct™ MI300 microarchitecture](./gpu-arch/mi300.md)
+* [AMD Instinct MI300/CDNA3 ISA](https://www.amd.com/content/dam/amd/en/documents/instinct-tech-docs/instruction-set-architectures/amd-instinct-mi300-cdna3-instruction-set-architecture.pdf)
+* [White paper](https://www.amd.com/content/dam/amd/en/documents/instinct-tech-docs/white-papers/amd-cdna-3-white-paper.pdf)
+* [MI300 performance counters](./gpu-arch/mi300-mi200-performance-counters.rst)
+* [MI350 Series performance counters](./gpu-arch/mi350-performance-counters.rst)
+:::
+
+:::{grid-item-card}
+**AMD Instinct MI200 Series**
+
+Review hardware aspects of the AMD Instinct™ MI200 Series GPUs and the CDNA™ 2
+architecture.
+
+* [AMD Instinct™ MI250 microarchitecture](./gpu-arch/mi250.md)
+* [AMD Instinct MI200/CDNA2 ISA](https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf)
+* [White paper](https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna2-white-paper.pdf)
+* [Performance counters](./gpu-arch/mi300-mi200-performance-counters.rst)
+
+:::
+
+:::{grid-item-card}
+**AMD Instinct MI100**
+
+Review hardware aspects of the AMD Instinct™ MI100 Series GPUs and the CDNA™ 1
+architecture.
+
+* [AMD Instinct™ MI100 microarchitecture](./gpu-arch/mi100.md)
+* [AMD Instinct MI100/CDNA1 ISA](https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf)
+* [White paper](https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna-white-paper.pdf)
+
+:::
+
+:::{grid-item-card}
+**RDNA**
+
+* [AMD RDNA4 ISA](https://www.amd.com/content/dam/amd/en/documents/radeon-tech-docs/instruction-set-architectures/rdna4-instruction-set-architecture.pdf)
+* [AMD RDNA3 ISA](https://www.amd.com/system/files/TechDocs/rdna3-shader-instruction-set-architecture-feb-2023_0.pdf)
+* [AMD RDNA2 ISA](https://www.amd.com/system/files/TechDocs/rdna2-shader-instruction-set-architecture.pdf)
+* [AMD RDNA ISA](https://www.amd.com/system/files/TechDocs/rdna-shader-instruction-set-architecture.pdf)
+
+:::
+
+:::{grid-item-card}
+**Older architectures**
+
+* [AMD Instinct MI50/Vega 7nm ISA](https://www.amd.com/system/files/TechDocs/vega-7nm-shader-instruction-set-architecture.pdf)
+* [AMD Instinct MI25/Vega ISA](https://www.amd.com/system/files/TechDocs/vega-shader-instruction-set-architecture.pdf)
+* [AMD GCN3 ISA](https://www.amd.com/system/files/TechDocs/gcn3-instruction-set-architecture.pdf)
+* [AMD Vega Architecture White Paper](https://en.wikichip.org/w/images/a/a1/vega-whitepaper.pdf)
+
+:::
+
+:::::

docs/conceptual/gpu-arch/mi100.md

@@ -0,0 +1,95 @@
+---
+myst:
+  html_meta:
+    "description lang=en": "Learn about the AMD Instinct MI100 Series architecture."
+    "keywords": "Instinct, MI100, microarchitecture, AMD, ROCm"
+---
+
+# AMD Instinct™ MI100 microarchitecture
+
+The following image shows the node-level architecture of a system that
+comprises two AMD EPYC™ processors and (up to) eight AMD Instinct™ GPUs.
+The two EPYC processors are connected to each other with the AMD Infinity™
+fabric which provides a high-bandwidth (up to 18 GT/sec) and coherent links such
+that each processor can access the available node memory as a single
+shared-memory domain in a non-uniform memory architecture (NUMA) fashion. In a
+2P, or dual-socket, configuration, three AMD Infinity™ fabric links are
+available to connect the processors plus one PCIe Gen 4 x16 link per processor
+can attach additional I/O devices such as the host adapters for the network
+fabric.
+
+![Structure of a single GCD in the AMD Instinct MI100 GPU](../../data/conceptual/gpu-arch/image004.png "Node-level system architecture with two AMD EPYC™ processors and eight AMD Instinct™ GPUs.")
+
+In a typical node configuration, each processor can host up to four AMD
+Instinct™ GPUs that are attached using PCIe Gen 4 links at 16 GT/sec,
+which corresponds to a peak bidirectional link bandwidth of 32 GB/sec. Each hive
+of four GPUs can participate in a fully connected, coherent AMD
+Instinct™ fabric that connects the four GPUs using 23 GT/sec AMD
+Infinity fabric links that run at a higher frequency than the inter-processor
+links. This inter-GPU link can be established in certified server systems if the
+GPUs are mounted in neighboring PCIe slots by installing the AMD Infinity
+Fabric™ bridge for the AMD Instinct™ GPUs.
+
+## Microarchitecture
+
+The microarchitecture of the AMD Instinct GPUs is based on the AMD CDNA
+architecture, which targets compute applications such as high-performance
+computing (HPC) and AI & machine learning (ML) that run on everything from
+individual servers to the world's largest exascale supercomputers. The overall
+system architecture is designed for extreme scalability and compute performance.
+
+![Structure of the AMD Instinct GPU (MI100 generation)](../../data/conceptual/gpu-arch/image005.png "Structure of the AMD Instinct GPU (MI100 generation)")
+
+The above image shows the AMD Instinct GPU with its PCIe Gen 4 x16
+link (16 GT/sec, at the bottom) that connects the GPU to (one of) the host
+processor(s). It also shows the three AMD Infinity Fabric ports that provide
+high-speed links (23 GT/sec, also at the bottom) to the other GPUs of the local
+hive.
+
+On the left and right of the floor plan, the High Bandwidth Memory (HBM)
+attaches via the GPU memory controller.  The MI100 generation of the AMD
+Instinct GPU offers four stacks of HBM generation 2 (HBM2) for a total
+of 32GB with a 4,096bit-wide memory interface. The peak memory bandwidth of the
+attached HBM2 is 1.228 TB/sec at a memory clock frequency of 1.2 GHz.
+
+The execution units of the GPU are depicted in the above image as Compute
+Units (CU). There are a total 120 compute units that are physically organized
+into eight Shader Engines (SE) with fifteen compute units per shader engine.
+Each compute unit is further sub-divided into four SIMD units that process SIMD
+instructions of 16 data elements per instruction. This enables the CU to process
+64 data elements (a so-called 'wavefront') at a peak clock frequency of 1.5 GHz.
+Therefore, the theoretical maximum FP64 peak performance is 11.5 TFLOPS
+(`4 [SIMD units] x 16 [elements per instruction] x 120 [CU] x 1.5 [GHz]`).
+
+![Block diagram of an MI100 compute unit with detailed SIMD view of the AMD CDNA architecture](../../data/conceptual/gpu-arch/image006.png "An MI100 compute unit with detailed SIMD view of the AMD CDNA architecture")
+
+The preceding image shows the block diagram of a single CU of an AMD Instinct™
+MI100 GPU and summarizes how instructions flow through the execution
+engines. The CU fetches the instructions via a 32KB instruction cache and moves
+them forward to execution via a dispatcher. The CU can handle up to ten
+wavefronts at a time and feed their instructions into the execution unit. The
+execution unit contains 256 vector general-purpose registers (VGPR) and 800
+scalar general-purpose registers (SGPR). The VGPR and SGPR are dynamically
+allocated to the executing wavefronts. A wavefront can access a maximum of 102
+scalar registers. Excess scalar-register usage will cause register spilling and
+thus may affect execution performance.
+
+A wavefront can occupy any number of VGPRs from 0 to 256, directly affecting
+occupancy; that is, the number of concurrently active wavefronts in the CU. For
+instance, with 119 VGPRs used, only two wavefronts can be active in the CU at
+the same time. With the instruction latency of four cycles per SIMD instruction,
+the occupancy should be as high as possible such that the compute unit can
+improve execution efficiency by scheduling instructions from multiple
+wavefronts.
+
+:::{table} Peak-performance capabilities of MI100 for different data types.
+:name: mi100-perf
+| Computation and Data Type | FLOPS/CLOCK/CU | Peak TFLOPS |
+| :------------------------ | :------------: | ----------: |
+| Vector FP64               | 64             | 11.5        |
+| Matrix FP32               | 256            | 46.1        |
+| Vector FP32               | 128            | 23.1        |
+| Matrix FP16               | 1024           | 184.6       |
+| Matrix BF16               | 512            | 92.3        |
+
+:::

docs/conceptual/gpu-arch/mi250.md

@@ -0,0 +1,127 @@
+---
+myst:
+  html_meta:
+    "description lang=en": "Learn about the AMD Instinct MI250 Series architecture."
+    "keywords": "Instinct, MI250, microarchitecture, AMD, ROCm"
+---
+
+# AMD Instinct™ MI250 microarchitecture
+
+The microarchitecture of the AMD Instinct MI250 GPU is based on the
+AMD CDNA 2 architecture that targets compute applications such as HPC,
+artificial intelligence (AI), and machine learning (ML) and that run on
+everything from individual servers to the world’s largest exascale
+supercomputers. The overall system architecture is designed for extreme
+scalability and compute performance.
+
+The following image shows the components of a single Graphics Compute Die (GCD) of the CDNA 2 architecture. On the top and the bottom are AMD Infinity Fabric™
+interfaces and their physical links that are used to connect the GPU die to the
+other system-level components of the node (see also Section 2.2). Both
+interfaces can drive four AMD Infinity Fabric links. One of the AMD Infinity
+Fabric links of the controller at the bottom can be configured as a PCIe link.
+Each of the AMD Infinity Fabric links between GPUs can run at up to 25 GT/sec,
+which correlates to a peak transfer bandwidth of 50 GB/sec for a 16-wide link (
+two bytes per transaction). Section 2.2 has more details on the number of AMD
+Infinity Fabric links and the resulting transfer rates between the system-level
+components.
+
+To the left and the right are memory controllers that attach the High Bandwidth
+Memory (HBM) modules to the GCD. AMD Instinct MI250 GPUs use HBM2e, which offers
+a peak memory bandwidth of 1.6 TB/sec per GCD.
+
+The execution units of the GPU are depicted in the following image as Compute
+Units (CU). The MI250 GCD has 104 active CUs. Each compute unit is further
+subdivided into four SIMD units that process SIMD instructions of 16 data
+elements per instruction (for the FP64 data type). This enables the CU to
+process 64 work items (a so-called “wavefront”) at a peak clock frequency of 1.7
+GHz. Therefore, the theoretical maximum FP64 peak performance per GCD is 22.6
+TFLOPS for vector instructions. This equates to 45.3 TFLOPS for vector instructions for both GCDs together. The MI250 compute units also provide specialized
+execution units (also called matrix cores), which are geared toward executing
+matrix operations like matrix-matrix multiplications. For FP64, the peak
+performance of these units amounts to 90.5 TFLOPS.
+
+![Structure of a single GCD in the AMD Instinct MI250 GPU.](../../data/conceptual/gpu-arch/image001.png "Structure of a single GCD in the AMD Instinct MI250 GPU.")
+
+```{list-table} Peak-performance capabilities of the MI250 OAM for different data types.
+:header-rows: 1
+:name: mi250-perf-table
+
+*
+  - Computation and Data Type
+  - FLOPS/CLOCK/CU
+  - Peak TFLOPS
+*
+  - Matrix FP64
+  - 256
+  - 90.5
+*
+  - Vector FP64
+  - 128
+  - 45.3
+*
+  - Matrix FP32
+  - 256
+  - 90.5
+*
+  - Packed FP32
+  - 256
+  - 90.5
+*
+  - Vector FP32
+  - 128
+  - 45.3
+*
+  - Matrix FP16
+  - 1024
+  - 362.1
+*
+  - Matrix BF16
+  - 1024
+  - 362.1
+*
+  - Matrix INT8
+  - 1024
+  - 362.1
+```
+
+The above table summarizes the aggregated peak performance of the AMD Instinct MI250 Open Compute Platform (OCP) Open Accelerator Modules (OAMs) and its two GCDs for different data types and execution units. The middle column lists the peak performance (number of data elements processed in a single instruction) of a single compute unit if a SIMD (or matrix) instruction is being retired in each clock cycle. The third column lists the theoretical peak performance of the OAM module. The theoretical aggregated peak memory bandwidth of the GPU is 3.2 TB/sec (1.6 TB/sec per GCD).
+
+![Dual-GCD architecture of the AMD Instinct MI250 GPUs](../../data/conceptual/gpu-arch/image002.png "Dual-GCD architecture of the AMD Instinct MI250 GPUs")
+
+The following image shows the block diagram of an OAM package that consists
+of two GCDs, each of which constitutes one GPU device in the system. The two
+GCDs in the package are connected via four AMD Infinity Fabric links running at
+a theoretical peak rate of 25 GT/sec, giving 200 GB/sec peak transfer bandwidth
+between the two GCDs of an OAM, or a bidirectional peak transfer bandwidth of
+400 GB/sec for the same.
+
+## Node-level architecture
+
+The following image shows the node-level architecture of a system that is
+based on the AMD Instinct MI250 GPU. The MI250 OAMs attach to the host
+system via PCIe Gen 4 x16 links (yellow lines). Each GCD maintains its own PCIe
+x16 link to the host part of the system. Depending on the server platform, the
+GCD can attach to the AMD EPYC processor directly or via an optional PCIe switch
+. Note that some platforms may offer an x8 interface to the GCDs, which reduces
+the available host-to-GPU bandwidth.
+
+![Block diagram of AMD Instinct MI250 GPUs with 3rd Generation AMD EPYC processor](../../data/conceptual/gpu-arch/image003.png "Block diagram of AMD Instinct MI250 GPUs with 3rd Generation AMD EPYC processor")
+
+The preceding image shows the node-level architecture of a system with AMD
+EPYC processors in a dual-socket configuration and four AMD Instinct MI250
+GPUs. The MI250 OAMs attach to the host processors system via PCIe Gen 4
+x16 links (yellow lines). Depending on the system design, a PCIe switch may
+exist to make more PCIe lanes available for additional components like network
+interfaces and/or storage devices. Each GCD maintains its own PCIe x16 link to
+the host part of the system or to the PCIe switch. Please note, some platforms
+may offer an x8 interface to the GCDs, which will reduce the available
+host-to-GPU bandwidth.
+
+Between the OAMs and their respective GCDs, a peer-to-peer (P2P) network allows
+for direct data exchange between the GPU dies via AMD Infinity Fabric links (
+black, green, and red lines). Each of these 16-wide links connects to one of the
+two GPU dies in the MI250 OAM and operates at 25 GT/sec, which corresponds to a
+theoretical peak transfer rate of 50 GB/sec per link (or 100 GB/sec
+bidirectional peak transfer bandwidth). The GCD pairs 2 and 6 as well as GCDs 0
+and 4 connect via two XGMI links, which is indicated by the thicker red line in
+the preceding image.

docs/conceptual/gpu-arch/mi300-mi200-performance-counters.rst

@@ -0,0 +1,757 @@
+.. meta::
+  :description: MI300 and MI200 Series performance counters and metrics
+  :keywords: MI300, MI200, performance counters, command processor counters
+
+***************************************************************************************************
+MI300 and MI200 Series performance counters and metrics
+***************************************************************************************************
+
+This document lists and describes the hardware performance counters and derived metrics available
+for the AMD Instinct™ MI300 and MI200 GPU. You can also access this information using the
+:doc:`ROCprofiler-SDK <rocprofiler-sdk:how-to/using-rocprofv3>`.
+
+MI300 and MI200 Series performance counters
+===============================================================
+
+Series performance counters include the following categories:
+
+* :ref:`command-processor-counters`
+* :ref:`graphics-register-bus-manager-counters`
+* :ref:`spi-counters`
+* :ref:`compute-unit-counters`
+* :ref:`l1i-and-sl1d-cache-counters`
+* :ref:`vector-l1-cache-subsystem-counters`
+* :ref:`l2-cache-access-counters`
+
+The following sections provide additional details for each category.
+
+.. note::
+
+  Preliminary validation of all MI300 and MI200 Series performance counters is in progress. Those with
+  an asterisk (*) require further evaluation.
+
+.. _command-processor-counters:
+
+Command processor counters
+---------------------------------------------------------------------------------------------------------------
+
+Command processor counters are further classified into command processor-fetcher and command
+processor-compute.
+
+Command processor-fetcher counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``CPF_CMP_UTCL1_STALL_ON_TRANSLATION``", "Cycles", "Number of cycles one of the compute unified translation caches (L1) is stalled waiting on translation"
+  "``CPF_CPF_STAT_BUSY``", "Cycles", "Number of cycles command processor-fetcher is busy"
+  "``CPF_CPF_STAT_IDLE``", "Cycles", "Number of cycles command processor-fetcher is idle"
+  "``CPF_CPF_STAT_STALL``", "Cycles", "Number of cycles command processor-fetcher is stalled"
+  "``CPF_CPF_TCIU_BUSY``", "Cycles", "Number of cycles command processor-fetcher texture cache interface unit interface is busy"
+  "``CPF_CPF_TCIU_IDLE``", "Cycles", "Number of cycles command processor-fetcher texture cache interface unit interface is idle"
+  "``CPF_CPF_TCIU_STALL``", "Cycles", "Number of cycles command processor-fetcher texture cache interface unit interface is stalled waiting on free tags"
+
+The texture cache interface unit is the interface between the command processor and the memory
+system.
+
+Command processor-compute counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``CPC_ME1_BUSY_FOR_PACKET_DECODE``", "Cycles", "Number of cycles command processor-compute micro engine is busy decoding packets"
+  "``CPC_UTCL1_STALL_ON_TRANSLATION``", "Cycles", "Number of cycles one of the unified translation caches (L1) is stalled waiting on translation"
+  "``CPC_CPC_STAT_BUSY``", "Cycles", "Number of cycles command processor-compute is busy"
+  "``CPC_CPC_STAT_IDLE``", "Cycles", "Number of cycles command processor-compute is idle"
+  "``CPC_CPC_STAT_STALL``", "Cycles", "Number of cycles command processor-compute is stalled"
+  "``CPC_CPC_TCIU_BUSY``", "Cycles", "Number of cycles command processor-compute texture cache interface unit interface is busy"
+  "``CPC_CPC_TCIU_IDLE``", "Cycles", "Number of cycles command processor-compute texture cache interface unit interface is idle"
+  "``CPC_CPC_UTCL2IU_BUSY``", "Cycles", "Number of cycles command processor-compute unified translation cache (L2) interface is busy"
+  "``CPC_CPC_UTCL2IU_IDLE``", "Cycles", "Number of cycles command processor-compute unified translation cache (L2) interface is idle"
+  "``CPC_CPC_UTCL2IU_STALL``", "Cycles", "Number of cycles command processor-compute unified translation cache (L2) interface is stalled"
+  "``CPC_ME1_DC0_SPI_BUSY``", "Cycles", "Number of cycles command processor-compute micro engine processor is busy"
+
+The micro engine runs packet-processing firmware on the command processor-compute counter.
+
+.. _graphics-register-bus-manager-counters:
+
+Graphics register bus manager counters
+---------------------------------------------------------------------------------------------------------------
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``GRBM_COUNT``", "Cycles","Number of free-running GPU cycles"
+  "``GRBM_GUI_ACTIVE``", "Cycles", "Number of GPU active cycles"
+  "``GRBM_CP_BUSY``", "Cycles", "Number of cycles any of the command processor blocks are busy"
+  "``GRBM_SPI_BUSY``", "Cycles", "Number of cycles any of the shader processor input is busy in the shader engines"
+  "``GRBM_TA_BUSY``", "Cycles", "Number of cycles any of the texture addressing unit is busy in the shader engines"
+  "``GRBM_TC_BUSY``", "Cycles", "Number of cycles any of the texture cache blocks are busy"
+  "``GRBM_CPC_BUSY``", "Cycles", "Number of cycles the command processor-compute is busy"
+  "``GRBM_CPF_BUSY``", "Cycles", "Number of cycles the command processor-fetcher is busy"
+  "``GRBM_UTCL2_BUSY``", "Cycles", "Number of cycles the unified translation cache (Level 2 [L2]) block is busy"
+  "``GRBM_EA_BUSY``", "Cycles", "Number of cycles the efficiency arbiter block is busy"
+
+Texture cache blocks include:
+
+* Texture cache arbiter
+* Texture cache per pipe, also known as vector Level 1 (L1) cache
+* Texture cache per channel, also known as known as L2 cache
+* Texture cache interface
+
+.. _spi-counters:
+
+Shader processor input counters
+---------------------------------------------------------------------------------------------------------------
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SPI_CSN_BUSY``", "Cycles", "Number of cycles with outstanding waves"
+  "``SPI_CSN_WINDOW_VALID``", "Cycles", "Number of cycles enabled by ``perfcounter_start`` event"
+  "``SPI_CSN_NUM_THREADGROUPS``", "Workgroups", "Number of dispatched workgroups"
+  "``SPI_CSN_WAVE``", "Wavefronts", "Number of dispatched wavefronts"
+  "``SPI_RA_REQ_NO_ALLOC``", "Cycles", "Number of arbiter cycles with requests but no allocation"
+  "``SPI_RA_REQ_NO_ALLOC_CSN``", "Cycles", "Number of arbiter cycles with compute shader (n\ :sup:`th` pipe) requests but no compute shader (n\ :sup:`th` pipe) allocation"
+  "``SPI_RA_RES_STALL_CSN``", "Cycles", "Number of arbiter stall cycles due to shortage of compute shader (n\ :sup:`th` pipe) pipeline slots"
+  "``SPI_RA_TMP_STALL_CSN``", "Cycles", "Number of stall cycles due to shortage of temp space"
+  "``SPI_RA_WAVE_SIMD_FULL_CSN``", "SIMD-cycles", "Accumulated number of single instruction, multiple data (SIMD) per cycle affected by shortage of wave slots for compute shader (n\ :sup:`th` pipe) wave dispatch"
+  "``SPI_RA_VGPR_SIMD_FULL_CSN``", "SIMD-cycles", "Accumulated number of SIMDs per cycle affected by shortage of vector general-purpose register (VGPR) slots for compute shader (n\ :sup:`th` pipe) wave dispatch"
+  "``SPI_RA_SGPR_SIMD_FULL_CSN``", "SIMD-cycles", "Accumulated number of SIMDs per cycle affected by shortage of scalar general-purpose register (SGPR) slots for compute shader (n\ :sup:`th` pipe) wave dispatch"
+  "``SPI_RA_LDS_CU_FULL_CSN``", "CU", "Number of compute units affected by shortage of local data share (LDS) space for compute shader (n\ :sup:`th` pipe) wave dispatch"
+  "``SPI_RA_BAR_CU_FULL_CSN``", "CU", "Number of compute units with compute shader (n\ :sup:`th` pipe) waves waiting at a BARRIER"
+  "``SPI_RA_BULKY_CU_FULL_CSN``", "CU", "Number of compute units with compute shader (n\ :sup:`th` pipe) waves waiting for BULKY resource"
+  "``SPI_RA_TGLIM_CU_FULL_CSN``", "Cycles", "Number of compute shader (n\ :sup:`th` pipe) wave stall cycles due to restriction of ``tg_limit`` for thread group size"
+  "``SPI_RA_WVLIM_STALL_CSN``", "Cycles", "Number of cycles compute shader (n\ :sup:`th` pipe) is stalled due to ``WAVE_LIMIT``"
+  "``SPI_VWC_CSC_WR``", "Qcycles", "Number of quad-cycles taken to initialize VGPRs when launching waves"
+  "``SPI_SWC_CSC_WR``", "Qcycles", "Number of quad-cycles taken to initialize SGPRs when launching waves"
+
+.. _compute-unit-counters:
+
+Compute unit counters
+---------------------------------------------------------------------------------------------------------------
+
+The compute unit counters are further classified into instruction mix, matrix fused multiply-add (FMA)
+operation counters, level counters, wavefront counters, wavefront cycle counters, and LDS counters.
+
+Instruction mix
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SQ_INSTS``", "Instr", "Number of instructions issued"
+  "``SQ_INSTS_VALU``", "Instr", "Number of vector arithmetic logic unit (VALU) instructions including matrix FMA issued"
+  "``SQ_INSTS_VALU_ADD_F16``", "Instr", "Number of VALU half-precision floating-point (F16) ``ADD`` or ``SUB`` instructions issued"
+  "``SQ_INSTS_VALU_MUL_F16``", "Instr", "Number of VALU F16 Multiply instructions issued"
+  "``SQ_INSTS_VALU_FMA_F16``", "Instr", "Number of VALU F16 FMA or multiply-add instructions issued"
+  "``SQ_INSTS_VALU_TRANS_F16``", "Instr", "Number of VALU F16 Transcendental instructions issued"
+  "``SQ_INSTS_VALU_ADD_F32``", "Instr", "Number of VALU full-precision floating-point (F32) ``ADD`` or ``SUB`` instructions issued"
+  "``SQ_INSTS_VALU_MUL_F32``", "Instr", "Number of VALU F32 Multiply instructions issued"
+  "``SQ_INSTS_VALU_FMA_F32``", "Instr", "Number of VALU F32 FMAor multiply-add instructions issued"
+  "``SQ_INSTS_VALU_TRANS_F32``", "Instr", "Number of VALU F32 Transcendental instructions issued"
+  "``SQ_INSTS_VALU_ADD_F64``", "Instr", "Number of VALU F64 ``ADD`` or ``SUB`` instructions issued"
+  "``SQ_INSTS_VALU_MUL_F64``", "Instr", "Number of VALU F64 Multiply instructions issued"
+  "``SQ_INSTS_VALU_FMA_F64``", "Instr", "Number of VALU F64 FMA or multiply-add instructions issued"
+  "``SQ_INSTS_VALU_TRANS_F64``", "Instr", "Number of VALU F64 Transcendental instructions issued"
+  "``SQ_INSTS_VALU_INT32``", "Instr", "Number of VALU 32-bit integer instructions (signed or unsigned) issued"
+  "``SQ_INSTS_VALU_INT64``", "Instr", "Number of VALU 64-bit integer instructions (signed or unsigned) issued"
+  "``SQ_INSTS_VALU_CVT``", "Instr", "Number of VALU Conversion instructions issued"
+  "``SQ_INSTS_VALU_MFMA_I8``", "Instr", "Number of 8-bit Integer matrix FMA instructions issued"
+  "``SQ_INSTS_VALU_MFMA_F16``", "Instr", "Number of F16 matrix FMA instructions issued"
+  "``SQ_INSTS_VALU_MFMA_F32``", "Instr", "Number of F32 matrix FMA instructions issued"
+  "``SQ_INSTS_VALU_MFMA_F64``", "Instr", "Number of F64 matrix FMA instructions issued"
+  "``SQ_INSTS_MFMA``", "Instr", "Number of matrix FMA instructions issued"
+  "``SQ_INSTS_VMEM_WR``", "Instr", "Number of vector memory write instructions (including flat) issued"
+  "``SQ_INSTS_VMEM_RD``", "Instr", "Number of vector memory read instructions (including flat) issued"
+  "``SQ_INSTS_VMEM``", "Instr", "Number of vector memory instructions issued, including both flat and buffer instructions"
+  "``SQ_INSTS_SALU``", "Instr", "Number of scalar arithmetic logic unit (SALU) instructions issued"
+  "``SQ_INSTS_SMEM``", "Instr", "Number of scalar memory instructions issued"
+  "``SQ_INSTS_SMEM_NORM``", "Instr", "Number of scalar memory instructions normalized to match ``smem_level`` issued"
+  "``SQ_INSTS_FLAT``", "Instr", "Number of flat instructions issued"
+  "``SQ_INSTS_FLAT_LDS_ONLY``", "Instr", "**MI200 Series only** Number of FLAT instructions that read/write only from/to LDS issued. Works only if ``EARLY_TA_DONE`` is enabled."
+  "``SQ_INSTS_LDS``", "Instr", "Number of LDS instructions issued **(MI200: includes flat; MI300: does not include flat)**"
+  "``SQ_INSTS_GDS``", "Instr", "Number of global data share instructions issued"
+  "``SQ_INSTS_EXP_GDS``", "Instr", "Number of EXP and global data share instructions excluding skipped export instructions issued"
+  "``SQ_INSTS_BRANCH``", "Instr", "Number of branch instructions issued"
+  "``SQ_INSTS_SENDMSG``", "Instr", "Number of ``SENDMSG`` instructions including ``s_endpgm`` issued"
+  "``SQ_INSTS_VSKIPPED``", "Instr", "Number of vector instructions skipped"
+
+Flat instructions allow read, write, and atomic access to a generic memory address pointer that can
+resolve to any of the following physical memories:
+
+* Global Memory
+* Scratch ("private")
+* LDS ("shared")
+* Invalid - ``MEM_VIOL`` TrapStatus
+
+Matrix fused multiply-add operation counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SQ_INSTS_VALU_MFMA_MOPS_I8``", "IOP", "Number of 8-bit integer matrix FMA ops in the unit of 512"
+  "``SQ_INSTS_VALU_MFMA_MOPS_F16``", "FLOP", "Number of F16 floating matrix FMA ops in the unit of 512"
+  "``SQ_INSTS_VALU_MFMA_MOPS_BF16``", "FLOP", "Number of BF16 floating matrix FMA ops in the unit of 512"
+  "``SQ_INSTS_VALU_MFMA_MOPS_F32``", "FLOP", "Number of F32 floating matrix FMA ops in the unit of 512"
+  "``SQ_INSTS_VALU_MFMA_MOPS_F64``", "FLOP", "Number of F64 floating matrix FMA ops in the unit of 512"
+
+Level counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. note::
+
+  All level counters must be followed by ``SQ_ACCUM_PREV_HIRES`` counter to measure average latency.
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SQ_ACCUM_PREV``", "Count", "Accumulated counter sample value where accumulation takes place once every four cycles"
+  "``SQ_ACCUM_PREV_HIRES``", "Count", "Accumulated counter sample value where accumulation takes place once every cycle"
+  "``SQ_LEVEL_WAVES``", "Waves", "Number of inflight waves"
+  "``SQ_INST_LEVEL_VMEM``", "Instr", "Number of inflight vector memory (including flat) instructions"
+  "``SQ_INST_LEVEL_SMEM``", "Instr", "Number of inflight scalar memory instructions"
+  "``SQ_INST_LEVEL_LDS``", "Instr", "Number of inflight LDS (including flat) instructions"
+  "``SQ_IFETCH_LEVEL``", "Instr", "Number of inflight instruction fetch requests from the cache"
+
+Use the following formulae to calculate latencies:
+
+* Vector memory latency = ``SQ_ACCUM_PREV_HIRES`` divided by ``SQ_INSTS_VMEM``
+* Wave latency = ``SQ_ACCUM_PREV_HIRES`` divided by ``SQ_WAVE``
+* LDS latency = ``SQ_ACCUM_PREV_HIRES`` divided by ``SQ_INSTS_LDS``
+* Scalar memory latency = ``SQ_ACCUM_PREV_HIRES`` divided by ``SQ_INSTS_SMEM_NORM``
+* Instruction fetch latency = ``SQ_ACCUM_PREV_HIRES`` divided by ``SQ_IFETCH``
+
+Wavefront counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SQ_WAVES``", "Waves", "Number of wavefronts dispatched to sequencers, including both new and restored wavefronts"
+  "``SQ_WAVES_SAVED``", "Waves", "Number of context-saved waves"
+  "``SQ_WAVES_RESTORED``", "Waves", "Number of context-restored waves sent to sequencers"
+  "``SQ_WAVES_EQ_64``", "Waves", "Number of wavefronts with exactly 64 active threads sent to sequencers"
+  "``SQ_WAVES_LT_64``", "Waves", "Number of wavefronts with less than 64 active threads sent to sequencers"
+  "``SQ_WAVES_LT_48``", "Waves", "Number of wavefronts with less than 48 active threads sent to sequencers"
+  "``SQ_WAVES_LT_32``", "Waves", "Number of wavefronts with less than 32 active threads sent to sequencers"
+  "``SQ_WAVES_LT_16``", "Waves", "Number of wavefronts with less than 16 active threads sent to sequencers"
+
+Wavefront cycle counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SQ_CYCLES``", "Cycles", "Clock cycles"
+  "``SQ_BUSY_CYCLES``", "Cycles", "Number of cycles while sequencers reports it to be busy"
+  "``SQ_BUSY_CU_CYCLES``", "Qcycles", "Number of quad-cycles each compute unit is busy"
+  "``SQ_VALU_MFMA_BUSY_CYCLES``", "Cycles", "Number of cycles the matrix FMA arithmetic logic unit (ALU) is busy"
+  "``SQ_WAVE_CYCLES``", "Qcycles", "Number of quad-cycles spent by waves in the compute units"
+  "``SQ_WAIT_ANY``", "Qcycles", "Number of quad-cycles spent waiting for anything"
+  "``SQ_WAIT_INST_ANY``", "Qcycles", "Number of quad-cycles spent waiting for any instruction to be issued"
+  "``SQ_ACTIVE_INST_ANY``", "Qcycles", "Number of quad-cycles spent by each wave to work on an instruction"
+  "``SQ_ACTIVE_INST_VMEM``", "Qcycles", "Number of quad-cycles spent by the sequencer instruction arbiter to work on a vector memory instruction"
+  "``SQ_ACTIVE_INST_LDS``", "Qcycles", "Number of quad-cycles spent by the sequencer instruction arbiter to work on an LDS instruction"
+  "``SQ_ACTIVE_INST_VALU``", "Qcycles", "Number of quad-cycles spent by the sequencer instruction arbiter to work on a VALU instruction"
+  "``SQ_ACTIVE_INST_SCA``", "Qcycles", "Number of quad-cycles spent by the sequencer instruction arbiter to work on a SALU or scalar memory instruction"
+  "``SQ_ACTIVE_INST_EXP_GDS``", "Qcycles", "Number of quad-cycles spent by the sequencer instruction arbiter to work on an ``EXPORT`` or ``GDS`` instruction"
+  "``SQ_ACTIVE_INST_MISC``", "Qcycles", "Number of quad-cycles spent by the sequencer instruction arbiter to work on a ``BRANCH`` or ``SENDMSG`` instruction"
+  "``SQ_ACTIVE_INST_FLAT``", "Qcycles", "Number of quad-cycles spent by the sequencer instruction arbiter to work on a flat instruction"
+  "``SQ_INST_CYCLES_VMEM_WR``", "Qcycles", "Number of quad-cycles spent to send addr and cmd data for vector memory write instructions"
+  "``SQ_INST_CYCLES_VMEM_RD``", "Qcycles", "Number of quad-cycles spent to send addr and cmd data for vector memory read instructions"
+  "``SQ_INST_CYCLES_SMEM``", "Qcycles", "Number of quad-cycles spent to execute scalar memory reads"
+  "``SQ_INST_CYCLES_SALU``", "Qcycles", "Number of quad-cycles spent to execute non-memory read scalar operations"
+  "``SQ_THREAD_CYCLES_VALU``", "Qcycles", "Number of quad-cycles spent to execute VALU operations on active threads"
+  "``SQ_WAIT_INST_LDS``", "Qcycles", "Number of quad-cycles spent waiting for LDS instruction to be issued"
+
+``SQ_THREAD_CYCLES_VALU`` is similar to ``INST_CYCLES_VALU``, but it's multiplied by the number of
+active threads.
+
+LDS counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SQ_LDS_ATOMIC_RETURN``", "Cycles", "Number of atomic return cycles in LDS"
+  "``SQ_LDS_BANK_CONFLICT``", "Cycles", "Number of cycles LDS is stalled by bank conflicts"
+  "``SQ_LDS_ADDR_CONFLICT``", "Cycles", "Number of cycles LDS is stalled by address conflicts"
+  "``SQ_LDS_UNALIGNED_STALL``", "Cycles", "Number of cycles LDS is stalled processing flat unaligned load or store operations"
+  "``SQ_LDS_MEM_VIOLATIONS``", "Count", "Number of threads that have a memory violation in the LDS"
+  "``SQ_LDS_IDX_ACTIVE``", "Cycles", "Number of cycles LDS is used for indexed operations"
+
+Miscellaneous counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SQ_IFETCH``", "Count", "Number of instruction fetch requests from L1i, in 32-byte width"
+  "``SQ_ITEMS``", "Threads", "Number of valid items per wave"
+
+.. _l1i-and-sl1d-cache-counters:
+
+L1 instruction cache (L1i) and scalar L1 data cache (L1d) counters
+---------------------------------------------------------------------------------------------------------------
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition"
+
+  "``SQC_ICACHE_REQ``", "Req", "Number of L1 instruction (L1i) cache requests"
+  "``SQC_ICACHE_HITS``", "Count", "Number of L1i cache hits"
+  "``SQC_ICACHE_MISSES``", "Count", "Number of non-duplicate L1i cache misses including uncached requests"
+  "``SQC_ICACHE_MISSES_DUPLICATE``", "Count", "Number of duplicate L1i cache misses whose previous lookup miss on the same cache line is not fulfilled yet"
+  "``SQC_DCACHE_REQ``", "Req", "Number of scalar L1d requests"
+  "``SQC_DCACHE_INPUT_VALID_READYB``", "Cycles", "Number of cycles while sequencer input is valid but scalar L1d is not ready"
+  "``SQC_DCACHE_HITS``", "Count", "Number of scalar L1d hits"
+  "``SQC_DCACHE_MISSES``", "Count", "Number of non-duplicate scalar L1d misses including uncached requests"
+  "``SQC_DCACHE_MISSES_DUPLICATE``", "Count", "Number of duplicate scalar L1d misses"
+  "``SQC_DCACHE_REQ_READ_1``", "Req", "Number of constant cache read requests in a single 32-bit data word"
+  "``SQC_DCACHE_REQ_READ_2``", "Req", "Number of constant cache read requests in two 32-bit data words"
+  "``SQC_DCACHE_REQ_READ_4``", "Req", "Number of constant cache read requests in four 32-bit data words"
+  "``SQC_DCACHE_REQ_READ_8``", "Req", "Number of constant cache read requests in eight 32-bit data words"
+  "``SQC_DCACHE_REQ_READ_16``", "Req", "Number of constant cache read requests in 16 32-bit data words"
+  "``SQC_DCACHE_ATOMIC``", "Req", "Number of atomic requests"
+  "``SQC_TC_REQ``", "Req", "Number of texture cache requests that were issued by instruction and constant caches"
+  "``SQC_TC_INST_REQ``", "Req", "Number of instruction requests to the L2 cache"
+  "``SQC_TC_DATA_READ_REQ``", "Req", "Number of data Read requests to the L2 cache"
+  "``SQC_TC_DATA_WRITE_REQ``", "Req", "Number of data write requests to the L2 cache"
+  "``SQC_TC_DATA_ATOMIC_REQ``", "Req", "Number of data atomic requests to the L2 cache"
+  "``SQC_TC_STALL``", "Cycles", "Number of cycles while the valid requests to the L2 cache are stalled"
+
+.. _vector-l1-cache-subsystem-counters:
+
+Vector L1 cache subsystem counters
+---------------------------------------------------------------------------------------------------------------
+
+The vector L1 cache subsystem counters are further classified into texture addressing unit, texture data
+unit, vector L1d or texture cache per pipe, and texture cache arbiter counters.
+
+Texture addressing unit counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition", "Value range for ``n``"
+
+  "``TA_TA_BUSY[n]``", "Cycles", "Texture addressing unit busy cycles", "0-15"
+  "``TA_TOTAL_WAVEFRONTS[n]``", "Instr", "Number of wavefronts processed by texture addressing unit", "0-15"
+  "``TA_BUFFER_WAVEFRONTS[n]``", "Instr", "Number of buffer wavefronts processed by texture addressing unit", "0-15"
+  "``TA_BUFFER_READ_WAVEFRONTS[n]``", "Instr", "Number of buffer read wavefronts processed by texture addressing unit", "0-15"
+  "``TA_BUFFER_WRITE_WAVEFRONTS[n]``", "Instr", "Number of buffer write wavefronts processed by texture addressing unit", "0-15"
+  "``TA_BUFFER_ATOMIC_WAVEFRONTS[n]``", "Instr", "Number of buffer atomic wavefronts processed by texture addressing unit", "0-15"
+  "``TA_BUFFER_TOTAL_CYCLES[n]``", "Cycles", "Number of buffer cycles (including read and write) issued to texture cache", "0-15"
+  "``TA_BUFFER_COALESCED_READ_CYCLES[n]``", "Cycles", "Number of coalesced buffer read cycles issued to texture cache", "0-15"
+  "``TA_BUFFER_COALESCED_WRITE_CYCLES[n]``", "Cycles", "Number of coalesced buffer write cycles issued to texture cache", "0-15"
+  "``TA_ADDR_STALLED_BY_TC_CYCLES[n]``", "Cycles", "Number of cycles texture addressing unit address path is stalled by texture cache", "0-15"
+  "``TA_DATA_STALLED_BY_TC_CYCLES[n]``", "Cycles", "Number of cycles texture addressing unit data path is stalled by texture cache", "0-15"
+  "``TA_ADDR_STALLED_BY_TD_CYCLES[n]``", "Cycles", "Number of cycles texture addressing unit address path is stalled by texture data unit", "0-15"
+  "``TA_FLAT_WAVEFRONTS[n]``", "Instr", "Number of flat opcode wavefronts processed by texture addressing unit", "0-15"
+  "``TA_FLAT_READ_WAVEFRONTS[n]``", "Instr", "Number of flat opcode read wavefronts processed by texture addressing unit", "0-15"
+  "``TA_FLAT_WRITE_WAVEFRONTS[n]``", "Instr", "Number of flat opcode write wavefronts processed by texture addressing unit", "0-15"
+  "``TA_FLAT_ATOMIC_WAVEFRONTS[n]``", "Instr", "Number of flat opcode atomic wavefronts processed by texture addressing unit", "0-15"
+
+Texture data unit counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition", "Value range for ``n``"
+
+  "``TD_TD_BUSY[n]``", "Cycle", "Texture data unit busy cycles while it is processing or waiting for data", "0-15"
+  "``TD_TC_STALL[n]``", "Cycle", "Number of cycles texture data unit is stalled waiting for texture cache data", "0-15"
+  "``TD_SPI_STALL[n]``", "Cycle", "Number of cycles texture data unit is stalled by shader processor input", "0-15"
+  "``TD_LOAD_WAVEFRONT[n]``", "Instr", "Number of wavefront instructions (read, write, atomic)", "0-15"
+  "``TD_STORE_WAVEFRONT[n]``", "Instr", "Number of write wavefront instructions", "0-15"
+  "``TD_ATOMIC_WAVEFRONT[n]``", "Instr", "Number of atomic wavefront instructions", "0-15"
+  "``TD_COALESCABLE_WAVEFRONT[n]``", "Instr", "Number of coalescable wavefronts according to texture addressing unit", "0-15"
+
+Texture cache per pipe counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition", "Value range for ``n``"
+
+  "``TCP_GATE_EN1[n]``", "Cycles", "Number of cycles vector L1d interface clocks are turned on", "0-15"
+  "``TCP_GATE_EN2[n]``", "Cycles", "Number of cycles vector L1d core clocks are turned on", "0-15"
+  "``TCP_TD_TCP_STALL_CYCLES[n]``", "Cycles", "Number of cycles texture data unit stalls vector L1d", "0-15"
+  "``TCP_TCR_TCP_STALL_CYCLES[n]``", "Cycles", "Number of cycles texture cache router stalls vector L1d", "0-15"
+  "``TCP_READ_TAGCONFLICT_STALL_CYCLES[n]``", "Cycles", "Number of cycles tag RAM conflict stalls on a read", "0-15"
+  "``TCP_WRITE_TAGCONFLICT_STALL_CYCLES[n]``", "Cycles", "Number of cycles tag RAM conflict stalls on a write", "0-15"
+  "``TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES[n]``", "Cycles", "Number of cycles tag RAM conflict stalls on an atomic", "0-15"
+  "``TCP_PENDING_STALL_CYCLES[n]``", "Cycles", "Number of cycles vector L1d is stalled due to data pending from L2 Cache", "0-15"
+  "``TCP_TCP_TA_DATA_STALL_CYCLES``", "Cycles", "Number of cycles texture cache per pipe stalls texture addressing unit data interface", "NA"
+  "``TCP_TA_TCP_STATE_READ[n]``", "Req", "Number of state reads", "0-15"
+  "``TCP_VOLATILE[n]``", "Req", "Number of L1 volatile pixels or buffers from texture addressing unit", "0-15"
+  "``TCP_TOTAL_ACCESSES[n]``", "Req", "Number of vector L1d accesses. Equals ``TCP_PERF_SEL_TOTAL_READ`+`TCP_PERF_SEL_TOTAL_NONREAD``", "0-15"
+  "``TCP_TOTAL_READ[n]``", "Req", "Number of vector L1d read accesses", "0-15"
+  "``TCP_TOTAL_WRITE[n]``", "Req", "Number of vector L1d write accesses", "0-15"
+  "``TCP_TOTAL_ATOMIC_WITH_RET[n]``", "Req", "Number of vector L1d atomic requests with return", "0-15"
+  "``TCP_TOTAL_ATOMIC_WITHOUT_RET[n]``", "Req", "Number of vector L1d atomic without return", "0-15"
+  "``TCP_TOTAL_WRITEBACK_INVALIDATES[n]``", "Count", "Total number of vector L1d writebacks and invalidates", "0-15"
+  "``TCP_UTCL1_REQUEST[n]``", "Req", "Number of address translation requests to unified translation cache (L1)", "0-15"
+  "``TCP_UTCL1_TRANSLATION_HIT[n]``", "Req", "Number of unified translation cache (L1) translation hits", "0-15"
+  "``TCP_UTCL1_TRANSLATION_MISS[n]``", "Req", "Number of unified translation cache (L1) translation misses", "0-15"
+  "``TCP_UTCL1_PERMISSION_MISS[n]``", "Req", "Number of unified translation cache (L1) permission misses", "0-15"
+  "``TCP_TOTAL_CACHE_ACCESSES[n]``", "Req", "Number of vector L1d cache accesses including hits and misses", "0-15"
+  "``TCP_TCP_LATENCY[n]``", "Cycles", "**MI200 Series only** Accumulated wave access latency to vL1D over all wavefronts", "0-15"
+  "``TCP_TCC_READ_REQ_LATENCY[n]``", "Cycles", "**MI200 Series only** Total vL1D to L2 request latency over all wavefronts for reads and atomics with return", "0-15"
+  "``TCP_TCC_WRITE_REQ_LATENCY[n]``", "Cycles", "**MI200 Series only** Total vL1D to L2 request latency over all wavefronts for writes and atomics without return", "0-15"
+  "``TCP_TCC_READ_REQ[n]``", "Req", "Number of read requests to L2 cache", "0-15"
+  "``TCP_TCC_WRITE_REQ[n]``", "Req", "Number of write requests to L2 cache", "0-15"
+  "``TCP_TCC_ATOMIC_WITH_RET_REQ[n]``", "Req", "Number of atomic requests to L2 cache with return", "0-15"
+  "``TCP_TCC_ATOMIC_WITHOUT_RET_REQ[n]``", "Req", "Number of atomic requests to L2 cache without return", "0-15"
+  "``TCP_TCC_NC_READ_REQ[n]``", "Req", "Number of non-coherently cached read requests to L2 cache", "0-15"
+  "``TCP_TCC_UC_READ_REQ[n]``", "Req", "Number of uncached read requests to L2 cache", "0-15"
+  "``TCP_TCC_CC_READ_REQ[n]``", "Req", "Number of coherently cached read requests to L2 cache", "0-15"
+  "``TCP_TCC_RW_READ_REQ[n]``", "Req", "Number of coherently cached with write read requests to L2 cache", "0-15"
+  "``TCP_TCC_NC_WRITE_REQ[n]``", "Req", "Number of non-coherently cached write requests to L2 cache", "0-15"
+  "``TCP_TCC_UC_WRITE_REQ[n]``", "Req", "Number of uncached write requests to L2 cache", "0-15"
+  "``TCP_TCC_CC_WRITE_REQ[n]``", "Req", "Number of coherently cached write requests to L2 cache", "0-15"
+  "``TCP_TCC_RW_WRITE_REQ[n]``", "Req", "Number of coherently cached with write write requests to L2 cache", "0-15"
+  "``TCP_TCC_NC_ATOMIC_REQ[n]``", "Req", "Number of non-coherently cached atomic requests to L2 cache", "0-15"
+  "``TCP_TCC_UC_ATOMIC_REQ[n]``", "Req", "Number of uncached atomic requests to L2 cache", "0-15"
+  "``TCP_TCC_CC_ATOMIC_REQ[n]``", "Req", "Number of coherently cached atomic requests to L2 cache", "0-15"
+  "``TCP_TCC_RW_ATOMIC_REQ[n]``", "Req", "Number of coherently cached with write atomic requests to L2 cache", "0-15"
+
+Note that:
+
+* ``TCP_TOTAL_READ[n]`` = ``TCP_PERF_SEL_TOTAL_HIT_LRU_READ`` + ``TCP_PERF_SEL_TOTAL_MISS_LRU_READ`` + ``TCP_PERF_SEL_TOTAL_MISS_EVICT_READ``
+* ``TCP_TOTAL_WRITE[n]`` = ``TCP_PERF_SEL_TOTAL_MISS_LRU_WRITE``+ ``TCP_PERF_SEL_TOTAL_MISS_EVICT_WRITE``
+* ``TCP_TOTAL_WRITEBACK_INVALIDATES[n]`` = ``TCP_PERF_SEL_TOTAL_WBINVL1``+ ``TCP_PERF_SEL_TOTAL_WBINVL1_VOL``+ ``TCP_PERF_SEL_CP_TCP_INVALIDATE``+ ``TCP_PERF_SEL_SQ_TCP_INVALIDATE_VOL``
+
+Texture cache arbiter counters
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. csv-table::
+  :header: "Hardware counter", "Unit", "Definition", "Value range for ``n``"
+
+  "``TCA_CYCLE[n]``", "Cycles", "Number of texture cache arbiter cycles", "0-31"
+  "``TCA_BUSY[n]``", "Cycles", "Number of cycles texture cache arbiter has a pending request", "0-31"
+
+.. _l2-cache-access-counters:
+
+L2 cache access counters
+---------------------------------------------------------------------------------------------------------------
+
+L2 cache is also known as texture cache per channel.
+
+.. tab-set::
+
+    .. tab-item:: MI300 hardware counter
+
+      .. csv-table::
+        :header: "Hardware counter", "Unit", "Definition", "Value range for ``n``"
+
+        "``TCC_CYCLE[n]``", "Cycles", "Number of L2 cache free-running clocks", "0-31"
+        "``TCC_BUSY[n]``", "Cycles", "Number of L2 cache busy cycles", "0-31"
+        "``TCC_REQ[n]``", "Req", "Number of L2 cache requests of all types (measured at the tag block)", "0-31"
+        "``TCC_STREAMING_REQ[n]``", "Req", "Number of L2 cache streaming requests (measured at the tag block)", "0-31"
+        "``TCC_NC_REQ[n]``", "Req", "Number of non-coherently cached requests (measured at the tag block)", "0-31"
+        "``TCC_UC_REQ[n]``", "Req", "Number of uncached requests. This is measured at the tag block", "0-31"
+        "``TCC_CC_REQ[n]``", "Req", "Number of coherently cached requests. This is measured at the tag block", "0-31"
+        "``TCC_RW_REQ[n]``", "Req", "Number of coherently cached with write requests. This is measured at the tag block", "0-31"
+        "``TCC_PROBE[n]``", "Req", "Number of probe requests", "0-31"
+        "``TCC_PROBE_ALL[n]``", "Req", "Number of external probe requests with ``EA_TCC_preq_all == 1``", "0-31"
+        "``TCC_READ[n]``", "Req", "Number of L2 cache read requests (includes compressed reads but not metadata reads)", "0-31"
+        "``TCC_WRITE[n]``", "Req", "Number of L2 cache write requests", "0-31"
+        "``TCC_ATOMIC[n]``", "Req", "Number of L2 cache atomic requests of all types", "0-31"
+        "``TCC_HIT[n]``", "Req", "Number of L2 cache hits", "0-31"
+        "``TCC_MISS[n]``", "Req", "Number of L2 cache misses", "0-31"
+        "``TCC_WRITEBACK[n]``", "Req", "Number of lines written back to the main memory, including writebacks of dirty lines and uncached write or atomic requests", "0-31"
+        "``TCC_EA0_WRREQ[n]``", "Req", "Number of 32-byte and 64-byte transactions going over the ``TC_EA_wrreq`` interface (doesn't include probe commands)", "0-31"
+        "``TCC_EA0_WRREQ_64B[n]``", "Req", "Total number of 64-byte transactions (write or ``CMPSWAP``) going over the ``TC_EA_wrreq`` interface", "0-31"
+        "``TCC_EA0_WR_UNCACHED_32B[n]``", "Req", "Number of 32 or 64-byte write or atomic going over the ``TC_EA_wrreq`` interface due to uncached traffic", "0-31"
+        "``TCC_EA0_WRREQ_STALL[n]``", "Cycles", "Number of cycles a write request is stalled", "0-31"
+        "``TCC_EA0_WRREQ_IO_CREDIT_STALL[n]``", "Cycles", "Number of cycles an efficiency arbiter write request is stalled due to the interface running out of input-output (IO) credits", "0-31"
+        "``TCC_EA0_WRREQ_GMI_CREDIT_STALL[n]``", "Cycles", "Number of cycles an efficiency arbiter write request is stalled due to the interface running out of GMI credits", "0-31"
+        "``TCC_EA0_WRREQ_DRAM_CREDIT_STALL[n]``", "Cycles", "Number of cycles an efficiency arbiter write request is stalled due to the interface running out of DRAM credits", "0-31"
+        "``TCC_TOO_MANY_EA_WRREQS_STALL[n]``", "Cycles", "Number of cycles the L2 cache is unable to send an efficiency arbiter write request due to it reaching its maximum capacity of pending efficiency arbiter write requests", "0-31"
+        "``TCC_EA0_WRREQ_LEVEL[n]``", "Req", "The accumulated number of efficiency arbiter write requests in flight", "0-31"
+        "``TCC_EA0_ATOMIC[n]``", "Req", "Number of 32-byte or 64-byte atomic requests going over the ``TC_EA_wrreq`` interface", "0-31"
+        "``TCC_EA0_ATOMIC_LEVEL[n]``", "Req", "The accumulated number of efficiency arbiter atomic requests in flight", "0-31"
+        "``TCC_EA0_RDREQ[n]``", "Req", "Number of 32-byte or 64-byte read requests to efficiency arbiter", "0-31"
+        "``TCC_EA0_RDREQ_32B[n]``", "Req", "Number of 32-byte read requests to efficiency arbiter", "0-31"
+        "``TCC_EA0_RD_UNCACHED_32B[n]``", "Req", "Number of 32-byte efficiency arbiter reads due to uncached traffic. A 64-byte request is counted as 2", "0-31"
+        "``TCC_EA0_RDREQ_IO_CREDIT_STALL[n]``", "Cycles", "Number of cycles there is a stall due to the read request interface running out of IO credits", "0-31"
+        "``TCC_EA0_RDREQ_GMI_CREDIT_STALL[n]``", "Cycles", "Number of cycles there is a stall due to the read request interface running out of GMI credits", "0-31"
+        "``TCC_EA0_RDREQ_DRAM_CREDIT_STALL[n]``", "Cycles", "Number of cycles there is a stall due to the read request interface running out of DRAM credits", "0-31"
+        "``TCC_EA0_RDREQ_LEVEL[n]``", "Req", "The accumulated number of efficiency arbiter read requests in flight", "0-31"
+        "``TCC_EA0_RDREQ_DRAM[n]``", "Req", "Number of 32-byte or 64-byte efficiency arbiter read requests to High Bandwidth Memory (HBM)", "0-31"
+        "``TCC_EA0_WRREQ_DRAM[n]``", "Req", "Number of 32-byte or 64-byte efficiency arbiter write requests to HBM", "0-31"
+        "``TCC_TAG_STALL[n]``", "Cycles", "Number of cycles the normal request pipeline in the tag is stalled for any reason", "0-31"
+        "``TCC_NORMAL_WRITEBACK[n]``", "Req", "Number of writebacks due to requests that are not writeback requests", "0-31"
+        "``TCC_ALL_TC_OP_WB_WRITEBACK[n]``", "Req", "Number of writebacks due to all ``TC_OP`` writeback requests", "0-31"
+        "``TCC_NORMAL_EVICT[n]``", "Req", "Number of evictions due to requests that are not invalidate or probe requests", "0-31"
+        "``TCC_ALL_TC_OP_INV_EVICT[n]``", "Req", "Number of evictions due to all ``TC_OP`` invalidate requests", "0-31"
+
+    .. tab-item:: MI200 hardware counter
+
+      .. csv-table::
+        :header: "Hardware counter", "Unit", "Definition", "Value range for ``n``"
+
+        "``TCC_CYCLE[n]``", "Cycles", "Number of L2 cache free-running clocks", "0-31"
+        "``TCC_BUSY[n]``", "Cycles", "Number of L2 cache busy cycles", "0-31"
+        "``TCC_REQ[n]``", "Req", "Number of L2 cache requests of all types (measured at the tag block)", "0-31"
+        "``TCC_STREAMING_REQ[n]``", "Req", "Number of L2 cache streaming requests (measured at the tag block)", "0-31"
+        "``TCC_NC_REQ[n]``", "Req", "Number of non-coherently cached requests (measured at the tag block)", "0-31"
+        "``TCC_UC_REQ[n]``", "Req", "Number of uncached requests. This is measured at the tag block", "0-31"
+        "``TCC_CC_REQ[n]``", "Req", "Number of coherently cached requests. This is measured at the tag block", "0-31"
+        "``TCC_RW_REQ[n]``", "Req", "Number of coherently cached with write requests. This is measured at the tag block", "0-31"
+        "``TCC_PROBE[n]``", "Req", "Number of probe requests", "0-31"
+        "``TCC_PROBE_ALL[n]``", "Req", "Number of external probe requests with ``EA_TCC_preq_all == 1``", "0-31"
+        "``TCC_READ[n]``", "Req", "Number of L2 cache read requests (includes compressed reads but not metadata reads)", "0-31"
+        "``TCC_WRITE[n]``", "Req", "Number of L2 cache write requests", "0-31"
+        "``TCC_ATOMIC[n]``", "Req", "Number of L2 cache atomic requests of all types", "0-31"
+        "``TCC_HIT[n]``", "Req", "Number of L2 cache hits", "0-31"
+        "``TCC_MISS[n]``", "Req", "Number of L2 cache misses", "0-31"
+        "``TCC_WRITEBACK[n]``", "Req", "Number of lines written back to the main memory, including writebacks of dirty lines and uncached write or atomic requests", "0-31"
+        "``TCC_EA_WRREQ[n]``", "Req", "Number of 32-byte and 64-byte transactions going over the ``TC_EA_wrreq`` interface (doesn't include probe commands)", "0-31"
+        "``TCC_EA_WRREQ_64B[n]``", "Req", "Total number of 64-byte transactions (write or ``CMPSWAP``) going over the ``TC_EA_wrreq`` interface", "0-31"
+        "``TCC_EA_WR_UNCACHED_32B[n]``", "Req", "Number of 32 write or atomic going over the ``TC_EA_wrreq`` interface due to uncached traffic. A 64-byte request will be counted as 2", "0-31"
+        "``TCC_EA_WRREQ_STALL[n]``", "Cycles", "Number of cycles a write request is stalled", "0-31"
+        "``TCC_EA_WRREQ_IO_CREDIT_STALL[n]``", "Cycles", "Number of cycles an efficiency arbiter write request is stalled due to the interface running out of input-output (IO) credits", "0-31"
+        "``TCC_EA_WRREQ_GMI_CREDIT_STALL[n]``", "Cycles", "Number of cycles an efficiency arbiter write request is stalled due to the interface running out of GMI credits", "0-31"
+        "``TCC_EA_WRREQ_DRAM_CREDIT_STALL[n]``", "Cycles", "Number of cycles an efficiency arbiter write request is stalled due to the interface running out of DRAM credits", "0-31"
+        "``TCC_TOO_MANY_EA_WRREQS_STALL[n]``", "Cycles", "Number of cycles the L2 cache is unable to send an efficiency arbiter write request due to it reaching its maximum capacity of pending efficiency arbiter write requests", "0-31"
+        "``TCC_EA_WRREQ_LEVEL[n]``", "Req", "The accumulated number of efficiency arbiter write requests in flight", "0-31"
+        "``TCC_EA_ATOMIC[n]``", "Req", "Number of 32-byte or 64-byte atomic requests going over the ``TC_EA_wrreq`` interface", "0-31"
+        "``TCC_EA_ATOMIC_LEVEL[n]``", "Req", "The accumulated number of efficiency arbiter atomic requests in flight", "0-31"
+        "``TCC_EA_RDREQ[n]``", "Req", "Number of 32-byte or 64-byte read requests to efficiency arbiter", "0-31"
+        "``TCC_EA_RDREQ_32B[n]``", "Req", "Number of 32-byte read requests to efficiency arbiter", "0-31"
+        "``TCC_EA_RD_UNCACHED_32B[n]``", "Req", "Number of 32-byte efficiency arbiter reads due to uncached traffic. A 64-byte request is counted as 2", "0-31"
+        "``TCC_EA_RDREQ_IO_CREDIT_STALL[n]``", "Cycles", "Number of cycles there is a stall due to the read request interface running out of IO credits", "0-31"
+        "``TCC_EA_RDREQ_GMI_CREDIT_STALL[n]``", "Cycles", "Number of cycles there is a stall due to the read request interface running out of GMI credits", "0-31"
+        "``TCC_EA_RDREQ_DRAM_CREDIT_STALL[n]``", "Cycles", "Number of cycles there is a stall due to the read request interface running out of DRAM credits", "0-31"
+        "``TCC_EA_RDREQ_LEVEL[n]``", "Req", "The accumulated number of efficiency arbiter read requests in flight", "0-31"
+        "``TCC_EA_RDREQ_DRAM[n]``", "Req", "Number of 32-byte or 64-byte efficiency arbiter read requests to High Bandwidth Memory (HBM)", "0-31"
+        "``TCC_EA_WRREQ_DRAM[n]``", "Req", "Number of 32-byte or 64-byte efficiency arbiter write requests to HBM", "0-31"
+        "``TCC_TAG_STALL[n]``", "Cycles", "Number of cycles the normal request pipeline in the tag is stalled for any reason", "0-31"
+        "``TCC_NORMAL_WRITEBACK[n]``", "Req", "Number of writebacks due to requests that are not writeback requests", "0-31"
+        "``TCC_ALL_TC_OP_WB_WRITEBACK[n]``", "Req", "Number of writebacks due to all ``TC_OP`` writeback requests", "0-31"
+        "``TCC_NORMAL_EVICT[n]``", "Req", "Number of evictions due to requests that are not invalidate or probe requests", "0-31"
+        "``TCC_ALL_TC_OP_INV_EVICT[n]``", "Req", "Number of evictions due to all ``TC_OP`` invalidate requests", "0-31"
+
+Note the following:
+
+* ``TCC_REQ[n]`` may be more than the number of requests arriving at the texture cache per channel,
+  but it's a good indication of the total amount of work that needs to be performed.
+* For ``TCC_EA0_WRREQ[n]``, atomics may travel over the same interface and are generally classified as
+  write requests.
+* CC mtypes can produce uncached requests, and those are included in
+  ``TCC_EA0_WR_UNCACHED_32B[n]``
+* ``TCC_EA0_WRREQ_LEVEL[n]`` is primarily intended to measure average efficiency arbiter write latency.
+
+  * Average write latency = ``TCC_PERF_SEL_EA0_WRREQ_LEVEL`` divided by ``TCC_PERF_SEL_EA0_WRREQ``
+
+* ``TCC_EA0_ATOMIC_LEVEL[n]`` is primarily intended to measure average efficiency arbiter atomic
+  latency
+
+  * Average atomic latency = ``TCC_PERF_SEL_EA0_WRREQ_ATOMIC_LEVEL`` divided by ``TCC_PERF_SEL_EA0_WRREQ_ATOMIC``
+
+* ``TCC_EA0_RDREQ_LEVEL[n]`` is primarily intended to measure average efficiency arbiter read latency.
+
+  * Average read latency = ``TCC_PERF_SEL_EA0_RDREQ_LEVEL`` divided by ``TCC_PERF_SEL_EA0_RDREQ``
+
+* Stalls can occur regardless of the need for a read to be performed
+* Normally, stalls are measured exactly at one point in the pipeline however in the case of
+  ``TCC_TAG_STALL[n]``, probes can stall the pipeline at a variety of places. There is no single point that
+  can accurately measure the total stalls
+
+MI300 and MI200 Series derived metrics list
+==============================================================
+
+.. csv-table::
+  :header: "Hardware counter", "Definition"
+
+  "``ALUStalledByLDS``", "Percentage of GPU time ALU units are stalled due to the LDS input queue being full or the output queue not being ready (value range: 0% (optimal) to 100%)"
+  "``FetchSize``", "Total kilobytes fetched from the video memory; measured with all extra fetches and any cache or memory effects taken into account"
+  "``FlatLDSInsts``", "Average number of flat instructions that read from or write to LDS, run per work item (affected by flow control)"
+  "``FlatVMemInsts``", "Average number of flat instructions that read from or write to the video memory, run per work item (affected by flow control). Includes flat instructions that read from or write to scratch"
+  "``GDSInsts``", "Average number of global data share read or write instructions run per work item (affected by flow control)"
+  "``GPUBusy``", "Percentage of time GPU is busy"
+  "``L2CacheHit``", "Percentage of fetch, write, atomic, and other instructions that hit the data in L2 cache (value range: 0% (no hit) to 100% (optimal))"
+  "``LDSBankConflict``", "Percentage of GPU time LDS is stalled by bank conflicts (value range: 0% (optimal) to 100%)"
+  "``LDSInsts``", "Average number of LDS read or write instructions run per work item (affected by flow control). Excludes flat instructions that read from or write to LDS."
+  "``MemUnitBusy``", "Percentage of GPU time the memory unit is active, which is measured with all extra fetches and writes and any cache or memory effects taken into account (value range: 0% to 100% (fetch-bound))"
+  "``MemUnitStalled``", "Percentage of GPU time the memory unit is stalled (value range: 0% (optimal) to 100%)"
+  "``MemWrites32B``", "Total number of effective 32B write transactions to the memory"
+  "``TCA_BUSY_sum``", "Total number of cycles texture cache arbiter has a pending request, over all texture cache arbiter instances"
+  "``TCA_CYCLE_sum``", "Total number of cycles over all texture cache arbiter instances"
+  "``SALUBusy``", "Percentage of GPU time scalar ALU instructions are processed (value range: 0% to 100% (optimal))"
+  "``SALUInsts``", "Average number of scalar ALU instructions run per work item (affected by flow control)"
+  "``SFetchInsts``", "Average number of scalar fetch instructions from the video memory run per work item (affected by flow control)"
+  "``VALUBusy``", "Percentage of GPU time vector ALU instructions are processed (value range: 0% to 100% (optimal))"
+  "``VALUInsts``", "Average number of vector ALU instructions run per work item (affected by flow control)"
+  "``VALUUtilization``", "Percentage of active vector ALU threads in a wave, where a lower number can mean either more thread divergence in a wave or that the work-group size is not a multiple of 64 (value range: 0%, 100% (optimal - no thread divergence))"
+  "``VFetchInsts``", "Average number of vector fetch instructions from the video memory run per work-item (affected by flow control); excludes flat instructions that fetch from video memory"
+  "``VWriteInsts``", "Average number of vector write instructions to the video memory run per work-item (affected by flow control); excludes flat instructions that write to video memory"
+  "``Wavefronts``", "Total wavefronts"
+  "``WRITE_REQ_32B``", "Total number of 32-byte effective memory writes"
+  "``WriteSize``", "Total kilobytes written to the video memory; measured with all extra fetches and any cache or memory effects taken into account"
+  "``WriteUnitStalled``", "Percentage of GPU time the write unit is stalled (value range: 0% (optimal) to 100%)"
+
+You can lower ``ALUStalledByLDS`` by reducing LDS bank conflicts or number of LDS accesses.
+You can lower ``MemUnitStalled`` by reducing the number or size of fetches and writes.
+``MemUnitBusy`` includes the stall time (``MemUnitStalled``).
+
+Hardware counters by and over all texture addressing unit instances
+---------------------------------------------------------------------------------------------------------------
+
+The following table shows the hardware counters *by* all texture addressing unit instances.
+
+.. csv-table::
+  :header: "Hardware counter", "Definition"
+
+  "``TA_BUFFER_WAVEFRONTS_sum``", "Total number of buffer wavefronts processed"
+  "``TA_BUFFER_READ_WAVEFRONTS_sum``", "Total number of buffer read wavefronts processed"
+  "``TA_BUFFER_WRITE_WAVEFRONTS_sum``", "Total number of buffer write wavefronts processed"
+  "``TA_BUFFER_ATOMIC_WAVEFRONTS_sum``", "Total number of buffer atomic wavefronts processed"
+  "``TA_BUFFER_TOTAL_CYCLES_sum``", "Total number of buffer cycles (including read and write) issued to texture cache"
+  "``TA_BUFFER_COALESCED_READ_CYCLES_sum``", "Total number of coalesced buffer read cycles issued to texture cache"
+  "``TA_BUFFER_COALESCED_WRITE_CYCLES_sum``", "Total number of coalesced buffer write cycles issued to texture cache"
+  "``TA_FLAT_READ_WAVEFRONTS_sum``", "Sum of flat opcode reads processed"
+  "``TA_FLAT_WRITE_WAVEFRONTS_sum``", "Sum of flat opcode writes processed"
+  "``TA_FLAT_WAVEFRONTS_sum``", "Total number of flat opcode wavefronts processed"
+  "``TA_FLAT_ATOMIC_WAVEFRONTS_sum``", "Total number of flat opcode atomic wavefronts processed"
+  "``TA_TOTAL_WAVEFRONTS_sum``", "Total number of wavefronts processed"
+
+The following table shows the hardware counters *over* all texture addressing unit instances.
+
+.. csv-table::
+  :header: "Hardware counter", "Definition"
+
+  "``TA_ADDR_STALLED_BY_TC_CYCLES_sum``", "Total number of cycles texture addressing unit address path is stalled by texture cache"
+  "``TA_ADDR_STALLED_BY_TD_CYCLES_sum``", "Total number of cycles texture addressing unit address path is stalled by texture data unit"
+  "``TA_BUSY_avr``", "Average number of busy cycles"
+  "``TA_BUSY_max``", "Maximum number of texture addressing unit busy cycles"
+  "``TA_BUSY_min``", "Minimum number of texture addressing unit busy cycles"
+  "``TA_DATA_STALLED_BY_TC_CYCLES_sum``", "Total number of cycles texture addressing unit data path is stalled by texture cache"
+  "``TA_TA_BUSY_sum``", "Total number of texture addressing unit busy cycles"
+
+Hardware counters over all texture cache per channel instances
+---------------------------------------------------------------------------------------------------------------
+
+.. csv-table::
+  :header: "Hardware counter", "Definition"
+
+  "``TCC_ALL_TC_OP_WB_WRITEBACK_sum``", "Total number of writebacks due to all ``TC_OP`` writeback requests."
+  "``TCC_ALL_TC_OP_INV_EVICT_sum``", "Total number of evictions due to all ``TC_OP`` invalidate requests."
+  "``TCC_ATOMIC_sum``", "Total number of L2 cache atomic requests of all types."
+  "``TCC_BUSY_avr``", "Average number of L2 cache busy cycles."
+  "``TCC_BUSY_sum``", "Total number of L2 cache busy cycles."
+  "``TCC_CC_REQ_sum``", "Total number of coherently cached requests."
+  "``TCC_CYCLE_sum``", "Total number of L2 cache free running clocks."
+  "``TCC_EA0_WRREQ_sum``", "Total number of 32-byte and 64-byte transactions going over the ``TC_EA0_wrreq`` interface. Atomics may travel over the same interface and are generally classified as write requests. This does not include probe commands."
+  "``TCC_EA0_WRREQ_64B_sum``", "Total number of 64-byte transactions (write or `CMPSWAP`) going over the ``TC_EA0_wrreq`` interface."
+  "``TCC_EA0_WR_UNCACHED_32B_sum``", "Total Number of 32-byte write or atomic going over the ``TC_EA0_wrreq`` interface due to uncached traffic. Note that coherently cached mtypes can produce uncached requests, and those are included in this. A 64-byte request is counted as 2."
+  "``TCC_EA0_WRREQ_STALL_sum``", "Total Number of cycles a write request is stalled, over all instances."
+  "``TCC_EA0_WRREQ_IO_CREDIT_STALL_sum``", "Total number of cycles an efficiency arbiter write request is stalled due to the interface running out of IO credits, over all instances."
+  "``TCC_EA0_WRREQ_GMI_CREDIT_STALL_sum``", "Total number of cycles an efficiency arbiter write request is stalled due to the interface running out of GMI credits, over all instances."
+  "``TCC_EA0_WRREQ_DRAM_CREDIT_STALL_sum``", "Total number of cycles an efficiency arbiter write request is stalled due to the interface running out of DRAM credits, over all instances."
+  "``TCC_EA0_WRREQ_LEVEL_sum``", "Total number of efficiency arbiter write requests in flight."
+  "``TCC_EA0_RDREQ_LEVEL_sum``", "Total number of efficiency arbiter read requests in flight."
+  "``TCC_EA0_ATOMIC_sum``", "Total Number of 32-byte or 64-byte atomic requests going over the ``TC_EA0_wrreq`` interface."
+  "``TCC_EA0_ATOMIC_LEVEL_sum``", "Total number of efficiency arbiter atomic requests in flight."
+  "``TCC_EA0_RDREQ_sum``", "Total number of 32-byte or 64-byte read requests to efficiency arbiter."
+  "``TCC_EA0_RDREQ_32B_sum``", "Total number of 32-byte read requests to efficiency arbiter."
+  "``TCC_EA0_RD_UNCACHED_32B_sum``", "Total number of 32-byte efficiency arbiter reads due to uncached traffic."
+  "``TCC_EA0_RDREQ_IO_CREDIT_STALL_sum``", "Total number of cycles there is a stall due to the read request interface running out of IO credits."
+  "``TCC_EA0_RDREQ_GMI_CREDIT_STALL_sum``", "Total number of cycles there is a stall due to the read request interface running out of GMI credits."
+  "``TCC_EA0_RDREQ_DRAM_CREDIT_STALL_sum``", "Total number of cycles there is a stall due to the read request interface running out of DRAM credits."
+  "``TCC_EA0_RDREQ_DRAM_sum``", "Total number of 32-byte or 64-byte efficiency arbiter read requests to HBM."
+  "``TCC_EA0_WRREQ_DRAM_sum``", "Total number of 32-byte or 64-byte efficiency arbiter write requests to HBM."
+  "``TCC_HIT_sum``", "Total number of L2 cache hits."
+  "``TCC_MISS_sum``", "Total number of L2 cache misses."
+  "``TCC_NC_REQ_sum``", "Total number of non-coherently cached requests."
+  "``TCC_NORMAL_WRITEBACK_sum``", "Total number of writebacks due to requests that are not writeback requests."
+  "``TCC_NORMAL_EVICT_sum``", "Total number of evictions due to requests that are not invalidate or probe requests."
+  "``TCC_PROBE_sum``", "Total number of probe requests."
+  "``TCC_PROBE_ALL_sum``", "Total number of external probe requests with ``EA0_TCC_preq_all == 1``."
+  "``TCC_READ_sum``", "Total number of L2 cache read requests (including compressed reads but not metadata reads)."
+  "``TCC_REQ_sum``", "Total number of all types of L2 cache requests."
+  "``TCC_RW_REQ_sum``", "Total number of coherently cached with write requests."
+  "``TCC_STREAMING_REQ_sum``", "Total number of L2 cache streaming requests."
+  "``TCC_TAG_STALL_sum``", "Total number of cycles the normal request pipeline in the tag is stalled for any reason."
+  "``TCC_TOO_MANY_EA0_WRREQS_STALL_sum``", "Total number of cycles L2 cache is unable to send an efficiency arbiter write request due to it reaching its maximum capacity of pending efficiency arbiter write requests."
+  "``TCC_UC_REQ_sum``", "Total number of uncached requests."
+  "``TCC_WRITE_sum``", "Total number of L2 cache write requests."
+  "``TCC_WRITEBACK_sum``", "Total number of lines written back to the main memory including writebacks of dirty lines and uncached write or atomic requests."
+  "``TCC_WRREQ_STALL_max``", "Maximum number of cycles a write request is stalled."
+
+Hardware counters by, for, or over all texture cache per pipe instances
+----------------------------------------------------------------------------------------------------------------
+
+The following table shows the hardware counters *by* all texture cache per pipe instances.
+
+.. csv-table::
+  :header: "Hardware counter", "Definition"
+
+  "``TCP_TA_TCP_STATE_READ_sum``", "Total number of state reads by ATCPPI"
+  "``TCP_TOTAL_CACHE_ACCESSES_sum``", "Total number of vector L1d accesses (including hits and misses)"
+  "``TCP_UTCL1_PERMISSION_MISS_sum``", "Total number of unified translation cache (L1) permission misses"
+  "``TCP_UTCL1_REQUEST_sum``", "Total number of address translation requests to unified translation cache (L1)"
+  "``TCP_UTCL1_TRANSLATION_MISS_sum``", "Total number of unified translation cache (L1) translation misses"
+  "``TCP_UTCL1_TRANSLATION_HIT_sum``", "Total number of unified translation cache (L1) translation hits"
+
+The following table shows the hardware counters *for* all texture cache per pipe instances.
+
+.. csv-table::
+  :header: "Hardware counter", "Definition"
+
+  "``TCP_TCC_READ_REQ_LATENCY_sum``", "Total vector L1d to L2 request latency over all wavefronts for reads and atomics with return"
+  "``TCP_TCC_WRITE_REQ_LATENCY_sum``", "Total vector L1d to L2 request latency over all wavefronts for writes and atomics without return"
+  "``TCP_TCP_LATENCY_sum``", "Total wave access latency to vector L1d over all wavefronts"
+
+The following table shows the hardware counters *over* all texture cache per pipe instances.
+
+.. csv-table::
+  :header: "Hardware counter", "Definition"
+
+  "``TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum``", "Total number of cycles tag RAM conflict stalls on an atomic"
+  "``TCP_GATE_EN1_sum``", "Total number of cycles vector L1d interface clocks are turned on"
+  "``TCP_GATE_EN2_sum``", "Total number of cycles vector L1d core clocks are turned on"
+  "``TCP_PENDING_STALL_CYCLES_sum``", "Total number of cycles vector L1d cache is stalled due to data pending from L2 Cache"
+  "``TCP_READ_TAGCONFLICT_STALL_CYCLES_sum``", "Total number of cycles tag RAM conflict stalls on a read"
+  "``TCP_TCC_ATOMIC_WITH_RET_REQ_sum``", "Total number of atomic requests to L2 cache with return"
+  "``TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum``", "Total number of atomic requests to L2 cache without return"
+  "``TCP_TCC_CC_READ_REQ_sum``", "Total number of coherently cached read requests to L2 cache"
+  "``TCP_TCC_CC_WRITE_REQ_sum``", "Total number of coherently cached write requests to L2 cache"
+  "``TCP_TCC_CC_ATOMIC_REQ_sum``", "Total number of coherently cached atomic requests to L2 cache"
+  "``TCP_TCC_NC_READ_REQ_sum``", "Total number of non-coherently cached read requests to L2 cache"
+  "``TCP_TCC_NC_WRITE_REQ_sum``", "Total number of non-coherently cached write requests to L2 cache"
+  "``TCP_TCC_NC_ATOMIC_REQ_sum``", "Total number of non-coherently cached atomic requests to L2 cache"
+  "``TCP_TCC_READ_REQ_sum``", "Total number of read requests to L2 cache"
+  "``TCP_TCC_RW_READ_REQ_sum``", "Total number of coherently cached with write read requests to L2 cache"
+  "``TCP_TCC_RW_WRITE_REQ_sum``", "Total number of coherently cached with write write requests to L2 cache"
+  "``TCP_TCC_RW_ATOMIC_REQ_sum``", "Total number of coherently cached with write atomic requests to L2 cache"
+  "``TCP_TCC_UC_READ_REQ_sum``", "Total number of uncached read requests to L2 cache"
+  "``TCP_TCC_UC_WRITE_REQ_sum``", "Total number of uncached write requests to L2 cache"
+  "``TCP_TCC_UC_ATOMIC_REQ_sum``", "Total number of uncached atomic requests to L2 cache"
+  "``TCP_TCC_WRITE_REQ_sum``", "Total number of write requests to L2 cache"
+  "``TCP_TCR_TCP_STALL_CYCLES_sum``", "Total number of cycles texture cache router stalls vector L1d"
+  "``TCP_TD_TCP_STALL_CYCLES_sum``", "Total number of cycles texture data unit stalls vector L1d"
+  "``TCP_TOTAL_ACCESSES_sum``", "Total number of vector L1d accesses"
+  "``TCP_TOTAL_READ_sum``", "Total number of vector L1d read accesses"
+  "``TCP_TOTAL_WRITE_sum``", "Total number of vector L1d write accesses"
+  "``TCP_TOTAL_ATOMIC_WITH_RET_sum``", "Total number of vector L1d atomic requests with return"
+  "``TCP_TOTAL_ATOMIC_WITHOUT_RET_sum``", "Total number of vector L1d atomic requests without return"
+  "``TCP_TOTAL_WRITEBACK_INVALIDATES_sum``", "Total number of vector L1d writebacks and invalidates"
+  "``TCP_VOLATILE_sum``", "Total number of L1 volatile pixels or buffers from texture addressing unit"
+  "``TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum``", "Total number of cycles tag RAM conflict stalls on a write"
+
+Hardware counter over all texture data unit instances
+--------------------------------------------------------
+
+.. csv-table::
+  :header: "Hardware counter", "Definition"
+
+  "``TD_ATOMIC_WAVEFRONT_sum``", "Total number of atomic wavefront instructions"
+  "``TD_COALESCABLE_WAVEFRONT_sum``", "Total number of coalescable wavefronts according to texture addressing unit"
+  "``TD_LOAD_WAVEFRONT_sum``", "Total number of wavefront instructions (read, write, atomic)"
+  "``TD_SPI_STALL_sum``", "Total number of cycles texture data unit is stalled by shader processor input"
+  "``TD_STORE_WAVEFRONT_sum``", "Total number of write wavefront instructions"
+  "``TD_TC_STALL_sum``", "Total number of cycles texture data unit is stalled waiting for texture cache data"
+  "``TD_TD_BUSY_sum``", "Total number of texture data unit busy cycles while it is processing or waiting for data"

docs/conceptual/gpu-arch/mi300.md

@@ -0,0 +1,129 @@
+---
+myst:
+  html_meta:
+    "description lang=en": "Learn about the AMD Instinct MI300 Series architecture."
+    "keywords": "Instinct, MI300X, MI300A, microarchitecture, AMD, ROCm"
+---
+
+# AMD Instinct™ MI300 Series microarchitecture
+
+The AMD Instinct MI300 Series GPUs are based on the AMD CDNA 3
+architecture which was designed to deliver leadership performance for HPC, artificial intelligence (AI), and machine
+learning (ML) workloads. The AMD Instinct MI300 Series GPUs are well-suited for extreme scalability and compute performance, running
+on everything from individual servers to the world’s largest exascale supercomputers.
+
+With the MI300 Series, AMD is introducing the Accelerator Complex Die (XCD), which contains the
+GPU computational elements of the processor along with the lower levels of the cache hierarchy.
+
+The following image depicts the structure of a single XCD in the AMD Instinct MI300 GPU Series.
+
+```{figure} ../../data/shared/xcd-sys-arch.png
+---
+name: mi300-xcd
+align: center
+---
+XCD-level system architecture showing 40 Compute Units, each with 32 KB L1 cache, a Unified Compute System with 4 ACE Compute Accelerators, shared 4MB of L2 cache and an HWS Hardware Scheduler.
+```
+
+On the XCD, four Asynchronous Compute Engines (ACEs) send compute shader workgroups to the
+Compute Units (CUs). The XCD has 40 CUs: 38 active CUs at the aggregate level and 2 disabled CUs for
+yield management. The CUs all share a 4 MB L2 cache that serves to coalesce all memory traffic for the
+die. With less than half of the CUs of the AMD Instinct MI200 Series compute die, the AMD CDNA™ 3
+XCD die is a smaller building block. However, it uses more advanced packaging and the processor
+can include 6 or 8 XCDs for up to 304 CUs, roughly 40% more than MI250X.
+
+The MI300 Series integrate up to 8 vertically stacked XCDs, 8 stacks of
+High-Bandwidth Memory 3 (HBM3) and 4 I/O dies (containing system
+infrastructure) using the AMD Infinity Fabric™ technology as interconnect.
+
+The Matrix Cores inside the CDNA 3 CUs have significant improvements, emphasizing AI and machine
+learning, enhancing throughput of existing data types while adding support for new data types.
+CDNA 2 Matrix Cores support FP16 and BF16, while offering INT8 for inference. Compared to MI250X
+GPUs, CDNA 3 Matrix Cores triple the performance for FP16 and BF16, while providing a
+performance gain of 6.8 times for INT8. FP8 has a performance gain of 16 times compared to FP32,
+while TF32 has a gain of 4 times compared to FP32.
+
+```{list-table} Peak-performance capabilities of the MI300X for different data types.
+:header-rows: 1
+:name: mi300x-perf-table
+
+*
+  - Computation and Data Type
+  - FLOPS/CLOCK/CU
+  - Peak TFLOPS
+*
+  - Matrix FP64
+  - 256
+  - 163.4
+*
+  - Vector FP64
+  - 128
+  - 81.7
+*
+  - Matrix FP32
+  - 256
+  - 163.4
+*
+  - Vector FP32
+  - 256
+  - 163.4
+*
+  - Vector TF32
+  - 1024
+  - 653.7
+*
+  - Matrix FP16
+  - 2048
+  - 1307.4
+*
+  - Matrix BF16
+  - 2048
+  - 1307.4
+*
+  - Matrix FP8
+  - 4096
+  - 2614.9
+*
+  - Matrix INT8
+  - 4096
+  - 2614.9
+```
+
+The above table summarizes the aggregated peak performance of the AMD Instinct MI300X Open
+Compute Platform (OCP) Open Accelerator Modules (OAMs) for different data types and command
+processors. The middle column lists the peak performance (number of data elements processed in a
+single instruction) of a single compute unit if a SIMD (or matrix) instruction is submitted in each clock
+cycle. The third column lists the theoretical peak performance of the OAM. The theoretical aggregated
+peak memory bandwidth of the GPU is 5.3 TB per second.
+
+The following image shows the block diagram of the APU (left) and the OAM package (right) both
+connected via AMD Infinity Fabric™ network on-chip.
+
+```{figure} ../../data/conceptual/gpu-arch/image008.png
+---
+name: mi300-arch
+alt:
+align: center
+---
+MI300 Series system architecture showing MI300A (left) with 6 XCDs and 3 CCDs, while the MI300X (right) has 8 XCDs.
+```
+
+## Node-level architecture
+
+```{figure} ../../data/shared/mi300-node-level-arch.png
+---
+name: mi300-node
+
+align: center
+---
+MI300 Series node-level architecture showing 8 fully interconnected MI300X OAM modules connected to (optional) PCIEe switches via retimers and HGX connectors.
+```
+
+The image above shows the node-level architecture of a system with AMD EPYC processors in a
+dual-socket configuration and eight AMD Instinct MI300X GPUs. The MI300X OAMs attach to the
+host system via PCIe Gen 5 x16 links (yellow lines). The GPUs are using seven high-bandwidth,
+low-latency AMD Infinity Fabric™ links (red lines) to form a fully connected 8-GPU system.
+
+<!---
+We need performance data about the P2P communication here.
+-->

docs/conceptual/gpu-arch/mi350-performance-counters.rst

@@ -0,0 +1,530 @@
+.. meta::
+  :description: MI355 Series performance counters and metrics
+  :keywords: MI355, MI355X, MI3XX
+
+***********************************
+MI350 Series performance counters
+***********************************
+
+This topic lists and describes the hardware performance counters and derived metrics available on the AMD Instinct MI350 and MI355 GPUs. These counters are available for profiling using `ROCprofiler-SDK <https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/latest/index.html>`_ and `ROCm Compute Profiler <https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/>`_.
+
+The following sections list the performance counters based on the IP blocks.
+
+Command processor packet processor counters (CPC)
+==================================================
+
+.. list-table::
+    :header-rows: 1
+
+    * - Hardware counter
+      - Definition
+
+    * - CPC_ALWAYS_COUNT
+      - Always count.
+
+    * - CPC_ADC_VALID_CHUNK_NOT_AVAIL
+      - ADC valid chunk is not available when dispatch walking is in progress in the multi-xcc mode.
+
+    * - CPC_ADC_DISPATCH_ALLOC_DONE
+      - ADC dispatch allocation is done.
+
+    * - CPC_ADC_VALID_CHUNK_END
+      - ADC crawler's valid chunk end in the multi-xcc mode.
+
+    * - CPC_SYNC_FIFO_FULL_LEVEL
+      - SYNC FIFO full last cycles.
+
+    * - CPC_SYNC_FIFO_FULL
+      - SYNC FIFO full times.
+
+    * - CPC_GD_BUSY
+      - ADC busy.
+
+    * - CPC_TG_SEND
+      - ADC thread group send.
+
+    * - CPC_WALK_NEXT_CHUNK
+      - ADC walking next valid chunk in the multi-xcc mode.
+
+    * - CPC_STALLED_BY_SE0_SPI
+      - ADC CSDATA stalled by SE0SPI.
+
+    * - CPC_STALLED_BY_SE1_SPI
+      - ADC CSDATA stalled by SE1SPI.
+
+    * - CPC_STALLED_BY_SE2_SPI
+      - ADC CSDATA stalled by SE2SPI.
+
+    * - CPC_STALLED_BY_SE3_SPI
+      - ADC CSDATA stalled by SE3SPI.
+
+    * - CPC_LTE_ALL
+      - CPC sync counter LteAll. Only Master XCD manages LteAll.
+
+    * - CPC_SYNC_WRREQ_FIFO_BUSY
+      - CPC sync counter request FIFO is not empty.
+
+    * - CPC_CANE_BUSY
+      - CPC CANE bus is busy, which indicates the presence of inflight sync counter requests.
+
+    * - CPC_CANE_STALL
+      - CPC sync counter sending is stalled by CANE.
+
+Shader pipe interpolators (SPI) counters
+=========================================
+
+.. list-table::
+    :header-rows: 1
+
+    * - Hardware counter
+      - Definition
+
+    * - SPI_CS0_WINDOW_VALID
+      - Clock count enabled by PIPE0 perfcounter_start event.
+
+    * - SPI_CS0_BUSY
+      - Number of clocks with outstanding waves for PIPE0 (SPI or SH).
+
+    * - SPI_CS0_NUM_THREADGROUPS
+      - Number of thread groups launched for PIPE0.
+
+    * - SPI_CS0_CRAWLER_STALL
+      - Number of clocks when PIPE0 event or wave order FIFO is full.
+
+    * - SPI_CS0_EVENT_WAVE
+      - Number of PIPE0 events and waves.
+
+    * - SPI_CS0_WAVE
+      - Number of PIPE0 waves.
+
+    * - SPI_CS1_WINDOW_VALID
+      - Clock count enabled by PIPE1 perfcounter_start event.
+
+    * - SPI_CS1_BUSY
+      - Number of clocks with outstanding waves for PIPE1 (SPI or SH).
+
+    * - SPI_CS1_NUM_THREADGROUPS
+      - Number of thread groups launched for PIPE1.
+
+    * - SPI_CS1_CRAWLER_STALL
+      - Number of clocks when PIPE1 event or wave order FIFO is full.
+
+    * - SPI_CS1_EVENT_WAVE
+      - Number of PIPE1 events and waves.
+
+    * - SPI_CS1_WAVE
+      - Number of PIPE1 waves.
+
+    * - SPI_CS2_WINDOW_VALID
+      - Clock count enabled by PIPE2 perfcounter_start event.
+
+    * - SPI_CS2_BUSY
+      - Number of clocks with outstanding waves for PIPE2 (SPI or SH).
+
+    * - SPI_CS2_NUM_THREADGROUPS
+      - Number of thread groups launched for PIPE2.
+
+    * - SPI_CS2_CRAWLER_STALL
+      - Number of clocks when PIPE2 event or wave order FIFO is full.
+
+    * - SPI_CS2_EVENT_WAVE
+      - Number of PIPE2 events and waves.
+
+    * - SPI_CS2_WAVE
+      - Number of PIPE2 waves.
+
+    * - SPI_CS3_WINDOW_VALID
+      - Clock count enabled by PIPE3 perfcounter_start event.
+
+    * - SPI_CS3_BUSY
+      - Number of clocks with outstanding waves for PIPE3 (SPI or SH).
+
+    * - SPI_CS3_NUM_THREADGROUPS
+      - Number of thread groups launched for PIPE3.
+
+    * - SPI_CS3_CRAWLER_STALL
+      - Number of clocks when PIPE3 event or wave order FIFO is full.
+
+    * - SPI_CS3_EVENT_WAVE
+      - Number of PIPE3 events and waves.
+
+    * - SPI_CS3_WAVE
+      - Number of PIPE3 waves.
+
+    * - SPI_CSQ_P0_Q0_OCCUPANCY
+      - Sum of occupancy info for PIPE0 Queue0.
+
+    * - SPI_CSQ_P0_Q1_OCCUPANCY
+      - Sum of occupancy info for PIPE0 Queue1.
+
+    * - SPI_CSQ_P0_Q2_OCCUPANCY
+      - Sum of occupancy info for PIPE0 Queue2.
+
+    * - SPI_CSQ_P0_Q3_OCCUPANCY
+      - Sum of occupancy info for PIPE0 Queue3.
+
+    * - SPI_CSQ_P0_Q4_OCCUPANCY
+      - Sum of occupancy info for PIPE0 Queue4.
+
+    * - SPI_CSQ_P0_Q5_OCCUPANCY
+      - Sum of occupancy info for PIPE0 Queue5.
+
+    * - SPI_CSQ_P0_Q6_OCCUPANCY
+      - Sum of occupancy info for PIPE0 Queue6.
+
+    * - SPI_CSQ_P0_Q7_OCCUPANCY
+      - Sum of occupancy info for PIPE0 Queue7.
+
+    * - SPI_CSQ_P1_Q0_OCCUPANCY
+      - Sum of occupancy info for PIPE1 Queue0.
+
+    * - SPI_CSQ_P1_Q1_OCCUPANCY
+      - Sum of occupancy info for PIPE1 Queue1.
+
+    * - SPI_CSQ_P1_Q2_OCCUPANCY
+      - Sum of occupancy info for PIPE1 Queue2.
+
+    * - SPI_CSQ_P1_Q3_OCCUPANCY
+      - Sum of occupancy info for PIPE1 Queue3.
+
+    * - SPI_CSQ_P1_Q4_OCCUPANCY
+      - Sum of occupancy info for PIPE1 Queue4.
+
+    * - SPI_CSQ_P1_Q5_OCCUPANCY
+      - Sum of occupancy info for PIPE1 Queue5.
+
+    * - SPI_CSQ_P1_Q6_OCCUPANCY
+      - Sum of occupancy info for PIPE1 Queue6.
+
+    * - SPI_CSQ_P1_Q7_OCCUPANCY
+      - Sum of occupancy info for PIPE1 Queue7.
+
+    * - SPI_CSQ_P2_Q0_OCCUPANCY
+      - Sum of occupancy info for PIPE2 Queue0.
+
+    * - SPI_CSQ_P2_Q1_OCCUPANCY
+      - Sum of occupancy info for PIPE2 Queue1.
+
+    * - SPI_CSQ_P2_Q2_OCCUPANCY
+      - Sum of occupancy info for PIPE2 Queue2.
+
+    * - SPI_CSQ_P2_Q3_OCCUPANCY
+      - Sum of occupancy info for PIPE2 Queue3.
+
+    * - SPI_CSQ_P2_Q4_OCCUPANCY
+      - Sum of occupancy info for PIPE2 Queue4.
+
+    * - SPI_CSQ_P2_Q5_OCCUPANCY
+      - Sum of occupancy info for PIPE2 Queue5.
+
+    * - SPI_CSQ_P2_Q6_OCCUPANCY
+      - Sum of occupancy info for PIPE2 Queue6.
+
+    * - SPI_CSQ_P2_Q7_OCCUPANCY
+      - Sum of occupancy info for PIPE2 Queue7.
+
+    * - SPI_CSQ_P3_Q0_OCCUPANCY
+      - Sum of occupancy info for PIPE3 Queue0.
+
+    * - SPI_CSQ_P3_Q1_OCCUPANCY
+      - Sum of occupancy info for PIPE3 Queue1.
+
+    * - SPI_CSQ_P3_Q2_OCCUPANCY
+      - Sum of occupancy info for PIPE3 Queue2.
+
+    * - SPI_CSQ_P3_Q3_OCCUPANCY
+      - Sum of occupancy info for PIPE3 Queue3.
+
+    * - SPI_CSQ_P3_Q4_OCCUPANCY
+      - Sum of occupancy info for PIPE3 Queue4.
+
+    * - SPI_CSQ_P3_Q5_OCCUPANCY
+      - Sum of occupancy info for PIPE3 Queue5.
+
+    * - SPI_CSQ_P3_Q6_OCCUPANCY
+      - Sum of occupancy info for PIPE3 Queue6.
+
+    * - SPI_CSQ_P3_Q7_OCCUPANCY
+      - Sum of occupancy info for PIPE3 Queue7.
+
+    * - SPI_CSQ_P0_OCCUPANCY
+      - Sum of occupancy info for all PIPE0 queues.
+
+    * - SPI_CSQ_P1_OCCUPANCY
+      - Sum of occupancy info for all PIPE1 queues.
+
+    * - SPI_CSQ_P2_OCCUPANCY
+      - Sum of occupancy info for all PIPE2 queues.
+
+    * - SPI_CSQ_P3_OCCUPANCY
+      - Sum of occupancy info for all PIPE3 queues.
+
+    * - SPI_VWC0_VDATA_VALID_WR
+      - Number of clocks VGPR bus_0 writes VGPRs.
+
+    * - SPI_VWC1_VDATA_VALID_WR
+      - Number of clocks VGPR bus_1 writes VGPRs.
+
+    * - SPI_CSC_WAVE_CNT_BUSY
+      - Number of cycles when there is any wave in the pipe.
+
+Compute unit (SQ) counters
+===========================
+
+.. list-table::
+    :header-rows: 1
+
+    * - Hardware counter
+      - Definition
+
+    * - SQ_INSTS_VALU_MFMA_F6F4
+      - Number of VALU V_MFMA_*_F6F4 instructions.
+
+    * - SQ_INSTS_VALU_MFMA_MOPS_F6F4
+      - Number of VALU matrix with the performed math operations (add or mul) divided by 512, assuming a full EXEC mask of F6 or F4 data type.
+
+    * - SQ_ACTIVE_INST_VALU2
+      - Number of quad-cycles when two VALU instructions are issued (per-simd, nondeterministic).
+
+    * - SQ_INSTS_LDS_LOAD
+      - Number of LDS load instructions issued (per-simd, emulated).
+
+    * - SQ_INSTS_LDS_STORE
+      - Number of LDS store instructions issued (per-simd, emulated).
+
+    * - SQ_INSTS_LDS_ATOMIC
+      - Number of LDS atomic instructions issued (per-simd, emulated).
+
+    * - SQ_INSTS_LDS_LOAD_BANDWIDTH
+      - Total number of 64-bytes loaded (instrSize * CountOnes(EXEC))/64 (per-simd, emulated).
+
+    * - SQ_INSTS_LDS_STORE_BANDWIDTH
+      - Total number of 64-bytes written (instrSize * CountOnes(EXEC))/64 (per-simd, emulated).
+
+    * - SQ_INSTS_LDS_ATOMIC_BANDWIDTH
+      - Total number of 64-bytes atomic (instrSize * CountOnes(EXEC))/64 (per-simd, emulated).
+
+    * - SQ_INSTS_VALU_FLOPS_FP16
+      - Counts FLOPS per instruction on float 16 excluding MFMA/SMFMA.
+
+    * - SQ_INSTS_VALU_FLOPS_FP32
+      - Counts FLOPS per instruction on float 32 excluding MFMA/SMFMA.
+
+    * - SQ_INSTS_VALU_FLOPS_FP64
+      - Counts FLOPS per instruction on float 64 excluding MFMA/SMFMA.
+
+    * - SQ_INSTS_VALU_FLOPS_FP16_TRANS
+      - Counts FLOPS per instruction on float 16 trans excluding MFMA/SMFMA.
+
+    * - SQ_INSTS_VALU_FLOPS_FP32_TRANS
+      - Counts FLOPS per instruction on float 32 trans excluding MFMA/SMFMA.
+
+    * - SQ_INSTS_VALU_FLOPS_FP64_TRANS
+      - Counts FLOPS per instruction on float 64 trans excluding MFMA/SMFMA.
+
+    * - SQ_INSTS_VALU_IOPS
+      - Counts OPS per instruction on integer or unsigned or bit data (per-simd, emulated).
+
+    * - SQ_LDS_DATA_FIFO_FULL
+      - Number of cycles LDS data FIFO is full (nondeterministic, unwindowed).
+
+    * - SQ_LDS_CMD_FIFO_FULL
+      - Number of cycles LDS command FIFO is full (nondeterministic, unwindowed).
+
+    * - SQ_VMEM_TA_ADDR_FIFO_FULL
+      - Number of cycles texture requests are stalled due to full address FIFO in TA (nondeterministic, unwindowed).
+
+    * - SQ_VMEM_TA_CMD_FIFO_FULL
+      - Number of cycles texture requests are stalled due to full cmd FIFO in TA (nondeterministic, unwindowed).
+
+    * - SQ_VMEM_WR_TA_DATA_FIFO_FULL
+      - Number of cycles texture writes are stalled due to full data FIFO in TA (nondeterministic, unwindowed).
+
+    * - SQC_ICACHE_MISSES_DUPLICATE
+      - Number of duplicate misses (access to a non-resident, miss pending CL) (per-SQ, per-Bank, nondeterministic).
+
+    * - SQC_DCACHE_MISSES_DUPLICATE
+      - Number of duplicate misses (access to a non-resident, miss pending CL) (per-SQ, per-Bank, nondeterministic).
+
+Texture addressing (TA) unit counters
+======================================
+
+.. list-table::
+    :header-rows: 1
+
+    * - Hardware counter
+      - Definition
+
+    * - TA_BUFFER_READ_LDS_WAVEFRONTS
+      - Number of buffer read wavefronts for LDS return processed by the TA.
+
+    * - TA_FLAT_READ_LDS_WAVEFRONTS
+      - Number of flat opcode reads for LDS return processed by the TA.
+
+Texture data (TD) unit counters
+================================
+
+.. list-table::
+    :header-rows: 1
+
+    * - Hardware counter
+      - Definition
+
+    * - TD_WRITE_ACKT_WAVEFRONT
+      - Number of write acknowledgments, sent to SQ and not to SP.
+
+    * - TD_TD_SP_TRAFFIC
+      - Number of times this TD sends data to the SP.
+
+Texture cache per pipe (TCP) counters
+======================================
+
+.. list-table::
+    :header-rows: 1
+
+    * - Hardware counter
+      - Definition
+
+    * - TCP_TCP_TA_ADDR_STALL_CYCLES
+      - TCP stalls TA addr interface.
+
+    * - TCP_TCP_TA_DATA_STALL_CYCLES
+      - TCP stalls TA data interface. Now windowed.
+
+    * - TCP_LFIFO_STALL_CYCLES
+      - Memory latency FIFOs full stall.
+
+    * - TCP_RFIFO_STALL_CYCLES
+      - Memory Request FIFOs full stall.
+
+    * - TCP_TCR_RDRET_STALL
+      - Write into cache stalled by read return from TCR.
+
+    * - TCP_PENDING_STALL_CYCLES
+      - Stall due to data pending from L2.
+
+    * - TCP_UTCL1_SERIALIZATION_STALL
+      - Total number of stalls caused due to serializing translation requests through the UTCL1.
+
+    * - TCP_UTCL1_THRASHING_STALL
+      - Stall caused by thrashing feature in any probe. Lacks accuracy when the stall signal overlaps between probe0 and probe1, which is worse with MECO of thrashing deadlock. Some probe0 events could miss being counted in with MECO on. This perf count provides a rough thrashing estimate.
+
+    * - TCP_UTCL1_TRANSLATION_MISS_UNDER_MISS
+      - Translation miss_under_miss.
+
+    * - TCP_UTCL1_STALL_INFLIGHT_MAX
+      - Total UTCL1 stalls due to inflight counter saturation.
+
+    * - TCP_UTCL1_STALL_LRU_INFLIGHT
+      - Total UTCL1 stalls due to LRU cache line with inflight traffic.
+
+    * - TCP_UTCL1_STALL_MULTI_MISS
+      - Total UTCL1 stalls due to arbitrated multiple misses.
+
+    * - TCP_UTCL1_LFIFO_FULL
+      - Total UTCL1 and UTCL2 latency, which hides FIFO full cycles.
+
+    * - TCP_UTCL1_STALL_LFIFO_NOT_RES
+      - Total UTCL1 stalls due to UTCL2 latency, which hides FIFO output (not resident).
+
+    * - TCP_UTCL1_STALL_UTCL2_REQ_OUT_OF_CREDITS
+      - Total UTCL1 stalls due to UTCL2_req being out of credits.
+
+    * - TCP_CLIENT_UTCL1_INFLIGHT
+      - The sum of inflight client to UTCL1 requests per cycle.
+
+    * - TCP_TAGRAM0_REQ
+      - Total L2 requests mapping to TagRAM 0 from this TCP to all TCCs.
+
+    * - TCP_TAGRAM1_REQ
+      - Total L2 requests mapping to TagRAM 1 from this TCP to all TCCs.
+
+    * - TCP_TAGRAM2_REQ
+      - Total L2 requests mapping to TagRAM 2 from this TCP to all TCCs.
+
+    * - TCP_TAGRAM3_REQ
+      - Total L2 requests mapping to TagRAM 3 from this TCP to all TCCs.
+
+    * - TCP_TCP_LATENCY
+      - Total TCP wave latency (from the first clock of wave entering to the first clock of wave leaving). Divide by TA_TCP_STATE_READ to find average wave latency.
+
+    * - TCP_TCC_READ_REQ_LATENCY
+      - Total TCP to TCC request latency for reads and atomics with return. Not Windowed.
+
+    * - TCP_TCC_WRITE_REQ_LATENCY
+      - Total TCP to TCC request latency for writes and atomics without return. Not Windowed.
+
+    * - TCP_TCC_WRITE_REQ_HOLE_LATENCY
+      - Total TCP req to TCC hole latency for writes and atomics. Not Windowed.
+
+Texture cache per channel (TCC) counters
+=========================================
+
+.. list-table::
+    :header-rows: 1
+
+    * - Hardware counter
+      - Definition
+
+    * - TCC_READ_SECTORS
+      - Total number of 32B data sectors in read requests.
+
+    * - TCC_WRITE_SECTORS
+      - Total number of 32B data sectors in write requests.
+
+    * - TCC_ATOMIC_SECTORS
+      - Total number of 32B data sectors in atomic requests.
+
+    * - TCC_BYPASS_REQ
+      - Number of bypass requests. This is measured at the tag block.
+
+    * - TCC_LATENCY_FIFO_FULL
+      - Number of cycles when the latency FIFO is full.
+
+    * - TCC_SRC_FIFO_FULL
+      - Number of cycles when the SRC FIFO is assumed to be full as measured at the IB block.
+
+    * - TCC_EA0_RDREQ_64B
+      - Number of 64-byte TCC/EA read requests.
+
+    * - TCC_EA0_RDREQ_128B
+      - Number of 128-byte TCC/EA read requests.
+
+    * - TCC_IB_REQ
+      - Number of requests through the IB. This measures the number of raw requests from graphics clients to this TCC.
+
+    * - TCC_IB_STALL
+      - Number of cycles when the IB output is stalled.
+
+    * - TCC_EA0_WRREQ_WRITE_DRAM
+      - Number of TCC/EA write requests (32-byte or 64-byte) destined for DRAM (MC).
+
+    * - TCC_EA0_WRREQ_ATOMIC_DRAM
+      - Number of TCC/EA atomic requests (32-byte or 64-byte) destined for DRAM (MC).
+
+    * - TCC_EA0_RDREQ_DRAM_32B
+      - Number of 32-byte TCC/EA read requests due to DRAM traffic. One 64-byte request is counted as two and one 128-byte as four.
+
+    * - TCC_EA0_RDREQ_GMI_32B
+      - Number of 32-byte TCC/EA read requests due to GMI traffic. One 64-byte request is counted as two and one 128-byte as four.
+
+    * - TCC_EA0_RDREQ_IO_32B
+      - Number of 32-byte TCC/EA read requests due to IO traffic. One 64-byte request is counted as two and one 128-byte as four.
+
+    * - TCC_EA0_WRREQ_WRITE_DRAM_32B
+      - Number of 32-byte TCC/EA write requests due to DRAM traffic. One 64-byte request is counted as two.
+
+    * - TCC_EA0_WRREQ_ATOMIC_DRAM_32B
+      - Number of 32-byte TCC/EA atomic requests due to DRAM traffic. One 64-byte request is counted as two.
+
+    * - TCC_EA0_WRREQ_WRITE_GMI_32B
+      - Number of 32-byte TCC/EA write requests due to GMI traffic. One 64-byte request is counted as two.
+
+    * - TCC_EA0_WRREQ_ATOMIC_GMI_32B
+      - Number of 32-byte TCC/EA atomic requests due to GMI traffic. One 64-byte request is counted as two.
+
+    * - TCC_EA0_WRREQ_WRITE_IO_32B
+      - Number of 32-byte TCC/EA write requests due to IO traffic. One 64-byte request is counted as two.
+
+    * - TCC_EA0_WRREQ_ATOMIC_IO_32B
+      - Number of 32-byte TCC/EA atomic requests due to IO traffic. One 64-byte request is counted as two.

docs/conceptual/gpu-isolation.md

@@ -0,0 +1,116 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="GPU isolation techniques">
+  <meta name="keywords" content="GPU isolation techniques, UUID, universally unique identifier,
+  environment variables, virtual machines, AMD, ROCm">
+</head>
+
+# GPU isolation techniques
+
+Restricting the access of applications to a subset of GPUs, aka isolating
+GPUs allows users to hide GPU resources from programs. The programs by default
+will only use the "exposed" GPUs ignoring other (hidden) GPUs in the system.
+
+There are multiple ways to achieve isolation of GPUs in the ROCm software stack,
+differing in which applications they apply to and the security they provide.
+This page serves as an overview of the techniques.
+
+## Environment variables
+
+The runtimes in the ROCm software stack read these environment variables to
+select the exposed or default device to present to applications using them.
+
+Environment variables shouldn't be used for isolating untrusted applications,
+as an application can reset them before initializing the runtime.
+
+### `ROCR_VISIBLE_DEVICES`
+
+A list of device indices or {abbr}`UUID (universally unique identifier)`s
+that will be exposed to applications.
+
+Runtime
+: ROCm Software Runtime. Applies to all applications using the user mode ROCm
+  software stack.
+
+```{code-block} shell
+:caption: Example to expose the 1. device and a device based on UUID.
+export ROCR_VISIBLE_DEVICES="0,GPU-4b2c1a9f-8d3e-6f7a-b5c9-2e4d8a1f6c3b"
+```
+
+### `GPU_DEVICE_ORDINAL`
+
+Devices indices exposed to OpenCL and HIP applications.
+
+Runtime
+: ROCm Compute Language Runtime (`ROCclr`). Applies to applications and runtimes
+  using the `ROCclr` abstraction layer including HIP and OpenCL applications.
+
+```{code-block} shell
+:caption: Example to expose the 1. and 3. device in the system.
+export GPU_DEVICE_ORDINAL="0,2"
+```
+
+(hip_visible_devices)=
+
+### `HIP_VISIBLE_DEVICES`
+
+Device indices exposed to HIP applications.
+
+Runtime: HIP runtime. Applies only to applications using HIP on the AMD platform.
+
+```{code-block} shell
+:caption: Example to expose the 1. and 3. devices in the system.
+export HIP_VISIBLE_DEVICES="0,2"
+```
+
+### `CUDA_VISIBLE_DEVICES`
+
+Provided for CUDA compatibility, has the same effect as `HIP_VISIBLE_DEVICES`
+on the AMD platform.
+
+Runtime
+: HIP or CUDA Runtime. Applies to HIP applications on the AMD or NVIDIA platform
+  and CUDA applications.
+
+### `OMP_DEFAULT_DEVICE`
+
+Default device used for OpenMP target offloading.
+
+Runtime
+: OpenMP Runtime. Applies only to applications using OpenMP offloading.
+
+```{code-block} shell
+:caption: Example on setting the default device to the third device.
+export OMP_DEFAULT_DEVICE="2"
+```
+
+## Docker
+
+Docker uses Linux kernel namespaces to provide isolated environments for
+applications. This isolation applies to most devices by default, including
+GPUs. To access them in containers explicit access must be granted, please see
+{ref}`docker-access-gpus-in-container` for details.
+Specifically refer to {ref}`docker-restrict-gpus` on exposing just a subset
+of all GPUs.
+
+Docker isolation is more secure than environment variables, and applies
+to all programs that use the `amdgpu` kernel module interfaces.
+Even programs that don't use the ROCm runtime, like graphics applications
+using OpenGL or Vulkan, can only access the GPUs exposed to the container.
+
+## GPU passthrough to virtual machines
+
+Virtual machines achieve the highest level of isolation, because even the kernel
+of the virtual machine is isolated from the host. Devices physically installed
+in the host system can be passed to the virtual machine using PCIe passthrough.
+This allows for using the GPU with a different operating systems like a Windows
+guest from a Linux host.
+
+Setting up PCIe passthrough is specific to the hypervisor used. ROCm officially
+supports [VMware ESXi](https://www.vmware.com/products/esxi-and-esx.html)
+for select GPUs.
+
+<!--
+TODO: This should link to a page about virtualization that explains
+      pass-through and SR-IOV and how-tos for maybe `libvirt` and `VMWare`
+-->

docs/conf.py

@@ -8,86 +8,68 @@ import os
 import shutil
 import sys
 from pathlib import Path
+from subprocess import run
 
-ROCM_VERSION = "7.10.0"
-GA_DATE = "2025-12-11"
-
-DOCS_DIR = Path(__file__).parent.resolve()
-ROOT_DIR = DOCS_DIR.parent
-
-
-def copy_rtd_file(src_path: Path, dest_path: Path):
-    dest_path.parent.mkdir(parents=True, exist_ok=True)
-    shutil.copy2(src_path, dest_path)
-    print(f"📁 Copied {src_path} → {dest_path}")
-
-
-# compat_matrix_src = DOCS_DIR / "compatibility" / "compatibility-matrix-historical-6.0.csv" # fmt: skip
-# compat_matrix_dest = ROOT_DIR / "_readthedocs" / "html" / "downloads" / "compatibility-matrix-historical-6.0.csv"  # fmt: skip
-# copy_rtd_file(compat_matrix_src, compat_matrix_dest)
-
-gh_release_path = ROOT_DIR / "RELEASE.md"
-rtd_release_path = DOCS_DIR / "about" / "release-notes.md"
-copy_rtd_file(gh_release_path, rtd_release_path)
-
-# gh_changelog_path = ROOT_DIR / "CHANGELOG.md"
-# rtd_changelog_path = DOCS_DIR / "release" / "changelog.md"
-# copy_rtd_file(gh_changelog_path, rtd_changelog_path)
-
+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(rtd_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(rtd_changelog_path, "r", encoding="utf-8") as file:
-#     lines = file.readlines()
-#
-#     modified_lines = []
-#     in_admonition_section = False
-#
-#     # Map for matching the specific admonition type to its corresponding Sphinx markdown syntax
-#     admonition_types = {
-#         "> [!NOTE]": "```{note}",
-#         "> [!TIP]": "```{tip}",
-#         "> [!IMPORTANT]": "```{important}",
-#         "> [!WARNING]": "```{warning}",
-#         "> [!CAUTION]": "```{caution}",
-#     }
-#
-#     for line in lines:
-#         if any(line.startswith(k) for k in admonition_types):
-#             for key in admonition_types:
-#                 if line.startswith(key):
-#                     modified_lines.append(admonition_types[key] + "\n")
-#                     break
-#             in_admonition_section = True
-#         elif in_admonition_section:
-#             if line.strip() == "":
-#                 # If we encounter an empty line, close the admonition section
-#                 modified_lines.append("```\n\n")  # Close the admonition block
-#                 in_admonition_section = False
-#             else:
-#                 modified_lines.append(line.lstrip("> "))
-#         else:
-#             modified_lines.append(line)
-#
-#     # In case the file ended while still in a admonition section, close it
-#     if in_admonition_section:
-#         modified_lines.append("```")
-#
-#     file.close()
-#
-#     with open(rtd_changelog_path, "w", encoding="utf-8") as file:
-#         file.writelines(modified_lines)
+with open(sphinx_changelog_path, "r+", encoding="utf-8") as file:
+    content = file.read()
+    file.seek(0)
+    file.write(":orphan:\n" + content)
 
-# 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)
+# Replace GitHub-style [!ADMONITION]s with Sphinx-compatible ```{admonition} blocks
+with open(sphinx_changelog_path, "r", encoding="utf-8") as file:
+    lines = file.readlines()
+
+    modified_lines = []
+    in_admonition_section = False
+
+    # Map for matching the specific admonition type to its corresponding Sphinx markdown syntax
+    admonition_types = {
+        '> [!NOTE]': '```{note}',
+        '> [!TIP]': '```{tip}',
+        '> [!IMPORTANT]': '```{important}',
+        '> [!WARNING]': '```{warning}',
+        '> [!CAUTION]': '```{caution}'
+    }
+
+    for line in lines:
+        if any(line.startswith(k) for k in admonition_types):
+            for key in admonition_types:
+                if(line.startswith(key)):
+                    modified_lines.append(admonition_types[key] + '\n')
+                    break
+            in_admonition_section = True
+        elif in_admonition_section:
+            if line.strip() == '':
+                # If we encounter an empty line, close the admonition section
+                modified_lines.append('```\n\n')  # Close the admonition block
+                in_admonition_section = False
+            else:
+                modified_lines.append(line.lstrip('> '))
+        else:
+            modified_lines.append(line)
+
+    # In case the file ended while still in a admonition section, close it
+    if in_admonition_section:
+        modified_lines.append('```')
+
+    file.close()
+
+    with open(sphinx_changelog_path, "w", encoding="utf-8") as file:
+        file.writelines(modified_lines)
+
+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 = {
@@ -99,104 +81,193 @@ latex_elements = {
 }
 
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "rocm.docs.amd.com")
-html_context = {}
+html_context = {"docs_header_version": "7.1.1"}
+if os.environ.get("READTHEDOCS", "") == "True":
+    html_context["READTHEDOCS"] = True
+
+# Check if the branch is a docs/ branch
+official_branch = run(["git", "rev-parse", "--abbrev-ref", "HEAD"], capture_output=True, text=True).stdout.find("docs/")
 
 # configurations for PDF output by Read the Docs
-project = "ROCm documentation"
-project_path = str(DOCS_DIR).replace("\\", "/")
+project = "ROCm Documentation"
+project_path = os.path.abspath(".").replace("\\", "/")
 author = "Advanced Micro Devices, Inc."
-copyright = "Copyright (c) %Y Advanced Micro Devices, Inc. All rights reserved."
-version = ROCM_VERSION
-release = ROCM_VERSION
-setting_all_article_info = False
+copyright = "Copyright (c) 2025 Advanced Micro Devices, Inc. All rights reserved."
+version = "7.1.1"
+release = "7.1.1"
+setting_all_article_info = True
 all_article_info_os = ["linux", "windows"]
 all_article_info_author = ""
 
 # pages with specific settings
 article_pages = [
-    {"file": "about/release-notes", "date": GA_DATE, "os": ["linux", "windows"]},
+    {"file": "about/release-notes", "os": ["linux"], "date": "2025-11-26"},
+    {"file": "release/changelog", "os": ["linux"],},
+    {"file": "compatibility/compatibility-matrix", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/tensorflow-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/jax-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/verl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/stanford-megatron-lm-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/dgl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/megablocks-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/ray-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/llama-cpp-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/flashinfer-compatibility", "os": ["linux"]},
+    {"file": "how-to/deep-learning-rocm", "os": ["linux"]},
+
+    {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/install", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/system-setup/index", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/system-setup/multi-node-setup", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/system-setup/prerequisite-system-validation", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/system-setup/system-health-check", "os": ["linux"]},
+
+    {"file": "how-to/rocm-for-ai/training/index", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/train-a-model", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/prerequisite-system-validation", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/scale-model-training", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/megatron-lm", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-history", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.3", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.4", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.5", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.6", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.7", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.8", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.9", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.10", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-primus-migration-guide", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/primus-megatron", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.7", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.8", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.9", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.10", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/pytorch-training", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-history", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.3", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.4", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.5", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.6", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.7", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.8", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.9", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.10", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-pytorch-v25.8", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-pytorch-v25.9", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-pytorch-v25.10", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-history", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.4", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.5", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/xdit-diffusion-inference", "os": ["linux"]},    
+
+    {"file": "how-to/rocm-for-ai/fine-tuning/index", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/fine-tuning/overview", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/fine-tuning/fine-tuning-and-inference", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference", "os": ["linux"]},
+
+    {"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/benchmark-docker/vllm", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-history", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.4.3", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.6.4", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.6.6", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.7.3-20250325", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.3-20250415", "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/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/previous-versions/vllm-0.10.0-20250812", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.1-20250909", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.2-20251006", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.11.1-20251103", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/sglang-history", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/xdit-diffusion-inference", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.10", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.11", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.12", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.13", "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"]},
+    {"file": "how-to/rocm-for-ai/inference-optimization/model-quantization", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference-optimization/optimizing-with-composable-kernel", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference-optimization/optimizing-triton-kernel", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference-optimization/profiling-and-debugging", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference-optimization/workload", "os": ["linux"]},
+
+    {"file": "how-to/system-optimization/index", "os": ["linux"]},
+    {"file": "how-to/system-optimization/mi300x", "os": ["linux"]},
+    {"file": "how-to/system-optimization/mi200", "os": ["linux"]},
+    {"file": "how-to/system-optimization/mi100", "os": ["linux"]},
+    {"file": "how-to/system-optimization/w6000-v620", "os": ["linux"]},
+    {"file": "how-to/tuning-guides/mi300x/index", "os": ["linux"]},
+    {"file": "how-to/tuning-guides/mi300x/system", "os": ["linux"]},
+    {"file": "how-to/tuning-guides/mi300x/workload", "os": ["linux"]},
+    {"file": "how-to/system-debugging", "os": ["linux"]},
+    {"file": "how-to/gpu-enabled-mpi", "os": ["linux"]},
 ]
 
 external_toc_path = "./sphinx/_toc.yml"
 
-# Register Sphinx extensions and static assets
-sys.path.append(str(DOCS_DIR / "extension"))
-extensions = [
-    "rocm_docs",
-    "rocm_docs_custom.selector",
-    "rocm_docs_custom.matrix",
-    "rocm_docs_custom.icon",
-    # "sphinxcontrib.datatemplates",
-    # "sphinx_reredirects",
-    # "sphinx_sitemap",
-    # "version-ref",
-    # "csv-to-list-table",
-]
-templates_path = ["extension/rocm_docs_custom/templates"]
+# Add the _extensions directory to Python's search path
+sys.path.append(str(Path(__file__).parent / 'extension'))
 
-html_static_path = ["sphinx/static"]
-html_js_files = ["setup-toc-install-headings.js"]
+extensions = ["rocm_docs", "sphinx_reredirects", "sphinx_sitemap", "sphinxcontrib.datatemplates", "remote-content", "version-ref", "csv-to-list-table"]
 
-# compatibility_matrix_file = str(
-#     DOCS_DIR / "compatibility/compatibility-matrix-historical-6.0.csv"
-# )
+compatibility_matrix_file = str(Path(__file__).parent / 'compatibility/compatibility-matrix-historical-6.0.csv')
 
 external_projects_current_project = "rocm"
-html_theme = "rocm_docs_theme"
-html_theme_options = {
-    "announcement": f"This is ROCm {ROCM_VERSION} technology preview release documentation. For the latest production stream release, refer to <a id='rocm-banner' href='https://rocm.docs.amd.com/en/latest/'>ROCm documentation</a>.",
-    "flavor": "generic",
-    "header_title": f"ROCm™ {ROCM_VERSION} Preview",
-    "header_link": f"https://rocm.docs.amd.com/en/{ROCM_VERSION}-preview/index.html",
-    "version_list_link": f"https://rocm.docs.amd.com/en/{ROCM_VERSION}-preview/release/versions.html",
-    "nav_secondary_items": {
-        "GitHub": "https://github.com/ROCm/ROCm",
-        "Community": "https://github.com/ROCm/ROCm/discussions",
-        "Blogs": "https://rocm.blogs.amd.com/",
-        "Instinct™ Docs": "https://instinct.docs.amd.com/",
-        "Support": "https://github.com/ROCm/ROCm/issues/new/choose",
-    },
-    "link_main_doc": False,
-    "secondary_sidebar_items": {
-        "**": ["page-toc"],
-        "compatibility/compatibility-matrix": ["selector-toc2"],
-        "install/rocm": ["selector-toc2"],
-        "rocm-for-ai/pytorch-comfyui": ["selector-toc2"],
-    },
-}
-html_title = f"AMD ROCm {ROCM_VERSION} preview"
 
-numfig = False
-rst_prolog = f"""
-.. |ROCM_VERSION| replace:: {ROCM_VERSION}
-"""
+# Uncomment if facing rate limit exceed issue with local build
+# external_projects_remote_repository = ""
 
-suppress_warnings = ["autosectionlabel.*"]
-
-# html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "https://rocm-stg.amd.com/")
-# html_context = {
-#     "project_path": {project_path},
-#     "gpu_type": [
-#         ("AMD Instinct accelerators", "intrinsic"),
-#         ("AMD gfx families", "gfx"),
-#         ("NVIDIA families", "nvidia"),
-#     ],
-#     "atomics_type": [("HW atomics", "hw-atomics"), ("CAS emulation", "cas-atomics")],
-#     "pcie_type": [("No PCIe atomics", "nopcie"), ("PCIe atomics", "pcie")],
-#     "memory_type": [
-#         ("Device DRAM", "device-dram"),
-#         ("Migratable Host DRAM", "migratable-host-dram"),
-#         ("Pinned Host DRAM", "pinned-host-dram"),
-#     ],
-#     "granularity_type": [
-#         ("Coarse-grained", "coarse-grained"),
-#         ("Fine-grained", "fine-grained"),
-#     ],
-#     "scope_type": [("Device", "device"), ("System", "system")],
-# }
+html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "https://rocm-stg.amd.com/")
+html_context = {"docs_header_version": "7.1.0"}
 if os.environ.get("READTHEDOCS", "") == "True":
     html_context["READTHEDOCS"] = True
 
-# temporary settings to speed up docs build for faster iteration
-# external_projects_remote_repository = ""
-# external_toc_exclude_missing = True
+html_context["official_branch"] = official_branch
+html_context["version"] = version
+html_context["release"] = release
+
+html_theme = "rocm_docs_theme"
+html_theme_options = {"flavor": "rocm-docs-home"}
+
+html_static_path = ["sphinx/static/css", "extension/how-to/rocm-for-ai/inference"]
+html_css_files = ["rocm_custom.css", "rocm_rn.css", "vllm-benchmark.css"]
+html_js_files = ["vllm-benchmark.js"]
+
+html_title = "ROCm Documentation"
+
+html_theme_options = {"link_main_doc": False}
+
+redirects = {"reference/openmp/openmp": "../../about/compatibility/openmp.html"}
+
+numfig = False
+suppress_warnings = ["autosectionlabel.*"]
+
+html_context = {
+    "project_path" : {project_path},
+    "gpu_type" : [('AMD Instinct GPUs', 'intrinsic'), ('AMD gfx families', 'gfx'), ('NVIDIA families', 'nvidia') ],
+    "atomics_type" : [('HW atomics', 'hw-atomics'), ('CAS emulation', 'cas-atomics')],
+    "pcie_type" : [('No PCIe atomics', 'nopcie'), ('PCIe atomics', 'pcie')],
+    "memory_type" : [('Device DRAM', 'device-dram'), ('Migratable Host DRAM', 'migratable-host-dram'), ('Pinned Host DRAM', 'pinned-host-dram')],
+    "granularity_type" : [('Coarse-grained', 'coarse-grained'), ('Fine-grained', 'fine-grained')],
+    "scope_type" : [('Device', 'device'), ('System', 'system')]
+}
+
+# Disable figure and table numbering
+numfig = False

docs/contribute/building.md

@@ -0,0 +1,168 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="Building ROCm documentation">
+  <meta name="keywords" content="documentation, Visual Studio Code, GitHub, command line,
+  AMD, ROCm">
+</head>
+
+# Building documentation
+
+## GitHub
+
+If you open a pull request and scroll down to the summary panel,
+there is a commit status section. Next to the line
+`docs/readthedocs.com:advanced-micro-devices-demo`, there is a `Details` link.
+If you click this, it takes you to the Read the Docs build for your pull request.
+
+![GitHub PR commit status](../data/contribute/commit-status.png)
+
+If you don't see this line, click `Show all checks` to get an itemized view.
+
+## Command line
+
+You can build our documentation via the command line using Python.
+
+See the `build.tools.python` setting in the [Read the Docs configuration file](https://github.com/ROCm/ROCm/blob/develop/.readthedocs.yaml) for the Python version used by Read the Docs to build documentation.
+
+See the [Python requirements file](https://github.com/ROCm/ROCm/blob/develop/docs/sphinx/requirements.txt) for Python packages needed to build the documentation.
+
+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
+```
+
+:::
+:::{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
+
+With the help of a few extensions, you can create a productive environment to author and test
+documentation locally using Visual Studio (VS) Code. Follow these steps to configure VS Code:
+
+1. Install the required extensions:
+
+   * Python: `(ms-python.python)`
+   * Live Server: `(ritwickdey.LiveServer)`
+
+2. Add the following entries to `.vscode/settings.json`.
+
+    ```json
+      {
+        "liveServer.settings.root": "/.vscode/build/html",
+        "liveServer.settings.wait": 1000,
+        "python.terminal.activateEnvInCurrentTerminal": true
+      }
+    ```
+
+    * `liveServer.settings.root`: Sets the root of the output website for live previews. Must be changed
+      alongside the `tasks.json` command.
+    * `liveServer.settings.wait`: Tells the live server to wait with the update in order to give Sphinx time to
+      regenerate the site contents and not refresh before the build is complete.
+    * `python.terminal.activateEnvInCurrentTerminal`: Activates the automatic virtual environment, so you
+      can build the site from the integrated terminal.
+
+3. Add the following tasks to `.vscode/tasks.json`.
+
+    ```json
+      {
+        "version": "2.0.0",
+        "tasks": [
+          {
+            "label": "Build Docs",
+            "type": "process",
+            "windows": {
+              "command": "${workspaceFolder}/.venv/Scripts/python.exe"
+            },
+            "command": "${workspaceFolder}/.venv/bin/python3",
+            "args": [
+              "-m",
+              "sphinx",
+              "-j",
+              "auto",
+              "-T",
+              "-b",
+              "html",
+              "-d",
+              "${workspaceFolder}/.vscode/build/doctrees",
+              "-D",
+              "language=en",
+              "${workspaceFolder}/docs",
+              "${workspaceFolder}/.vscode/build/html"
+            ],
+            "problemMatcher": [
+              {
+                "owner": "sphinx",
+                "fileLocation": "absolute",
+                "pattern": {
+                  "regexp": "^(?:.*\\.{3}\\s+)?(\\/[^:]*|[a-zA-Z]:\\\\[^:]*):(\\d+):\\s+(WARNING|ERROR):\\s+(.*)$",
+                  "file": 1,
+                  "line": 2,
+                  "severity": 3,
+                  "message": 4
+                }
+              },
+              {
+              "owner": "sphinx",
+                "fileLocation": "absolute",
+                "pattern": {
+                  "regexp": "^(?:.*\\.{3}\\s+)?(\\/[^:]*|[a-zA-Z]:\\\\[^:]*):{1,2}\\s+(WARNING|ERROR):\\s+(.*)$",
+                  "file": 1,
+                  "severity": 2,
+                  "message": 3
+                }
+              }
+            ],
+            "group": {
+              "kind": "build",
+              "isDefault": true
+            }
+          }
+        ]
+      }
+    ```
+
+    > Implementation detail: two problem matchers were needed to be defined,
+    > because VS Code doesn't tolerate some problem information being potentially
+    > absent. While a single regex could match all types of errors, if a capture
+    > group remains empty (the line number doesn't show up in all warning/error
+    > messages) but the `pattern` references said empty capture group, VS Code
+    > discards the message completely.
+
+4. Configure the Python virtual environment (`venv`).
+
+    From the Command Palette, run `Python: Create Environment`. Select `venv` environment and
+    `docs/sphinx/requirements.txt`.
+
+5. Build the docs.
+
+    Launch the default build task using one of the following options:
+
+    * A hotkey (the default is `Ctrl+Shift+B`)
+    * Issuing the `Tasks: Run Build Task` from the Command Palette
+
+6. Open the live preview.
+
+    Navigate to the site output within VS Code: right-click on `.vscode/build/html/index.html` and
+    select `Open with Live Server`. The contents should update on every rebuild without having to
+    refresh the browser.

docs/contribute/contributing.md

@@ -0,0 +1,77 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="Contributing to ROCm">
+  <meta name="keywords" content="ROCm, contributing, contribute, maintainer, contributor">
+</head>
+
+# Contributing to the ROCm documentation
+
+The ROCm documentation, like all of ROCm, is open source and available on GitHub. You can contribute to the ROCm documentation by forking the appropriate repository, making your changes, and opening a pull request.
+
+To provide feedback on the ROCm documentation, including submitting an issue or suggesting a feature, see [Providing feedback about the ROCm documentation](./feedback.md).
+
+## The ROCm repositories
+
+The repositories for ROCm and all ROCm components are available on GitHub.
+
+| Module | Documentation location |
+| --- | --- |
+| ROCm framework | [https://github.com/ROCm/ROCm/tree/develop/docs](https://github.com/ROCm/ROCm/tree/develop/docs) |
+| ROCm installation for Linux | [https://github.com/ROCm/rocm-install-on-linux/tree/develop/docs](https://github.com/ROCm/rocm-install-on-linux/tree/develop/docs) |
+| ROCm HIP SDK installation for Windows |  [https://github.com/ROCm/rocm-install-on-windows/tree/develop/docs](https://github.com/ROCm/rocm-install-on-windows/tree/develop/docs) |
+
+Individual components have their own repositories with their own documentation in their own `docs` folders.
+
+The sub-folders within the `docs` folders across ROCm are typically structured as follows:
+
+| Sub-folder name | Documentation type |
+|-------|----------|
+| `install` | Installation instructions, build instructions, and prerequisites |
+| `conceptual` | Important concepts |
+| `how-to` | How to implement specific use cases |
+| `tutorials` | Tutorials |
+| `reference` | API references and other reference resources |
+
+## Editing and adding to the documentation
+
+ROCm documentation follows the [Google developer documentation style guide](https://developers.google.com/style/highlights).
+
+Most topics in the ROCm documentation are written in [reStructuredText (rst)](https://www.sphinx-doc.org/en/master/usage/restructuredtext/index.html), with some topics written in Markdown. Only use reStructuredText when adding new topics. Only use Markdown if the topic you are editing is already in Markdown.
+
+To edit or add to the documentation:
+
+1. Fork the repository you want to add to or edit.
+2. Clone your fork locally.
+3. Create a new local branch cut from the `develop` branch of the repository.
+4. Make your changes to the documentation.
+
+5. Optionally, build the documentation locally before creating a pull request by running the following commands from within the `docs` folder:
+
+    ```bash
+     pip3 install -r sphinx/requirements.txt  # You only need to run this command once
+     python3 -m sphinx -T -E -b html -d _build/doctrees -D language=en . _build/html
+     ```
+
+    The output files will be located in the `docs/_build` folder. Open `docs/_build/html/index.html` to view the documentation.
+
+    For more information on ROCm build tools, see [Documentation toolchain](toolchain.md).
+6. Push your changes. A GitHub link will be returned in the output of the `git push` command. Open this link in a browser to create the pull request.
+
+    The documentation is built as part of the checks on pull request, along with spell checking and linting. Scroll to the bottom of your pull request to view all the checks.
+
+    Verify that the linting and spell checking have passed, and that the documentation was built successfully. New words or acronyms can be added to the [wordlist file](https://github.com/ROCm/rocm-docs-core/blob/develop/.wordlist.txt). The wordlist is subject to approval by the ROCm documentation team.
+
+    The Read The Docs build of your pull request can be accessed by clicking on the Details link next to the Read The Docs build check. Verify that your changes are in the build and look as expected.
+
+    ![The GitHub checks are collapsed by default and can be accessed by clicking on "Show All Checks".](../data/contribute/GitHubCheck-Highlight.png)
+  
+    ![The Read The Docs Build is accessed from the Details link in the Read The Docs check.](../data/contribute/GitHub-ReadThe-Docs-Highlight.png)
+
+    Your pull request will be reviewed by a member of the ROCm documentation team.
+
+See the [GitHub documentation](https://docs.github.com/en) for information on how to fork and clone a repository, and how to create and push a local branch.
+
+```{important}
+By creating a pull request (PR), you agree to allow your contribution to be licensed under the terms of the
+LICENSE.txt file in the corresponding repository. Different repositories can use different licenses.
+```

docs/contribute/feedback.md

@@ -0,0 +1,27 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="Providing feedback for ROCm documentation">
+  <meta name="keywords" content="documentation, pull request, GitHub, AMD, ROCm">
+</head>
+
+# Providing feedback about the ROCm documentation
+
+Feedback about the ROCm documentation is welcome. You can provide feedback about the ROCm documentation either through GitHub Discussions or GitHub Issues.
+
+## Participating in discussions through GitHub Discussions
+
+You can ask questions, view announcements, suggest new features, and communicate with other members of the community through [GitHub Discussions](https://github.com/ROCm/ROCm/discussions).
+
+## Submitting issues through GitHub Issues
+
+You can submit issues through [GitHub Issues](https://github.com/ROCm/ROCm/issues).
+
+When creating a new issue, follow the following guidelines:
+
+1. Always do a search to see if the same issue already exists. If the issue already exists, upvote it, and comment or post to provide any additional details you might have.
+2. If you find an issue that is similar to your issue, log your issue, then add a comment that includes a link to the similar issue, as well as its issue number.
+3. Always provide as much information as possible. This helps reduce the time required to reproduce the issue.
+
+After creating your issue, make sure to check it regularly for any requests for additional information.
+
+For information about contributing content to the ROCm documentation, see [Contributing to the ROCm documentation](./contributing.md).

docs/contribute/toolchain.md

@@ -0,0 +1,46 @@
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="ROCm documentation toolchain">
+  <meta name="keywords" content="documentation, toolchain, Sphinx, Doxygen, MyST, AMD, ROCm">
+</head>
+
+# ROCm documentation toolchain
+
+The ROCm documentation relies on several open source toolchains and sites.
+
+## rocm-docs-core
+
+[rocm-docs-core](https://github.com/ROCm/rocm-docs-core) is an AMD-maintained
+project that applies customizations for the ROCm documentation. This project is the tool most ROCm repositories use as part of their documentation build pipeline. It is available as a [pip package on PyPI](https://pypi.org/project/rocm-docs-core/).
+
+See the user and developer guides for rocm-docs-core at
+{doc}`rocm-docs-core documentation<rocm-docs-core:index>`.
+
+## Sphinx
+
+[Sphinx](https://www.sphinx-doc.org/en/master/) is a documentation generator originally used for Python. It is now widely used in the open source community.
+
+### Sphinx External ToC
+
+[Sphinx External ToC](https://sphinx-external-toc.readthedocs.io/en/latest/intro.html) is a Sphinx extension used for ROCm documentation navigation. This tool generates a navigation menu on the left
+based on a YAML file (`_toc.yml.in`) that contains the table of contents.
+
+### Sphinx-book-theme
+
+[Sphinx-book-theme](https://sphinx-book-theme.readthedocs.io/en/latest/) is a Sphinx theme that defines the base appearance for ROCm documentation. ROCm documentation applies some customization, such as a custom header and footer, on top of the Sphinx Book Theme.
+
+### Sphinx Design
+
+[Sphinx design](https://sphinx-design.readthedocs.io/en/latest/index.html) is a Sphinx extension that adds design functionality. ROCm documentation uses Sphinx Design for grids, cards, and synchronized tabs.
+
+## Doxygen
+
+[Doxygen](https://www.doxygen.nl/) is a documentation generator that extracts information from in-code comments. It is used for API documentation.
+
+## Breathe
+
+[Breathe](https://www.breathe-doc.org/) is a Sphinx plugin for integrating Doxygen content.
+
+## Read the Docs
+
+[Read the Docs](https://docs.readthedocs.io/en/stable/) is the service that builds and hosts the HTML version of the ROCm documentation.

docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20251006-benchmark-models.yaml

@@ -0,0 +1,316 @@
+dockers:
+  - pull_tag: rocm/vllm:rocm7.0.0_vllm_0.10.2_20251006
+    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.10.2_20251006/images/sha256-94fd001964e1cf55c3224a445b1fb5be31a7dac302315255db8422d813edd7f5
+    components:
+      ROCm: 7.0.0
+      vLLM: 0.10.2 (0.11.0rc2.dev160+g790d22168.rocm700)
+      PyTorch: 2.9.0a0+git1c57644
+      hipBLASLt: 1.0.0
+    dockerfile:
+      commit: 790d22168820507f3105fef29596549378cfe399
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 4096
+          max_model_len: 4096
+      - 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
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 405B MXFP4
+        mad_tag: pyt_vllm_llama-3.1-405b_fp4
+        model_repo: amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        precision: float4
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B
+        mad_tag: pyt_vllm_llama-3.3-70b
+        model_repo: meta-llama/Llama-3.3-70B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B FP8
+        mad_tag: pyt_vllm_llama-3.3-70b_fp8
+        model_repo: amd/Llama-3.3-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B MXFP4
+        mad_tag: pyt_vllm_llama-3.3-70b_fp4
+        model_repo: amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+        precision: float4
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 4 Scout 17Bx16E
+        mad_tag: pyt_vllm_llama-4-scout-17b-16e
+        model_repo: meta-llama/Llama-4-Scout-17B-16E-Instruct
+        url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Llama 4 Maverick 17Bx128E
+        mad_tag: pyt_vllm_llama-4-maverick-17b-128e
+        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Llama 4 Maverick 17Bx128E FP8
+        mad_tag: pyt_vllm_llama-4-maverick-17b-128e_fp8
+        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek R1 0528 FP8
+        mad_tag: pyt_vllm_deepseek-r1
+        model_repo: deepseek-ai/DeepSeek-R1-0528
+        url: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_seqs: 1024
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+  - group: OpenAI GPT OSS
+    tag: gpt-oss
+    models:
+      - model: GPT OSS 20B
+        mad_tag: pyt_vllm_gpt-oss-20b
+        model_repo: openai/gpt-oss-20b
+        url: https://huggingface.co/openai/gpt-oss-20b
+        precision: bfloat16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 8192
+          max_model_len: 8192
+      - model: GPT OSS 120B
+        mad_tag: pyt_vllm_gpt-oss-120b
+        model_repo: openai/gpt-oss-120b
+        url: https://huggingface.co/openai/gpt-oss-120b
+        precision: bfloat16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 8192
+          max_model_len: 8192
+  - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 65536
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 65536
+          max_model_len: 8192
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen3 8B
+        mad_tag: pyt_vllm_qwen3-8b
+        model_repo: Qwen/Qwen3-8B
+        url: https://huggingface.co/Qwen/Qwen3-8B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 32B
+        mad_tag: pyt_vllm_qwen3-32b
+        model_repo: Qwen/Qwen3-32b
+        url: https://huggingface.co/Qwen/Qwen3-32B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 30B A3B
+        mad_tag: pyt_vllm_qwen3-30b-a3b
+        model_repo: Qwen/Qwen3-30B-A3B
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 30B A3B FP8
+        mad_tag: pyt_vllm_qwen3-30b-a3b_fp8
+        model_repo: Qwen/Qwen3-30B-A3B-FP8
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 235B A22B
+        mad_tag: pyt_vllm_qwen3-235b-a22b
+        model_repo: Qwen/Qwen3-235B-A22B
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 235B A22B FP8
+        mad_tag: pyt_vllm_qwen3-235b-a22b_fp8
+        model_repo: Qwen/Qwen3-235B-A22B-FP8
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+  - 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
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 16384
+          max_model_len: 8192

docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.11.1_20251103-benchmark-models.yaml

@@ -0,0 +1,316 @@
+dockers:
+  - pull_tag: rocm/vllm:rocm7.0.0_vllm_0.11.1_20251103
+    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.11.1_20251103/images/sha256-8d60429043d4d00958da46039a1de0d9b82df814d45da482497eef26a6076506
+    components:
+      ROCm: 7.0.0
+      vLLM: 0.11.1 (0.11.1rc2.dev141+g38f225c2a.rocm700)
+      PyTorch: 2.9.0a0+git1c57644
+      hipBLASLt: 1.0.0
+    dockerfile:
+      commit: 38f225c2abeadc04c2cc398814c2f53ea02c3c72
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 4096
+          max_model_len: 4096
+      - 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
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.1 405B MXFP4
+        mad_tag: pyt_vllm_llama-3.1-405b_fp4
+        model_repo: amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        precision: float4
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B
+        mad_tag: pyt_vllm_llama-3.3-70b
+        model_repo: meta-llama/Llama-3.3-70B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B FP8
+        mad_tag: pyt_vllm_llama-3.3-70b_fp8
+        model_repo: amd/Llama-3.3-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-FP8-KV
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 3.3 70B MXFP4
+        mad_tag: pyt_vllm_llama-3.3-70b_fp4
+        model_repo: amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+        precision: float4
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+      - model: Llama 4 Scout 17Bx16E
+        mad_tag: pyt_vllm_llama-4-scout-17b-16e
+        model_repo: meta-llama/Llama-4-Scout-17B-16E-Instruct
+        url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Llama 4 Maverick 17Bx128E
+        mad_tag: pyt_vllm_llama-4-maverick-17b-128e
+        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - model: Llama 4 Maverick 17Bx128E FP8
+        mad_tag: pyt_vllm_llama-4-maverick-17b-128e_fp8
+        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek R1 0528 FP8
+        mad_tag: pyt_vllm_deepseek-r1
+        model_repo: deepseek-ai/DeepSeek-R1-0528
+        url: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_seqs: 1024
+          max_num_batched_tokens: 131072
+          max_model_len: 8192
+  - group: OpenAI GPT OSS
+    tag: gpt-oss
+    models:
+      - model: GPT OSS 20B
+        mad_tag: pyt_vllm_gpt-oss-20b
+        model_repo: openai/gpt-oss-20b
+        url: https://huggingface.co/openai/gpt-oss-20b
+        precision: bfloat16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 8192
+          max_model_len: 8192
+      - model: GPT OSS 120B
+        mad_tag: pyt_vllm_gpt-oss-120b
+        model_repo: openai/gpt-oss-120b
+        url: https://huggingface.co/openai/gpt-oss-120b
+        precision: bfloat16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 8192
+          max_model_len: 8192
+  - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 32768
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 65536
+          max_model_len: 8192
+      - 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
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 65536
+          max_model_len: 8192
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen3 8B
+        mad_tag: pyt_vllm_qwen3-8b
+        model_repo: Qwen/Qwen3-8B
+        url: https://huggingface.co/Qwen/Qwen3-8B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 32B
+        mad_tag: pyt_vllm_qwen3-32b
+        model_repo: Qwen/Qwen3-32b
+        url: https://huggingface.co/Qwen/Qwen3-32B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 30B A3B
+        mad_tag: pyt_vllm_qwen3-30b-a3b
+        model_repo: Qwen/Qwen3-30B-A3B
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 30B A3B FP8
+        mad_tag: pyt_vllm_qwen3-30b-a3b_fp8
+        model_repo: Qwen/Qwen3-30B-A3B-FP8
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 235B A22B
+        mad_tag: pyt_vllm_qwen3-235b-a22b
+        model_repo: Qwen/Qwen3-235B-A22B
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B
+        precision: float16
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+      - model: Qwen3 235B A22B FP8
+        mad_tag: pyt_vllm_qwen3-235b-a22b_fp8
+        model_repo: Qwen/Qwen3-235B-A22B-FP8
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8
+        precision: float8
+        config:
+          tp: 8
+          dtype: auto
+          kv_cache_dtype: fp8
+          max_num_batched_tokens: 40960
+          max_model_len: 8192
+  - 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
+        precision: float16
+        config:
+          tp: 1
+          dtype: auto
+          kv_cache_dtype: auto
+          max_num_batched_tokens: 16384
+          max_model_len: 8192

docs/data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.10-inference-models.yaml

@@ -0,0 +1,55 @@
+xdit_diffusion_inference:
+  docker:
+    pull_tag: rocm/pytorch-xdit:v25.10
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.10/images/sha256-d79715ff18a9470e3f907cec8a9654d6b783c63370b091446acffc0de4d7070e
+    ROCm: 7.9.0
+    components:
+      TheRock: 7afbe45
+      rccl: 9b04b2a
+      composable_kernel: b7a806f
+      rocm-libraries: f104555
+      rocm-systems: 25922d0
+      torch: 2.10.0a0+gite9c9017
+      torchvision: 0.22.0a0+966da7e
+      triton: 3.5.0+git52e49c12
+      accelerate: 1.11.0.dev0
+      aiter: 0.1.5.post4.dev20+ga25e55e79
+      diffusers: 0.36.0.dev0
+      xfuser: 0.4.4
+      yunchang: 0.6.3.post1
+
+  model_groups:
+    - group: Hunyuan Video
+      tag: hunyuan
+      models:
+        - model: Hunyuan Video
+          model_name: hunyuanvideo
+          model_repo: tencent/HunyuanVideo
+          revision: refs/pr/18
+          url: https://huggingface.co/tencent/HunyuanVideo
+          github: https://github.com/Tencent-Hunyuan/HunyuanVideo
+          mad_tag: pyt_xdit_hunyuanvideo
+    - group: Wan-AI
+      tag: wan
+      models:
+        - model: Wan2.1
+          model_name: wan2_1-i2v-14b-720p
+          model_repo: Wan-AI/Wan2.1-I2V-14B-720P
+          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P
+          github: https://github.com/Wan-Video/Wan2.1
+          mad_tag: pyt_xdit_wan_2_1
+        - model: Wan2.2
+          model_name: wan2_2-i2v-a14b
+          model_repo: Wan-AI/Wan2.2-I2V-A14B
+          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B
+          github: https://github.com/Wan-Video/Wan2.2
+          mad_tag: pyt_xdit_wan_2_2
+    - group: FLUX
+      tag: flux
+      models:
+        - model: FLUX.1
+          model_name: FLUX.1-dev
+          model_repo: black-forest-labs/FLUX.1-dev
+          url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+          github: https://github.com/black-forest-labs/flux
+          mad_tag: pyt_xdit_flux

docs/data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.11-inference-models.yaml

@@ -0,0 +1,109 @@
+xdit_diffusion_inference:
+  docker:
+    - version: v25-11
+      pull_tag: rocm/pytorch-xdit:v25.11
+      docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.11/images/sha256-c9fa659439bb024f854b4d5eea598347251b02c341c55f66c98110832bde4216
+      ROCm: 7.10.0
+      supported_models:
+        - group: Hunyuan Video
+          models:
+            - Hunyuan Video
+        - group: Wan-AI
+          models:
+            - Wan2.1
+            - Wan2.2
+        - group: FLUX
+          models:
+            - FLUX.1
+      whats_new:
+        - "Minor bug fixes and clarifications to READMEs."
+        - "Bumps TheRock, AITER, Diffusers, xDiT versions."
+        - "Changes Aiter rounding mode for faster gfx942 FWD Attention."
+      components:
+        TheRock: 3e3f834
+        rccl: d23d18f
+        composable_kernel: 2570462
+        rocm-libraries: 0588f07
+        rocm-systems: 473025a
+        torch: 73adac
+        torchvision: f5c6c2e
+        triton: 7416ffc
+        accelerate: 34c1779
+        aiter: de14bec
+        diffusers: 40528e9
+        xfuser: 83978b5
+        yunchang: 2c9b712
+
+    - version: v25-10
+      pull_tag: rocm/pytorch-xdit:v25.10
+      docker_hub_url: https://hub.docker.com/r/rocm/pytorch-xdit
+      ROCm: 7.9.0
+      supported_models:
+        - group: Hunyuan Video
+          models:
+            - Hunyuan Video
+        - group: Wan-AI
+          models:
+            - Wan2.1
+            - Wan2.2
+        - group: FLUX
+          models:
+            - FLUX.1
+      whats_new:
+        - "First official xDiT Docker Release for Diffusion Inference."
+        - "Supports gfx942 and gfx950 series (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X)."
+        - "Support Wan 2.1, Wan 2.2, HunyuanVideo and Flux workloads."
+      components:
+        TheRock: 7afbe45
+        rccl: 9b04b2a
+        composable_kernel: b7a806f
+        rocm-libraries: f104555
+        rocm-systems: 25922d0
+        torch: 2.10.0a0+gite9c9017
+        torchvision: 0.22.0a0+966da7e
+        triton: 3.5.0+git52e49c12
+        accelerate: 1.11.0.dev0
+        aiter: 0.1.5.post4.dev20+ga25e55e79
+        diffusers: 0.36.0.dev0
+        xfuser: 0.4.4
+        yunchang: 0.6.3.post1
+
+  model_groups:
+    - group: Hunyuan Video
+      tag: hunyuan
+      models:
+        - model: Hunyuan Video
+          page_tag: hunyuan_tag
+          model_name: hunyuanvideo
+          model_repo: tencent/HunyuanVideo
+          revision: refs/pr/18
+          url: https://huggingface.co/tencent/HunyuanVideo
+          github: https://github.com/Tencent-Hunyuan/HunyuanVideo
+          mad_tag: pyt_xdit_hunyuanvideo
+    - group: Wan-AI
+      tag: wan
+      models:
+        - model: Wan2.1
+          page_tag: wan_21_tag
+          model_name: wan2_1-i2v-14b-720p
+          model_repo: Wan-AI/Wan2.1-I2V-14B-720P
+          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P
+          github: https://github.com/Wan-Video/Wan2.1
+          mad_tag: pyt_xdit_wan_2_1
+        - model: Wan2.2
+          page_tag: wan_22_tag
+          model_name: wan2_2-i2v-a14b
+          model_repo: Wan-AI/Wan2.2-I2V-A14B
+          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B
+          github: https://github.com/Wan-Video/Wan2.2
+          mad_tag: pyt_xdit_wan_2_2
+    - group: FLUX
+      tag: flux
+      models:
+        - model: FLUX.1
+          page_tag: flux_1_tag
+          model_name: FLUX.1-dev
+          model_repo: black-forest-labs/FLUX.1-dev
+          url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+          github: https://github.com/black-forest-labs/flux
+          mad_tag: pyt_xdit_flux

docs/data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.12-inference-models.yaml

@@ -0,0 +1,91 @@
+docker:
+  pull_tag: rocm/pytorch-xdit:v25.12
+  docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.12/images/sha256-e06895132316bf3c393366b70a91eaab6755902dad0100e6e2b38310547d9256
+  ROCm: 7.10.0
+  whats_new:
+      - "Adds T2V and TI2V support for Wan models."
+      - "Adds support for SD-3.5 T2I model."
+  components:
+    TheRock: 
+      version: 3e3f834
+      url: https://github.com/ROCm/TheRock
+    rccl:
+      version: d23d18f
+      url: https://github.com/ROCm/rccl
+    composable_kernel:
+      version: 2570462
+      url: https://github.com/ROCm/composable_kernel
+    rocm-libraries:
+      version: 0588f07
+      url: https://github.com/ROCm/rocm-libraries
+    rocm-systems:
+      version: 473025a
+      url: https://github.com/ROCm/rocm-systems
+    torch:
+      version: 73adac
+      url: https://github.com/pytorch/pytorch
+    torchvision:
+      version: f5c6c2e
+      url: https://github.com/pytorch/vision
+    triton:
+      version: 7416ffc
+      url: https://github.com/triton-lang/triton
+    accelerate:
+      version: 34c1779
+      url: https://github.com/huggingface/accelerate
+    aiter:
+      version: de14bec
+      url: https://github.com/ROCm/aiter
+    diffusers:
+      version: 40528e9
+      url: https://github.com/huggingface/diffusers
+    xfuser:
+      version: ccba9d5
+      url: https://github.com/xdit-project/xDiT
+    yunchang:
+      version: 2c9b712
+      url: https://github.com/feifeibear/long-context-attention
+  supported_models:
+    - group: Hunyuan Video
+      js_tag: hunyuan
+      models:
+        - model: Hunyuan Video
+          model_repo: tencent/HunyuanVideo
+          revision: refs/pr/18
+          url: https://huggingface.co/tencent/HunyuanVideo
+          github: https://github.com/Tencent-Hunyuan/HunyuanVideo
+          mad_tag: pyt_xdit_hunyuanvideo
+          js_tag: hunyuan_tag
+    - group: Wan-AI
+      js_tag: wan
+      models:
+        - model: Wan2.1
+          model_repo: Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+          github: https://github.com/Wan-Video/Wan2.1
+          mad_tag: pyt_xdit_wan_2_1
+          js_tag: wan_21_tag
+        - model: Wan2.2
+          model_repo: Wan-AI/Wan2.2-I2V-A14B-Diffusers
+          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers
+          github: https://github.com/Wan-Video/Wan2.2
+          mad_tag: pyt_xdit_wan_2_2
+          js_tag: wan_22_tag
+    - group: FLUX
+      js_tag: flux
+      models:
+        - model: FLUX.1
+          model_repo: black-forest-labs/FLUX.1-dev
+          url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+          github: https://github.com/black-forest-labs/flux
+          mad_tag: pyt_xdit_flux
+          js_tag: flux_1_tag
+    - group: Stable Diffusion
+      js_tag: stablediffusion
+      models:
+        - model: stable-diffusion-3.5-large
+          model_repo: stabilityai/stable-diffusion-3.5-large
+          url: https://huggingface.co/stabilityai/stable-diffusion-3.5-large
+          github: https://github.com/Stability-AI/sd3.5
+          mad_tag: pyt_xdit_sd_3_5
+          js_tag: stable_diffusion_3_5_large_tag

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

@@ -1,13 +1,13 @@
 dockers:
-  - pull_tag: rocm/vllm:rocm7.0.0_vllm_0.10.2_20251006
-    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.10.2_20251006/images/sha256-94fd001964e1cf55c3224a445b1fb5be31a7dac302315255db8422d813edd7f5
+  - pull_tag: rocm/vllm:rocm7.0.0_vllm_0.11.2_20251210
+    docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.11.2_20251210/images/sha256-e7f02dd2ce3824959658bc0391296f6158638e3ebce164f6c019c4eca8150ec7
     components:
       ROCm: 7.0.0
-      vLLM: 0.10.2 (0.11.0rc2.dev160+g790d22168.rocm700)
+      vLLM: 0.11.2 (0.11.2.dev673+g839868462.rocm700)
       PyTorch: 2.9.0a0+git1c57644
       hipBLASLt: 1.0.0
     dockerfile:
-      commit: 790d22168820507f3105fef29596549378cfe399
+      commit: 8398684622109c806a35d660647060b0b9910663
 model_groups:
   - group: Meta Llama
     tag: llama

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

@@ -0,0 +1,105 @@
+docker:
+  pull_tag: rocm/pytorch-xdit:v25.13
+  docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v25.13/images/sha256-81954713070d67bde08595e03f62110c8a3dd66a9ae17a77d611e01f83f0f4ef
+  ROCm: 7.11.0
+  whats_new:
+    - "Flux.1 Kontext support"
+    - "Flux.2 Dev support"
+    - "Flux FP8 GEMM support"
+    - "Hybrid FP8 attention support for Wan models"
+  components:
+    TheRock: 
+      version: 1728a81
+      url: https://github.com/ROCm/TheRock
+    rccl:
+      version: d23d18f
+      url: https://github.com/ROCm/rccl
+    composable_kernel:
+      version: ab0101c
+      url: https://github.com/ROCm/composable_kernel
+    rocm-libraries:
+      version: a2f7c35
+      url: https://github.com/ROCm/rocm-libraries
+    rocm-systems:
+      version: 659737c
+      url: https://github.com/ROCm/rocm-systems
+    torch:
+      version: 91be249
+      url: https://github.com/ROCm/pytorch
+    torchvision:
+      version: b919bd0
+      url: https://github.com/pytorch/vision
+    triton:
+      version: a272dfa
+      url: https://github.com/ROCm/triton
+    accelerate:
+      version: b521400f
+      url: https://github.com/huggingface/accelerate
+    aiter:
+      version: de14bec0
+      url: https://github.com/ROCm/aiter
+    diffusers:
+      version: a1f36ee3e
+      url: https://github.com/huggingface/diffusers
+    xfuser:
+      version: adf2681
+      url: https://github.com/xdit-project/xDiT
+    yunchang:
+      version: 2c9b712
+      url: https://github.com/feifeibear/long-context-attention
+  supported_models:
+    - group: Hunyuan Video
+      js_tag: hunyuan
+      models:
+        - model: Hunyuan Video
+          model_repo: tencent/HunyuanVideo
+          revision: refs/pr/18
+          url: https://huggingface.co/tencent/HunyuanVideo
+          github: https://github.com/Tencent-Hunyuan/HunyuanVideo
+          mad_tag: pyt_xdit_hunyuanvideo
+          js_tag: hunyuan_tag
+    - group: Wan-AI
+      js_tag: wan
+      models:
+        - model: Wan2.1
+          model_repo: Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+          github: https://github.com/Wan-Video/Wan2.1
+          mad_tag: pyt_xdit_wan_2_1
+          js_tag: wan_21_tag
+        - model: Wan2.2
+          model_repo: Wan-AI/Wan2.2-I2V-A14B-Diffusers
+          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers
+          github: https://github.com/Wan-Video/Wan2.2
+          mad_tag: pyt_xdit_wan_2_2
+          js_tag: wan_22_tag
+    - group: FLUX
+      js_tag: flux
+      models:
+        - model: FLUX.1
+          model_repo: black-forest-labs/FLUX.1-dev
+          url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+          github: https://github.com/black-forest-labs/flux
+          mad_tag: pyt_xdit_flux
+          js_tag: flux_1_tag
+        - model: FLUX.1 Kontext
+          model_repo: black-forest-labs/FLUX.1-Kontext-dev
+          url: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev
+          github: https://github.com/black-forest-labs/flux
+          mad_tag: pyt_xdit_flux_kontext
+          js_tag: flux_1_kontext_tag
+        - model: FLUX.2
+          model_repo: black-forest-labs/FLUX.2-dev
+          url: https://huggingface.co/black-forest-labs/FLUX.2-dev
+          github: https://github.com/black-forest-labs/flux2
+          mad_tag: pyt_xdit_flux_2
+          js_tag: flux_2_tag
+    - group: StableDiffusion
+      js_tag: stablediffusion
+      models:
+        - model: stable-diffusion-3.5-large
+          model_repo: stabilityai/stable-diffusion-3.5-large
+          url: https://huggingface.co/stabilityai/stable-diffusion-3.5-large
+          github: https://github.com/Stability-AI/sd3.5
+          mad_tag: pyt_xdit_sd_3_5
+          js_tag: stable_diffusion_3_5_large_tag

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

@@ -1,47 +1,16 @@
 dockers:
-  - pull_tag: rocm/jax-training:maxtext-v25.7-jax060
-    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
+  - pull_tag: rocm/jax-training:maxtext-v25.11
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.11/images/sha256-18e4d8f0b8ce7a7422c58046940dd5f32249960449fca09a562b65fb8eb1562a
     components:
-      ROCm: 6.4.1
-      JAX: 0.6.0
-      Python: 3.10.12
-      Transformer Engine: 2.1.0+90d703dd
-      hipBLASLt: 1.1.0-499ece1c21
-  - pull_tag: rocm/jax-training:maxtext-v25.7
-    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
-    components:
-      ROCm: 6.4.1
-      JAX: 0.5.0
-      Python: 3.10.12
-      Transformer Engine: 2.1.0+90d703dd
-      hipBLASLt: 1.x.x
+      ROCm: 7.1.0
+      JAX: 0.7.1
+      Python: 3.12
+      Transformer Engine: 2.4.0.dev0+281042de
+      hipBLASLt: 1.2.x
 model_groups:
   - group: Meta Llama
     tag: llama
     models:
-      - model: Llama 3.3 70B
-        mad_tag: jax_maxtext_train_llama-3.3-70b
-        model_repo: Llama-3.3-70B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3.1 8B
-        mad_tag: jax_maxtext_train_llama-3.1-8b
-        model_repo: Llama-3.1-8B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3.1 70B
-        mad_tag: jax_maxtext_train_llama-3.1-70b
-        model_repo: Llama-3.1-70B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3 8B
-        mad_tag: jax_maxtext_train_llama-3-8b
-        multinode_training_script: llama3_8b_multinode.sh
-        doc_options: ["multi-node"]
-      - model: Llama 3 70B
-        mad_tag: jax_maxtext_train_llama-3-70b
-        multinode_training_script: llama3_70b_multinode.sh
-        doc_options: ["multi-node"]
       - model: Llama 2 7B
         mad_tag: jax_maxtext_train_llama-2-7b
         model_repo: Llama-2-7B
@@ -54,6 +23,29 @@ model_groups:
         precision: bf16
         multinode_training_script: llama2_70b_multinode.sh
         doc_options: ["single-node", "multi-node"]
+      - model: Llama 3 8B (multi-node)
+        mad_tag: jax_maxtext_train_llama-3-8b
+        multinode_training_script: llama3_8b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3 70B (multi-node)
+        mad_tag: jax_maxtext_train_llama-3-70b
+        multinode_training_script: llama3_70b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3.1 8B
+        mad_tag: jax_maxtext_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 70B
+        mad_tag: jax_maxtext_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.3 70B
+        mad_tag: jax_maxtext_train_llama-3.3-70b
+        model_repo: Llama-3.3-70B
+        precision: bf16
+        doc_options: ["single-node"]
   - group: DeepSeek
     tag: deepseek
     models:

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

@@ -1,14 +1,17 @@
-dockers:
-  - pull_tag: rocm/megatron-lm:v25.8_py310
-    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
-      Python: "3.10"
-      Transformer Engine: 2.2.0.dev0+54dd2bdc
-      hipBLASLt: d1b517fc7a
-      Triton: 3.3.0
-      RCCL: 2.22.3
+docker:
+  pull_tag: rocm/primus:v25.10
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  components:
+    ROCm: 7.1.0
+    Primus: 0.3.0
+    Primus Turbo: 0.1.1
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Flash Attention: 2.8.3
+    hipBLASLt: 1.2.0-09ab7153e2
+    Triton: 3.4.0
+    RCCL: 2.27.7
 model_groups:
   - group: Meta Llama
     tag: llama
@@ -19,8 +22,6 @@ model_groups:
         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 3.1 70B (proxy)
-        mad_tag: pyt_megatron_lm_train_llama-3.1-70b-proxy
       - model: Llama 2 7B
         mad_tag: pyt_megatron_lm_train_llama-2-7b
       - model: Llama 2 70B

docs/data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v25.7-benchmark-models.yaml

@@ -0,0 +1,72 @@
+dockers:
+  - pull_tag: rocm/jax-training:maxtext-v25.7-jax060
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
+    components:
+      ROCm: 6.4.1
+      JAX: 0.6.0
+      Python: 3.10.12
+      Transformer Engine: 2.1.0+90d703dd
+      hipBLASLt: 1.1.0-499ece1c21
+  - pull_tag: rocm/jax-training:maxtext-v25.7
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
+    components:
+      ROCm: 6.4.1
+      JAX: 0.5.0
+      Python: 3.10.12
+      Transformer Engine: 2.1.0+90d703dd
+      hipBLASLt: 1.x.x
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: jax_maxtext_train_llama-3.3-70b
+        model_repo: Llama-3.3-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 8B
+        mad_tag: jax_maxtext_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 70B
+        mad_tag: jax_maxtext_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3 8B
+        mad_tag: jax_maxtext_train_llama-3-8b
+        multinode_training_script: llama3_8b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3 70B
+        mad_tag: jax_maxtext_train_llama-3-70b
+        multinode_training_script: llama3_70b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 2 7B
+        mad_tag: jax_maxtext_train_llama-2-7b
+        model_repo: Llama-2-7B
+        precision: bf16
+        multinode_training_script: llama2_7b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+      - model: Llama 2 70B
+        mad_tag: jax_maxtext_train_llama-2-70b
+        model_repo: Llama-2-70B
+        precision: bf16
+        multinode_training_script: llama2_70b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V2-Lite (16B)
+        mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
+        model_repo: DeepSeek-V2-lite
+        precision: bf16
+        doc_options: ["single-node"]
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: jax_maxtext_train_mixtral-8x7b
+        model_repo: Mixtral-8x7B
+        precision: bf16
+        doc_options: ["single-node"]

docs/data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v25.9-benchmark-models.yaml

@@ -0,0 +1,64 @@
+dockers:
+  - pull_tag: rocm/jax-training:maxtext-v25.9.1
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.9.1/images/sha256-60946cfbd470f6ee361fc9da740233a4fb2e892727f01719145b1f7627a1cff6
+    components:
+      ROCm: 7.0.0
+      JAX: 0.6.2
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+c91bac54
+      hipBLASLt: 1.x.x
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 2 7B
+        mad_tag: jax_maxtext_train_llama-2-7b
+        model_repo: Llama-2-7B
+        precision: bf16
+        multinode_training_script: llama2_7b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+      - model: Llama 2 70B
+        mad_tag: jax_maxtext_train_llama-2-70b
+        model_repo: Llama-2-70B
+        precision: bf16
+        multinode_training_script: llama2_70b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+      - model: Llama 3 8B (multi-node)
+        mad_tag: jax_maxtext_train_llama-3-8b
+        multinode_training_script: llama3_8b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3 70B (multi-node)
+        mad_tag: jax_maxtext_train_llama-3-70b
+        multinode_training_script: llama3_70b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3.1 8B
+        mad_tag: jax_maxtext_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 70B
+        mad_tag: jax_maxtext_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.3 70B
+        mad_tag: jax_maxtext_train_llama-3.3-70b
+        model_repo: Llama-3.3-70B
+        precision: bf16
+        doc_options: ["single-node"]
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V2-Lite (16B)
+        mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
+        model_repo: DeepSeek-V2-lite
+        precision: bf16
+        doc_options: ["single-node"]
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: jax_maxtext_train_mixtral-8x7b
+        model_repo: Mixtral-8x7B
+        precision: bf16
+        doc_options: ["single-node"]

docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.10-benchmark-models.yaml

@@ -0,0 +1,49 @@
+docker:
+  pull_tag: rocm/primus:v25.10
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  components:
+    ROCm: 7.1.0
+    Primus: 0.3.0
+    Primus Turbo: 0.1.1
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Flash Attention: 2.8.3
+    hipBLASLt: 1.2.0-09ab7153e2
+    Triton: 3.4.0
+    RCCL: 2.27.7
+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 (proxy)
+        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 (proxy)
+        mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-7b
+      - model: Qwen 2.5 72B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-72b

docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.8-benchmark-models.yaml

@@ -0,0 +1,48 @@
+dockers:
+  - pull_tag: rocm/megatron-lm:v25.8_py310
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      hipBLASLt: d1b517fc7a
+      Triton: 3.3.0
+      RCCL: 2.22.3
+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 3.1 70B (proxy)
+        mad_tag: pyt_megatron_lm_train_llama-3.1-70b-proxy
+      - 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 (proxy)
+        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 (proxy)
+        mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-7b
+      - model: Qwen 2.5 72B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-72b

docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.9-benchmark-models.yaml

@@ -0,0 +1,53 @@
+dockers:
+  MI355X and MI350X:
+    pull_tag: rocm/megatron-lm:v25.9_gfx950
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
+    components: &docker_components
+      ROCm: 7.0.0
+      Primus: aab4234
+      PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      Flash Attention: 2.8.3
+      hipBLASLt: 911283acd1
+      Triton: 3.4.0+rocm7.0.0.git56765e8c
+      RCCL: 2.26.6
+  MI325X and MI300X:
+    pull_tag: rocm/megatron-lm:v25.9_gfx942
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
+    components: *docker_components
+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 (proxy)
+        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 (proxy)
+        mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-7b
+      - model: Qwen 2.5 72B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-72b

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.10-benchmark-models.yaml

@@ -0,0 +1,58 @@
+docker:
+  pull_tag: rocm/primus:v25.10
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  components:
+    ROCm: 7.1.0
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Flash Attention: 2.8.3
+    hipBLASLt: 1.2.0-09ab7153e2
+    Triton: 3.4.0
+    RCCL: 2.27.7
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
+        config_name: llama3.3_70B-pretrain.yaml
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
+        config_name: llama3.1_70B-pretrain.yaml
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
+        config_name: llama3.1_8B-pretrain.yaml
+      - model: Llama 2 7B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
+        config_name: llama2_7B-pretrain.yaml
+      - model: Llama 2 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
+        config_name: llama2_70B-pretrain.yaml
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
+        config_name: deepseek_v3-pretrain.yaml
+      - model: DeepSeek-V2-Lite
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
+        config_name: deepseek_v2_lite-pretrain.yaml
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
+        config_name: mixtral_8x7B_v0.1-pretrain.yaml
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+        config_name: mixtral_8x22B_v0.1-pretrain.yaml
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
+        config_name: primus_qwen2.5_7B-pretrain.yaml
+      - model: Qwen 2.5 72B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
+        config_name: qwen2.5_72B-pretrain.yaml

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml

@@ -0,0 +1,58 @@
+dockers:
+  - pull_tag: rocm/megatron-lm:v25.8_py310
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
+    components:
+      ROCm: 6.4.3
+      Primus: 927a717
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      hipBLASLt: d1b517fc7a
+      Triton: 3.3.0
+      RCCL: 2.22.3
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
+        config_name: llama3.3_70B-pretrain.yaml
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
+        config_name: llama3.1_70B-pretrain.yaml
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
+        config_name: llama3.1_8B-pretrain.yaml
+      - model: Llama 2 7B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
+        config_name: llama2_7B-pretrain.yaml
+      - model: Llama 2 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
+        config_name: llama2_70B-pretrain.yaml
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
+        config_name: deepseek_v3-pretrain.yaml
+      - model: DeepSeek-V2-Lite
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
+        config_name: deepseek_v2_lite-pretrain.yaml
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
+        config_name: mixtral_8x7B_v0.1-pretrain.yaml
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+        config_name: mixtral_8x22B_v0.1-pretrain.yaml
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
+        config_name: primus_qwen2.5_7B-pretrain.yaml
+      - model: Qwen 2.5 72B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
+        config_name: qwen2.5_72B-pretrain.yaml

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.9-benchmark-models.yaml

@@ -0,0 +1,65 @@
+dockers:
+  MI355X and MI350X:
+    pull_tag: rocm/primus:v25.9_gfx950
+    docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
+    components: &docker_components
+      ROCm: 7.0.0
+      Primus: 0.3.0
+      Primus Turbo: 0.1.1
+      PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      Flash Attention: 2.8.3
+      hipBLASLt: 911283acd1
+      Triton: 3.4.0+rocm7.0.0.git56765e8c
+      RCCL: 2.26.6
+  MI325X and MI300X:
+    pull_tag: rocm/primus:v25.9_gfx942
+    docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
+    components: *docker_components
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
+        config_name: llama3.3_70B-pretrain.yaml
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
+        config_name: llama3.1_70B-pretrain.yaml
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
+        config_name: llama3.1_8B-pretrain.yaml
+      - model: Llama 2 7B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
+        config_name: llama2_7B-pretrain.yaml
+      - model: Llama 2 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
+        config_name: llama2_70B-pretrain.yaml
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
+        config_name: deepseek_v3-pretrain.yaml
+      - model: DeepSeek-V2-Lite
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
+        config_name: deepseek_v2_lite-pretrain.yaml
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
+        config_name: mixtral_8x7B_v0.1-pretrain.yaml
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+        config_name: mixtral_8x22B_v0.1-pretrain.yaml
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
+        config_name: primus_qwen2.5_7B-pretrain.yaml
+      - model: Qwen 2.5 72B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
+        config_name: qwen2.5_72B-pretrain.yaml

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.10-benchmark-models.yaml

@@ -0,0 +1,32 @@
+docker:
+  pull_tag: rocm/primus:v25.10
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  components:
+    ROCm: 7.1.0
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Flash Attention: 2.8.3
+    hipBLASLt: 1.2.0-09ab7153e2
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: BF16
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        url: https://huggingface.co/meta-llama/Llama-3.1-70B
+        precision: BF16
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek V2 16B
+        mad_tag: primus_pyt_train_deepseek-v2
+        model_repo: DeepSeek-V2
+        url: https://huggingface.co/deepseek-ai/DeepSeek-V2
+        precision: BF16

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml

@@ -0,0 +1,24 @@
+dockers:
+  - pull_tag: rocm/pytorch-training:v25.8
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+a1e66aae
+      Flash Attention: 3.0.0.post1
+      hipBLASLt: 1.1.0-d1b517fc7a
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 3.1 8B
+      mad_tag: primus_pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+    - model: Llama 3.1 70B
+      mad_tag: primus_pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B
+      precision: BF16

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.9-benchmark-models.yaml

@@ -0,0 +1,39 @@
+dockers:
+  MI355X and MI350X:
+    pull_tag: rocm/primus:v25.9_gfx950
+    docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
+    components: &docker_components
+      ROCm: 7.0.0
+      Primus: 0.3.0
+      Primus Turbo: 0.1.1
+      PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      Flash Attention: 2.8.3
+      hipBLASLt: 911283acd1
+      Triton: 3.4.0+rocm7.0.0.git56765e8c
+      RCCL: 2.26.6
+  MI325X and MI300X:
+    pull_tag: rocm/primus:v25.9_gfx942
+    docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
+    components: *docker_components
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 3.1 8B
+      mad_tag: primus_pyt_train_llama-3.1-8b
+      model_repo: meta-llama/Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+      config_file:
+        bf16: "./llama3_8b_fsdp_bf16.toml"
+        fp8: "./llama3_8b_fsdp_fp8.toml"
+    - model: Llama 3.1 70B
+      mad_tag: primus_pyt_train_llama-3.1-70b
+      model_repo: meta-llama/Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B
+      precision: BF16
+      config_file:
+        bf16: "./llama3_70b_fsdp_bf16.toml"
+        fp8: "./llama3_70b_fsdp_fp8.toml"

docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.10-benchmark-models.yaml

@@ -0,0 +1,197 @@
+docker:
+  pull_tag: rocm/primus:v25.10
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  components:
+    ROCm: 7.1.0
+    Primus: 0.3.0
+    Primus Turbo: 0.1.1
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Flash Attention: 2.8.3
+    hipBLASLt: 1.2.0-09ab7153e2
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    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: [pretrain, finetune_fw, finetune_lora, HF_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, finetune_fw, finetune_lora]
+    - 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]
+    - 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]
+  - group: OpenAI
+    tag: openai
+    models:
+    - model: GPT OSS 20B
+      mad_tag: pyt_train_gpt_oss_20b
+      model_repo: GPT-OSS-20B
+      url: https://huggingface.co/openai/gpt-oss-20b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+    - model: GPT OSS 120B
+      mad_tag: pyt_train_gpt_oss_120b
+      model_repo: GPT-OSS-120B
+      url: https://huggingface.co/openai/gpt-oss-120b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+  - group: DeepSeek
+    tag: deepseek
+    models:
+    - model: DeepSeek V2 16B
+      mad_tag: primus_pyt_train_deepseek-v2
+      model_repo: DeepSeek-V2
+      url: https://huggingface.co/deepseek-ai/DeepSeek-V2
+      precision: BF16
+      training_modes: [pretrain]
+  - group: Qwen
+    tag: qwen
+    models:
+    - model: Qwen 3 8B
+      mad_tag: pyt_train_qwen3-8b
+      model_repo: Qwen3-8B
+      url: https://huggingface.co/Qwen/Qwen3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 3 32B
+      mad_tag: pyt_train_qwen3-32b
+      model_repo: Qwen3-32
+      url: https://huggingface.co/Qwen/Qwen3-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 32B
+      mad_tag: pyt_train_qwen2.5-32b
+      model_repo: Qwen2.5-32B
+      url: https://huggingface.co/Qwen/Qwen2.5-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 72B
+      mad_tag: pyt_train_qwen2.5-72b
+      model_repo: Qwen2.5-72B
+      url: https://huggingface.co/Qwen/Qwen2.5-72B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2 1.5B
+      mad_tag: pyt_train_qwen2-1.5b
+      model_repo: Qwen2-1.5B
+      url: https://huggingface.co/Qwen/Qwen2-1.5B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 2 7B
+      mad_tag: pyt_train_qwen2-7b
+      model_repo: Qwen2-7B
+      url: https://huggingface.co/Qwen/Qwen2-7B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+  - group: Stable Diffusion
+    tag: sd
+    models:
+    - model: Stable Diffusion XL
+      mad_tag: pyt_huggingface_stable_diffusion_xl_2k_lora_finetuning
+      model_repo: SDXL
+      url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+      precision: BF16
+      training_modes: [posttrain]
+  - group: Flux
+    tag: flux
+    models:
+    - 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: [posttrain]
+  - group: NCF
+    tag: ncf
+    models:
+    - model: NCF
+      mad_tag: pyt_ncf_training
+      model_repo:
+      url: https://github.com/ROCm/FluxBenchmark
+      precision: FP32
+  - group: DLRM
+    tag: dlrm
+    models:
+    - model: DLRM v2
+      mad_tag: pyt_train_dlrm
+      model_repo: DLRM
+      url: https://github.com/AMD-AGI/DLRMBenchmark
+      training_modes: [pretrain]

docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.8-benchmark-models.yaml

@@ -0,0 +1,178 @@
+dockers:
+  - pull_tag: rocm/pytorch-training:v25.8
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+a1e66aae
+      Flash Attention: 3.0.0.post1
+      hipBLASLt: 1.1.0-d1b517fc7a
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    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: [pretrain, finetune_fw, finetune_lora, HF_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, finetune_fw, finetune_lora]
+    - 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]
+    - 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]
+  - group: OpenAI
+    tag: openai
+    models:
+    - model: GPT OSS 20B
+      mad_tag: pyt_train_gpt_oss_20b
+      model_repo: GPT-OSS-20B
+      url: https://huggingface.co/openai/gpt-oss-20b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+    - model: GPT OSS 120B
+      mad_tag: pyt_train_gpt_oss_120b
+      model_repo: GPT-OSS-120B
+      url: https://huggingface.co/openai/gpt-oss-120b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+  - group: Qwen
+    tag: qwen
+    models:
+    - model: Qwen 3 8B
+      mad_tag: pyt_train_qwen3-8b
+      model_repo: Qwen3-8B
+      url: https://huggingface.co/Qwen/Qwen3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 3 32B
+      mad_tag: pyt_train_qwen3-32b
+      model_repo: Qwen3-32
+      url: https://huggingface.co/Qwen/Qwen3-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 32B
+      mad_tag: pyt_train_qwen2.5-32b
+      model_repo: Qwen2.5-32B
+      url: https://huggingface.co/Qwen/Qwen2.5-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 72B
+      mad_tag: pyt_train_qwen2.5-72b
+      model_repo: Qwen2.5-72B
+      url: https://huggingface.co/Qwen/Qwen2.5-72B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2 1.5B
+      mad_tag: pyt_train_qwen2-1.5b
+      model_repo: Qwen2-1.5B
+      url: https://huggingface.co/Qwen/Qwen2-1.5B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 2 7B
+      mad_tag: pyt_train_qwen2-7b
+      model_repo: Qwen2-7B
+      url: https://huggingface.co/Qwen/Qwen2-7B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+  - group: Stable Diffusion
+    tag: sd
+    models:
+    - model: Stable Diffusion XL
+      mad_tag: pyt_huggingface_stable_diffusion_xl_2k_lora_finetuning
+      model_repo: SDXL
+      url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+      precision: BF16
+      training_modes: [finetune_lora]
+  - group: Flux
+    tag: flux
+    models:
+    - 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: NCF
+    tag: ncf
+    models:
+    - model: NCF
+      mad_tag: pyt_ncf_training
+      model_repo:
+      url: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Recommendation/NCF
+      precision: FP32

docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.9-benchmark-models.yaml

@@ -0,0 +1,186 @@
+dockers:
+  MI355X and MI350X:
+    pull_tag: rocm/pytorch-training:v25.9_gfx950
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
+    components: &docker_components
+      ROCm: 7.0.0
+      Primus: aab4234
+      PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      Flash Attention: 2.8.3
+      hipBLASLt: 911283acd1
+      Triton: 3.4.0+rocm7.0.0.git56765e8c
+      RCCL: 2.26.6
+  MI325X and MI300X:
+    pull_tag: rocm/pytorch-training:v25.9_gfx942
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
+    components: *docker_components
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    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: [pretrain, finetune_fw, finetune_lora, HF_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, finetune_fw, finetune_lora]
+    - 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]
+    - 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]
+  - group: OpenAI
+    tag: openai
+    models:
+    - model: GPT OSS 20B
+      mad_tag: pyt_train_gpt_oss_20b
+      model_repo: GPT-OSS-20B
+      url: https://huggingface.co/openai/gpt-oss-20b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+    - model: GPT OSS 120B
+      mad_tag: pyt_train_gpt_oss_120b
+      model_repo: GPT-OSS-120B
+      url: https://huggingface.co/openai/gpt-oss-120b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+  - group: Qwen
+    tag: qwen
+    models:
+    - model: Qwen 3 8B
+      mad_tag: pyt_train_qwen3-8b
+      model_repo: Qwen3-8B
+      url: https://huggingface.co/Qwen/Qwen3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 3 32B
+      mad_tag: pyt_train_qwen3-32b
+      model_repo: Qwen3-32
+      url: https://huggingface.co/Qwen/Qwen3-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 32B
+      mad_tag: pyt_train_qwen2.5-32b
+      model_repo: Qwen2.5-32B
+      url: https://huggingface.co/Qwen/Qwen2.5-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 72B
+      mad_tag: pyt_train_qwen2.5-72b
+      model_repo: Qwen2.5-72B
+      url: https://huggingface.co/Qwen/Qwen2.5-72B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2 1.5B
+      mad_tag: pyt_train_qwen2-1.5b
+      model_repo: Qwen2-1.5B
+      url: https://huggingface.co/Qwen/Qwen2-1.5B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 2 7B
+      mad_tag: pyt_train_qwen2-7b
+      model_repo: Qwen2-7B
+      url: https://huggingface.co/Qwen/Qwen2-7B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+  - group: Stable Diffusion
+    tag: sd
+    models:
+    - model: Stable Diffusion XL
+      mad_tag: pyt_huggingface_stable_diffusion_xl_2k_lora_finetuning
+      model_repo: SDXL
+      url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+      precision: BF16
+      training_modes: [posttrain-p]
+  - group: Flux
+    tag: flux
+    models:
+    - 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: [posttrain-p]
+  - group: NCF
+    tag: ncf
+    models:
+    - model: NCF
+      mad_tag: pyt_ncf_training
+      model_repo:
+      url: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Recommendation/NCF
+      precision: FP32

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

@@ -1,15 +1,15 @@
-dockers:
-  - pull_tag: rocm/megatron-lm:v25.8_py310
-    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
-    components:
-      ROCm: 6.4.3
-      Primus: 927a717
-      PyTorch: 2.8.0a0+gitd06a406
-      Python: "3.10"
-      Transformer Engine: 2.2.0.dev0+54dd2bdc
-      hipBLASLt: d1b517fc7a
-      Triton: 3.3.0
-      RCCL: 2.22.3
+docker:
+  pull_tag: rocm/primus:v25.11
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  components:
+    ROCm: 7.1.0
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Flash Attention: 2.8.3
+    hipBLASLt: 1.2.0-09ab7153e2
+    Triton: 3.4.0
+    RCCL: 2.27.7
 model_groups:
   - group: Meta Llama
     tag: llama

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

@@ -1,24 +1,32 @@
-dockers:
-  - pull_tag: rocm/pytorch-training:v25.8
-    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
-      Python: 3.10.18
-      Transformer Engine: 2.2.0.dev0+a1e66aae
-      Flash Attention: 3.0.0.post1
-      hipBLASLt: 1.1.0-d1b517fc7a
+docker:
+  pull_tag: rocm/primus:v25.11
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  components:
+    ROCm: 7.1.0
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Flash Attention: 2.8.3
+    hipBLASLt: 1.2.0-09ab7153e2
 model_groups:
   - group: Meta Llama
     tag: llama
     models:
-    - model: Llama 3.1 8B
-      mad_tag: primus_pyt_train_llama-3.1-8b
-      model_repo: Llama-3.1-8B
-      url: https://huggingface.co/meta-llama/Llama-3.1-8B
-      precision: BF16
-    - model: Llama 3.1 70B
-      mad_tag: primus_pyt_train_llama-3.1-70b
-      model_repo: Llama-3.1-70B
-      url: https://huggingface.co/meta-llama/Llama-3.1-70B
-      precision: BF16
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: BF16
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        url: https://huggingface.co/meta-llama/Llama-3.1-70B
+        precision: BF16
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek V3 16B
+        mad_tag: primus_pyt_train_deepseek-v3-16b
+        model_repo: DeepSeek-V3
+        url: https://huggingface.co/deepseek-ai/DeepSeek-V3
+        precision: BF16

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

@@ -1,13 +1,15 @@
-dockers:
-  - pull_tag: rocm/pytorch-training:v25.8
-    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
-      Python: 3.10.18
-      Transformer Engine: 2.2.0.dev0+a1e66aae
-      Flash Attention: 3.0.0.post1
-      hipBLASLt: 1.1.0-d1b517fc7a
+docker:
+  pull_tag: rocm/primus:v25.10
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  components:
+    ROCm: 7.1.0
+    Primus: 0.3.0
+    Primus Turbo: 0.1.1
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Flash Attention: 2.8.3
+    hipBLASLt: 1.2.0-09ab7153e2
 model_groups:
   - group: Meta Llama
     tag: llama
@@ -111,6 +113,15 @@ model_groups:
       url: https://huggingface.co/openai/gpt-oss-120b
       precision: BF16
       training_modes: [HF_finetune_lora]
+  - group: DeepSeek
+    tag: deepseek
+    models:
+    - model: DeepSeek V2 16B
+      mad_tag: primus_pyt_train_deepseek-v2
+      model_repo: DeepSeek-V2
+      url: https://huggingface.co/deepseek-ai/DeepSeek-V2
+      precision: BF16
+      training_modes: [pretrain]
   - group: Qwen
     tag: qwen
     models:
@@ -158,7 +169,7 @@ model_groups:
       model_repo: SDXL
       url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
       precision: BF16
-      training_modes: [finetune_lora]
+      training_modes: [posttrain]
   - group: Flux
     tag: flux
     models:
@@ -167,12 +178,20 @@ model_groups:
       model_repo: Flux
       url: https://huggingface.co/black-forest-labs/FLUX.1-dev
       precision: BF16
-      training_modes: [pretrain]
+      training_modes: [posttrain]
   - group: NCF
     tag: ncf
     models:
     - model: NCF
       mad_tag: pyt_ncf_training
       model_repo:
-      url: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Recommendation/NCF
+      url: https://github.com/ROCm/FluxBenchmark
       precision: FP32
+  - group: DLRM
+    tag: dlrm
+    models:
+    - model: DLRM v2
+      mad_tag: pyt_train_dlrm
+      model_repo: DLRM
+      url: https://github.com/AMD-AGI/DLRMBenchmark
+      training_modes: [pretrain]

docs/data/reference/gpu-atomics-operation/cas-atomics_nopcie_instinct.csv

@@ -1,4 +1,4 @@
-Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X series,MI300A,MI350X series
+Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X Series,MI300A,MI350X Series
 32 bit atomicAdd,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS
 32 bit atomicSub,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS
 32 bit atomicMin,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS

docs/data/reference/gpu-atomics-operation/cas-atomics_pcie_instinct.csv

@@ -1,4 +1,4 @@
-Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X series,MI300A,MI350X series
+Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X Series,MI300A,MI350X Series
 32 bit atomicAdd,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS
 32 bit atomicSub,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS
 32 bit atomicMin,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS

docs/data/reference/gpu-atomics-operation/hw-atomics_nopcie_instinct.csv

@@ -1,4 +1,4 @@
-Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X series,MI300A,MI350X series
+Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X Series,MI300A,MI350X Series
 32 bit atomicAdd,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native
 32 bit atomicSub,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native
 32 bit atomicMin,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native

docs/data/reference/gpu-atomics-operation/hw-atomics_pcie_instinct.csv

@@ -1,4 +1,4 @@
-Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X series,MI300A,MI350X series
+Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X Series,MI300A,MI350X Series
 32 bit atomicAdd,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native
 32 bit atomicSub,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native
 32 bit atomicMin,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native

docs/data/reference/precision-support/precision-support.yaml

@@ -32,7 +32,7 @@ library_groups:
 
       - name: "MIGraphX"
         tag: "migraphx"
-        doc_link: "amdmigraphx:reference/cpp"
+        doc_link: "amdmigraphx:reference/MIGraphX-cpp"
         data_types:
           - type: "int8"
             support: "⚠️"
@@ -290,7 +290,7 @@ library_groups:
 
       - name: "Tensile"
         tag: "tensile"
-        doc_link: "tensile:reference/precision-support"
+        doc_link: "tensile:src/reference/precision-support"
         data_types:
           - type: "int8"
             support: "✅"