Reverting Optiq note

Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.31.0 to 1.31.1.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.31.0...v1.31.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-version: 1.31.1
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@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/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" --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 }}
+- ${{ 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/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-examples.yml

@@ -17,21 +17,39 @@ parameters:
     - libdw-dev
     - libglfw3-dev
     - libmsgpack-dev
-    - libomp-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
@@ -45,6 +63,10 @@ parameters:
     - llvm-project
     - MIOpen
     - MIVisionX
+    - rocm_smi_lib
+    - rccl
+    - rocAL
+    - rocALUTION
     - rocBLAS
     - rocDecode
     - rocFFT
@@ -63,7 +85,11 @@ parameters:
   type: object
   default:
     - AMDMIGraphX
+    - aomp
+    - aomp-extras
     - clr
+    - half
+    - composable_kernel
     - hipBLAS
     - hipBLAS-common
     - hipBLASLt
@@ -77,6 +103,10 @@ parameters:
     - llvm-project
     - MIOpen
     - MIVisionX
+    - rocm_smi_lib
+    - rccl
+    - rocAL
+    - rocALUTION
     - rocBLAS
     - rocDecode
     - rocFFT
@@ -121,6 +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:
@@ -220,5 +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/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/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:

.gitignore

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

.wordlist.txt

@@ -79,6 +79,7 @@ CX
 Cavium
 CentOS
 ChatGPT
+Cholesky
 CoRR
 Codespaces
 Commitizen
@@ -137,8 +138,10 @@ ESXi
 EP
 EoS
 etcd
+equalto
 fas
 FBGEMM
+FiLM
 FIFOs
 FFT
 FFTs
@@ -159,10 +162,12 @@ Fortran
 Fuyu
 GALB
 GAT
+GATNE
 GCC
 GCD
 GCDs
 GCN
+GCNN
 GDB
 GDDR
 GDR
@@ -181,6 +186,8 @@ Glibc
 GLXT
 Gloo
 GMI
+GNN
+GNNs
 GPG
 GPR
 GPT
@@ -220,6 +227,8 @@ href
 Hyperparameters
 HybridEngine
 Huggingface
+Hunyuan
+HunyuanVideo
 IB
 ICD
 ICT
@@ -250,6 +259,7 @@ Intersphinx
 Intra
 Ioffe
 JAX's
+JAXLIB
 Jinja
 JSON
 Jupyter
@@ -270,6 +280,7 @@ LLM
 LLMs
 LLVM
 LM
+logsumexp
 LRU
 LSAN
 LSan
@@ -322,6 +333,7 @@ Mooncake
 Mpops
 Multicore
 Multithreaded
+mx
 MXFP
 MyEnvironment
 MyST
@@ -385,6 +397,7 @@ perf
 PEQT
 PIL
 PILImage
+PJRT
 POR
 PRNG
 PRs
@@ -531,6 +544,7 @@ UAC
 UC
 UCC
 UCX
+ud
 UE
 UIF
 UMC
@@ -842,6 +856,7 @@ pallas
 parallelization
 parallelizing
 param
+params
 parameterization
 passthrough
 pe
@@ -888,6 +903,7 @@ querySelectorAll
 queueing
 qwen
 radeon
+rc
 rccl
 rdc
 rdma
@@ -949,6 +965,7 @@ scalability
 scalable
 scipy
 seealso
+selectattr
 selectedTag
 sendmsg
 seqs
@@ -1052,6 +1069,8 @@ writebacks
 wrreq
 wzo
 xargs
+xdit
+xDiT
 xGMI
 xPacked
 xz

CHANGELOG.md

@@ -4,6 +4,977 @@ This page is a historical overview of changes made to ROCm components. This
 consolidated changelog documents key modifications and improvements across
 different versions of the ROCm software stack and its components.
 
+## ROCm 7.1.1
+
+See the [ROCm 7.1.1 release notes](https://rocm.docs.amd.com/en/docs-7.1.1/about/release-notes.html#rocm-7-1-1-release-notes)
+for a complete overview of this release.
+
+### **AMD SMI** (26.2.0)
+
+#### Added
+
+- Caching for repeated ASIC information calls.  
+  - The cache added to `amdsmi_get_gpu_asic_info` improves performance by avoiding redundant hardware queries.
+  - The cache stores ASIC info for each GPU device with a configurable duration, defaulting to 10 seconds. Use the `AMDSMI_ASIC_INFO_CACHE_MS` environment variable for cache duration configuration for `amdsmi_get_gpu_asic_info` API calls.
+
+- Support for GPU partition metrics.
+  - Provides support for `xcp_metrics` v1.0 and extends support for v1.1 (dynamic metrics).
+  - Added `amdsmi_get_gpu_partition_metrics_info`, which provides per XCP (partition) metrics.
+
+- Support for displaying newer VRAM memory types in `amd-smi static --vram`.
+  - The `amdsmi_get_gpu_vram_info()` API now supports detecting DDR5, LPDDR4, LPDDR5, and HBM3E memory types.
+
+#### Changed
+
+- Updated `amd-smi static --numa` socket affinity data structure. It now displays CPU affinity information in both hexadecimal bitmask format and expanded CPU core ranges, replacing the previous simplified socket enumeration approach.
+
+#### Resolved issues
+
+- Fixed incorrect topology weight calculations.  
+  - Out-of-bound writes caused corruption in the weights field.
+
+- Fixed `amd-smi event` not respecting the Linux timeout command.  
+
+- Fixed an issue where `amdsmi_get_power_info` returned `AMDSMI_STATUS_API_FAILED`.  
+  - VMs were incorrectly reporting `AMDSMI_STATUS_API_FAILED` when unable to get the power cap within the `amdsmi_get_power_info`.
+  - The API now returns `N/A` or `UINT_MAX` for values that can't be retrieved, instead of failing.
+
+- Fixed output for `amd-smi xgmi -l --json`.
+
+```{note}
+See the full [AMD SMI changelog](https://github.com/ROCm/amdsmi/blob/release/rocm-rel-7.1/CHANGELOG.md#amd_smi_lib-for-rocm-711) for details, examples, and in-depth descriptions.
+```
+
+### **Composable Kernel** (1.1.0)
+
+#### Upcoming changes
+
+* Composable Kernel will adopt C++20 features in an upcoming ROCm release, updating the minimum compiler requirement to C++20. Ensure that your development environment meets this requirement to facilitate a seamless transition.
+  
+### **HIP** (7.1.1)
+
+#### Added
+
+* Support for the flag `hipHostRegisterIoMemory` in `hipHostRegister`, used to register I/O memory with HIP runtime so the GPU can access it.
+
+#### Resolved issues
+
+* Incorrect Compute Unit (CU) mask in logging. HIP runtime now correctly sets the field width for the output print operation. When logging is enabled via the environment variable `AMD_LOG_LEVEL`, the runtime logs the accurate CU mask.
+* A segmentation fault occurred when the dynamic queue management mechanism was enabled. HIP runtime now ensures GPU queues aren't `NULL` during marker submission, preventing crashes and improving robustness.
+* An error encountered on HIP tear-down after device reset in certain applications due to accessing stale memory objects. HIP runtime now properly releases memory associated with host calls, ensuring reliable device resets.
+* A race condition occurred in certain graph-related applications when pending asynchronous signal handlers referenced device memory that had already been released, leading to memory corruption. HIP runtime now uses a reference counting strategy to manage access to device objects in asynchronous event handlers, ensuring safe and reliable memory usage.
+
+### **MIGraphX** (2.14.0)
+
+#### Resolved issues
+
+* Fixed an error that resulted when running `make check` on systems running on a gfx1201 GPU.
+
+### **RCCL** (2.27.7)
+
+#### Resolved issues
+
+* Fixed a single-node data corruption issue in MSCCL on the AMD Instinct MI350X and MI355X GPUs for the LL protocol. This previously affected about two percent of the runs for single-node `AllReduce` with inputs smaller than 512 KiB.
+
+### **rocBLAS** (5.1.1)
+
+#### Changed
+  * By default, rocBLAS will not use stream order allocation for its internal workspace. To enable this behavior, set the `ROCBLAS_STREAM_ORDER_ALLOC` environment variable.
+
+### **ROCm Bandwidth Test** (2.6.0)
+
+#### Resolved issues
+
+- Test failure with error message `Cannot make canonical path`.
+- Healthcheck test failure with seg fault on gfx942.
+- Segmentation fault observed in `schmoo` and `one2all` when executed on `sgpu` setup.
+
+#### Known issues
+
+- `rocm-bandwidth-test` folder fails to be removed after driver uninstallation:
+    * After running `amdgpu-uninstall`, the `rocm-bandwidth-test` folder and package are still present.
+    * Workaround: Remove the package manually using: 
+    ```
+    sudo apt-get remove -y rocm-bandwidth-test
+    ```
+
+### **ROCm Compute Profiler** (3.3.1)
+
+#### Added
+
+* Support for PC sampling of multi-kernel applications.
+  * PC Sampling output instructions are displayed with the name of the kernel to which the individual instruction belongs.
+  * Single kernel selection is supported so that the PC samples of the selected kernel can be displayed.
+
+#### Changed
+
+* Roofline analysis now runs on GPU 0 by default instead of all GPUs.
+
+#### Optimized
+
+* Improved roofline benchmarking by updating the `flops_benchmark` calculation.
+
+* Improved standalone roofline plots in profile mode (PDF output) and analyze mode (CLI and GUI visual plots):
+  * Fixed the peak MFMA/VALU lines being cut off.
+  * Cleaned up the overlapping roofline numeric values by moving them into the side legend.
+  * Added AI points chart with respective values, cache level, and compute/memory bound status.
+  * Added full kernel names to the symbol chart.
+
+#### Resolved issues
+
+* Resolved existing issues to improve stability.
+
+### **ROCm Systems Profiler** (1.2.1)
+
+#### Resolved issues
+
+- Fixed an issue of OpenMP Tools (OMPT) events, GPU performance counters, VA-API, MPI, and host events failing to be collected in the `rocpd` output.
+
+### **ROCm Validation Suite** (1.3.0)
+
+#### Added
+
+* Support for different test levels with `-r` option for AMD Instinct MI3XXx GPUs.
+* Set compute type for DGEMM operations on AMD Instinct MI350X and MI355X GPUs.
+
+### **rocSHMEM** (3.1.0)
+
+#### Added
+
+* Allowed IPC, RO, and GDA backends to be selected at runtime.
+* GDA conduit for different NIC vendors:
+   * Broadcom BNXT\_RE (Thor 2)
+   * Mellanox MLX5 (IB and RoCE ConnectX-7)
+* New APIs:
+   * `rocshmem_get_device_ctx`
+
+#### Changed
+
+* The following APIs have been deprecated:
+  * `rocshmem_wg_init`
+  * `rocshmem_wg_finalize`
+  * `rocshmem_wg_init_thread`
+
+* `rocshmem_ptr`  can now return non-null pointer to a shared memory region when the IPC transport is available to reach that region. Previously, it would return a null pointer.
+* `ROCSHMEM_RO_DISABLE_IPC` is renamed to `ROCSHMEM_DISABLE_MIXED_IPC`. 
+    - This environment variable wasn't documented in earlier releases. It's now documented.
+
+#### Removed
+
+* rocSHMEM no longer requires rocPRIM and rocThrust as dependencies.
+* Removed MPI compile-time dependency.
+
+#### Known issues
+
+* Only a subset of rocSHMEM APIs are implemented for the GDA conduit.
+
+### **rocWMMA** (2.1.0)
+
+#### Added
+
+* More unit tests to increase the code coverage.
+
+#### Changed
+
+* Increased compile timeout and improved visualization in `math-ci`.
+
+#### Removed
+
+* Absolute paths from the `RPATH` of sample and test binary files.
+
+#### Resolved issues
+
+* Fixed issues caused by HIP changes:
+    * Removed the `.data` member from `HIP_vector_type`.
+    * Broadcast constructor now only writes to the first vector element.
+* Fixed a bug related to `int32_t` usage in `hipRTC_gemm` for gfx942, caused by breaking changes in HIP.
+* Replaced `#pragma unroll` with `static for` to fix a bug caused by the upgraded compiler which no longer supports using `#pragma unroll` with template parameter indices.
+* Corrected test predicates for `BLK` and `VW` cooperative kernels.
+* Modified `compute_utils.sh` in `build-infra` to ensure rocWMMA is built with gfx1151 target for ROCm 7.0 and beyond.
+
+## ROCm 7.1.0
+
+See the [ROCm 7.1.0 release notes](https://rocm.docs.amd.com/en/docs-7.1.0/about/release-notes.html#rocm-7-1-0-release-notes)
+for a complete overview of this release.
+
+### **AMD SMI** (26.1.0)
+
+#### Added
+
+* `GPU LINK PORT STATUS` table to `amd-smi xgmi` command. The `amd-smi xgmi -s` or `amd-smi xgmi --source-status` will now show the `GPU LINK PORT STATUS` table.  
+
+* `amdsmi_get_gpu_revision()` to Python API. This function retrieves the GPU revision ID. Available in `amdsmi_interface.py` as `amdsmi_get_gpu_revision()`.
+
+* Gpuboard and baseboard temperatures to `amd-smi metric` command.
+
+#### Changed
+
+* Struct `amdsmi_topology_nearest_t` member `processor_list`. Member size changed, processor_list[AMDSMI_MAX_DEVICES * AMDSMI_MAX_NUM_XCP].
+
+* `amd-smi reset --profile` behavior so that it won't also reset the performance level.  
+  * The performance level can still be reset using `amd-smi reset --perf-determinism`.  
+
+* Setting power cap is now available in Linux Guest. You can now use `amd-smi set --power-cap` as usual in Linux Guest systems too.
+
+* Changed `amd-smi static --vbios` to `amd-smi static --ifwi`.  
+  * VBIOS naming is replaced with IFWI (Integrated Firmware Image) for improved clarity and consistency.
+  * AMD Instinct MI300 Series GPUs (and later) now use a new version format with enhanced build information.
+  * Legacy command `amd-smi static --vbios` remains functional for backward compatibility, but displays updated IFWI heading.
+  * The Python, C, and Rust API for `amdsmi_get_gpu_vbios_version()` will now have a new field called `boot_firmware`, which will return the legacy vbios version number that is also known as the Unified BootLoader (UBL) version.
+
+#### Optimized
+
+* Optimized the way `amd-smi process` validates, which processes are running on a GPU. 
+
+#### Resolved issues
+
+* Fixed a CPER record count mismatch issue when using the `amd-smi ras --cper --file-limit`. Updated the deletion calculation to use `files_to_delete = len(folder_files) - file_limit` for exact file count management.
+
+* Fixed the event monitoring segfaults causing RDC to crash. Added the mutex locking around access to device event notification file pointer.
+
+* Fixed an issue where using `amd-smi ras --folder <folder_name>` was forcing the created folder's name to be lowercase. This fix also makes all string input options case-insensitive.
+
+* Fixed certain output in `amd-smi monitor` when GPUs are partitioned. It fixes the issue with amd-smi monitor such as: `amd-smi monitor -Vqt`, `amd-smi monitor -g 0 -Vqt -w 1`, and `amd-smi monitor -Vqt --file /tmp/test1`. These commands will now be able to display as normal in partitioned GPU scenarios.
+
+```{note}
+See the full [AMD SMI changelog](https://github.com/ROCm/amdsmi/blob/release/rocm-rel-7.1/CHANGELOG.md#amd_smi_lib-for-rocm-710) for details, examples, and in-depth descriptions.
+```
+
+### **Composable Kernel** (1.1.0)
+
+#### Added
+ 
+* Support for hdim as a multiple of 32 for FMHA (fwd/fwd_splitkv/bwd).
+* Support for elementwise kernel.
+ 
+#### Upcoming changes
+ 
+* Non-grouped convolutions are deprecated. Their functionality is supported by grouped convolution.
+
+### **HIP** (7.1.0)
+
+#### Added
+
+* New HIP APIs
+    - `hipModuleGetFunctionCount` returns the number of functions within a module
+    - `hipMemsetD2D8` sets 2D memory range with specified 8-bit values
+    - `hipMemsetD2D8Async` asynchronously sets 2D memory range with specified 8-bit values
+    - `hipMemsetD2D16` sets 2D memory range with specified 16-bit values
+    - `hipMemsetD2D16Async` asynchronously sets 2D memory range with specified 16-bit values
+    - `hipMemsetD2D32` sets 2D memory range with specified 32-bit values
+    - `hipMemsetD2D32Async` asynchronously sets 2D memory range with specified 32-bit values
+    - `hipStreamSetAttribute` sets attributes such as synchronization policy for a given stream
+    - `hipStreamGetAttribute` returns attributes such as priority for a given stream
+    - `hipModuleLoadFatBinary`  loads fatbin binary to a module
+    - `hipMemcpyBatchAsync` asynchronously performs a batch copy of 1D or 2D memory
+    - `hipMemcpy3DBatchAsync` asynchronously performs a batch copy of 3D memory
+    - `hipMemcpy3DPeer` copies memory between devices
+    - `hipMemcpy3DPeerAsync` asynchronously copies memory between devices
+    - `hipMemsetD2D32Async` asynchronously sets 2D memory range with specified 32-bit values
+    - `hipMemPrefetchAsync_v2`  prefetches memory to the specified location
+    - `hipMemAdvise_v2`         advises about the usage of a given memory range
+    - `hipGetDriverEntryPoint ` gets function pointer of a HIP API.
+    - `hipSetValidDevices`      sets a default list of devices that can be used by HIP
+    - `hipStreamGetId`          queries the id of a stream
+* Support for nested tile partitioning within cooperative groups, matching CUDA functionality.
+
+#### Optimized
+
+* Improved HIP module loading latency.
+* Optimized kernel metadata retrieval during module post-load.
+* Optimized doorbell ring in HIP runtime for the following performance improvements:
+    - Makes efficient packet batching for HIP graph launch
+    - Dynamic packet copying based on a defined maximum threshold or power-of-2 staggered copy pattern
+    - If timestamps are not collected for a signal for reuse, it creates a new signal. This can potentially increase the signal footprint if the handler doesn't run fast enough
+
+#### Resolved issues
+
+* A segmentation fault occurred in the application when capturing the same HIP graph from multiple streams with cross-stream dependencies.  The HIP runtime has fixed an issue where a forked stream joined to a parent stream that was not originally created with the API `hipStreamBeginCapture`.
+* Different behavior of en-queuing command on a legacy stream during stream capture on AMD ROCM platform, compared with CUDA. HIP runtime now returns an error in this specific situation to match CUDA behavior.
+* Failure of memory access fault occurred in rocm-examples test suite. When Heterogeneous Memory Management (HMM) is not supported in the driver, `hipMallocManaged` will only allocate system memory in HIP runtime.
+
+#### Known issues
+
+* SPIR-V-enabled applications might encounter a segmentation fault. The problem doesn't exist when SPIR-V is disabled. The issue will be fixed in the next ROCm release. 
+
+### **hipBLAS** (3.1.0)
+
+#### Added
+
+* `--clients-only` build option to only build clients against a prebuilt library.
+* gfx1150, gfx1151, gfx1200, and gfx1201 support enabled.
+* FORTRAN enabled for the Microsoft Windows build and tests.
+* Additional reference library fallback options added.
+
+#### Changed
+
+* Improved the build time for clients by removing `clients_common.cpp` from the hipblas-test build.
+
+### **hipBLASLt** (1.1.0)
+
+#### Added
+
+* Fused Clamp GEMM for ``HIPBLASLT_EPILOGUE_CLAMP_EXT`` and ``HIPBLASLT_EPILOGUE_CLAMP_BIAS_EXT``. This feature requires the minimum (``HIPBLASLT_MATMUL_DESC_EPILOGUE_ACT_ARG0_EXT``) and maximum (``HIPBLASLT_MATMUL_DESC_EPILOGUE_ACT_ARG1_EXT``) to be set.
+* Support for ReLU/Clamp activation functions with auxiliary output for the `FP16` and `BF16` data types for gfx942 to capture intermediate results. This feature is enabled for ``HIPBLASLT_EPILOGUE_RELU_AUX``, ``HIPBLASLT_EPILOGUE_RELU_AUX_BIAS``, ``HIPBLASLT_EPILOGUE_CLAMP_AUX_EXT``, and ``HIPBLASLT_EPILOGUE_CLAMP_AUX_BIAS_EXT``.
+* Support for `HIPBLAS_COMPUTE_32F_FAST_16BF` for FP32 data type for gfx950 only.
+* CPP extension APIs ``setMaxWorkspaceBytes`` and ``getMaxWorkspaceBytes``.
+* Feature to print logs (using ``HIPBLASLT_LOG_MASK=32``) for Grouped GEMM.
+* Support for swizzleA by using the hipblaslt-ext cpp API.
+* Support for hipBLASLt extop for gfx11XX and gfx12XX.
+
+#### Changed
+
+* ``hipblasLtMatmul()`` now returns an error when the workspace size is insufficient, rather than causing a segmentation fault.
+
+#### Optimized
+
+* `TF32` kernel optimization for the AMD Instinct MI355X GPU to enhance training and inference efficiency.
+
+#### Resolved issues
+
+* Fixed incorrect results when using ldd and ldc dimension parameters with some solutions.
+
+### **hipCUB** (4.1.0)
+
+#### Added
+
+* Exposed Thread-level reduction API `hipcub::ThreadReduce`.
+* `::hipcub::extents`, with limited parity to C++23's `std::extents`. Only `static extents` is supported; `dynamic extents` is not. Helper structs have been created to perform computations on `::hipcub::extents` only when the backend is rocPRIM. For the CUDA backend, similar functionality exists.
+* `projects/hipcub/hipcub/include/hipcub/backend/rocprim/util_mdspan.hpp` to support `::hipcub::extents`.
+* `::hipcub::ForEachInExtents` API.
+* `hipcub::DeviceTransform::Transform` and `hipcub::DeviceTransform::TransformStableArgumentAddresses`.
+* hipCUB and its dependency rocPRIM have been moved into the new `rocm-libraries` [monorepo repository](https://github.com/ROCm/rocm-libraries). This repository contains a number of ROCm libraries that are frequently used together.
+  * The repository migration requires a few changes to the way that hipCUB fetches library dependencies.
+  * CMake build option `ROCPRIM_FETCH_METHOD` may be set to one of the following:
+    * `PACKAGE` - (default) searches for a preinstalled packaged version of the dependency. If it is not found, the build will fall back using option `DOWNLOAD`, below.
+    * `DOWNLOAD` - downloads the dependency from the rocm-libraries repository. If git >= 2.25 is present, this option uses a sparse checkout that avoids downloading more than it needs to. If not, the whole monorepo is downloaded (this may take some time).
+    * `MONOREPO` - this option is intended to be used if you are building hipCUB from within a copy of the rocm-libraries repository that you have cloned (and therefore already contains rocPRIM). When selected, the build will try find the dependency in the local repository tree. If it cannot be found, the build will attempt to use git to perform a sparse-checkout of rocPRIM. If that also fails, it will fall back to using the `DOWNLOAD` option described above.
+
+* A new CMake option `-DUSE_SYSTEM_LIB` to allow tests to be built from installed `hipCUB` provided by the system.
+
+#### Changed
+
+* Changed include headers to avoid relative includes that have slipped in.
+* Changed `CUDA_STANDARD` for tests in `test/hipcub`, due to C++17 APIs such as `std::exclusive_scan` is used in some tests. Still use `CUDA_STANDARD 14` for `test/extra`.
+* Changed `CCCL_MINIMUM_VERSION` to `2.8.2` to align with CUB.
+* Changed `cmake_minimum_required` from `3.16` to `3.18`, in order to support `CUDA_STANDARD 17` as a valid value.
+* Add support for large num_items `DeviceScan`, `DevicePartition` and `Reduce::{ArgMin, ArgMax}`.
+* Added tests for large num_items.
+* The previous dependency-related build option `DEPENDENCIES_FORCE_DOWNLOAD` has been renamed `EXTERNAL_DEPS_FORCE_DOWNLOAD` to differentiate it from the new rocPRIM dependency option described above. Its behavior remains the same - it forces non-ROCm dependencies (Google Benchmark and Google Test) to be downloaded rather than searching for installed packages. This option defaults to `OFF`.
+
+#### Removed
+
+* Removed `TexRefInputIterator`, which was removed from CUB after CCCL's 2.6.0 release. This API should have already been removed, but somehow it remained and was not tested.
+* Deprecated `hipcub::ConstantInputIterator`, use `rocprim::constant_iterator` or `rocthrust::constant_iterator` instead.
+* Deprecated `hipcub::CountingInputIterator`, use `rocprim::counting_iterator` or `rocthrust::counting_iterator` instead.
+* Deprecated `hipcub::DiscardOutputIterator`, use `rocprim::discard_iterator` or `rocthrust::discard_iterator` instead.
+* Deprecated `hipcub::TransformInputIterator`, use `rocprim::transform_iterator` or `rocthrust::transform_iterator` instead.
+* Deprecated `hipcub::AliasTemporaries`, which is considered to be an internal API. Moved to the detail namespace.
+* Deprecated almost all functions in `projects/hipcub/hipcub/include/hipcub/backend/rocprim/util_ptx.hpp`.
+* Deprecated hipCUB macros: `HIPCUB_MAX`, `HIPCUB_MIN`, `HIPCUB_QUOTIENT_FLOOR`, `HIPCUB_QUOTIENT_CEILING`, `HIPCUB_ROUND_UP_NEAREST` and `HIPCUB_ROUND_DOWN_NEAREST`.
+
+#### Known issues
+
+* The `__half` template specializations of Simd operators are currently disabled due to possible build issues with PyTorch.
+
+### **hipFFT** (1.0.21)
+
+#### Added
+
+* Improved test coverage of multi-stream plans, user-specified work areas, and default stride calculation.
+* Experimental introduction of hipFFTW library, interfacing rocFFT on AMD platforms using the same symbols as FFTW3 (with partial support).
+
+### **hipfort** (0.7.1)
+
+#### Added
+
+* Support for building with CMake 4.0.
+
+#### Resolved issues
+
+* Fixed a potential integer overflow issue in `hipMalloc` interfaces.
+
+### **hipRAND** (3.1.0)
+
+#### Resolved issues
+
+* Updated error handling for several hipRAND unit tests to accommodate the new `hipGetLastError` behavior that was introduced in ROCm 7.0.0. As of ROCm 7.0.0, the internal error state is cleared on each call to `hipGetLastError` rather than on every HIP API call.
+
+### **hipSOLVER** (3.1.0)
+
+#### Added
+
+* Extended test suites for `hipsolverDn` compatibility functions.
+
+#### Changed
+
+* Changed code coverage to use `llvm-cov` instead of `gcov`.
+
+### **hipSPARSE** (4.1.0)
+
+#### Added
+
+* Brain half float mixed precision for the following routines:
+    * `hipsparseAxpby` where X and Y use bfloat16 and result and the compute type use float.
+    * `hipsparseSpVV` where X and Y use bfloat16 and result and the compute type use float.
+    * `hipsparseSpMV` where A and X use bfloat16 and Y and the compute type use float.
+    * `hipsparseSpMM` where A and B use bfloat16 and C and the compute type use float.
+    * `hipsparseSDDMM` where A and B use bfloat16 and C and the compute type use float.
+    * `hipsparseSDDMM` where A and B and C use bfloat16 and the compute type use float.
+* Half float mixed precision to `hipsparseSDDMM` where A and B and C use float16 and the compute type use float.
+* Brain half float uniform precision to `hipsparseScatter` and `hipsparseGather` routines.
+* Documentation for installing and building hipSPARSE on Microsoft Windows.
+
+### **hipSPARSELt** (0.2.5)
+
+#### Changed
+
+* Changed the behavior of the Relu activation.
+
+#### Optimized
+
+* Provided more kernels for the `FP16` and `BF16` data types.
+
+### **MIGraphX** (2.14.0)
+
+#### Added
+
+* Python 3.13 support.
+* PyTorch wheels to the Dockerfile.
+* Python API for returning serialized bytes.
+* `fixed_pad` operator for padding dynamic shapes to the maximum static shape.
+* Matcher to upcast base `Softmax` operations.
+* Support for the `convolution_backwards` operator through rocMLIR.
+* `LSE` output to attention fusion.
+* Flags to `EnableControlFlowGuard` due to BinSkim errors.
+* New environment variable documentation and reorganized structure.
+* `stash_type` attribute for `LayerNorm` and expanded test coverage.
+* Operator builders (phase 2).
+* `MIGRAPHX_GPU_HIP_FLAGS` to allow extra HIP compile flags.
+
+#### Changed
+
+* Updated C API to include `current()` caller information in error reporting.
+* Updated documentation dependencies:
+  * **rocm-docs-core** bumped from 1.21.1 → 1.25.0 across releases.
+  * **Doxygen** updated to 1.14.0.
+  * **urllib3** updated from 2.2.2 → 2.5.0.
+* Updated `src/CMakeLists.txt` to support `msgpack` 6.x (`msgpack-cxx`).
+* Updated model zoo test generator to fix test issues and add summary logging.
+* Updated `rocMLIR` and `ONNXRuntime` mainline references across commits.
+* Updated module sorting algorithm for improved reliability.
+* Restricted FP8 quantization to `dot` and `convolution` operators.
+* Moved ONNX Runtime launcher script into MIGraphX and updated build scripts.
+* Simplified ONNX `Resize` operator parser for correctness and maintainability.
+* Updated `any_ptr` assertion to avoid failure on default HIP stream.
+* Print kernel and module information on compile failure.
+
+#### Removed
+
+* Removed Perl dependency from SLES builds.
+* Removed redundant includes and unused internal dependencies.
+
+#### Optimized
+
+* Reduced nested visits in reference operators to improve compile time.
+* Avoided dynamic memory allocation during kernel launches.
+* Removed redundant NOP instructions for GFX11/12 platforms.
+* Improved `Graphviz` output (node color and layout updates).
+* Optimized interdependency checking during compilation.
+* Skip hipBLASLt solutions that require a workspace size larger than 128 MB for efficient memory utilization.
+
+#### Resolved issues
+
+* Error in `MIGRAPHX_GPU_COMPILE_PARALLEL` documentation (#4337).
+* rocMLIR `rewrite_reduce` issue (#4218).
+* Bug with `invert_permutation` on GPU (#4194).
+* Compile error when `MIOPEN` is disabled (missing `std` includes) (#4281).
+* ONNX `Resize` parsing when input and output shapes are identical (#4133, #4161).
+* Issue with MHA in attention refactor (#4152).
+* Synchronization issue from upstream ONNX Runtime (#4189).
+* Spelling error in “Contiguous” (#4287).
+* Tidy complaint about duplicate header (#4245).
+* `reshape`, `transpose`, and `broadcast` rewrites between pointwise and reduce operators (#3978).
+* Extraneous include file in HIPRTC-based compilation (#4130).
+* CI Perl dependency issue for SLES builds (#4254).
+* Compiler warnings for ROCm 7.0 of ``error: unknown warning option '-Wnrvo'``(#4192).
+
+### **MIOpen** (3.5.1)
+
+#### Added
+
+* Added a new trust verify find mode.
+* Ported Op4dTensorLite kernel from OpenCL to HIP.
+* Implemented a generic HIP kernel for backward layer normalization.
+
+#### Changed
+
+* Kernel DBs moved from Git LFS to DVC (Data Version Control).
+
+#### Optimized
+
+* [Conv] Enabled Composable Kernel (CK) implicit gemms on gfx950.
+
+#### Resolved issues
+
+* [BatchNorm] Fixed a bug for the NHWC layout when a variant was not applicable.
+* Fixed a bug that caused a zero-size LDS array to be defined on Navi.
+
+### **MIVisionX** (3.4.0)
+
+#### Added
+
+* VX_RPP - Update blur
+* HIP - HIP_CHECK for hipLaunchKernelGGL for gated launch
+
+#### Changed
+
+* AMD Custom V1.1.0 - OpenMP updates
+* HALF - Fix half.hpp path updates
+
+#### Resolved issues
+
+* AMD Custom - dependency linking errors resolved
+* VX_RPP - Fix memory leak
+* Packaging - Remove Meta Package dependency for HIP
+
+#### Known issues
+
+* Installation on RedHat/SLES requires the manual installation of the `FFMPEG` &amp; `OpenCV` dev packages.
+
+#### Upcoming changes
+
+* VX_AMD_MEDIA - rocDecode support for hardware decode
+
+### **RCCL** (2.27.7)
+
+#### Added
+
+* `RCCL_P2P_BATCH_THRESHOLD` to set the message size limit for batching P2P operations. This mainly affects small message performance for alltoall at a large scale but also applies to alltoallv.
+* `RCCL_P2P_BATCH_ENABLE` to enable batching P2P operations to receive performance gains for smaller messages up to 4MB for alltoall when the workload requires it. This is to avoid performance dips for larger messages.
+
+#### Changed
+
+* The MSCCL++ feature is now disabled by default. The `--disable-mscclpp` build flag is replaced with `--enable-mscclpp` in the `rccl/install.sh` script.
+* Compatibility with NCCL 2.27.7.
+
+#### Optimized
+* Enabled and optimized batched P2P operations to improve small message performance for `AllToAll` and `AllGather`.
+* Optimized channel count selection to improve efficiency for small-to-medium message sizes in `ReduceScatter`.
+* Changed code inlining to improve latency for small message sizes for `AllReduce`, `AllGather`, and `ReduceScatter`.
+
+#### Known issues
+
+* Symmetric memory kernels are currently disabled due to ongoing CUMEM enablement work.
+* When running this version of RCCL using ROCm versions earlier than 6.4.0, the user must set the environment flag `HSA_NO_SCRATCH_RECLAIM=1`.
+
+### **rocAL** (2.4.0)
+
+#### Added
+* JAX iterator support in rocAL
+* rocJPEG - Fused Crop decoding support
+
+#### Changed
+* CropResize - updates and fixes
+* Packaging - Remove Meta Package dependency for HIP
+
+#### Resolved issues
+* OpenMP - dependency linking errors resolved.
+* Bugfix - memory leaks in rocAL.
+
+#### Known issues
+* Package installation on SLES requires manually installing `TurboJPEG`.
+* Package installation on RedHat and SLES requires manually installing the `FFMPEG Dev` package.
+
+### **rocALUTION** (4.0.1)
+
+#### Added
+
+* Support for gfx950.
+
+#### Changed
+
+* Updated the default build standard to C++17 when compiling rocALUTION from source (previously C++14).
+
+#### Optimized
+
+* Improved and expanded user documentation.
+
+#### Resolved issues
+
+* Fixed a bug in the GPU hashing algorithm that occurred when not compiling with -O2/-O3.
+* Fixed an issue with the SPAI preconditioner when using complex numbers.
+
+### **rocBLAS** (5.1.0)
+
+#### Added
+
+* Sample for clients using OpenMP threads calling rocBLAS functions.
+* gfx1150 and gfx1151 enabled.
+
+#### Changed
+
+* By default, the Tensile build is no longer based on `tensile_tag.txt` but uses the same commit from shared/tensile in the rocm-libraries repository. The rmake or install `-t` option can build from another local path with a different commit.
+
+#### Optimized
+
+* Improved the performance of Level 2 gemv transposed (`TransA != N`) for the problem sizes where `m` is small and `n` is large on gfx90a and gfx942.
+
+### **ROCdbgapi** (0.77.4)
+
+#### Added
+
+* gfx1150 and gfx1151 enabled.
+
+### **rocDecode** (1.4.0)
+
+#### Added
+
+* AV1 12-bit decode support on VA-API version 1.23.0 and later.
+* rocdecode-host V1.0.0 library for software decode
+* FFmpeg version support for 5.1 and 6.1
+* Find package - rocdecode-host
+
+#### Resolved issues
+
+* rocdecode-host - failure to build debuginfo packages without FFmpeg resolved.
+* Fix a memory leak for rocDecodeNegativeTests
+
+#### Changed
+
+* HIP meta package changed - Use hip-dev/devel to bring required hip dev deps
+* rocdecode host - linking updates to rocdecode-host library
+
+### **rocFFT** (1.0.35)
+
+#### Optimized
+
+* Implemented single-kernel plans for some 2D problem sizes, on devices with at least 160KiB of LDS.
+* Improved performance of unit-strided, complex-interleaved, forward/inverse FFTs for lengths: (64,64,128), (64,64,52), (60,60,60)
+, (32,32,128), (32,32,64), (64,32,128)
+* Improved performance of 3D MPI pencil decompositions by using sub-communicators for global transpose operations.
+
+### **rocJPEG** (1.2.0)
+
+#### Changed
+* HIP meta package has been changed. Use `hip-dev/devel` to bring required hip dev deps.
+
+#### Resolved issues
+* Fixed an issue where extra padding was incorrectly included when saving decoded JPEG images to files.
+* Resolved a memory leak in the jpegDecode application.
+
+### **ROCm Compute Profiler** (3.3.0)
+
+#### Added
+* Dynamic process attachment feature that allows coupling with a workload process, without controlling its start or end.
+  * Use '--attach-pid' to specify the target process ID.
+  * Use '--attach-duration-msec' to specify time duration.
+* `rocpd` choice for `--format-rocprof-output` option in profile mode.
+* `--retain-rocpd-output` option in profile mode to save large raw rocpd databases in workload directory.
+* Feature to show description of metrics during analysis.
+  * Use `--include-cols Description` to show the Description column, which is excluded by default from the
+  ROCm Compute Profiler CLI output.
+* `--set` filtering option in profile mode to enable single-pass counter collection for predefined subsets of metrics.
+* `--list-sets` filtering option in profile mode to list the sets available for single pass counter collection.
+* Missing counters based on register specification which enables missing metrics.
+  * Enabled `SQC_DCACHE_INFLIGHT_LEVEL` counter and associated metrics.
+  * Enabled `TCP_TCP_LATENCY` counter and associated counter for all GPUs except MI300.
+* Interactive metric descriptions in TUI analyze mode.
+  * You can now left click on any metric cell to view detailed descriptions in the dedicated `METRIC DESCRIPTION` tab.
+* Support for analysis report output as a SQLite database using ``--output-format db`` analysis mode option.
+* `Compute Throughput` panel to TUI's `High Level Analysis` category with the following metrics: VALU FLOPs, VALU IOPs, MFMA FLOPs (F8), MFMA FLOPs (BF16), MFMA FLOPs (F16), MFMA FLOPs (F32), MFMA FLOPs (F64), MFMA FLOPs (F6F4) (in gfx950), MFMA IOPs (Int8), SALU Utilization, VALU Utilization, MFMA Utilization, VMEM Utilization, Branch Utilization, IPC
+
+* `Memory Throughput` panel to TUI's `High Level Analysis` category with the following metrics: vL1D Cache BW, vL1D Cache Utilization, Theoretical LDS Bandwidth, LDS Utilization, L2 Cache BW, L2 Cache Utilization, L2-Fabric Read BW, L2-Fabric Write BW, sL1D Cache BW, L1I BW, Address Processing Unit Busy, Data-Return Busy, L1I-L2 Bandwidth, sL1D-L2 BW
+* Roofline support for Debian 12 and Azure Linux 3.0.
+* Notice for change in default output format to `rocpd` in a future release
+  * This is displayed when `--format-rocprof-output rocpd` is not used in profile mode
+
+#### Changed
+
+* In the memory chart, long string of numbers are now displayed as scientific notation. It also solves the issue of overflow of displaying long number
+* When `--format-rocprof-output rocpd` is used, only `pmc_perf.csv` will be written to workload directory instead of multiple CSV files.
+* CLI analysis mode baseline comparison will now only compare common metrics across workloads and will not show the Metric ID.
+  * Removed metrics from analysis configuration files which are explicitly marked as empty or None.
+* Changed the basic (default) view of TUI from aggregated analysis data to individual kernel analysis data.
+* Updated `Unit` of the following `Bandwidth` related metrics to `Gbps` instead of `Bytes per Normalization Unit`:
+  * Theoretical Bandwidth (section 1202)
+  * L1I-L2 Bandwidth (section 1303)
+  * sL1D-L2 BW (section 1403)
+  * Cache BW (section 1603)
+  * L1-L2 BW (section 1603)
+  * Read BW (section 1702)
+  * Write and Atomic BW (section 1702)
+  * Bandwidth (section 1703)
+  * Atomic/Read/Write Bandwidth (section 1703)
+  * Atomic/Read/Write Bandwidth - (HBM/PCIe/Infinity Fabric) (section 1706)
+* Updated the metric name for the following `Bandwidth` related metrics whose `Unit` is `Percent` by adding `Utilization`:
+  * Theoretical Bandwidth Utilization (section 1201)
+  * L1I-L2 Bandwidth Utilization (section 1301)
+  * Bandwidth Utilization (section 1301)
+  * Bandwidth Utilization (section 1401)
+  * sL1D-L2 BW Utilization (section 1401)
+  * Bandwidth Utilization (section 1601)
+* Updated `System Speed-of-Light` panel to `GPU Speed-of-Light` in TUI for the following metrics:
+  * Theoretical LDS Bandwidth
+  * vL1D Cache BW
+  * L2 Cache BW
+  * L2-Fabric Read BW
+  * L2-Fabric Write BW
+  * Kernel Time
+  * Kernel Time (Cycles)
+  * SIMD Utilization
+  * Clock Rate
+* Analysis output:
+  * Replaced `-o / --output` analyze mode option with `--output-format` and `--output-name`.
+    * Use ``--output-format`` analysis mode option to select the output format of the analysis report.
+    * Use ``--output-name`` analysis mode option to override the default file/folder name.
+  * Replaced `--save-dfs` analyze mode option with `--output-format csv`.
+* Command-line options:
+  * `--list-metrics` and `--config-dir` options moved to general command-line options.
+  * `--list-metrics` option cannot be used without GPU architecture argument.
+  * `--list-metrics` option do not show number of L2 channels.
+  * `--list-available-metrics` profile mode option to display the metrics available for profiling in current GPU.
+  * `--list-available-metrics` analyze mode option to display the metrics available for analysis.
+  * `--block` option cannot be used with `--list-metrics` and `--list-available-metrics`options.
+* Default `rocprof` interface changed from `rocprofv3` to `rocprofiler-sdk`
+  * Use ROCPROF=rocprofv3 to use rocprofv3 interface
+* Updated metric names for better alignment between analysis configuration and documentation.
+
+#### Removed
+
+* Usage of `rocm-smi` in favor of `amd-smi`.
+* Hardware IP block-based filtering has been removed in favor of analysis report block-based filtering.
+* Aggregated analysis view from TUI analyze mode.
+
+#### Optimized
+
+* Improved `--time-unit` option in analyze mode to apply time unit conversion across all analysis sections, not just kernel top stats.
+* Improved logic to obtain rocprof-supported counters, which prevents unnecessary warnings.
+* Improved post-analysis runtime performance by caching and multi-processing.
+* Improve analysis block based filtering to accept metric ID level filtering.
+  * This can be used to collect individual metrics from various sections of the analysis config.
+
+#### Resolved issues
+
+* Fixed an issue of not detecting the memory clock when using `amd-smi`.
+* Fixed standalone GUI crashing.
+* Fixed L2 read/write/atomic bandwidths on AMD Instinct MI350 Series GPUs.
+* Fixed an issue where accumulation counters could not be collected on AMD Instinct MI100.
+* Fixed an issue of kernel filtering not working in the roofline chart.
+
+#### Known issues
+
+* MI300A/X L2-Fabric 64B read counter may display negative values - The rocprof-compute metric 17.6.1 (Read 64B) can report negative values due to incorrect calculation when TCC_BUBBLE_sum + TCC_EA0_RDREQ_32B_sum exceeds TCC_EA0_RDREQ_sum.
+  * A workaround has been implemented using max(0, calculated_value) to prevent negative display values while the root cause is under investigation.
+* The profile mode crashes when `--format-rocprof-output json` is selected.
+    * As a workaround, this option should either not be provided or should be set to `csv` instead of `json`. This issue does not affect the profiling results since both `csv` and `json` output formats lead to the same profiling data.  
+
+### **ROCm Data Center Tool** (1.2.0)
+
+#### Added
+
+- CPU monitoring support with 30+ CPU field definitions through AMD SMI integration.
+- CPU partition format support (c0.0, c1.0) for monitoring AMD EPYC processors.
+- Mixed GPU/CPU monitoring in single `rdci dmon` command.
+
+#### Optimized
+
+- Improved profiler metrics path detection for counter definitions.
+
+#### Resolved issues
+
+- Group management issues with listing created/non-created groups.
+- ECC_UNCORRECT field behavior.
+
+### **ROCm Debugger (ROCgdb)** (16.3)
+
+#### Added
+
+* gfx1150 and gfx1151 support enabled.
+
+### **ROCm Systems Profiler** (1.2.0)
+
+#### Added
+
+- ``ROCPROFSYS_ROCM_GROUP_BY_QUEUE`` configuration setting to allow grouping of events by hardware queue, instead of the default grouping.
+- Support for `rocpd` database output with the `ROCPROFSYS_USE_ROCPD` configuration setting.
+- Support for profiling PyTorch workloads using the `rocpd` output database.
+- Support for tracing OpenMP API in Fortran applications.
+- An error warning is triggered if the profiler application fails because SELinux enforcement is enabled. The warning includes steps to disable SELinux enforcement.
+
+#### Changed
+
+- Updated the grouping of "kernel dispatch" and "memory copy" events in Perfetto traces. They are now grouped together by HIP Stream rather than separately and by hardware queue.
+- Updated PAPI module to v7.2.0b2.
+- ROCprofiler-SDK is now used for tracing OMPT API calls.
+
+#### Known issues
+
+* Profiling PyTorch and other AI workloads might fail because it is unable to find the libraries in the default linker path. As a workaround, you need to explicitly add the library path to ``LD_LIBRARY_PATH``. For example, when using PyTorch with Python 3.10, add the following to the environment:
+
+```
+export LD_LIBRARY_PATH=:/opt/venv/lib/python3.10/site-packages/torch/lib:$LD_LIBRARY_PATH
+```
+
+### **rocPRIM** (4.1.0)
+
+#### Added
+
+* `get_sreg_lanemask_lt`, `get_sreg_lanemask_le`, `get_sreg_lanemask_gt` and `get_sreg_lanemask_ge`.
+* `rocprim::transform_output_iterator` and `rocprim::make_transform_output_iterator`.
+* Experimental support for SPIR-V, to use the correct tuned config for part of the appliable algorithms.
+* A new cmake option, `BUILD_OFFLOAD_COMPRESS`. When rocPRIM is build with this option enabled, the `--offload-compress` switch is passed to the compiler. This causes the compiler to compress the binary that it generates. Compression can be useful in cases where you are compiling for a large number of targets, since this often results in a large binary. Without compression, in some cases, the generated binary may become so large symbols are placed out of range, resulting in linking errors. The new `BUILD_OFFLOAD_COMPRESS` option is set to `ON` by default.
+* A new CMake option `-DUSE_SYSTEM_LIB` to allow tests to be built from `ROCm` libraries provided by the system.
+* `rocprim::apply` which applies a function to a `rocprim::tuple`.
+
+#### Changed
+
+* Changed tests to support `ptr-to-const` output in `/test/rocprim/test_device_batch_memcpy.cpp`.
+
+#### Optimized
+
+* Improved performance of many algorithms by updating their tuned configs.
+  * 891 specializations have been improved.
+  * 399 specializations have been added.
+
+#### Resolved issues
+
+* Fixed `device_select`, `device_merge`, and `device_merge_sort` not allocating the correct amount of virtual shared memory on the host.
+* Fixed the `-&gt;` operator for the `transform_iterator`, the `texture_cache_iterator`, and the `arg_index_iterator`, by now returning a proxy pointer.
+  * The `arg_index_iterator` also now only returns the internal iterator for the `-&gt;`.
+
+#### Upcoming changes
+
+* Deprecated the `-&gt;` operator for the `zip_iterator`.
+
+### **ROCProfiler** (2.0.0)
+
+#### Removed
+
+* `rocprofv2` doesn't support gfx12XX Series GPUs. For gfx12XX Series GPUs, use `rocprofv3` tool.
+
+### **ROCprofiler-SDK** (1.0.0)
+
+#### Added
+* Dynamic process attachment- ROCprofiler-SDK and `rocprofv3` now facilitate dynamic profiling of a running GPU application by attaching to its process ID (PID), rather than launching the application through the profiler itself.
+* Scratch-memory trace information to the Perfetto output in `rocprofv3`.
+* New capabilities to the thread trace support in `rocprofv3`:
+    * Real-time clock support for thread trace alignment on gfx9XX architecture. This enables high-resolution clock computation and better synchronization across shader engines. 
+    * `MultiKernelDispatch` thread trace support is now available across all ASICs.
+* Documentation for dynamic process attachment.
+* Documentation for `rocpd` summaries.
+
+#### Optimized
+* Improved the stability and robustness of the `rocpd` output.
+
+### **rocPyDecode** (0.7.0)
+
+#### Added
+* rocPyJpegPerfSample - samples for JPEG decode
+
+#### Changed
+* Package - rocjpeg set as required dependency.
+* rocDecode host - rocdecode host linking updates
+
+#### Resolved issues
+* rocJPEG Bindings - bug fixes
+* Test package - find dependencies updated
+
+### **rocRAND** (4.1.0)
+
+#### Changed
+
+* Changed the `USE_DEVICE_DISPATCH` flag so it can turn device dispatch off by setting it to zero. Device dispatch should be turned off when building for SPIRV.
+
+#### Resolved issues
+
+* Updated error handling for several rocRAND unit tests to accommodate the new `hipGetLastError` behavior that was introduced in ROCm 7.0.
+As of ROCm 7.0, the internal error state is cleared on each call to `hipGetLastError` rather than on every HIP API call.
+
+### **rocSOLVER** (3.31.0)
+
+#### Optimized
+
+Improved the performance of:
+
+* LARF, LARFT, GEQR2, and downstream functions such as GEQRF.
+* STEDC and divide and conquer Eigensolvers.
+
+### **rocSPARSE** (4.1.0)
+
+#### Added
+
+* Brain half float mixed precision for the following routines:
+   * `rocsparse_axpby` where X and Y use bfloat16 and result and the compute type use float.
+   * `rocsparse_spvv` where X and Y use bfloat16 and result and the compute type use float.
+   * `rocsparse_spmv` where A and X use bfloat16 and Y and the compute type use float.
+   * `rocsparse_spmm` where A and B use bfloat16 and C and the compute type use float.
+   * `rocsparse_sddmm` where A and B use bfloat16 and C and the compute type use float.
+   * `rocsparse_sddmm` where A and B and C use bfloat16 and the compute type use float.
+* Half float mixed precision to `rocsparse_sddmm` where A and B and C use float16 and the compute type use float.
+* Brain half float uniform precision to `rocsparse_scatter` and `rocsparse_gather` routines.
+
+#### Optimized
+
+* Improved the user documentation.
+
+#### Upcoming changes
+
+* Deprecate trace, debug, and bench logging using the environment variable `ROCSPARSE_LAYER`.
+
+### **rocThrust** (4.1.0)
+
+#### Added
+
+* A new CMake option `-DSQLITE_USE_SYSTEM_PACKAGE` to allow SQLite to be provided by the system.
+* Introduced `libhipcxx` as a soft dependency. When `libhipcxx` can be included, rocThrust can use structs and methods defined in `libhipcxx`. This allows for a more complete behavior parity with CCCL and mirrors CCCL's thrust own dependency on `libcudacxx`.
+* Added a new CMake option `-DUSE_SYSTEM_LIB` to allow tests to be built from `ROCm` libraries provided by the system.
+
+#### Changed
+
+* The previously hidden cmake build option `FORCE_DEPENDENCIES_DOWNLOAD` has been unhidden and renamed `EXTERNAL_DEPS_FORCE_DOWNLOAD` to differentiate it from the new rocPRIM and rocRAND dependency options described above. Its behavior remains the same - it forces non-ROCm dependencies (Google Benchmark, Google Test, and SQLite) to be downloaded instead of searching for existing installed packages. This option defaults to `OFF`.
+
+#### Removed
+
+* The previous dependency-related build options `DOWNLOAD_ROCPRIM` and `DOWNLOAD_ROCRAND` have been removed. Use `ROCPRIM_FETCH_METHOD=DOWNLOAD` and `ROCRAND_FETCH_METHOD=DOWNLOAD` instead.
+
+#### Known issues
+
+* `event` test is failing on CI and local runs on MI300, MI250 and MI210.
+
+* rocThrust, as well as its dependencies rocPRIM and rocRAND have been moved into the new `rocm-libraries` monorepo repository (https://github.com/ROCm/rocm-libraries). This repository contains several ROCm libraries that are frequently used together.
+  * The repository migration requires a few changes to the way that rocThrust's ROCm library dependencies are fetched.
+  * There are new cmake options for obtaining rocPRIM and (optionally, if BUILD_BENCHMARKS is enabled) rocRAND.
+  * cmake build options `ROCPRIM_FETCH_METHOD` and `ROCRAND_FETCH_METHOD` may be set to one of the following:
+    * `PACKAGE` - (default) searches for a preinstalled packaged version of the dependency. If it's not found, the build will fall back using option `DOWNLOAD`, described below.
+    * `DOWNLOAD` - downloads the dependency from the rocm-libraries repository. If git >= 2.25 is present, this option uses a sparse checkout that avoids downloading more than it needs to. If not, the whole monorepo is downloaded (this may take some time).
+    * `MONOREPO` - this option is intended to be used if you are building rocThrust from within a copy of the rocm-libraries repository that you have cloned (and therefore already contains the dependencies rocPRIM and rocRAND). When selected, the build will try to find the dependency in the local repository tree. If it can't be found, the build will attempt to add it to the local tree using a sparse-checkout. If that also fails, it will fall back to using the `DOWNLOAD` option.
+
+### **RPP** (2.1.0)
+
+#### Added
+
+* Solarize augmentation for HOST and HIP.
+* Hue and Saturation adjustment augmentations for HOST and HIP.
+* Find RPP - cmake module.
+* Posterize augmentation for HOST and HIP.
+
+#### Changed
+
+* HALF - Fix `half.hpp` path updates.
+* Box filter - padding updates.
+
+#### Removed
+
+* Packaging - Removed Meta Package dependency for HIP.
+* SLES 15 SP6 support.
+
+#### Resolved issues
+
+* Test Suite - Fixes for accuracy.
+* HIP Backend - Check return status warning fixes.
+* Bug fix - HIP vector types init.
+
 ## ROCm 7.0.2
 
 See the [ROCm 7.0.2 release notes](https://rocm.docs.amd.com/en/docs-7.0.2/about/release-notes.html#rocm-7-0-2-release-notes)
@@ -265,10 +1236,6 @@ for a complete overview of this release.
 
 - `amd-smi monitor` on Linux Guest systems triggers an attribute error.
 
-```{note}
-See the full [AMD SMI changelog](https://github.com/ROCm/amdsmi/blob/release/rocm-rel-7.0/CHANGELOG.md) for details, examples, and in-depth descriptions.
-```
-
 ### **Composable Kernel** (1.1.0) 
 
 #### Added
@@ -1585,7 +2552,7 @@ The previous default accumulator types could lead to situations in which unexpec
 
 #### Added
 
-* Hybrid computation support for existing routines: STEQR
+* Hybrid computation support for existing STEQR routines.
 
 #### Optimized
 

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

@@ -1,137 +1,137 @@
-ROCm Version,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>`,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, 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 10.0 [#rhel-10-702-past-60]_, 9.6 [#rhel-10-702-past-60]_, 9.4 [#rhel-94-702-past-60]_","RHEL 9.6 [#rhel-10-702-past-60]_, 9.4 [#rhel-94-702-past-60]_","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-700-past-60]_,RHEL 8.10 [#rhel-700-past-60]_,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-db-700-past-60]_,SLES 15 SP7 [#sles-db-700-past-60]_,"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 [#ol-700-mi300x-past-60]_","Oracle Linux 9, 8 [#ol-700-mi300x-past-60]_","Oracle Linux 9, 8 [#mi300x-past-60]_","Oracle Linux 9, 8 [#mi300x-past-60]_","Oracle Linux 9, 8 [#mi300x-past-60]_","Oracle Linux 9, 8 [#mi300x-past-60]_",Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,,,
-      ,"Debian 13 [#db-mi300x-past-60]_, 12 [#sles-db-700-past-60]_",Debian 12 [#sles-db-700-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,,,,,,,,,,,
-      ,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-630-past-60]_,Azure Linux 3.0 [#az-mi300x-630-past-60]_,,,,,,,,,,,,
-      ,Rocky Linux 9 [#rl-700-past-60]_,Rocky Linux 9 [#rl-700-past-60]_,,,,,,,,,,,,,,,,,,
-      ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,
-      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,CDNA4,,,,,,,,,,,,,,,,,,
-      ,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
-      ,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,,,,,,,,,,,,,,,
-      ,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
-      ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx950 [#mi350x-os-past-60]_,gfx950 [#mi350x-os-past-60]_,,,,,,,,,,,,,,,,,,
-      ,gfx1201 [#RDNA-OS-700-past-60]_,gfx1201 [#RDNA-OS-700-past-60]_,gfx1201 [#RDNA-OS-past-60]_,gfx1201 [#RDNA-OS-past-60]_,gfx1201 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
-      ,gfx1200 [#RDNA-OS-700-past-60]_,gfx1200 [#RDNA-OS-700-past-60]_,gfx1200 [#RDNA-OS-past-60]_,gfx1200 [#RDNA-OS-past-60]_,gfx1200 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
-      ,gfx1101 [#RDNA-OS-700-past-60]_ [#rd-v710-past-60]_,gfx1101 [#RDNA-OS-700-past-60]_ [#rd-v710-past-60]_,gfx1101 [#RDNA-OS-past-60]_ [#7700XT-OS-past-60]_,gfx1101 [#RDNA-OS-past-60]_ [#7700XT-OS-past-60]_,gfx1101 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
-      ,gfx1100 [#RDNA-OS-700-past-60]_,gfx1100 [#RDNA-OS-700-past-60]_,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
-      ,gfx1030 [#RDNA-OS-700-past-60]_ [#rd-v620-past-60]_,gfx1030 [#RDNA-OS-700-past-60]_ [#rd-v620-past-60]_,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
-      ,gfx942 [#mi325x-os-past-60]_ [#mi300x-os-past-60]_ [#mi300A-os-past-60]_,gfx942 [#mi325x-os-past-60]_ [#mi300x-os-past-60]_ [#mi300A-os-past-60]_,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942 [#mi300_624-past-60]_,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
-      ,gfx90a [#mi200x-os-past-60]_,gfx90a [#mi200x-os-past-60]_,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
-      ,gfx908 [#mi100-os-past-60]_,gfx908 [#mi100-os-past-60]_,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>`,"2.8, 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>`,"2.19.1, 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>`,0.6.0,0.6.0,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
-      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat-past-60]_,N/A,N/A,N/A,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,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,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,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,1.8.0b1,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,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,b6356,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,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>`_,1.22.0,1.22.0,1.20.0,1.20.0,1.20.0,1.20.0,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
-      ,,,,,,,,,,,,,,,,,,,,
-      ,,,,,,,,,,,,,,,,,,,,
-      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,
-      `UCC <https://github.com/ROCm/ucc>`_,>=1.4.0,>=1.4.0,>=1.3.0,>=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,>=1.15.0,>=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,2.6.0,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      CUB,2.6.0,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      ,,,,,,,,,,,,,,,,,,,,
-     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>`,"30.10.2, 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
-      :doc:`MIGraphX <amdmigraphx:index>`,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>`,3.5.0,3.5.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`MIVisionX <mivisionx:index>`,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
-      :doc:`rocAL <rocal:index>`,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`rocDecode <rocdecode:index>`,1.0.0,1.0.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
-      :doc:`rocJPEG <rocjpeg:index>`,1.1.0,1.1.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`rocPyDecode <rocpydecode:index>`,0.6.0,0.6.0,0.3.1,0.3.1,0.3.1,0.3.1,0.2.0,0.2.0,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`RPP <rpp:index>`,2.0.0,2.0.0,1.9.10,1.9.10,1.9.10,1.9.10,1.9.1,1.9.1,1.9.1,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
-      ,,,,,,,,,,,,,,,,,,,,
-      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,
-      :doc:`RCCL <rccl:index>`,2.26.6,2.26.6,2.22.3,2.22.3,2.22.3,2.22.3,2.21.5,2.21.5,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
-      :doc:`rocSHMEM <rocshmem:index>`,3.0.0,3.0.0,2.0.1,2.0.1,2.0.0,2.0.0,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
-      :doc:`hipBLAS <hipblas:index>`,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>`,1.0.0,1.0.0,0.12.1,0.12.1,0.12.1,0.12.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
-      :doc:`hipFFT <hipfft:index>`,1.0.20,1.0.20,1.0.18,1.0.18,1.0.18,1.0.18,1.0.17,1.0.17,1.0.17,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
-      :doc:`hipfort <hipfort:index>`,0.7.0,0.7.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.1,0.5.1,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
-      :doc:`hipRAND <hiprand:index>`,3.0.0,3.0.0,2.12.0,2.12.0,2.12.0,2.12.0,2.11.1,2.11.1,2.11.1,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
-      :doc:`hipSOLVER <hipsolver:index>`,3.0.0,3.0.0,2.4.0,2.4.0,2.4.0,2.4.0,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
-      :doc:`hipSPARSE <hipsparse:index>`,4.0.1,4.0.1,3.2.0,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.4,0.2.4,0.2.3,0.2.3,0.2.3,0.2.3,0.2.2,0.2.2,0.2.2,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
-      :doc:`rocALUTION <rocalution:index>`,4.0.0,4.0.0,3.2.3,3.2.3,3.2.3,3.2.2,3.2.1,3.2.1,3.2.1,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
-      :doc:`rocBLAS <rocblas:index>`,5.0.2,5.0.0,4.4.1,4.4.1,4.4.0,4.4.0,4.3.0,4.3.0,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
-      :doc:`rocFFT <rocfft:index>`,1.0.34,1.0.34,1.0.32,1.0.32,1.0.32,1.0.32,1.0.31,1.0.31,1.0.31,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
-      :doc:`rocRAND <rocrand:index>`,4.0.0,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
-      :doc:`rocSOLVER <rocsolver:index>`,3.30.1,3.30.0,3.28.2,3.28.2,3.28.0,3.28.0,3.27.0,3.27.0,3.27.0,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
-      :doc:`rocSPARSE <rocsparse:index>`,4.0.2,4.0.2,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
-      :doc:`rocWMMA <rocwmma:index>`,2.0.0,2.0.0,1.7.0,1.7.0,1.7.0,1.7.0,1.6.0,1.6.0,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
-      :doc:`Tensile <tensile:src/index>`,4.44.0,4.44.0,4.43.0,4.43.0,4.43.0,4.43.0,4.42.0,4.42.0,4.42.0,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
-      ,,,,,,,,,,,,,,,,,,,,
-      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,
-      :doc:`hipCUB <hipcub:index>`,4.0.0,4.0.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`hipTensor <hiptensor:index>`,2.0.0,2.0.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
-      :doc:`rocPRIM <rocprim:index>`,4.0.1,4.0.0,3.4.1,3.4.1,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`rocThrust <rocthrust:index>`,4.0.0,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      ,,,,,,,,,,,,,,,,,,,,
-      SUPPORT LIBS,,,,,,,,,,,,,,,,,,,,
-      `hipother <https://github.com/ROCm/hipother>`_,7.0.51830,7.0.51830,6.4.43483,6.4.43483,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
-      `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]_,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>`,26.0.2,26.0.0,25.5.1,25.5.1,25.4.2,25.3.0,24.7.1,24.7.1,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
-      :doc:`ROCm Data Center Tool <rdc:index>`,1.1.0,1.1.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
-      :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
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,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>`,1.2.0,1.2.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60105,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
-      ,,,,,,,,,,,,,,,,,,,,
-      PERFORMANCE TOOLS,,,,,,,,,,,,,,,,,,,,
-      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,2.6.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
-      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.2.3,3.2.3,3.1.1,3.1.1,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.1.1,1.1.0,1.0.2,1.0.2,1.0.1,1.0.0,0.1.2,0.1.1,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70002,2.0.70000,2.0.60403,2.0.60402,2.0.60401,2.0.60400,2.0.60303,2.0.60302,2.0.60301,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
-      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.0.0,1.0.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCTracer <roctracer:index>`,4.1.70002,4.1.70000,4.1.60403,4.1.60402,4.1.60401,4.1.60400,4.1.60303,4.1.60302,4.1.60301,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
-      ,,,,,,,,,,,,,,,,,,,,
-      DEVELOPMENT TOOLS,,,,,,,,,,,,,,,,,,,,
-      :doc:`HIPIFY <hipify:index>`,20.0.0,20.0.0,19.0.0,19.0.0,19.0.0,19.0.0,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
-      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.4,0.77.3,0.77.2,0.77.2,0.77.2,0.77.2,0.77.0,0.77.0,0.77.0,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,16.3.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
-      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
-      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.1.0,2.0.4,2.0.4,2.0.4,2.0.4,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
-      ,,,,,,,,,,,,,,,,,,,,
-      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,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
-      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      `Flang <https://github.com/ROCm/flang>`_,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`llvm-project <llvm-project:index>`,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      ,,,,,,,,,,,,,,,,,,,,
-      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,7.0.51831,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      :doc:`HIP <hip:index>`,7.0.51831,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `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
-      :doc:`ROCr Runtime <rocr-runtime:index>`,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
+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,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:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,1.8.0b1,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,N/A,N/A,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>`,5.1.0,5.1.0,5.0.2,5.0.0,4.4.1,4.4.1,4.4.0,4.4.0,4.3.0,4.3.0,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
+      :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>`,2.0.0,2.0.0,2.0.0,2.0.0,1.7.0,1.7.0,1.7.0,1.7.0,1.6.0,1.6.0,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
+      :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>`_,7.1.0,7.1.0,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
+      `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>`,26.1.0,26.1.0,26.0.2,26.0.0,25.5.1,25.5.1,25.4.2,25.3.0,24.7.1,24.7.1,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
+      :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>`,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60105,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
+      ,,,,,,,,,,,,,,,,,,,,,,
+      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>`,3.3.0,3.3.0,3.2.3,3.2.3,3.1.1,3.1.1,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.2.0,1.2.0,1.1.1,1.1.0,1.0.2,1.0.2,1.0.1,1.0.0,0.1.2,0.1.1,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,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

@@ -12,7 +12,7 @@ You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-
 
 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 :docs:`Use ROCm on Radeon and Ryzen <radeon:index.html>` to verify
+workloads, see the :doc:`Use ROCm on Radeon and Ryzen <radeon:index>` to verify
 compatibility and system requirements.
 
 .. |br| raw:: html
@@ -22,18 +22,18 @@ compatibility and system requirements.
 .. container:: format-big-table
 
   .. csv-table::
-      :header: "ROCm Version", "7.0.2", "7.0.1/7.0.0", "6.4.0"
+      :header: "ROCm Version", "7.1.1", "7.1.0", "6.4.0"
       :stub-columns: 1
 
-      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.2
+      :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 10.0 [#rhel-10-702]_, 9.6 [#rhel-10-702]_, 9.4 [#rhel-94-702]_","RHEL 9.6 [#rhel-10-702]_, 9.4 [#rhel-94-702]_","RHEL 9.5, 9.4"
-      ,RHEL 8.10 [#rhel-700]_,RHEL 8.10 [#rhel-700]_,RHEL 8.10
-      ,SLES 15 SP7 [#sles-db-700]_,SLES 15 SP7 [#sles-db-700]_,SLES 15 SP6
-      ,"Oracle Linux 10, 9, 8 [#ol-700-mi300x]_","Oracle Linux 9, 8 [#ol-700-mi300x]_","Oracle Linux 9, 8 [#ol-mi300x]_"
-      ,"Debian 13 [#db-mi300x]_, 12 [#sles-db-700]_",Debian 12 [#sles-db-700]_,Debian 12 [#single-node]_
-      ,Azure Linux 3.0 [#az-mi300x]_,Azure Linux 3.0 [#az-mi300x]_,Azure Linux 3.0 [#az-mi300x]_
-      ,Rocky Linux 9 [#rl-700]_,Rocky Linux 9 [#rl-700]_,
+      ,"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,Azure Linux 3.0,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
@@ -43,99 +43,99 @@ compatibility and system requirements.
       ,RDNA3,RDNA3,RDNA3
       ,RDNA2,RDNA2,RDNA2
       ,.. _gpu-support-compatibility-matrix:,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx950 [#mi350x-os]_,gfx950 [#mi350x-os]_,
-      ,gfx1201 [#RDNA-OS-700]_,gfx1201 [#RDNA-OS-700]_,
-      ,gfx1200 [#RDNA-OS-700]_,gfx1200 [#RDNA-OS-700]_,
-      ,gfx1101 [#RDNA-OS-700]_ [#rd-v710]_,gfx1101 [#RDNA-OS-700]_ [#rd-v710]_,
-      ,gfx1100 [#RDNA-OS-700]_,gfx1100 [#RDNA-OS-700]_,gfx1100
-      ,gfx1030 [#RDNA-OS-700]_ [#rd-v620]_,gfx1030 [#RDNA-OS-700]_ [#rd-v620]_,gfx1030
-      ,gfx942 [#mi325x-os]_ [#mi300x-os]_ [#mi300A-os]_,gfx942 [#mi325x-os]_ [#mi300x-os]_ [#mi300A-os]_,gfx942
-      ,gfx90a [#mi200x-os]_,gfx90a [#mi200x-os]_,gfx90a
-      ,gfx908 [#mi100-os]_,gfx908 [#mi100-os]_,gfx908
+      :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>`,"2.8, 2.7, 2.6","2.7, 2.6, 2.5","2.6, 2.5, 2.4, 2.3"
-      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.19.1, 2.18.1, 2.17.1 [#tf-mi350]_","2.19.1, 2.18.1, 2.17.1 [#tf-mi350]_","2.18.1, 2.17.1, 2.16.2"
-      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.6.0,0.6.0,0.4.35
+      :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,b6356,b5997
-      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.22.0,1.22.0,1.20.0
+      :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,2.6.0,2.6.0,2.5.0
-      CUB,2.6.0,2.6.0,2.5.0
+      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>`,"30.10.2, 30.10.1 [#driver_patch]_, |br| 30.10, 6.4.x, 6.3.x","30.10.1 [#driver_patch]_, 30.10, |br| 6.4.x, 6.3.x, 6.2.x","6.4.x, 6.3.x, 6.2.x, 6.1.x"
+      :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>`,2.13.0,2.13.0,2.12.0
-      :doc:`MIOpen <miopen:index>`,3.5.0,3.5.0,3.4.0
-      :doc:`MIVisionX <mivisionx:index>`,3.3.0,3.3.0,3.2.0
-      :doc:`rocAL <rocal:index>`,2.3.0,2.3.0,2.2.0
-      :doc:`rocDecode <rocdecode:index>`,1.0.0,1.0.0,0.10.0
-      :doc:`rocJPEG <rocjpeg:index>`,1.1.0,1.1.0,0.8.0
-      :doc:`rocPyDecode <rocpydecode:index>`,0.6.0,0.6.0,0.3.1
-      :doc:`RPP <rpp:index>`,2.0.0,2.0.0,1.9.10
+      :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>`,2.26.6,2.26.6,2.22.3
-      :doc:`rocSHMEM <rocshmem:index>`,3.0.0,3.0.0,2.0.0
+      :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>`,3.0.2,3.0.0,2.4.0
-      :doc:`hipBLASLt <hipblaslt:index>`,1.0.0,1.0.0,0.12.0
-      :doc:`hipFFT <hipfft:index>`,1.0.20,1.0.20,1.0.18
-      :doc:`hipfort <hipfort:index>`,0.7.0,0.7.0,0.6.0
-      :doc:`hipRAND <hiprand:index>`,3.0.0,3.0.0,2.12.0
-      :doc:`hipSOLVER <hipsolver:index>`,3.0.0,3.0.0,2.4.0
-      :doc:`hipSPARSE <hipsparse:index>`,4.0.1,4.0.1,3.2.0
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.4,0.2.4,0.2.3
-      :doc:`rocALUTION <rocalution:index>`,4.0.0,4.0.0,3.2.2
-      :doc:`rocBLAS <rocblas:index>`,5.0.2,5.0.0,4.4.0
-      :doc:`rocFFT <rocfft:index>`,1.0.34,1.0.34,1.0.32
-      :doc:`rocRAND <rocrand:index>`,4.0.0,4.0.0,3.3.0
-      :doc:`rocSOLVER <rocsolver:index>`,3.30.1,3.30.0,3.28.0
-      :doc:`rocSPARSE <rocsparse:index>`,4.0.2,4.0.2,3.4.0
+      :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>`,5.1.0,5.1.0,4.4.0
+      :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>`,2.0.0,2.0.0,1.7.0
       :doc:`Tensile <tensile:src/index>`,4.44.0,4.44.0,4.43.0
       ,,,
       PRIMITIVES,.. _primitivelibs-support-compatibility-matrix:,,
-      :doc:`hipCUB <hipcub:index>`,4.0.0,4.0.0,3.4.0
+      :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>`,4.0.1,4.0.0,3.4.0
-      :doc:`rocThrust <rocthrust:index>`,4.0.0,4.0.0,3.3.0
+      :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>`_,7.0.51830,7.0.51830,6.4.43482
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.2,7.0.1/7.0.0,6.4.0
+      `hipother <https://github.com/ROCm/hipother>`_,7.1.52802,7.1.25424,6.4.43482
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.1.0,7.1.0,6.4.0
       `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>`,26.0.2,26.0.0,25.3.0
-      :doc:`ROCm Data Center Tool <rdc:index>`,1.1.0,1.1.0,0.3.0
+      :doc:`AMD SMI <amdsmi:index>`,26.1.0,26.1.0,25.3.0
+      :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>`,1.2.0,1.2.0,1.1.0
       ,,,
       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>`,3.2.3,3.2.3,3.1.0
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.1.1,1.1.0,1.0.0
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70002,2.0.70000,2.0.60400
+      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.3.0,3.3.0,3.1.0
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.2.0,1.2.0,1.0.0
+      :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>`,4.1.70002,4.1.70000,4.1.60400
+      :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>`,0.77.4,0.77.3,0.77.2
+      :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
@@ -143,45 +143,27 @@ compatibility and system requirements.
       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>`_,20.0.0.25385,20.0.0.25314,19.0.0.25133
-      :doc:`llvm-project <llvm-project:index>`,20.0.0.25385,20.0.0.25314,19.0.0.25133
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,20.0.0.25385,20.0.0.25314,19.0.0.25133
+      `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>`,7.0.51831,7.0.51830,6.4.43482
-      :doc:`HIP <hip:index>`,7.0.51831,7.0.51830,6.4.43482
+      :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
 
 .. rubric:: Footnotes
 
-.. [#rhel-10-702] RHEL 10.0 and RHEL 9.6 are supported on all listed :ref:`supported_GPUs` except AMD Radeon PRO V620 GPU.
-.. [#rhel-94-702] RHEL 9.4 is supported on all AMD Instinct GPUs listed under :ref:`supported_GPUs`.
-.. [#rhel-700] RHEL 8.10 is supported only on AMD Instinct MI300X, MI300A, MI250X, MI250, MI210, and MI100 GPUs.
-.. [#ol-700-mi300x] **For ROCm 7.0.x** - Oracle Linux 10 and 9 are supported only on AMD Instinct MI355X, MI350X, and MI300X GPUs. Oracle Linux 8 is supported only on AMD Instinct MI300X GPU.
-.. [#ol-mi300x] **Prior ROCm 7.0.0** - Oracle Linux is supported only on AMD Instinct MI300X GPUs.
-.. [#db-mi300x] **For ROCm 7.0.2** - Debian 13 is supported only on AMD Instinct MI300X GPUs.
-.. [#sles-db-700] **For ROCm 7.0.x** - SLES 15 SP7 and Debian 12 are supported only on AMD Instinct MI300X, MI300A, MI250X, MI250, and MI210 GPUs.
-.. [#az-mi300x] Starting ROCm 6.4.0, Azure Linux 3.0 is supported only on AMD Instinct MI300X and AMD Radeon PRO V710 GPUs.
-.. [#rl-700] Rocky Linux 9 is supported only on AMD Instinct MI300X and MI300A GPUs.
-.. [#single-node] **Prior to ROCm 7.0.0** - Debian 12 is supported only on AMD Instinct MI300X GPUs for single-node functionality.
-.. [#mi350x-os] AMD Instinct MI355X (gfx950) and MI350X(gfx950) GPUs are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, RHEL 9.4, Oracle Linux 10, and Oracle Linux 9.
-.. [#RDNA-OS-700] **For ROCm 7.0.x** - AMD Radeon PRO AI PRO R9700 (gfx1201), AMD Radeon RX 9070 XT (gfx1201), AMD Radeon RX 9070 GRE (gfx1201), AMD Radeon RX 9070 (gfx1201), AMD Radeon RX 9060 XT (gfx1200), AMD Radeon RX 9060 (gfx1200), AMD Radeon RX 7800 XT (gfx1101), AMD Radeon RX 7700 XT (gfx1101), AMD Radeon PRO W7700 (gfx1101), and AMD Radeon PRO W6800 (gfx1030) are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, and RHEL 9.6.
-.. [#rd-v710] **For ROCm 7.0.x** - AMD Radeon PRO V710 (gfx1101) GPUs are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, and Azure Linux 3.0.
-.. [#rd-v620] **For ROCm 7.0.x** - AMD Radeon PRO V620 (gfx1030) GPUs are supported only on Ubuntu 24.04.3 and Ubuntu 22.04.5.
-.. [#mi325x-os] **For ROCm 7.0.x** - AMD Instinct MI325X GPUs (gfx942) are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
-.. [#mi300x-os] **For ROCm 7.0.x** - AMD Instinct MI300X GPUs (gfx942) are supported on all listed :ref:`supported_distributions`.
-.. [#mi300A-os] **For ROCm 7.0.x** - AMD Instinct MI300A GPUs (gfx942) are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, Debian 12, and Rocky Linux 9.
-.. [#mi200x-os] **For ROCm 7.0.x** - AMD Instinct MI200 Series GPUs (gfx90a) are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, and Debian 12.
-.. [#mi100-os] **For ROCm 7.0.x** - AMD Instinct MI100 GPUs (gfx908) are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
-.. [#tf-mi350] 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.
-.. [#dgl_compat] DGL is supported only on ROCm 6.4.0.
+.. [#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 supported only on ROCm 7.0.0, ROCm 6.4.3 and ROCm 6.4.0.
 .. [#llama-cpp_compat] llama.cpp is supported only 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.
 
-
 .. _OS-kernel-versions:
 
 Operating systems, kernel and Glibc versions
@@ -200,9 +182,11 @@ Use this lookup table to confirm which operating system and kernel versions are
    ,,
    `Ubuntu <https://ubuntu.com/about/release-cycle#ubuntu-kernel-release-cycle>`_, 22.04.5, "5.15 [GA], 6.8 [HWE]", 2.35
    ,,
-   `Red Hat Enterprise Linux (RHEL 10) <https://access.redhat.com/articles/3078#RHEL9>`_, 10.0, 6.12.0-55, 2.39
+   `Red Hat Enterprise Linux (RHEL 10) <https://access.redhat.com/articles/3078#RHEL9>`_, 10.1, 6.12.0-124, 2.39
+   ,10.0, 6.12.0-55, 2.39
    ,,
-   `Red Hat Enterprise Linux (RHEL 9) <https://access.redhat.com/articles/3078#RHEL9>`_, 9.6, 5.14.0-570, 2.34
+   `Red Hat Enterprise Linux (RHEL 9) <https://access.redhat.com/articles/3078#RHEL9>`_, 9.7, 5.14.0-611, 2.34
+   ,9.6, 5.14.0-570, 2.34
    ,9.5, 5.14+, 2.34
    ,9.4, 5.14.0-427, 2.34
    ,,
@@ -254,46 +238,18 @@ Expand for full historical view of:
 
    .. rubric:: Footnotes
 
-   .. [#rhel-10-702-past-60] RHEL 10.0 and RHEL 9.6 are supported on all listed :ref:`supported_GPUs` except AMD Radeon PRO V620 GPU.
-   .. [#rhel-94-702-past-60] RHEL 9.4 is supported on all AMD Instinct GPUs listed under :ref:`supported_GPUs`.
-   .. [#rhel-700-past-60] **For ROCm 7.0.x** - RHEL 8.10 is supported only on AMD Instinct MI300X, MI300A, MI250X, MI250, MI210, and MI100 GPUs.
-   .. [#ol-700-mi300x-past-60] **For ROCm 7.0.x** - Oracle Linux 10 and 9 are supported only on AMD Instinct MI355X, MI350X, and MI300X GPUs. Oracle Linux 8 is supported only on AMD Instinct MI300X GPU.
-   .. [#mi300x-past-60] **Prior ROCm 7.0.0** - Oracle Linux is supported only on AMD Instinct MI300X GPUs.
-   .. [#db-mi300x-past-60] **For ROCm 7.0.2** - Debian 13 is supported only on AMD Instinct MI300X GPUs.
-   .. [#sles-db-700-past-60] **For ROCm 7.0.x** - SLES 15 SP7 and Debian 12 are supported only on AMD Instinct MI300X, MI300A, MI250X, MI250, and MI210 GPUs.
-   .. [#single-node-past-60] **Prior to ROCm 7.0.0** - Debian 12 is supported only on AMD Instinct MI300X GPUs for single-node functionality.
-   .. [#az-mi300x-past-60] Starting from ROCm 6.4.0, Azure Linux 3.0 is supported only on AMD Instinct MI300X and AMD Radeon PRO V710 GPUs.
-   .. [#az-mi300x-630-past-60] **Prior ROCm 6.4.0**- Azure Linux 3.0 is supported only on AMD Instinct MI300X GPUs.
-   .. [#rl-700-past-60] Rocky Linux 9 is supported only on AMD Instinct MI300X and MI300A GPUs.
-   .. [#mi350x-os-past-60] AMD Instinct MI355X (gfx950) and MI350X(gfx950) GPUs are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and Oracle Linux 9.
-   .. [#RDNA-OS-700-past-60] **For ROCm 7.0.x** AMD Radeon PRO AI PRO R9700 (gfx1201), AMD Radeon RX 9070 XT (gfx1201), AMD Radeon RX 9070 GRE (gfx1201), AMD Radeon RX 9070 (gfx1201), AMD Radeon RX 9060 XT (gfx1200), AMD Radeon RX 9060 (gfx1200), AMD Radeon RX 7800 XT (gfx1101), AMD Radeon RX 7700 XT (gfx1101), AMD Radeon PRO W7700 (gfx1101), and AMD Radeon PRO W6800 (gfx1030) are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, RHEL 9.4, Oracle Linux 10, and Oracle Linux 9.
-   .. [#RDNA-OS-past-60] **Prior ROCm 7.0.0** - Radeon AI PRO R9700, Radeon RX 9070 XT (gfx1201), Radeon RX 9060 XT (gfx1200), Radeon PRO W7700 (gfx1101), and Radeon RX 7800 XT (gfx1101) are supported only on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
-   .. [#rd-v710-past-60] **For ROCm 7.0.x** - AMD Radeon PRO V710 (gfx1101) is supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, and Azure Linux 3.0.
-   .. [#rd-v620-past-60] **For ROCm 7.0.x** - AMD Radeon PRO V620 (gfx1030) is supported only on Ubuntu 24.04.3 and Ubuntu 22.04.5.
-   .. [#mi325x-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI325X GPU (gfx942) is supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
-   .. [#mi300x-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI300X GPU (gfx942) is supported on all listed :ref:`supported_distributions`.
-   .. [#mi300A-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI300A GPU (gfx942) is supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, Debian 12, and Rocky Linux 9.
-   .. [#mi200x-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI200 Series GPUs (gfx90a) are supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, and Debian 12.
-   .. [#mi100-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI100 GPU (gfx908) is supported only on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 10.0, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
-   .. [#7700XT-OS-past-60] **Prior to ROCm 7.0.0** - Radeon RX 7700 XT (gfx1101) is supported only on Ubuntu 24.04.2 and RHEL 9.6.
-   .. [#mi300_624-past-60] **For ROCm 6.2.4** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
-   .. [#mi300_622-past-60] **For ROCm 6.2.2** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
-   .. [#mi300_621-past-60] **For ROCm 6.2.1** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
-   .. [#mi300_620-past-60] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
-   .. [#mi300_612-past-60] **For ROCm 6.1.2** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is supported only on Ubuntu 22.04.4 and Oracle Linux.
-   .. [#mi300_611-past-60] **For ROCm 6.1.1** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is supported only on Ubuntu 22.04.4 and Oracle Linux.
-   .. [#mi300_610-past-60] **For ROCm 6.1.0** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is supported only on Ubuntu 22.04.4.
-   .. [#mi300_602-past-60] **For ROCm 6.0.2** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is supported only on Ubuntu 22.04.3.
-   .. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is supported only on Ubuntu 22.04.3.
+   .. [#os-compatibility-past-60] Some operating systems are supported on limited GPUs. For detailed information, see :ref:`supported_distributions` and select the required ROCm version for version specific support.
+   .. [#gpu-compatibility-past-60] Some GPUs have limited operating system support. For detailed information, see :ref:`supported_GPUs` and select the required ROCm version for version specific support.
    .. [#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 supported only on ROCm 6.2.0.
+   .. [#verl_compat-past-60] verl is supported only on ROCm 7.0.0 and 6.2.0.
    .. [#stanford-megatron-lm_compat-past-60] Stanford Megatron-LM is supported only on ROCm 6.3.0.
-   .. [#dgl_compat-past-60] DGL is supported only on ROCm 6.4.0.
+   .. [#dgl_compat-past-60] DGL is supported only on ROCm 7.0.0, ROCm 6.4.3 and ROCm 6.4.0.
    .. [#megablocks_compat-past-60] Megablocks is supported only on ROCm 6.3.0.
    .. [#taichi_compat-past-60] Taichi is supported only on ROCm 6.3.2.
    .. [#ray_compat-past-60] Ray is supported only on ROCm 6.4.1.
    .. [#llama-cpp_compat-past-60] llama.cpp is supported only on ROCm 7.0.0 and 6.4.x.
    .. [#flashinfer_compat-past-60] FlashInfer is supported only 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/ml-compatibility/dgl-compatibility.rst

@@ -39,13 +39,13 @@ Support overview
 Version support
 --------------------------------------------------------------------------------
 
-DGL is supported on `ROCm 6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__.
+DGL is supported on `ROCm 7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__, 
+`ROCm 6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__, and `ROCm 6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__.
 
 Supported devices
 --------------------------------------------------------------------------------
 
-- **Officially Supported**: AMD Instinct™ MI300X (through `hipBLASlt <https://rocm.docs.amd.com/projects/hipBLASLt/en/latest/index.html>`__)
-- **Partially Supported**: AMD Instinct™ MI250X
+**Officially Supported**: AMD Instinct™ MI300X, MI250X
 
 .. _dgl-recommendations:
 
@@ -60,16 +60,35 @@ GAT, GCN, and GraphSage. Using these models, a variety of use cases are supporte
 - 1D (Temporal) and 2D (Image) Classification
 - Drug Discovery
 
-Multiple use cases of DGL have been tested and verified.
-However, a recommended example follows a drug discovery pipeline using the ``SE3Transformer``.
-Refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`_, 
-where you can search for DGL examples and best practices to optimize your training workflows on AMD GPUs. 
+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.
 
-Coverage includes:
+* 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. 
 
-- Single-GPU training/inference
-- Multi-GPU training
+* 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
 
 .. _dgl-docker-compat:
 
@@ -85,7 +104,7 @@ 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:: DGL Docker image components
+.. list-table::
     :header-rows: 1
     :class: docker-image-compatibility
 
@@ -98,43 +117,83 @@ Click the |docker-icon| to view the image on Docker Hub.
 
     * - .. 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></a>
+           <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>
 
-      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__.
+      - `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/ROCm/pytorch/tree/release/2.6>`__
+      - `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/>`__
 
     * - .. 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></a>
+           <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>
 
-      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__.
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
       - `2.4.0 <https://github.com/dmlc/dgl/releases/tag/v2.4.0>`__
-      - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`__
+      - `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/>`__
+
+    * - .. 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/>`__
+
+    * - .. 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/>`__
+
+    * - .. 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/>`__
+
+    * - .. 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/>`__
 
 
     * - .. 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></a>
+           <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/>`__.
+      - `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/ROCm/pytorch/tree/release/2.4>`__
+      - `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/>`__
 
 
     * - .. 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></a>
+           <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/>`__.
+      - `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/ROCm/pytorch/tree/release/2.3>`__
+      - `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/>`__
       
@@ -150,81 +209,102 @@ If you prefer to build it yourself, ensure the following dependencies are instal
     :header-rows: 1
 
     * - ROCm library
-      - ROCm 6.4.0 Version
+      - 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>`_
-      - :version-ref:`rocAL rocm_version`
+      - 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>`_
-      - 2.2.0
+      - 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
@@ -253,26 +333,29 @@ Instead of listing them all, support is grouped into the following categories to
 * DGL NN
 * DGL Optim
 * DGL Sparse
-
+* GraphBolt
 
 Unsupported features
 ================================================================================
 
-* GraphBolt
-* Partial TF32 Support (MI250X only)
+* TF32 Support (only supported for PyTorch 2.7 and above)
 * Kineto/ROCTracer integration
 
 
 Unsupported functions
 ================================================================================
 
-* ``more_nnz``
+* ``bfs``
 * ``format``
 * ``multiprocess_sparse_adam_state_dict``
-* ``record_stream_ndarray``
 * ``half_spmm``
 * ``segment_mm`` 
 * ``gather_mm_idx_b``
-* ``pgexplainer``
 * ``sample_labors_prob``
 * ``sample_labors_noprob``
+* ``sparse_admin``
+
+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/jax-compatibility.rst

@@ -43,6 +43,26 @@ 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
 ================================================================================
 

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

@@ -45,7 +45,7 @@ llama.cpp is supported on `ROCm 7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
 Supported devices
 --------------------------------------------------------------------------------
 
-**Officially Supported**: AMD Instinct™ MI300X, MI325X, MI210
+**Officially Supported**: AMD Instinct™ MI325X, MI300X, MI210
 
 Use cases and recommendations
 ================================================================================
@@ -109,27 +109,27 @@ Click |docker-icon| to view the image on Docker Hub.
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm7.0.0_ubuntu24.04_full/images/sha256-a2ecd635eaa65bb289a9041330128677f3ae88bee6fee0597424b17e38d4903c"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+           <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-b6356_rocm7.0.0_ubuntu24.04_server/images/sha256-cb46b47df415addb5ceb6e6fdf0be70bf9d7f6863bbe6e10c2441ecb84246d52"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+           <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-b6356_rocm7.0.0_ubuntu24.04_light/images/sha256-8f8536eec4b05c0ff1c022f9fc6c527ad1c89e6c1ca0906e4d39e4de73edbde9"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
-      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+           <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
 
     * - .. raw:: html
 
-           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm7.0.0_ubuntu22.04_full/images/sha256-f36de2a3b03ae53e81c85422cb3780368c9891e1ac7884b04403a921fe2ea45d"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+           <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-b6356_rocm7.0.0_ubuntu22.04_server/images/sha256-df15e8ab11a6837cd3736644fec1e047465d49e37d610ab0b79df000371327df"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+           <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-b6356_rocm7.0.0_ubuntu22.04_light/images/sha256-4ea2d5bb7964f0ee3ea9b30ba7f343edd6ddfab1b1037669ca7eafad2e3c2bd7"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
-      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+           <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
 

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

@@ -349,7 +349,7 @@ with ROCm.
         you need to explicitly move audio data (waveform tensor) to GPU using
         ``.to('cuda')``.
 
-    * - `torchtune <https://docs.pytorch.org/torchtune/stable/index.html>`_
+    * - `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.
@@ -361,21 +361,12 @@ with ROCm.
         popular datasets, model architectures, and common image transformations
         for computer vision applications.
 
-    * - `torchtext <https://docs.pytorch.org/text/stable/index.html>`_
-      - Text processing library for PyTorch. Provides data processing utilities
-        and popular datasets for natural language processing, including
-        tokenization, vocabulary management, and text embeddings.
-
-        **Note:** ``torchtext`` does not implement ROCm-specific kernels.
-        ROCm acceleration is provided through the underlying PyTorch framework
-        and ROCm library integration. Only official release exists.
-
     * - `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://docs.pytorch.org/torchrec/>`_
+    * - `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.
@@ -408,7 +399,40 @@ with ROCm.
 
         **Note:** Only official release exists.
 
-Key features and enhancements for PyTorch 2.7 with ROCm 7.0
+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
@@ -443,10 +467,6 @@ Key features and enhancements for PyTorch 2.7 with ROCm 7.0
   ROCm-specific test conditions, and enhanced unit test coverage for Flash
   Attention and Memory Efficient operations.
 
-- Build system and infrastructure improvements: Provides updated CentOS Stream 9
-  support, improved Docker configuration, migration to public MAGMA repository,
-  and enhanced QA automation scripts for PyTorch unit testing.
-
 - Composable Kernel (CK) updates: Features updated CK submodule integration with
   the latest optimizations and performance improvements for core mathematical
   operations.
@@ -468,7 +488,7 @@ Key features and enhancements for PyTorch 2.7 with ROCm 7.0
   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 with ROCm 7.0
+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

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

@@ -136,7 +136,7 @@ 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
@@ -254,7 +254,7 @@ are as follows:
       - 1.7
 
 Features
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+---------------
 
 This table provides an overview of key features in TensorFlow and their
 availability in ROCm.
@@ -346,7 +346,7 @@ availability in ROCm.
       - 1.9.2
 
 Distributed library features
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+-----------------------------------
 
 Enables developers to scale computations across multiple devices on a single machine or
 across multiple machines.

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

@@ -31,7 +31,7 @@ Support overview
 - 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>` 
+  - 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/>`__ 
@@ -40,7 +40,8 @@ Support overview
 Version support
 --------------------------------------------------------------------------------
 
-verl is supported on `ROCm 6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`__.
+verl is supported on `ROCm 7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__ and
+`ROCm 6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`__.
 
 Supported devices
 --------------------------------------------------------------------------------
@@ -57,7 +58,7 @@ Use cases and recommendations
   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 
-  Instinct™ MI300X GPUs. The guide details the process of building a Docker image, 
+  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, 
@@ -79,12 +80,20 @@ The following table shows verl on ROCm support for GPU-accelerated modules.
       - ROCm version
     * - ``FSDP``
       - Training engine
-      - 0.3.0.post0
-      - 6.2.0
+      - 
+       * 0.6.0
+       * 0.3.0.post0
+      - 
+       * 7.0.0
+       * 6.2.0
     * - ``vllm``
       - Inference engine
-      - 0.3.0.post0
-      - 6.2.0
+      - 
+       * 0.6.0
+       * 0.3.0.post0
+      - 
+       * 7.0.0
+       * 6.2.0
 
 .. _verl-docker-compat:
 
@@ -95,28 +104,45 @@ Docker image compatibility
 
    <i class="fab fa-docker"></i>
 
-AMD validates and publishes ready-made `verl Docker images <https://hub.docker.com/r/rocm/verl/tags>`_
+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
+.. list-table::
+   :header-rows: 1
+   :class: docker-image-compatibility
 
-    *   - Docker image
-        - ROCm
-        - verl
-        - Ubuntu
-        - Pytorch
-        - Python
-        - vllm
+   * - Docker image
+     - ROCm
+     - verl
+     - Ubuntu
+     - PyTorch
+     - Python
+     - vllm
 
-    *   - .. raw:: html
+   * - .. 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/>`_
-        - `0.3.0post0 <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>`_
+        <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>`__
+
+   * - .. 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>`__
+
+
+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/gpu-isolation.md

@@ -34,7 +34,7 @@ Runtime
 
 ```{code-block} shell
 :caption: Example to expose the 1. device and a device based on UUID.
-export ROCR_VISIBLE_DEVICES="0,GPU-DEADBEEFDEADBEEF"
+export ROCR_VISIBLE_DEVICES="0,GPU-4b2c1a9f-8d3e-6f7a-b5c9-2e4d8a1f6c3b"
 ```
 
 ### `GPU_DEVICE_ORDINAL`

docs/conf.py

@@ -8,6 +8,7 @@ import os
 import shutil
 import sys
 from pathlib import Path
+from subprocess import run
 
 gh_release_path = os.path.join("..", "RELEASE.md")
 gh_changelog_path = os.path.join("..", "CHANGELOG.md")
@@ -80,24 +81,27 @@ 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 = os.path.abspath(".").replace("\\", "/")
 author = "Advanced Micro Devices, Inc."
 copyright = "Copyright (c) 2025 Advanced Micro Devices, Inc. All rights reserved."
-version = "7.0.2"
-release = "7.0.2"
+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", "os": ["linux"], "date": "2025-10-10"},
+    {"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"]},
@@ -141,6 +145,7 @@ article_pages = [
     {"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/inference/xdit-diffusion-inference", "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/primus-pytorch", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/pytorch-training", "os": ["linux"]},
@@ -202,7 +207,7 @@ external_toc_path = "./sphinx/_toc.yml"
 # Add the _extensions directory to Python's search path
 sys.path.append(str(Path(__file__).parent / 'extension'))
 
-extensions = ["rocm_docs", "sphinx_reredirects", "sphinx_sitemap", "sphinxcontrib.datatemplates", "version-ref", "csv-to-list-table"]
+extensions = ["rocm_docs", "sphinx_reredirects", "sphinx_sitemap", "sphinxcontrib.datatemplates", "remote-content", "version-ref", "csv-to-list-table"]
 
 compatibility_matrix_file = str(Path(__file__).parent / 'compatibility/compatibility-matrix-historical-6.0.csv')
 
@@ -212,10 +217,14 @@ external_projects_current_project = "rocm"
 # external_projects_remote_repository = ""
 
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "https://rocm-stg.amd.com/")
-html_context = {}
+html_context = {"docs_header_version": "7.1.0"}
 if os.environ.get("READTHEDOCS", "") == "True":
     html_context["READTHEDOCS"] = 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"}
 
@@ -241,3 +250,6 @@ html_context = {
     "granularity_type" : [('Coarse-grained', 'coarse-grained'), ('Fine-grained', 'fine-grained')],
     "scope_type" : [('Device', 'device'), ('System', 'system')]
 }
+
+# Disable figure and table numbering
+numfig = False

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/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/r/rocm/pytorch-xdit
+    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/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_0.11.1_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: 0.10.2 (0.11.0rc2.dev160+g790d22168.rocm700)
+      vLLM: 0.11.1 (0.11.1rc2.dev141+g38f225c2a.rocm700)
       PyTorch: 2.9.0a0+git1c57644
       hipBLASLt: 1.0.0
     dockerfile:
-      commit: 790d22168820507f3105fef29596549378cfe399
+      commit: 38f225c2abeadc04c2cc398814c2f53ea02c3c72
 model_groups:
   - group: Meta Llama
     tag: llama

docs/data/how-to/rocm-for-ai/inference/xdit-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/r/rocm/pytorch-xdit
+      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/training/megatron-lm-benchmark-models.yaml

@@ -1,21 +1,17 @@
-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
+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

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-v25.9-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-v25.9-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-v25.9-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

@@ -1,22 +1,15 @@
-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
+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

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

@@ -1,39 +1,32 @@
-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
+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: 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"
+      - 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/pytorch-training-benchmark-models.yaml

@@ -1,21 +1,15 @@
-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
+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
@@ -119,6 +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:
@@ -166,7 +169,7 @@ model_groups:
       model_repo: SDXL
       url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
       precision: BF16
-      training_modes: [posttrain-p]
+      training_modes: [posttrain]
   - group: Flux
     tag: flux
     models:
@@ -175,12 +178,20 @@ model_groups:
       model_repo: Flux
       url: https://huggingface.co/black-forest-labs/FLUX.1-dev
       precision: BF16
-      training_modes: [posttrain-p]
+      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/extension/remote-content.py

@@ -0,0 +1,141 @@
+from docutils import nodes
+from docutils.parsers.rst import Directive
+from docutils.statemachine import ViewList
+from sphinx.util import logging
+from sphinx.util.nodes import nested_parse_with_titles
+import requests
+import re
+
+logger = logging.getLogger(__name__)
+
+class BranchAwareRemoteContent(Directive):
+    """
+    Directive that downloads and includes content from other repositories,
+    matching the branch/tag of the current documentation build.
+
+    Usage:
+    .. remote-content::
+       :repo: owner/repository
+       :path: path/to/file.rst
+       :default_branch: docs/develop  # Branch to use when not on a release
+       :tag_prefix: Docs/  # Optional
+    """
+
+    required_arguments = 0
+    optional_arguments = 0
+    final_argument_whitespace = True
+    has_content = False
+    option_spec = {
+        'repo': str,
+        'path': str,
+        'default_branch': str,  # Branch to use when not on a release tag
+        'start_line': int,      # Include the file from a specific line
+        'tag_prefix': str,      # Prefix for release tags (e.g., 'Docs/')
+    }
+
+    def get_current_version(self):
+        """Get current version/branch being built"""
+        env = self.state.document.settings.env
+        html_context = env.config.html_context
+
+        # Check if building from a tag
+        if "official_branch" in html_context:
+            if html_context["official_branch"] == 0:
+                if "version" in html_context:
+                    # Remove any 'v' prefix
+                    version = html_context["version"]
+                    if re.match(r'^\d+\.\d+\.\d+$', version):
+                        return version
+
+        # Not a version tag, so we'll use the default branch
+        return None
+
+    def get_target_ref(self):
+        """Get target reference for the remote repository"""
+        current_version = self.get_current_version()
+
+        # If it's a version number, use tag prefix and version
+        if current_version:
+            tag_prefix = self.options.get('tag_prefix', '')
+            return f'{tag_prefix}{current_version}'
+
+        # For any other case, use the specified default branch
+        if 'default_branch' not in self.options:
+            logger.warning('No default_branch specified and not building from a version tag')
+            return None
+
+        return self.options['default_branch']
+
+    def construct_raw_url(self, repo, path, ref):
+        """Construct the raw.githubusercontent.com URL"""
+        return f'https://raw.githubusercontent.com/{repo}/{ref}/{path}'
+
+    def fetch_and_parse_content(self, url, source_path):
+        """Fetch content and parse it as RST"""
+        response = requests.get(url)
+        response.raise_for_status()
+        content = response.text
+
+        start_line = self.options.get('start_line', 0)
+
+        # Create ViewList for parsing
+        line_count = 0
+        content_list = ViewList()
+        for line_no, line in enumerate(content.splitlines()):
+            if line_count >= start_line:
+                content_list.append(line, source_path, line_no)
+            line_count+=1 
+
+        # Create a section node and parse content
+        node = nodes.section()
+        nested_parse_with_titles(self.state, content_list, node)
+
+        return node.children
+
+    def run(self):
+        if 'repo' not in self.options or 'path' not in self.options:
+            logger.warning('Both repo and path options are required')
+            return []
+
+        target_ref = self.get_target_ref()
+        if not target_ref:
+            return []
+
+        raw_url = self.construct_raw_url(
+            self.options['repo'],
+            self.options['path'],
+            target_ref
+        )
+
+        try:
+            logger.info(f'Attempting to fetch content from {raw_url}')
+            return self.fetch_and_parse_content(raw_url, self.options['path'])
+        except requests.exceptions.RequestException as e:
+            logger.warning(f'Failed to fetch content from {raw_url}: {str(e)}')
+
+            # If we failed on a tag, try falling back to default_branch
+            if re.match(r'^\d+\.\d+\.\d+$', target_ref) or target_ref.startswith('Docs/'):
+                if 'default_branch' in self.options:
+                    try:
+                        fallback_ref = self.options['default_branch']
+                        logger.info(f'Attempting fallback to {fallback_ref}...')
+
+                        fallback_url = self.construct_raw_url(
+                            self.options['repo'],
+                            self.options['path'],
+                            fallback_ref
+                        )
+
+                        return self.fetch_and_parse_content(fallback_url, self.options['path'])
+                    except requests.exceptions.RequestException as e2:
+                        logger.warning(f'Fallback also failed: {str(e2)}')
+
+            return []
+
+def setup(app):
+    app.add_directive('remote-content', BranchAwareRemoteContent)
+
+    return {
+        'parallel_read_safe': True,
+        'parallel_write_safe': True,
+    }

docs/how-to/deep-learning-rocm.rst

@@ -84,6 +84,8 @@ The table below summarizes information about ROCm-enabled deep learning framewor
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/dgl-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
         - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/dgl-install.html#use-a-prebuilt-docker-image-with-dgl-pre-installed>`__
+        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/dgl-install.html#use-a-wheels-package>`__
+
       - .. raw:: html
 
           <a href="https://github.com/ROCm/dgl"><i class="fab fa-github fa-lg"></i></a> 

docs/how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference.rst

@@ -130,7 +130,7 @@ After loading the model in this way, the model is fully ready to use the resourc
 torchtune for fine-tuning and inference
 =============================================
 
-`torchtune <https://pytorch.org/torchtune/main/>`_ is a PyTorch-native library for easy single and multi-GPU 
+`torchtune <https://meta-pytorch.org/torchtune/main/>`_ is a PyTorch-native library for easy single and multi-GPU 
 model fine-tuning and inference with LLMs.
 
 #. Install torchtune using pip.

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

@@ -46,6 +46,8 @@ The following variables are generally useful for Instinct MI300X/MI355X GPUs and
     multi-GPU distributed workloads** (tensor parallelism, pipeline
     parallelism). Single-GPU inference does not need this.
 
+.. _vllm-optimization-aiter-switches:
+
 AITER (AI Tensor Engine for ROCm) switches
 ==========================================
 
@@ -65,7 +67,7 @@ Quick start examples:
    export VLLM_ROCM_USE_AITER=1
    vllm serve MODEL_NAME
 
-   # Enable only AITER Triton Prefill-Decode (split) attention
+   # Enable AITER Fused MoE and enable Triton Prefill-Decode (split) attention
    export VLLM_ROCM_USE_AITER=1
    export VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1
    export VLLM_ROCM_USE_AITER_MHA=0
@@ -242,14 +244,17 @@ Most users won't need this, but you can override the defaults:
    * - AITER MHA (standard models)
      - ``VLLM_ROCM_USE_AITER=1`` (auto-selects for non-MLA models)
 
-   * - AITER Triton Prefill-Decode (split)
+   * - vLLM Triton Unified (default)
+     - ``VLLM_ROCM_USE_AITER=0`` (or unset)
+
+   * - Triton Prefill-Decode (split) without AITER
+     - | ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``
+
+   * - Triton Prefill-Decode (split) along with AITER Fused-MoE
      - | ``VLLM_ROCM_USE_AITER=1``
        | ``VLLM_ROCM_USE_AITER_MHA=0``
        | ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``
 
-   * - vLLM Triton Unified (default)
-     - ``VLLM_ROCM_USE_AITER=0`` (or unset)
-
    * - AITER Unified Attention
      - | ``VLLM_ROCM_USE_AITER=1``
        | ``VLLM_ROCM_USE_AITER_MHA=0``
@@ -267,11 +272,11 @@ Most users won't need this, but you can override the defaults:
        --block-size 1 \
        --tensor-parallel-size 8
 
-   # Advanced: Use Prefill-Decode split (for short input cases)
+   # Advanced: Use Prefill-Decode split (for short input cases) with AITER Fused-MoE
    VLLM_ROCM_USE_AITER=1 \
    VLLM_ROCM_USE_AITER_MHA=0 \
    VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1 \
-   vllm serve meta-llama/Llama-3.3-70B-Instruct
+   vllm serve meta-llama/Llama-4-Scout-17B-16E
 
 **Which backend should I choose?**
 
@@ -350,14 +355,14 @@ vLLM V1 on ROCm provides these attention implementations:
 
 3. **AITER Triton Prefill–Decode Attention** (hybrid, Instinct MI300X-optimized)
 
-   * Enable with ``VLLM_ROCM_USE_AITER=1``, ``VLLM_ROCM_USE_AITER_MHA=0``, and ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``
+   * Enable with ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``
    * Uses separate kernels for prefill and decode phases:
 
      * **Prefill**: ``context_attention_fwd`` Triton kernel
      * **Primary decode**: ``torch.ops._rocm_C.paged_attention`` (custom ROCm kernel optimized for head sizes 64/128, block sizes 16/32, GQA 1–16, context ≤131k; sliding window not supported)
      * **Fallback decode**: ``kernel_paged_attention_2d`` Triton kernel when shapes don't meet primary decode requirements
 
-   * Usually better compared to unified Triton kernels (both vLLM and AITER variants)
+   * Usually better compared to unified Triton kernels
    * Performance vs AITER MHA varies: AITER MHA is typically faster overall, but Prefill-Decode split may win in short input scenarios
    * The custom paged attention decode kernel is controlled by ``VLLM_ROCM_CUSTOM_PAGED_ATTN`` (default **True**)
 
@@ -693,7 +698,9 @@ There are two strategies:
 vLLM engine arguments
 =====================
 
-Selected arguments that often help on ROCm. See `engine args docs <https://docs.vllm.ai/en/latest/serving/engine_args.html>`_ for the full list.
+Selected arguments that often help on ROCm. See `Engine Arguments
+<https://docs.vllm.ai/en/stable/configuration/engine_args.html>`__ in the vLLM
+documentation for the full list.
 
 Configure --max-num-seqs
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.2-20251006.rst

@@ -0,0 +1,482 @@
+:orphan:
+
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the ROCm vLLM Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+**********************************
+vLLM inference performance testing
+**********************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   inference performance documentation. See :doc:`../vllm` for the latest version.
+
+.. _vllm-benchmark-unified-docker-930:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20251006-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+
+   The `ROCm vLLM Docker <{{ docker.docker_hub_url }}>`_ image offers a
+   prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on AMD Instinct™ MI355X, MI350X, MI325X and MI300X
+   GPUs. This ROCm vLLM Docker image integrates vLLM and PyTorch tailored
+   specifically for AMD data center GPUs and includes the following components:
+
+   .. tab-set::
+
+      .. tab-item:: {{ docker.pull_tag }}
+
+         .. list-table::
+            :header-rows: 1
+
+            * - Software component
+              - Version
+
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}
+
+With this Docker image, you can quickly test the :ref:`expected
+inference performance numbers <vllm-benchmark-performance-measurements-930>` for
+AMD Instinct GPUs.
+
+What's new
+==========
+
+The following is summary of notable changes since the :doc:`previous ROCm/vLLM Docker release <vllm-history>`.
+
+* Added support for AMD Instinct MI355X and MI350X GPUs.
+
+* Added support and benchmarking instructions for the following models. See :ref:`vllm-benchmark-supported-models-930`.
+
+  * Llama 4 Scout and Maverick
+
+  * DeepSeek R1 0528 FP8
+
+  * MXFP4 models (MI355X and MI350X only): Llama 3.3 70B MXFP4 and Llama 3.1 405B MXFP4
+
+  * GPT OSS 20B and 120B
+
+  * Qwen 3 32B, 30B-A3B, and 235B-A22B
+
+* Removed the deprecated ``--max-seq-len-to-capture`` flag.
+
+* ``--gpu-memory-utilization`` is now configurable via the `configuration files
+  <https://github.com/ROCm/MAD/tree/develop/scripts/vllm/configs>`__ in the MAD
+  repository.
+
+.. _vllm-benchmark-supported-models-930:
+
+Supported models
+================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20251006-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+
+   .. _vllm-benchmark-available-models-930:
+
+   The following models are supported for inference performance benchmarking
+   with vLLM and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started. MXFP4 models
+   are only supported on MI355X and MI350X GPUs.
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+   .. _vllm-benchmark-vllm-930:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.mad_tag }}
+
+
+      {% if model.precision == "float4" %}
+      .. important::
+
+         MXFP4 is supported only on MI355X and MI350X GPUs.
+      {% endif %}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
+         Some models require access authorization prior to use via an external license agreement through a third party.
+      {% if model.precision == "float8" and model.model_repo.startswith("amd") %}
+         This model uses FP8 quantization via `AMD Quark <https://quark.docs.amd.com/latest/>`__ for efficient inference on AMD GPUs.
+      {% endif %}
+      {% if model.precision == "float4" and model.model_repo.startswith("amd") %}
+         This model uses FP4 quantization via `AMD Quark <https://quark.docs.amd.com/latest/>`__ for efficient inference on AMD GPUs.
+      {% endif %}
+
+      {% endfor %}
+   {% endfor %}
+
+.. _vllm-benchmark-performance-measurements-930:
+
+Performance measurements
+========================
+
+To evaluate performance, the
+`Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+page provides reference throughput and serving measurements for inferencing popular AI models.
+
+.. important::
+
+   The performance data presented in
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
+   only reflects the latest version of this inference benchmarking environment.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct GPUs or ROCm software.
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+Pull the Docker image
+=====================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20251006-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+
+   Download the `ROCm vLLM Docker image <{{ docker.docker_hub_url }}>`_.
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ docker.pull_tag }}
+
+Benchmarking
+============
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20251006-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+
+   Once the setup is complete, choose between two options to reproduce the
+   benchmark results:
+
+   .. _vllm-benchmark-mad-930:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`vllm-benchmark-supported-models-930` to switch to another available model.
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. On the host machine, use this command to run the performance benchmark test on
+               the `{{model.model}} <{{ model.url }}>`_ model using one node with the
+               :literal:`{{model.precision}}` data type.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{model.mad_tag}} \
+                      --keep-model-dir \
+                      --live-output
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
+            model are collected in the following paths: ``{{ model.mad_tag }}_throughput.csv``
+            and ``{{ model.mad_tag }}_serving.csv``.
+
+            Although the :ref:`available models
+            <vllm-benchmark-available-models-930>` are preconfigured to collect
+            offline throughput and online serving performance data, you can
+            also change the benchmarking parameters. See the standalone
+            benchmarking tab for more information.
+
+            {% if model.tunableop %}
+
+            .. note::
+
+               For improved performance, consider enabling :ref:`PyTorch TunableOp <mi300x-tunableop>`.
+               TunableOp automatically explores different implementations and configurations of certain PyTorch
+               operators to find the fastest one for your hardware.
+
+               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled (see
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To enable it, include
+               the ``--tunableop on`` argument in your run.
+
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the
+               performance-collection run.
+
+            {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            The following commands are optimized for {{ model.model }}.
+            See :ref:`vllm-benchmark-supported-models-930` to switch to another available model.
+
+            .. seealso::
+
+               For more information on configuration, see the `config files
+               <https://github.com/ROCm/MAD/tree/develop/scripts/vllm/configs>`__
+               in the MAD repository. Refer to the `vLLM engine <https://docs.vllm.ai/en/latest/configuration/engine_args.html#engineargs>`__
+               for descriptions of available configuration options
+               and `Benchmarking vLLM <https://github.com/vllm-project/vllm/blob/main/benchmarks/README.md>`__ for
+               additional benchmarking information.
+
+            .. rubric:: Launch the container
+
+            You can run the vLLM benchmark tool independently by starting the
+            `Docker container <{{ docker.docker_hub_url }}>`_ as shown
+            in the following snippet.
+
+            .. code-block:: shell
+
+               docker pull {{ docker.pull_tag }}
+               docker run -it \
+                   --device=/dev/kfd \
+                   --device=/dev/dri \
+                   --group-add video \
+                   --shm-size 16G \
+                   --security-opt seccomp=unconfined \
+                   --security-opt apparmor=unconfined \
+                   --cap-add=SYS_PTRACE \
+                   -v $(pwd):/workspace \
+                   --env HUGGINGFACE_HUB_CACHE=/workspace \
+                   --name test \
+                   {{ docker.pull_tag }}
+
+            .. rubric:: Throughput command
+
+            Use the following command to start the throughput benchmark.
+
+            .. code-block:: shell
+
+               model={{ model.model_repo }}
+               tp={{ model.config.tp }}
+               num_prompts={{ model.config.num_prompts | default(1024) }}
+               in={{ model.config.in | default(128) }}
+               out={{ model.config.in | default(128) }}
+               dtype={{ model.config.dtype | default("auto") }}
+               kv_cache_dtype={{ model.config.kv_cache_dtype }}
+               max_num_seqs={{ model.config.max_num_seqs | default(1024) }}
+               max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
+               max_model_len={{ model.config.max_model_len }}
+
+               vllm bench throughput --model $model \
+                   -tp $tp \
+                   --num-prompts $num_prompts \
+                   --input-len $in \
+                   --output-len $out \
+                   --dtype $dtype \
+                   --kv-cache-dtype $kv_cache_dtype \
+                   --max-num-seqs $max_num_seqs \
+                   --max-num-batched-tokens $max_num_batched_tokens \
+                   --max-model-len $max_model_len \
+                   --trust-remote-code \
+                   --output-json ${model}_throughput.json \
+                   --gpu-memory-utilization {{ model.config.gpu_memory_utilization | default(0.9) }}
+
+            .. rubric:: Serving command
+
+            1. Start the server using the following command:
+
+               .. code-block:: shell
+
+                  model={{ model.model_repo }}
+                  tp={{ model.config.tp }}
+                  dtype={{ model.config.dtype }}
+                  kv_cache_dtype={{ model.config.kv_cache_dtype }}
+                  max_num_seqs=256
+                  max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
+                  max_model_len={{ model.config.max_model_len }}
+
+                  vllm serve $model \
+                      -tp $tp \
+                      --dtype $dtype \
+                      --kv-cache-dtype $kv_cache_dtype \
+                      --max-num-seqs $max_num_seqs \
+                      --max-num-batched-tokens $max_num_batched_tokens \
+                      --max-model-len $max_model_len \
+                      --no-enable-prefix-caching \
+                      --swap-space 16 \
+                      --disable-log-requests \
+                      --trust-remote-code \
+                      --gpu-memory-utilization 0.9
+
+               Wait until the model has loaded and the server is ready to accept requests.
+
+            2. On another terminal on the same machine, run the benchmark:
+
+               .. code-block:: shell
+
+                  # Connect to the container
+                  docker exec -it test bash
+
+                  # Wait for the server to start
+                  until curl -s http://localhost:8000/v1/models; do sleep 30; done
+
+                  # Run the benchmark
+                  model={{ model.model_repo }}
+                  max_concurrency=1
+                  num_prompts=10
+                  in=128
+                  out=128
+                  vllm bench serve --model $model \
+                      --percentile-metrics "ttft,tpot,itl,e2el" \
+                      --dataset-name random \
+                      --ignore-eos \
+                      --max-concurrency $max_concurrency \
+                      --num-prompts $num_prompts \
+                      --random-input-len $in \
+                      --random-output-len $out \
+                      --trust-remote-code \
+                      --save-result \
+                      --result-filename ${model}_serving.json
+
+            .. note::
+
+               For improved performance with certain Mixture of Experts models, such as Mixtral 8x22B,
+               try adding ``export VLLM_ROCM_USE_AITER=1`` to your commands.
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block::
+
+                  OSError: You are trying to access a gated repo.
+
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Advanced usage
+==============
+
+For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
+see the developer's guide at `<https://github.com/ROCm/vllm/blob/documentation/docs/dev-docker/README.md>`__.
+
+Reproducing the Docker image
+----------------------------
+
+To reproduce this ROCm-enabled vLLM Docker image release, follow these steps:
+
+1. Clone the `vLLM repository <https://github.com/vllm-project/vllm>`__.
+
+   .. code-block:: shell
+
+      git clone https://github.com/vllm-project/vllm.git
+      cd vllm
+
+2. Use the following command to build the image directly from the specified commit.
+
+   .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.10.1_20251006-benchmark-models.yaml
+
+      {% set docker = data.dockers[0] %}
+      .. code-block:: shell
+
+         docker build -f docker/Dockerfile.rocm \
+             --build-arg REMOTE_VLLM=1 \
+             --build-arg VLLM_REPO=https://github.com/ROCm/vllm \
+             --build-arg VLLM_BRANCH="{{ docker.dockerfile.commit }}" \
+             -t vllm-rocm .
+
+   .. tip::
+
+      Replace ``vllm-rocm`` with your desired image tag.
+
+Further reading
+===============
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+  a brief introduction to vLLM and optimization strategies.
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`vllm-history` to find documentation for previous releases
+of the ``ROCm/vllm`` Docker image.

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

@@ -16,14 +16,23 @@ previous releases of the ``ROCm/vllm`` Docker image on `Docker Hub <https://hub.
      - Components
      - Resources
 
-   * - ``rocm/vllm:rocm7.0.0_vllm_0.10.2_20251006``
+   * - ``rocm/vllm:rocm7.0.0_vllm_0.11.1_20251024``
        (latest)
+     -
+       * ROCm 7.0.0
+       * vLLM 0.11.1
+       * PyTorch 2.9.0
+     -
+       * :doc:`Documentation <../vllm>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.10.2_20251006/images/sha256-94fd001964e1cf55c3224a445b1fb5be31a7dac302315255db8422d813edd7f5>`__
+
+   * - ``rocm/vllm:rocm7.0.0_vllm_0.10.2_20251006``
      -
        * ROCm 7.0.0
        * vLLM 0.10.2
        * PyTorch 2.9.0
      -
-       * :doc:`Documentation <../vllm>`
+       * :doc:`Documentation <vllm-0.10.2-20251006>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm7.0.0_vllm_0.10.2_20251006/images/sha256-94fd001964e1cf55c3224a445b1fb5be31a7dac302315255db8422d813edd7f5>`__
 
    * - ``rocm/vllm:rocm6.4.1_vllm_0.10.1_20250909``

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.10.rst

@@ -0,0 +1,396 @@
+.. meta::
+   :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using
+                 prebuilt and optimized docker images.
+   :keywords: xDiT, diffusion, video, video generation, image, image generation, validate, benchmark
+
+************************
+xDiT diffusion inference
+************************
+
+.. _xdit-video-diffusion:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.10-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker %}
+   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+
+   The `rocm/pytorch-xdit <{{ docker.docker_hub_url }}>`_ Docker image offers
+   a prebuilt, optimized inference environment based on `xDiT
+   <https://github.com/xdit-project/xDiT>`_ for benchmarking diffusion-based
+   video and image generation on AMD Instinct MI355X, MI350X (gfx950), MI325X,
+   and MI300X (gfx942) GPUs.
+   This image is based on ROCm {{docker.ROCm}} preview release via `TheRock <https://github.com/ROCm/TheRock>`_
+   and includes the following software components:
+
+   .. tab-set::
+
+      .. tab-item:: {{ docker.pull_tag }}
+
+         .. list-table::
+            :header-rows: 1
+
+            * - Software component
+              - Version
+
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}
+
+Follow this guide to pull the required image, spin up a container, download the model, and run a benchmark.
+For preview and development releases, see `amdsiloai/pytorch-xdit <https://hub.docker.com/r/amdsiloai/pytorch-xdit>`_.
+
+What's new
+==========
+
+- Initial ROCm-enabled xDiT Docker release for diffusion inference.
+- Supported architectures: gfx942 and gfx950 (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X).
+- Supported workloads: Wan 2.1, Wan 2.2, HunyuanVideo, and Flux models.
+
+.. _xdit-video-diffusion-supported-models:
+
+Supported models
+================
+
+The following models are supported for inference performance benchmarking.
+Some instructions, commands, and recommendations in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.10-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker %}
+   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+          <div class="row gx-0">
+              <div class="col-2 me-1 px-2 model-param-head">Model</div>
+              <div class="row col-10 pe-0">
+        {% for model_group in model_groups %}
+                  <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+        {% endfor %}
+              </div>
+          </div>
+
+          <div class="row gx-0 pt-1">
+              <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+              <div class="row col-10 pe-0">
+        {% for model_group in model_groups %}
+            {% set models = model_group.models %}
+            {% for model in models %}
+                {% if models|length == 1 %}
+                <div class="col-12 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+                {% else %}
+                <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+                {% endif %}
+            {% endfor %}
+        {% endfor %}
+              </div>
+          </div>
+      </div>
+
+   {% for model_group in model_groups %}
+       {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.mad_tag }}
+
+      .. note::
+
+         To learn more about your specific model see the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_
+         or visit the `GitHub page <{{ model.github }}>`__. Note that some models require access authorization before use via an
+         external license agreement through a third party.
+
+       {% endfor %}
+   {% endfor %}
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA
+auto-balancing, you can skip this step. Otherwise, complete the procedures in
+the `System validation and optimization
+<https://rocm.docs.amd.com/en/latest/how-to/rocm-for-ai/system-setup/prerequisite-system-validation.html>`__
+guide to properly configure your system settings before starting.
+
+Pull the Docker image
+=====================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.10-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker %}
+
+   For this tutorial, it's recommended to use the latest ``{{ docker.pull_tag }}`` Docker image.
+   Pull the image using the following command:
+
+   .. code-block:: shell
+
+      docker pull {{ docker.pull_tag }}
+
+Validate and benchmark
+======================
+
+Once the image has been downloaded you can follow these steps to
+run benchmarks and generate outputs.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.10-inference-models.yaml
+
+   {% set model_groups = data.xdit_diffusion_inference.model_groups %}
+   {% for model_group in model_groups %}
+     {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      The following commands are written for {{ model.model }}.
+      See :ref:`xdit-video-diffusion-supported-models` to switch to another available model.
+
+     {% endfor %}
+   {% endfor %}
+
+.. _xdit-video-diffusion-setup:
+
+Prepare the model
+-----------------
+
+.. note::
+
+   If you're using ROCm MAD to :ref:`run your model
+   <xdit-video-diffusion-run>`, you can skip this section. MAD will handle
+   starting the container and downloading required models inside the container.
+
+You can either use an existing Hugging Face cache or download the model fresh inside the container.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.10-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker %}
+   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+
+   {% for model_group in model_groups %}
+     {% for model in model_group.models %}
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: Option 1: Use existing Hugging Face cache
+
+            If you already have models downloaded on your host system, you can mount your existing cache.
+
+            1. Set your Hugging Face cache location.
+
+               .. code-block:: shell
+
+                  export HF_HOME=/your/hf_cache/location
+
+            2. Download the model (if not already cached).
+
+               .. code-block:: shell
+
+                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
+
+            3. Launch the container with mounted cache.
+
+               .. code-block:: shell
+
+                  docker run \
+                      -it --rm \
+                      --cap-add=SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --user root \
+                      --device=/dev/kfd \
+                      --device=/dev/dri \
+                      --group-add video \
+                      --ipc=host \
+                      --network host \
+                      --privileged \
+                      --shm-size 128G \
+                      --name pytorch-xdit \
+                      -e HSA_NO_SCRATCH_RECLAIM=1 \
+                      -e OMP_NUM_THREADS=16 \
+                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+                      -e HF_HOME=/app/huggingface_models \
+                      -v $HF_HOME:/app/huggingface_models \
+                      {{ docker.pull_tag }}
+
+         .. tab-item:: Option 2: Download inside container
+
+            If you prefer to keep the container self-contained or don't have an existing cache.
+
+            1. Launch the container
+
+               .. code-block:: shell
+
+                  docker run \
+                      -it --rm \
+                      --cap-add=SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --user root \
+                      --device=/dev/kfd \
+                      --device=/dev/dri \
+                      --group-add video \
+                      --ipc=host \
+                      --network host \
+                      --privileged \
+                      --shm-size 128G \
+                      --name pytorch-xdit \
+                      -e HSA_NO_SCRATCH_RECLAIM=1 \
+                      -e OMP_NUM_THREADS=16 \
+                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+                      {{ docker.pull_tag }}
+
+            2. Inside the container, set the Hugging Face cache location and download the model.
+
+               .. code-block:: shell
+
+                  export HF_HOME=/app/huggingface_models
+                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
+
+               .. warning::
+
+                  Models will be downloaded to the container's filesystem and will be lost when the container is removed unless you persist the data with a volume.
+     {% endfor %}
+   {% endfor %}
+
+.. _xdit-video-diffusion-run:
+
+Run inference
+=============
+
+You can benchmark models through `MAD <https://github.com/ROCm/MAD>`__-integrated automation or standalone
+torchrun commands.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_25.10-inference-models.yaml
+
+   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+   {% for model_group in model_groups %}
+     {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.mad_tag }}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. On the host machine, use this command to run the performance benchmark test on
+               the `{{model.model}} <{{ model.url }}>`_ model using one node.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{model.mad_tag}} \
+                      --keep-model-dir \
+                      --live-output
+                     
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
+            model are collected in the following paths: ``{{ model.mad_tag }}_throughput.csv``
+            and ``{{ model.mad_tag }}_serving.csv``.
+
+         .. tab-item:: Standalone benchmarking
+
+            To run the benchmarks for {{ model.model }}, use the following command:
+
+            .. code-block:: shell
+            {% if model.model == "Hunyuan Video" %}
+               cd /app/Hunyuanvideo
+               mkdir results
+
+               torchrun --nproc_per_node=8 run.py \
+                  --model tencent/HunyuanVideo \
+                  --prompt "In the large cage, two puppies were wagging their tails at each other." \
+                  --height 720 --width 1280 --num_frames 129 \
+                  --num_inference_steps 50 --warmup_steps 1 --n_repeats 1 \
+                  --ulysses_degree 8 \
+                  --enable_tiling --enable_slicing \
+                  --use_torch_compile \
+                  --bench_output results
+            {% endif %}
+            {% if model.model == "Wan2.1" %}
+               cd Wan2.1
+               mkdir results
+
+               torchrun --nproc_per_node=8 run.py \
+                  --task i2v-14B \
+                  --size 720*1280 --frame_num 81 \
+                  --ckpt_dir "${HF_HOME}/hub/models--Wan-AI--Wan2.1-I2V-14B-720P/snapshots/8823af45fcc58a8aa999a54b04be9abc7d2aac98/" \
+                  --image "/app/Wan2.1/examples/i2v_input.JPG" \
+                  --ulysses_size 8 --ring_size 1 \
+                  --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside." \
+                  --benchmark_output_directory results --save_file video.mp4 --num_benchmark_steps 1 \
+                  --offload_model 0 \
+                  --vae_dtype bfloat16 \
+                  --allow_tf32 \
+                  --compile
+            {% endif %}
+            {% if model.model == "Wan2.2" %}
+               cd Wan2.2
+               mkdir results
+
+               torchrun --nproc_per_node=8 run.py \
+                  --task i2v-A14B \
+                  --size 720*1280 --frame_num 81 \
+                  --ckpt_dir "${HF_HOME}/hub/models--Wan-AI--Wan2.2-I2V-A14B/snapshots/206a9ee1b7bfaaf8f7e4d81335650533490646a3/" \
+                  --image "/app/Wan2.2/examples/i2v_input.JPG" \
+                  --ulysses_size 8 --ring_size 1 \
+                  --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside." \
+                  --benchmark_output_directory results --save_file video.mp4 --num_benchmark_steps 1 \
+                  --offload_model 0 \
+                  --vae_dtype bfloat16 \
+                  --allow_tf32 \
+                  --compile
+            {% endif %}
+
+            {% if model.model == "FLUX.1" %}
+               cd Flux
+               mkdir results
+
+               torchrun --nproc_per_node=8 /app/Flux/run.py \
+                  --model black-forest-labs/FLUX.1-dev \
+                  --seed 42 \
+                  --prompt "A small cat" \
+                  --height 1024 \
+                  --width 1024 \
+                  --num_inference_steps 25 \
+                  --max_sequence_length 256 \
+                  --warmup_steps 5 \
+                  --no_use_resolution_binning \
+                  --ulysses_degree 8 \
+                  --use_torch_compile \
+                  --num_repetitions 1 \
+                  --benchmark_output_directory results
+
+            {% endif %}
+
+            The generated video will be stored under the results directory. For the actual benchmark step runtimes, see {% if model.model == "Hunyuan Video" %}stdout.{% elif model.model in ["Wan2.1", "Wan2.2"] %}results/outputs/rank0_*.json{% elif model.model == "FLUX.1" %}results/timing.json{% endif %}
+
+            {% if model.model == "FLUX.1" %}You may also use ``run_usp.py`` which implements USP without modifying the default diffusers pipeline. {% endif %}
+
+      {% endfor %}
+    {% endfor %}
+
+Further reading
+===============
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- For a list of other ready-made Docker images for AI with ROCm, see `AMD
+  Infinity Hub
+  <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`__.
+
+Previous versions
+=================
+
+See :doc:`xdit-history` to find documentation for previous releases
+of xDiT diffusion inference performance testing.

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

@@ -0,0 +1,56 @@
+:orphan:
+
+************************************************************
+xDiT diffusion inference performance testing version history
+************************************************************
+
+This table lists previous versions of the ROCm xDiT diffusion inference performance
+testing environment. For detailed information about available models for
+benchmarking, see the version-specific documentation.
+
+.. list-table::
+   :header-rows: 1
+
+   * - Docker image tag
+     - Components
+     - Resources
+
+   * - ``rocm/pytorch-xdit:v25.11`` (latest)
+     - 
+       * ROCm 7.10.0 preview
+       * 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
+     - 
+       * :doc:`Documentation <../../xdit-diffusion-inference>`
+       * `Docker Hub <https://hub.docker.com/r/rocm/pytorch-xdit>`__
+
+   * - ``rocm/pytorch-xdit:v25.10``
+     - 
+       * ROCm 7.9.0 preview
+       * 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
+     - 
+       * :doc:`Documentation <xdit-25.10>`
+       * `Docker Hub <https://hub.docker.com/r/rocm/pytorch-xdit>`__

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

@@ -6,7 +6,7 @@
 vLLM inference performance testing
 **********************************
 
-.. _vllm-benchmark-unified-docker-930:
+.. _vllm-benchmark-unified-docker-1024:
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
 
@@ -34,7 +34,7 @@ vLLM inference performance testing
             {% endfor %}
 
 With this Docker image, you can quickly test the :ref:`expected
-inference performance numbers <vllm-benchmark-performance-measurements-930>` for
+inference performance numbers <vllm-benchmark-performance-measurements-1024>` for
 AMD Instinct GPUs.
 
 What's new
@@ -42,27 +42,13 @@ What's new
 
 The following is summary of notable changes since the :doc:`previous ROCm/vLLM Docker release <previous-versions/vllm-history>`.
 
-* Added support for AMD Instinct MI355X and MI350X GPUs.
+* Enabled :ref:`AITER <vllm-optimization-aiter-switches>` by default.
 
-* Added support and benchmarking instructions for the following models. See :ref:`vllm-benchmark-supported-models-930`.
+* Fixed ``rms_norm`` segfault issue with Qwen 3 235B.
 
-  * Llama 4 Scout and Maverick
+* Known performance degradation on Llama 4 models due to `an upstream vLLM issue <https://github.com/vllm-project/vllm/issues/26320>`_.
 
-  * DeepSeek R1 0528 FP8
-
-  * MXFP4 models (MI355X and MI350X only): Llama 3.3 70B MXFP4 and Llama 3.1 405B MXFP4
-
-  * GPT OSS 20B and 120B
-
-  * Qwen 3 32B, 30B-A3B, and 235B-A22B
-
-* Removed the deprecated ``--max-seq-len-to-capture`` flag.
-
-* ``--gpu-memory-utilization`` is now configurable via the `configuration files
-  <https://github.com/ROCm/MAD/tree/develop/scripts/vllm/configs>`__ in the MAD
-  repository.
-
-.. _vllm-benchmark-supported-models-930:
+.. _vllm-benchmark-supported-models-1024:
 
 Supported models
 ================
@@ -72,7 +58,7 @@ Supported models
    {% set docker = data.dockers[0] %}
    {% set model_groups = data.model_groups %}
 
-   .. _vllm-benchmark-available-models-930:
+   .. _vllm-benchmark-available-models-1024:
 
    The following models are supported for inference performance benchmarking
    with vLLM and ROCm. Some instructions, commands, and recommendations in this
@@ -108,7 +94,7 @@ Supported models
          </div>
       </div>
 
-   .. _vllm-benchmark-vllm-930:
+   .. _vllm-benchmark-vllm-1024:
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
@@ -136,7 +122,7 @@ Supported models
       {% endfor %}
    {% endfor %}
 
-.. _vllm-benchmark-performance-measurements-930:
+.. _vllm-benchmark-performance-measurements-1024:
 
 Performance measurements
 ========================
@@ -192,7 +178,7 @@ Benchmarking
    Once the setup is complete, choose between two options to reproduce the
    benchmark results:
 
-   .. _vllm-benchmark-mad-930:
+   .. _vllm-benchmark-mad-1024:
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
@@ -204,7 +190,7 @@ Benchmarking
          .. tab-item:: MAD-integrated benchmarking
 
             The following run command is tailored to {{ model.model }}.
-            See :ref:`vllm-benchmark-supported-models-930` to switch to another available model.
+            See :ref:`vllm-benchmark-supported-models-1024` to switch to another available model.
 
             1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
                directory and install the required packages on the host machine.
@@ -233,7 +219,7 @@ Benchmarking
             and ``{{ model.mad_tag }}_serving.csv``.
 
             Although the :ref:`available models
-            <vllm-benchmark-available-models-930>` are preconfigured to collect
+            <vllm-benchmark-available-models-1024>` are preconfigured to collect
             offline throughput and online serving performance data, you can
             also change the benchmarking parameters. See the standalone
             benchmarking tab for more information.
@@ -258,7 +244,7 @@ Benchmarking
          .. tab-item:: Standalone benchmarking
 
             The following commands are optimized for {{ model.model }}.
-            See :ref:`vllm-benchmark-supported-models-930` to switch to another available model.
+            See :ref:`vllm-benchmark-supported-models-1024` to switch to another available model.
 
             .. seealso::
 
@@ -419,6 +405,10 @@ Advanced usage
 For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
 see the developer's guide at `<https://github.com/ROCm/vllm/blob/documentation/docs/dev-docker/README.md>`__.
 
+.. note::
+
+   If you’re using this Docker image on other AMD GPUs such as the AMD Instinct MI200 Series or Radeon, add ``export VLLM_ROCM_USE_AITER=0`` to your command, since AITER is only supported on gfx942 and gfx950 architectures.
+
 Reproducing the Docker image
 ----------------------------
 

docs/how-to/rocm-for-ai/inference/deploy-your-model.rst

@@ -22,7 +22,7 @@ See the `GitHub repository <https://github.com/vllm-project/vllm>`_ and `officia
 <https://docs.vllm.ai/>`_ for more information.
 
 For guidance on using vLLM with ROCm, refer to `Installation with ROCm
-<https://docs.vllm.ai/en/latest/getting_started/amd-installation.html>`_.
+<https://docs.vllm.ai/en/stable/getting_started/installation/gpu.html#amd-rocm>`__.
 
 vLLM installation
 -----------------

docs/how-to/rocm-for-ai/inference/index.rst

@@ -27,3 +27,6 @@ training, fine-tuning, and inference. It leverages popular machine learning fram
 - :doc:`SGLang inference performance testing <benchmark-docker/sglang>`
 
 - :doc:`Deploying your model <deploy-your-model>`
+
+- :doc:`xDiT diffusion inference <xdit-diffusion-inference>`
+

docs/how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst

@@ -0,0 +1,388 @@
+.. meta::
+   :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using
+                 prebuilt and optimized docker images.
+   :keywords: xDiT, diffusion, video, video generation, image, image generation, validate, benchmark
+
+************************
+xDiT diffusion inference
+************************
+
+.. _xdit-video-diffusion:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
+   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+
+   The `rocm/pytorch-xdit <{{ docker.docker_hub_url }}>`_ Docker image offers a prebuilt, optimized environment based on `xDiT <https://github.com/xdit-project/xDiT>`_ for
+   benchmarking diffusion model video and image generation on gfx942 and gfx950 series (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X) GPUs.
+   The image runs ROCm **{{docker.ROCm}}** (preview) based on `TheRock <https://github.com/ROCm/TheRock>`_
+   and includes the following components:
+
+   .. dropdown:: Software components
+
+      .. list-table::
+         :header-rows: 1
+
+         * - Software component
+           - Version
+
+         {% for component_name, component_version in docker.components.items() %}
+         * - {{ component_name }}
+           - {{ component_version }}
+         {% endfor %}
+
+Follow this guide to pull the required image, spin up a container, download the model, and run a benchmark.
+For preview and development releases, see `amdsiloai/pytorch-xdit <https://hub.docker.com/r/amdsiloai/pytorch-xdit>`_.
+
+What's new
+==========
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
+   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+
+   {% for item in docker.whats_new %}
+   * {{ item }}
+   {% endfor %}
+
+.. _xdit-video-diffusion-supported-models:
+
+Supported models
+================
+
+The following models are supported for inference performance benchmarking.
+Some instructions, commands, and recommendations in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
+   {% set model_groups = data.xdit_diffusion_inference.model_groups %}
+   
+   {# Create a lookup for supported models #}
+   {% set supported_lookup = {} %}
+   {% for supported in docker.supported_models %}
+   {% set _ = supported_lookup.update({supported.group: supported.models}) %}
+   {% endfor %}
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+          <div class="row gx-0">
+              <div class="col-2 me-1 px-2 model-param-head">Model</div>
+              <div class="row col-10 pe-0">
+        {% for model_group in model_groups %}
+            {% if model_group.group in supported_lookup %}
+                  <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+            {% endif %}
+        {% endfor %}
+              </div>
+          </div>
+
+          <div class="row gx-0 pt-1">
+              <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+              <div class="row col-10 pe-0">
+        {% for model_group in model_groups %}
+            {% if model_group.group in supported_lookup %}
+            {% set supported_models = supported_lookup[model_group.group] %}
+            {% set models = model_group.models %}
+            {% for model in models %}
+                {% if model.model in supported_models %}
+                {% if models|length % 3 == 0 %}
+                <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.page_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+                {% else %}
+                <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.page_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+                {% endif %}
+                {% endif %}
+            {% endfor %}
+            {% endif %}
+        {% endfor %}
+              </div>
+          </div>
+      </div>
+
+   {% for model_group in model_groups %}
+       {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.page_tag }}
+
+      .. note::
+
+         To learn more about your specific model see the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_
+         or visit the `GitHub page <{{ model.github }}>`__. Note that some models require access authorization before use via an
+         external license agreement through a third party.
+
+       {% endfor %}
+   {% endfor %}
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+Pull the Docker image
+=====================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
+
+   For this tutorial, it's recommended to use the latest ``{{ docker.pull_tag }}`` Docker image.
+   Pull the image using the following command:
+
+   .. code-block:: shell
+
+      docker pull {{ docker.pull_tag }}
+
+Validate and benchmark
+======================
+
+Once the image has been downloaded you can follow these steps to
+run benchmarks and generate outputs.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% for model_group in model_groups %}
+     {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.page_tag}}
+
+      The following commands are written for {{ model.model }}.
+      See :ref:`xdit-video-diffusion-supported-models` to switch to another available model.
+
+     {% endfor %}
+   {% endfor %}
+
+Choose your setup method
+------------------------
+
+You can either use an existing Hugging Face cache or download the model fresh inside the container.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set docker = data.xdit_diffusion_inference.docker | selectattr("version", "equalto", "v25-11") | first %}
+   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+
+   {% for model_group in model_groups %}
+     {% for model in model_group.models %}
+   .. container:: model-doc {{model.page_tag}}
+
+      .. tab-set::
+
+         .. tab-item:: Option 1: Use existing Hugging Face cache
+
+            If you already have models downloaded on your host system, you can mount your existing cache.
+
+            1. Set your Hugging Face cache location.
+
+               .. code-block:: shell
+
+                  export HF_HOME=/your/hf_cache/location
+
+            2. Download the model (if not already cached).
+
+               .. code-block:: shell
+
+                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
+
+            3. Launch the container with mounted cache.
+
+               .. code-block:: shell
+
+                  docker run \
+                      -it --rm \
+                      --cap-add=SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --user root \
+                      --device=/dev/kfd \
+                      --device=/dev/dri \
+                      --group-add video \
+                      --ipc=host \
+                      --network host \
+                      --privileged \
+                      --shm-size 128G \
+                      --name pytorch-xdit \
+                      -e HSA_NO_SCRATCH_RECLAIM=1 \
+                      -e OMP_NUM_THREADS=16 \
+                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+                      -e HF_HOME=/app/huggingface_models \
+                      -v $HF_HOME:/app/huggingface_models \
+                      {{ docker.pull_tag }}
+
+         .. tab-item:: Option 2: Download inside container
+
+            If you prefer to keep the container self-contained or don't have an existing cache.
+
+            1. Launch the container
+
+               .. code-block:: shell
+
+                  docker run \
+                      -it --rm \
+                      --cap-add=SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --user root \
+                      --device=/dev/kfd \
+                      --device=/dev/dri \
+                      --group-add video \
+                      --ipc=host \
+                      --network host \
+                      --privileged \
+                      --shm-size 128G \
+                      --name pytorch-xdit \
+                      -e HSA_NO_SCRATCH_RECLAIM=1 \
+                      -e OMP_NUM_THREADS=16 \
+                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+                      {{ docker.pull_tag }}
+
+            2. Inside the container, set the Hugging Face cache location and download the model.
+
+               .. code-block:: shell
+
+                  export HF_HOME=/app/huggingface_models
+                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
+
+               .. warning::
+
+                  Models will be downloaded to the container's filesystem and will be lost when the container is removed unless you persist the data with a volume.
+     {% endfor %}
+   {% endfor %}
+
+Run inference
+=============
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
+
+   {% set model_groups = data.xdit_diffusion_inference.model_groups%}
+   {% for model_group in model_groups %}
+     {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.page_tag }}
+
+      .. tab-set::
+
+         .. tab-item:: MAD-integrated benchmarking
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. On the host machine, use this command to run the performance benchmark test on
+               the `{{model.model}} <{{ model.url }}>`_ model using one node.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{model.mad_tag}} \
+                      --keep-model-dir \
+                      --live-output
+                     
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
+            model are collected in the following paths: ``{{ model.mad_tag }}_throughput.csv``
+            and ``{{ model.mad_tag }}_serving.csv``.
+
+         .. tab-item:: Standalone benchmarking
+
+            To run the benchmarks for {{ model.model }}, use the following command:
+
+            .. code-block:: shell
+            {% if model.model == "Hunyuan Video" %}
+               cd /app/Hunyuanvideo
+               mkdir results
+
+               torchrun --nproc_per_node=8 run.py \
+                  --model tencent/HunyuanVideo \
+                  --prompt "In the large cage, two puppies were wagging their tails at each other." \
+                  --height 720 --width 1280 --num_frames 129 \
+                  --num_inference_steps 50 --warmup_steps 1 --n_repeats 1 \
+                  --ulysses_degree 8 \
+                  --enable_tiling --enable_slicing \
+                  --use_torch_compile \
+                  --bench_output results
+            {% endif %}
+            {% if model.model == "Wan2.1" %}
+               cd Wan2.1
+               mkdir results
+
+               torchrun --nproc_per_node=8 run.py \
+                  --task i2v-14B \
+                  --size 720*1280 --frame_num 81 \
+                  --ckpt_dir "${HF_HOME}/hub/models--Wan-AI--Wan2.1-I2V-14B-720P/snapshots/8823af45fcc58a8aa999a54b04be9abc7d2aac98/" \
+                  --image "/app/Wan2.1/examples/i2v_input.JPG" \
+                  --ulysses_size 8 --ring_size 1 \
+                  --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside." \
+                  --benchmark_output_directory results --save_file video.mp4 --num_benchmark_steps 1 \
+                  --offload_model 0 \
+                  --vae_dtype bfloat16 \
+                  --allow_tf32 \
+                  --compile
+            {% endif %}
+            {% if model.model == "Wan2.2" %}
+               cd Wan2.2
+               mkdir results
+
+               torchrun --nproc_per_node=8 run.py \
+                  --task i2v-A14B \
+                  --size 720*1280 --frame_num 81 \
+                  --ckpt_dir "${HF_HOME}/hub/models--Wan-AI--Wan2.2-I2V-A14B/snapshots/206a9ee1b7bfaaf8f7e4d81335650533490646a3/" \
+                  --image "/app/Wan2.2/examples/i2v_input.JPG" \
+                  --ulysses_size 8 --ring_size 1 \
+                  --prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside." \
+                  --benchmark_output_directory results --save_file video.mp4 --num_benchmark_steps 1 \
+                  --offload_model 0 \
+                  --vae_dtype bfloat16 \
+                  --allow_tf32 \
+                  --compile
+            {% endif %}
+
+            {% if model.model == "FLUX.1" %}
+               cd Flux
+               mkdir results
+
+               torchrun --nproc_per_node=8 /app/Flux/run.py \
+                  --model black-forest-labs/FLUX.1-dev \
+                  --seed 42 \
+                  --prompt "A small cat" \
+                  --height 1024 \
+                  --width 1024 \
+                  --num_inference_steps 25 \
+                  --max_sequence_length 256 \
+                  --warmup_steps 5 \
+                  --no_use_resolution_binning \
+                  --ulysses_degree 8 \
+                  --use_torch_compile \
+                  --num_repetitions 1 \
+                  --benchmark_output_directory results
+
+            {% endif %}
+
+            The generated video will be stored under the results directory. For the actual benchmark step runtimes, see {% if model.model == "Hunyuan Video" %}stdout.{% elif model.model in ["Wan2.1", "Wan2.2"] %}results/outputs/rank0_*.json{% elif model.model == "FLUX.1" %}results/timing.json{% endif %}
+
+            {% if model.model == "FLUX.1" %}You may also use ``run_usp.py`` which implements USP without modifying the default diffusers pipeline. {% endif %}
+
+      {% endfor %}
+    {% endfor %}
+
+Previous versions
+=================
+
+See :doc:`benchmark-docker/previous-versions/xdit-history` to find documentation for previous releases
+of xDiT diffusion inference performance testing.

docs/how-to/rocm-for-ai/system-setup/multi-node-setup.rst

@@ -254,7 +254,7 @@ PyTorch training
    The ROCm PyTorch Training Docker image now focuses on :doc:`Training a model
    with Primus and PyTorch <../training/benchmark-docker/primus-pytorch>`. The
    following example refers to the legacy workflow :ref:`Training a
-   model with PyTorch <amd-pytorch-training-multinode-examples>`.
+   model with PyTorch <amd-pytorch-training-multinode-examples-v259>`.
 
 1. Download the ``run_multinode_train.sh`` benchmarking script from `<https://github.com/ROCm/MAD/tree/develop/scripts/pytorch_train>`__.
 
@@ -277,7 +277,7 @@ PyTorch training
 
 .. seealso::
 
-   See :ref:`Training a model with PyTorch <amd-pytorch-multinode-examples>` for more examples and information.
+   See :ref:`Training a model with PyTorch <amd-pytorch-training-multinode-examples-v259>` for more examples and information.
 
 Megatron-LM
 -----------

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

@@ -36,12 +36,10 @@ accelerate training workloads:
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
    .. tab-set::
 
-   {% for supported_gpus, docker in dockers.items() %}
-      .. tab-item:: {{ supported_gpus }}
-         :sync: {{ supported_gpus }}
+      .. tab-item:: {{ data.docker.pull_tag }}
+         :sync: {{ data.docker.pull_tag }}
 
          .. list-table::
             :header-rows: 1
@@ -49,12 +47,12 @@ accelerate training workloads:
             * - Software component
               - Version
 
-            {% for component_name, component_version in docker.components.items() %}
+            {% for component_name, component_version in data.docker.components.items() %}
             * - {{ component_name }}
               - {{ component_version }}
             {% endfor %}
-   {% endfor %}
-   .. _amd-megatron-lm-model-support:
+
+   .. _amd-megatron-lm-model-support-v2510:
 
    Supported models
    ================
@@ -99,7 +97,7 @@ accelerate training workloads:
    Some models, such as Llama, require an external license agreement through
    a third party (for example, Meta).
 
-.. _amd-megatron-lm-performance-measurements:
+.. _amd-megatron-lm-performance-measurements-v2510:
 
 Performance measurements
 ========================
@@ -131,7 +129,7 @@ To test for optimal performance, consult the recommended :ref:`System health ben
 <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
 system's configuration.
 
-.. _mi300x-amd-megatron-lm-training:
+.. _mi300x-amd-megatron-lm-training-v2510:
 
 Environment setup
 =================
@@ -140,52 +138,38 @@ Use the following instructions to set up the environment, configure the script t
 reproduce the benchmark results on MI300X Series GPUs with the AMD Megatron-LM Docker
 image.
 
-.. _amd-megatron-lm-requirements:
+.. _amd-megatron-lm-requirements-v2510:
 
 Download the Docker image
 -------------------------
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
+   {% set docker = data.docker %}
    1. Use the following command to pull the Docker image from Docker Hub.
 
-      .. tab-set::
+      .. code-block:: shell
 
-         {% for supported_gpus, docker in dockers.items() %}
-         .. tab-item:: {{ supported_gpus }}
-            :sync: {{ supported_gpus }}
-
-            .. code-block:: shell
-
-               docker pull {{ docker.pull_tag }}
-         {% endfor %}
+         docker pull {{ docker.pull_tag }}
 
    2. Launch the Docker container.
 
-      .. tab-set::
+      .. code-block:: shell
 
-         {% for supported_gpus, docker in dockers.items() %}
-         .. tab-item:: {{ supported_gpus }}
-            :sync: {{ supported_gpus }}
-
-            .. code-block:: shell
-
-               docker run -it \
-                   --device /dev/dri \
-                   --device /dev/kfd \
-                   --device /dev/infiniband \
-                   --network host --ipc host \
-                   --group-add video \
-                   --cap-add SYS_PTRACE \
-                   --security-opt seccomp=unconfined \
-                   --privileged \
-                   -v $HOME:$HOME \
-                   -v $HOME/.ssh:/root/.ssh \
-                   --shm-size 128G \
-                   --name megatron_training_env \
-                   {{ docker.pull_tag }}
-         {% endfor %}
+         docker run -it \
+             --device /dev/dri \
+             --device /dev/kfd \
+             --device /dev/infiniband \
+             --network host --ipc host \
+             --group-add video \
+             --cap-add SYS_PTRACE \
+             --security-opt seccomp=unconfined \
+             --privileged \
+             -v $HOME:$HOME \
+             -v $HOME/.ssh:/root/.ssh \
+             --shm-size 128G \
+             --name megatron_training_env \
+             {{ docker.pull_tag }}
 
 3. Use these commands if you exit the ``megatron_training_env`` container and need to return to it.
 
@@ -206,7 +190,7 @@ Download the Docker image
 The Docker container hosts a verified commit of
 `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev>`__.
 
-.. _amd-megatron-lm-environment-setup:
+.. _amd-megatron-lm-environment-setup-v2510:
 
 Configuration
 =============
@@ -216,39 +200,39 @@ Configuration
    Update the ``train_llama3.sh`` configuration script in the ``examples/llama``
    directory of
    `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev/examples/llama>`__ to configure your training run.
-   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training>`.
+   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training-v2510>`.
 
 .. container:: model-doc pyt_megatron_lm_train_llama-2-7b pyt_megatron_lm_train_llama-2-70b
 
    Update the ``train_llama2.sh`` configuration script in the ``examples/llama``
    directory of
    `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev/examples/llama>`__ to configure your training run.
-   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training>`.
+   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training-v2510>`.
 
 .. container:: model-doc pyt_megatron_lm_train_deepseek-v3-proxy
 
    Update the ``train_deepseekv3.sh`` configuration script in the ``examples/deepseek_v3``
    directory of
    `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev/examples/deepseek_v3>`__ to configure your training run.
-   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training>`.
+   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training-v2510>`.
 
 .. container:: model-doc pyt_megatron_lm_train_deepseek-v2-lite-16b
 
    Update the ``train_deepseekv2.sh`` configuration script in the ``examples/deepseek_v2``
    directory of
    `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev/examples/deepseek_v2>`__ to configure your training run.
-   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training>`.
+   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training-v2510>`.
 
 .. container:: model-doc pyt_megatron_lm_train_mixtral-8x7b pyt_megatron_lm_train_mixtral-8x22b-proxy
 
    Update the ``train_mixtral_moe.sh`` configuration script in the ``examples/mixtral``
    directory of
    `<https://github.com/ROCm/Megatron-LM/tree/rocm_dev/examples/mixtral>`__ to configure your training run.
-   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training>`.
+   Options can also be passed as command line arguments as described in :ref:`Run training <amd-megatron-lm-run-training-v2510>`.
 
 .. note::
 
-   See :ref:`Key options <amd-megatron-lm-benchmark-test-vars>` for more information on configuration options.
+   See :ref:`Key options <amd-megatron-lm-benchmark-test-vars-v2510>` for more information on configuration options.
 
 Multi-node configuration
 ------------------------
@@ -256,7 +240,7 @@ Multi-node configuration
 Refer to :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your environment for multi-node
 training. See :ref:`amd-megatron-lm-multi-node-examples` for example run commands.
 
-.. _amd-megatron-lm-tokenizer:
+.. _amd-megatron-lm-tokenizer-v2510:
 
 Tokenizer
 ---------
@@ -393,7 +377,7 @@ Download the dataset
 
    ``TOKENIZER_MODEL`` can be any accessible Hugging Face tokenizer.
    Remember to either pre-download the tokenizer or setup Hugging Face access
-   otherwise when needed -- see the :ref:`Tokenizer <amd-megatron-lm-tokenizer>` section.
+   otherwise when needed -- see the :ref:`Tokenizer <amd-megatron-lm-tokenizer-v2510>` section.
 
    .. note::
 
@@ -495,15 +479,38 @@ Download the dataset
 
    Ensure that the files are accessible inside the Docker container.
 
-.. _amd-megatron-lm-run-training:
+.. _amd-megatron-lm-run-training-v2510:
 
 Run training
 ============
 
 Use the following example commands to set up the environment, configure
-:ref:`key options <amd-megatron-lm-benchmark-test-vars>`, and run training on
+:ref:`key options <amd-megatron-lm-benchmark-test-vars-v2510>`, and run training on
 MI300X Series GPUs with the AMD Megatron-LM environment.
 
+Before starting training, export the following environment variables.
+
+.. tab-set::
+
+   .. tab-item:: MI355X and MI350X
+
+      .. code-block:: shell
+
+         export HSA_NO_SCRATCH_RECLAIM=1
+         export NVTE_CK_USES_BWD_V3=1
+         export NVTE_CK_USES_BWD_V3=1
+
+   .. tab-item:: MI325X and MI300X
+
+      .. code-block:: shell
+
+         export HSA_NO_SCRATCH_RECLAIM=1
+         export NVTE_CK_USES_BWD_V3=1
+         export NVTE_CK_USES_BWD_V3=1
+
+         # Set this on MI325X/MI300X only
+         export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
 Single node training
 --------------------
 
@@ -913,7 +920,7 @@ Single node training
           RECOMPUTE_ACTIVATIONS=full \
           CKPT_FORMAT=torch_dist
 
-.. _amd-megatron-lm-multi-node-examples:
+.. _amd-megatron-lm-multi-node-examples-v2510:
 
 Multi-node training examples
 ----------------------------
@@ -964,7 +971,7 @@ training on 16 nodes, try the following command:
 
    sbatch examples/deepseek_v3/train_deepseek_v3_slurm.sh
 
-.. _amd-megatron-lm-benchmark-test-vars:
+.. _amd-megatron-lm-benchmark-test-vars-v2510:
 
 Key options
 -----------
@@ -1029,11 +1036,6 @@ The benchmark tests support the following sets of variables.
 ``RECOMPUTE_NUM_LAYERS``
   Number of layers used for checkpointing recompute.
 
-Known issues
-============
-
-PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
-
 Previous versions
 =================
 

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

@@ -16,14 +16,23 @@ previous releases of the ``ROCm/megatron-lm`` Docker image on `Docker Hub <https
      - Components
      - Resources
 
-   * - v25.9 (latest)
+   * - v25.10 (latest)
+     -
+       * ROCm 7.1.0
+       * PyTorch 2.10.0.dev20251112+rocm7.1
+     -
+       * :doc:`Primus Megatron documentation <../primus-megatron>`
+       * :doc:`Megatron-LM (legacy) documentation <../megatron-lm>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197>`__
+
+   * - v25.9
      -
        * ROCm 7.0.0
        * Primus 0.3.0
        * PyTorch 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
      -
-       * :doc:`Primus Megatron documentation <../primus-megatron>`
-       * :doc:`Megatron-LM (legacy) documentation <../megatron-lm>`
+       * :doc:`Primus Megatron documentation <primus-megatron-v25.9>`
+       * :doc:`Megatron-LM (legacy) documentation <megatron-lm-v25.9>`
        * `Docker Hub (gfx950) <https://hub.docker.com/layers/rocm/primus/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6>`__
        * `Docker Hub (gfx942) <https://hub.docker.com/layers/rocm/primus/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357>`__
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-pytorch-v25.9.rst

@@ -0,0 +1,574 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using PyTorch for ROCm.
+   :keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
+
+****************************************
+Training a model with Primus and PyTorch
+****************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm Primus PyTorch training
+   performance benchmark documentation. See :doc:`../primus-pytorch` for the latest version.
+
+`Primus <https://github.com/AMD-AGI/Primus>`__ is a unified and flexible
+LLM training framework designed to streamline training. It streamlines LLM
+training on AMD Instinct GPUs using a modular, reproducible configuration paradigm.
+Primus now supports the PyTorch torchtitan backend.
+
+.. note::
+
+   For a unified training solution on AMD GPUs with ROCm, the `rocm/pytorch-training
+   <https://hub.docker.com/r/rocm/pytorch-training/>`__ Docker Hub registry will be
+   deprecated soon in favor of `rocm/primus <https://hub.docker.com/r/rocm/primus>`__.
+   The ``rocm/primus`` Docker containers will cover PyTorch training ecosystem frameworks,
+   including torchtitan and :doc:`Megatron-LM <../primus-megatron>`.
+
+   Primus with the PyTorch torchtitan backend is designed to replace the
+   :doc:`ROCm PyTorch training <../pytorch-training>` workflow. See
+   :doc:`../pytorch-training` to see steps to run workloads without Primus.
+
+AMD provides a ready-to-use Docker image for MI355X, MI350X, MI325X, and
+MI300X GPUs containing essential components for Primus and PyTorch training
+with Primus Turbo optimizations.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.9-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   .. tab-set::
+
+   {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}
+
+         .. list-table::
+            :header-rows: 1
+
+            * - Software component
+              - Version
+
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}
+   {% endfor %}
+
+.. _amd-primus-pytorch-model-support-v259:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
+Some instructions, commands, and training recommendations in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.9-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-12 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+.. seealso::
+
+   For additional workloads, including Llama 3.3, Llama 3.2, Llama 2, GPT OSS, Qwen, and Flux models,
+   see the documentation :doc:`../pytorch-training` (without Primus)
+
+.. _amd-primus-pytorch-performance-measurements-v259:
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+This Docker image is optimized for specific model configurations outlined
+below. Performance can vary for other training workloads, as AMD
+doesn’t test configurations and run conditions outside those described.
+
+Pull the Docker image
+=====================
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.9-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. tab-set::
+
+      {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}
+
+         .. code-block:: shell
+
+            docker pull {{ docker.pull_tag }}
+      {% endfor %}
+
+Run training
+============
+
+Once the setup is complete, choose between the following two workflows to start benchmarking training.
+For fine-tuning workloads and multi-node training examples, see :doc:`../pytorch-training` (without Primus).
+For best performance on MI325X, MI350X, and MI355X GPUs, you might need to
+tweak some configurations (such as batch sizes).
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.9-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set model_groups = data.model_groups %}
+
+   .. tab-set::
+
+      .. tab-item:: MAD-integrated benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. For example, use this command to run the performance benchmark test on the {{ model.model }} model
+               using one node with the {{ model.precision }} data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{ model.mad_tag }} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+               MAD launches a Docker container with the name
+               ``container_ci-{{ model.mad_tag }}``. The latency and throughput reports of the
+               model are collected in ``~/MAD/perf.csv``.
+
+               .. note::
+
+                  Currently, Primus torchtitan models are run with Primus Turbo
+                  enabled for enhanced performance. To disable Primus Turbo,
+                  modify respective configuration file
+                  ``scripts/primus/pytorch_train/primus_torchtitan_scripts/llama3_[8B|70B]-[BF16|FP8].yaml``.
+
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Primus benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run commands are tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
+
+            .. rubric:: Download the Docker image and required packages
+
+            1. Pull the appropriate Docker image for your AMD GPU architecture from Docker Hub.
+
+               .. tab-set::
+
+                  {% for supported_gpus, docker in dockers.items() %}
+                  .. tab-item:: {{ supported_gpus }}
+                     :sync: {{ supported_gpus }}
+
+                     .. code-block:: shell
+
+                        docker pull {{ docker.pull_tag }}
+                  {% endfor %}
+
+            2. Run the Docker container.
+
+               .. tab-set::
+
+                  {% for supported_gpus, docker in dockers.items() %}
+                  .. tab-item:: {{ supported_gpus }}
+                     :sync: {{ supported_gpus }}
+
+                     .. code-block:: shell
+
+                        docker run -it \
+                            --device /dev/dri \
+                            --device /dev/kfd \
+                            --network host \
+                            --ipc host \
+                            --group-add video \
+                            --cap-add SYS_PTRACE \
+                            --security-opt seccomp=unconfined \
+                            --privileged \
+                            -v $HOME:$HOME \
+                            -v $HOME/.ssh:/root/.ssh \
+                            --shm-size 64G \
+                            --name training_env \
+                            {{ docker.pull_tag }}
+                  {% endfor %}
+
+               Use these commands if you exit the ``training_env`` container and need to return to it.
+
+               .. code-block:: shell
+
+                  docker start training_env
+                  docker exec -it training_env bash
+
+            .. rubric:: Prepare training datasets and dependencies
+
+            The following benchmarking examples require downloading models and datasets
+            from Hugging Face. To ensure successful access to gated repos, set your
+            ``HF_TOKEN``.
+
+            .. code-block:: shell
+
+               export HF_TOKEN=$your_personal_hugging_face_access_token
+
+            .. rubric:: Pretraining
+
+            To get started, navigate to the ``Primus`` directory in your container.
+
+            .. code-block::
+
+               cd /workspace/Primus
+
+            Now, to start the pretraining benchmark, use the ``run_pretrain.sh`` script
+            included with Primus with the appropriate options.
+
+            .. rubric:: Benchmarking examples
+
+            .. container:: model-doc primus_pyt_train_llama-3.1-8b
+
+               Use the following command to run train Llama 3.1 8B with BF16 precision using Primus torchtitan.
+
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 5
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 6
+
+                  .. tab-item:: MI300X
+                     :sync: MI325X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 4
+
+
+               To train Llama 3.1 8B with FP8 precision, use the following command.
+
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 8
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 7
+
+                  .. tab-item:: MI300X
+                     :sync: MI325X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 5
+
+            .. container:: model-doc primus_pyt_train_llama-3.1-70b
+
+               Use the following command to run train Llama 3.1 70B with BF16 precision using Primus torchtitan.
+
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 8
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 6
+
+                  .. tab-item:: MI300X
+                     :sync: MI325X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 4
+
+               To train Llama 3.1 70B with FP8 precision, use the following command.
+
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 6
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 5
+
+                  .. tab-item:: MI300X
+                     :sync: MI325X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 3
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Standalone torchtitan benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run commands are tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
+
+            .. rubric:: Download the Docker image and required packages
+
+            1. Pull the appropriate Docker image for your AMD GPU architecture from Docker Hub.
+
+               .. tab-set::
+
+                  {% for supported_gpus, docker in dockers.items() %}
+                  .. tab-item:: {{ supported_gpus }}
+                     :sync: {{ supported_gpus }}
+
+                     .. code-block:: shell
+
+                        docker pull {{ docker.pull_tag }}
+                  {% endfor %}
+
+            2. Run the Docker container.
+
+               .. tab-set::
+
+                  {% for supported_gpus, docker in dockers.items() %}
+                  .. tab-item:: {{ supported_gpus }}
+                     :sync: {{ supported_gpus }}
+
+                     .. code-block:: shell
+
+                        docker run -it \
+                            --device /dev/dri \
+                            --device /dev/kfd \
+                            --network host \
+                            --ipc host \
+                            --group-add video \
+                            --cap-add SYS_PTRACE \
+                            --security-opt seccomp=unconfined \
+                            --privileged \
+                            -v $HOME:$HOME \
+                            -v $HOME/.ssh:/root/.ssh \
+                            --shm-size 64G \
+                            --name training_env \
+                            {{ docker.pull_tag }}
+                  {% endfor %}
+
+               Use these commands if you exit the ``training_env`` container and need to return to it.
+
+               .. code-block:: shell
+
+                  docker start training_env
+                  docker exec -it training_env bash
+
+            3. Navigate to the ``torchtitan`` workspace directory.
+
+               .. code-block:: shell
+
+                  cd /workspace/torchtitan
+
+            .. rubric:: Download the tokenizer
+
+            1. The following benchmarking examples require downloading models and datasets
+               from Hugging Face. To ensure successful access to gated repos, set your
+               ``HF_TOKEN``.
+
+               .. code-block:: shell
+
+                  export HF_TOKEN=$your_personal_hugging_face_access_token
+
+            2. Download the tokenizer for your model.
+
+               .. container:: model-doc {{ model.mad_tag }}
+
+                  .. code-block:: shell
+
+                     python3 scripts/download_tokenizer.py \
+                        --repo_id {{ model.model_repo }} \
+                        --tokenizer_path "original" \
+                        --hf_token=${HF_TOKEN}
+
+            .. rubric:: Pretraining examples
+
+            Run the training script with the appropriate configuration file.
+
+            For train with BF16 precicion, use the following command:
+
+            .. container:: model-doc {{ model.mad_tag }}
+
+               .. code-block:: shell
+
+                  CONFIG_FILE={{ model.config_file.bf16 }} \
+                  .run_train.sh
+
+            For train with BF16 precicion, use the following command:
+
+            .. container:: model-doc {{ model.mad_tag }}
+
+               .. code-block:: shell
+
+                  CONFIG_FILE={{ model.config_file.fp8 }} \
+                  .run_train.sh
+      {% endfor %}
+   {% endfor %}
+
+Known issues
+============
+
+PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
+
+
+Further reading
+===============
+
+- For an introduction to Primus, see `Primus: A Lightweight, Unified Training
+  Framework for Large Models on AMD GPUs <https://rocm.blogs.amd.com/software-tools-optimization/primus/README.html>`__.
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`pytorch-training-history` to find documentation for previous releases
+of the ``ROCm/pytorch-training`` Docker image.

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

@@ -16,14 +16,23 @@ previous releases of the ``ROCm/pytorch-training`` Docker image on `Docker Hub <
      - Components
      - Resources
 
-   * - v25.9 (latest)
+   * - v25.10 (latest)
+     -
+       * ROCm 7.1.0
+       * PyTorch 2.10.0.dev20251112+rocm7.1
+     -
+       * :doc:`Primus PyTorch Training documentation <../primus-pytorch>`
+       * :doc:`PyTorch training (legacy) documentation <../pytorch-training>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197>`__
+
+   * - v25.9
      -
        * ROCm 7.0.0
        * Primus 0.3.0
        * PyTorch 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
      -
-       * :doc:`Primus PyTorch Training documentation <../primus-pytorch>`
-       * :doc:`PyTorch training (legacy) documentation <../pytorch-training>`
+       * :doc:`Primus PyTorch Training documentation <primus-pytorch-v25.9>`
+       * :doc:`PyTorch training (legacy) documentation <pytorch-training-v25.9>`
        * `Docker Hub (gfx950) <https://hub.docker.com/layers/rocm/primus/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6>`__
        * `Docker Hub (gfx942) <https://hub.docker.com/layers/rocm/primus/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357>`__
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.6.rst

@@ -240,7 +240,7 @@ The following models are pre-optimized for performance on the AMD Instinct MI325
                  - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
 
                * - ``torchdata``
-                 - `TorchData <https://pytorch.org/data/beta/index.html>`_
+                 - `TorchData <https://meta-pytorch.org/data/beta/index.html>`_
 
                * - ``tomli``
                  - `Tomli <https://pypi.org/project/tomli/>`_

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.9.rst

@@ -0,0 +1,667 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using PyTorch for ROCm.
+   :keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
+
+**************************************
+Training a model with PyTorch on ROCm
+**************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm PyTorch training
+   performance benchmark documentation. See :doc:`../pytorch-training` for the latest version.
+
+.. note::
+
+   For a unified training solution on AMD GPUs with ROCm, the `rocm/pytorch-training
+   <https://hub.docker.com/r/rocm/pytorch-training/>`__ Docker Hub registry will be
+   deprecated soon in favor of `rocm/primus <https://hub.docker.com/r/rocm/primus>`__.
+   The ``rocm/primus`` Docker containers will cover PyTorch training ecosystem frameworks,
+   including torchtitan and :doc:`Megatron-LM <../primus-megatron>`.
+
+   See :doc:`../primus-pytorch` for details.
+
+PyTorch is an open-source machine learning framework that is widely used for
+model training with GPU-optimized components for transformer-based models.
+The PyTorch for ROCm training Docker image provides a prebuilt optimized
+environment for fine-tuning and pretraining a model on AMD Instinct MI325X
+and MI300X GPUs. It includes the following software components to accelerate
+training workloads:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.9-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   .. tab-set::
+
+   {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}
+
+         .. list-table::
+            :header-rows: 1
+
+            * - Software component
+              - Version
+
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}
+   {% endfor %}
+
+.. _amd-pytorch-training-model-support-v259:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on the AMD Instinct
+MI355X, MI350X, MI325X, and MI300X GPUs. Some instructions, commands, and
+training recommendations in this documentation might vary by model -- select
+one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.9-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+.. _amd-pytorch-training-supported-training-modes-v259:
+
+The following table lists supported training modes per model.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.9-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   .. dropdown:: Supported training modes
+
+      .. list-table::
+         :header-rows: 1
+
+         * - Model
+           - Supported training modes
+
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+         {% if model.training_modes %}
+         * - {{ model.model }}
+           - ``{{ model.training_modes | join('``, ``') }}``
+
+         {% endif %}
+         {% endfor %}
+      {% endfor %}
+
+      .. note::
+
+         Some model and fine-tuning combinations are not listed. This is
+         because the `upstream torchtune repository <https://github.com/pytorch/torchtune>`__
+         doesn't provide default YAML configurations for them.
+         For advanced usage, you can create a custom configuration to enable
+         unlisted fine-tuning methods by using an existing file in the
+         ``/workspace/torchtune/recipes/configs`` directory as a template.
+
+.. _amd-pytorch-training-performance-measurements-v259:
+
+Performance measurements
+========================
+
+To evaluate performance, the
+`Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
+page provides reference throughput and latency measurements for training
+popular AI models.
+
+.. note::
+
+   The performance data presented in
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
+   should not be interpreted as the peak performance achievable by AMD
+   Instinct MI325X and MI300X GPUs or ROCm software.
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+This Docker image is optimized for specific model configurations outlined
+below. Performance can vary for other training workloads, as AMD
+doesn’t test configurations and run conditions outside those described.
+
+Run training
+============
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.9-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set model_groups = data.model_groups %}
+
+   Once the setup is complete, choose between two options to start benchmarking training:
+
+   .. tab-set::
+
+      .. tab-item:: MAD-integrated benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`amd-pytorch-training-model-support-v259` to switch to another available model.
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. For example, use this command to run the performance benchmark test on the {{ model.model }} model
+               using one node with the {{ model.precision }} data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{ model.mad_tag }} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+               MAD launches a Docker container with the name
+               ``container_ci-{{ model.mad_tag }}``. The latency and throughput reports of the
+               model are collected in ``~/MAD/perf.csv``.
+
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Standalone benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following commands are tailored to {{ model.model }}.
+            See :ref:`amd-pytorch-training-model-support-v259` to switch to another available model.
+
+      {% endfor %}
+   {% endfor %}
+
+         .. rubric:: Download the Docker image and required packages
+
+         1. Use the following command to pull the Docker image from Docker Hub.
+
+            .. tab-set::
+
+               {% for supported_gpus, docker in dockers.items() %}
+               .. tab-item:: {{ supported_gpus }}
+                  :sync: {{ supported_gpus }}
+
+                  .. code-block:: shell
+
+                     docker pull {{ docker.pull_tag }}
+               {% endfor %}
+
+         2. Launch the Docker container.
+
+            .. tab-set::
+
+               {% for supported_gpus, docker in dockers.items() %}
+               .. tab-item:: {{ supported_gpus }}
+                  :sync: {{ supported_gpus }}
+
+                  .. code-block:: shell
+
+                     docker run -it \
+                         --device /dev/dri \
+                         --device /dev/kfd \
+                         --network host \
+                         --ipc host \
+                         --group-add video \
+                         --cap-add SYS_PTRACE \
+                         --security-opt seccomp=unconfined \
+                         --privileged \
+                         -v $HOME:$HOME \
+                         -v $HOME/.ssh:/root/.ssh \
+                         --shm-size 64G \
+                         --name training_env \
+                         {{ docker.pull_tag }}
+               {% endfor %}
+
+            Use these commands if you exit the ``training_env`` container and need to return to it.
+
+            .. code-block:: shell
+
+               docker start training_env
+               docker exec -it training_env bash
+
+         3. In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
+            repository and navigate to the benchmark scripts directory
+            ``/workspace/MAD/scripts/pytorch_train``.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/pytorch_train
+
+         .. rubric:: Prepare training datasets and dependencies
+
+         1. The following benchmarking examples require downloading models and datasets
+            from Hugging Face. To ensure successful access to gated repos, set your
+            ``HF_TOKEN``.
+
+            .. code-block:: shell
+
+               export HF_TOKEN=$your_personal_hugging_face_access_token
+
+         2. Run the setup script to install libraries and datasets needed for benchmarking.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_setup.sh
+
+            .. container:: model-doc pyt_train_llama-3.1-8b
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 8B:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``accelerate``
+                    - `Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
+
+            .. container:: model-doc pyt_train_llama-3.1-70b
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 70B:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
+
+                  * - ``torchdata``
+                    - `TorchData <https://meta-pytorch.org/data/beta/index.html#torchdata>`__
+
+                  * - ``tomli``
+                    - `Tomli <https://pypi.org/project/tomli/>`__
+
+                  * - ``tiktoken``
+                    - `tiktoken <https://github.com/openai/tiktoken>`__
+
+                  * - ``blobfile``
+                    - `blobfile <https://pypi.org/project/blobfile/>`__
+
+                  * - ``tabulate``
+                    - `tabulate <https://pypi.org/project/tabulate/>`__
+
+                  * - ``wandb``
+                    - `Weights & Biases <https://github.com/wandb/wandb>`__
+
+                  * - ``sentencepiece``
+                    - `SentencePiece <https://github.com/google/sentencepiece>`__ 0.2.0
+
+                  * - ``tensorboard``
+                    - `TensorBoard <https://www.tensorflow.org/tensorboard>`__ 2.18.0
+
+            .. container:: model-doc pyt_train_flux
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for FLUX:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``accelerate``
+                    - `Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`__ 3.2.0
+
+                  * - ``sentencepiece``
+                    - `SentencePiece <https://github.com/google/sentencepiece>`__ 0.2.0
+
+                  * - ``tensorboard``
+                    - `TensorBoard <https://www.tensorflow.org/tensorboard>`__ 2.18.0
+
+                  * - ``csvkit``
+                    - `csvkit <https://csvkit.readthedocs.io/en/latest/>`__ 2.0.1
+
+                  * - ``deepspeed``
+                    - `DeepSpeed <https://github.com/deepspeedai/DeepSpeed>`__ 0.16.2
+
+                  * - ``diffusers``
+                    - `Hugging Face Diffusers <https://huggingface.co/docs/diffusers/en/index>`__ 0.31.0
+
+                  * - ``GitPython``
+                    - `GitPython <https://github.com/gitpython-developers/GitPython>`__ 3.1.44
+
+                  * - ``opencv-python-headless``
+                    - `opencv-python-headless <https://pypi.org/project/opencv-python-headless/>`__ 4.10.0.84
+
+                  * - ``peft``
+                    - `PEFT <https://huggingface.co/docs/peft/en/index>`__ 0.14.0
+
+                  * - ``protobuf``
+                    - `Protocol Buffers <https://github.com/protocolbuffers/protobuf>`__ 5.29.2
+
+                  * - ``pytest``
+                    - `PyTest <https://docs.pytest.org/en/stable/>`__ 8.3.4
+
+                  * - ``python-dotenv``
+                    - `python-dotenv <https://pypi.org/project/python-dotenv/>`__ 1.0.1
+
+                  * - ``seaborn``
+                    - `Seaborn <https://seaborn.pydata.org/>`__ 0.13.2
+
+                  * - ``transformers``
+                    - `Transformers <https://huggingface.co/docs/transformers/en/index>`__ 4.47.0
+
+            ``pytorch_benchmark_setup.sh`` downloads the following datasets from Hugging Face:
+
+            * `frank-chieng/chinese_architecture_siheyuan <https://huggingface.co/datasets/frank-chieng/chinese_architecture_siheyuan>`__
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+         {% set training_modes = model.training_modes %}
+         {% set training_mode_descs = {
+            "pretrain": "Benchmark pre-training.",
+            "HF_pretrain": "Llama 3.1 8B pre-training with FP8 precision."
+         } %}
+         {% set available_modes = training_modes | select("in", ["pretrain", "HF_pretrain"]) | list %}
+         {% if available_modes %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Pre-training
+
+            To start the pre-training benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t {% if available_modes | length == 1 %}{{ available_modes[0] }}{% else %}$training_mode{% endif %} \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+            {% if model.mad_tag == "pyt_train_flux" %}
+            .. container:: model-doc {{ model.mad_tag }}
+
+               .. note::
+
+                  Currently, FLUX models are not supported out-of-the-box on this Docker.
+                  To use FLUX, refer to ``rocm/pytorch-training`` Docker: :doc:`previous-versions/pytorch-training-v25.6`
+
+                  Occasionally, downloading the Flux dataset might fail. In the event of this
+                  error, manually download it from Hugging Face at
+                  `black-forest-labs/FLUX.1-dev <https://huggingface.co/black-forest-labs/FLUX.1-dev>`_
+                  and save it to `/workspace/FluxBenchmark`. This ensures that the test script can access
+                  the required dataset.
+            {% endif %}
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if model.mad_tag == "pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+         {% endif %}
+
+         {% set training_modes = model.training_modes %}
+         {% set training_mode_descs = {
+            "posttrain": "Benchmark post-training.",
+         } %}
+         {% set available_modes = training_modes | select("in", ["posttrain"]) | list %}
+         {% if available_modes %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Post-training
+
+            To start the post-training benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t {% if available_modes | length == 1 %}{{ available_modes[0] }}{% else %}$training_mode{% endif %} \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if model.mad_tag == "pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+         {% endif %}
+
+         {% set training_mode_descs = {
+            "finetune_fw": "Full weight fine-tuning (BF16 and FP8 supported).",
+            "finetune_lora": "LoRA fine-tuning (BF16 supported).",
+            "finetune_qlora": "QLoRA fine-tuning (BF16 supported).",
+            "HF_finetune_lora": "LoRA fine-tuning with Hugging Face PEFT.",
+         } %}
+         {% set available_modes = training_modes | select("in", ["finetune_fw", "finetune_lora", "finetune_qlora", "HF_finetune_lora"]) | list %}
+         {% if available_modes %}
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Fine-tuning
+
+            To start the fine-tuning benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+            See :ref:`supported training modes <amd-pytorch-training-supported-training-modes-v259>`.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t $training_mode \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if "finetune_fw" in available_modes %} or ``FP8``{% endif %}
+                 - All models support BF16.{% if "finetune_fw" in available_modes %} FP8 is only available for full weight fine-tuning.{% endif %}
+
+               * - ``$sequence_length``
+                 - Between 2048 and 16384.
+                 - Sequence length for the language model.
+
+            {% if model.mad_tag in ["pyt_train_llama3.2-vision-11b", "pyt_train_llama-3.2-vision-90b"] %}
+            .. note::
+
+               For LoRA and QLoRA support with vision models (Llama 3.2 11B and 90B),
+               use the following torchtune commit for compatibility:
+
+               .. code-block:: shell
+
+                  git checkout 48192e23188b1fc524dd6d127725ceb2348e7f0e
+
+            {% elif model.mad_tag in ["pyt_train_llama-2-7b", "pyt_train_llama-2-13b", "pyt_train_llama-2-70b"] %}
+            .. note::
+
+               You might encounter the following error with Llama 2: ``ValueError: seq_len (16384) of
+               input tensor should be smaller than max_seq_len (4096)``.
+               This error indicates that an input sequence is longer than the model's maximum context window.
+
+               Ensure your tokenized input does not exceed the model's ``max_seq_len`` (4096
+               tokens in this case). You can resolve this by truncating the input or splitting
+               it into smaller chunks before passing it to the model.
+
+               Note on reproducibility: The results in this guide are based on
+               commit ``b4c98ac`` from the upstream
+               `<https://github.com/pytorch/torchtune>`__ repository. For the
+               latest updates, you can use the main branch.
+
+            {% endif %}
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+
+            .. rubric:: Benchmarking examples
+
+            For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.
+
+.. _amd-pytorch-training-multinode-examples-v259:
+
+Multi-node training
+-------------------
+
+Refer to :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your environment for multi-node
+training. See :ref:`rocm-for-ai-multi-node-setup-pyt-train-example` for example Slurm run commands.
+
+Pre-training
+~~~~~~~~~~~~
+
+Multi-node training with torchtitan is supported. The provided SLURM script is pre-configured for Llama 3 70B.
+
+To launch the training job on a SLURM cluster for Llama 3 70B, run the following commands from the MAD repository.
+
+.. code-block:: shell
+
+   # In the MAD repository
+   cd scripts/pytorch_train
+   sbatch run_slurm_train.sh
+
+Fine-tuning
+~~~~~~~~~~~
+
+Multi-node training with torchtune is supported. The provided SLURM script is pre-configured for Llama 3.3 70B.
+
+To launch the training job on a SLURM cluster for Llama 3.3 70B, run the following commands from the MAD repository.
+
+.. code-block:: shell
+
+   huggingface-cli login # Get access to HF Llama model space
+   huggingface-cli download meta-llama/Llama-3.3-70B-Instruct --local-dir ./models/Llama-3.3-70B-Instruct # Download the Llama 3.3 model locally
+   # In the MAD repository
+   cd scripts/pytorch_train
+   sbatch Torchtune_Multinode.sh
+
+.. note::
+
+   Information regarding benchmark setup:
+
+   * By default, Llama 3.3 70B is fine-tuned using ``alpaca_dataset``.
+   * You can adjust the torchtune `YAML configuration file
+     <https://github.com/pytorch/torchtune/blob/main/recipes/configs/llama3_3/70B_full_multinode.yaml>`__
+     if you're using a different model.
+   * The number of nodes and other parameters can be tuned in the SLURM script ``Torchtune_Multinode.sh``.
+   * Set the ``mounting_paths`` inside the SLURM script.
+
+Once the run is finished, you can find the log files in the ``result_torchtune/`` directory.
+
+Known issues
+============
+
+PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
+
+Further reading
+===============
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`pytorch-training-history` to find documentation for previous releases
+of the ``ROCm/pytorch-training`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst

@@ -31,12 +31,10 @@ Megatron-LM.
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
    .. tab-set::
 
-   {% for supported_gpus, docker in dockers.items() %}
-      .. tab-item:: {{ supported_gpus }}
-         :sync: {{ supported_gpus }}
+      .. tab-item:: {{ data.docker.pull_tag }}
+         :sync: {{ data.docker.pull_tag }}
 
          .. list-table::
             :header-rows: 1
@@ -44,13 +42,12 @@ Megatron-LM.
             * - Software component
               - Version
 
-            {% for component_name, component_version in docker.components.items() %}
+            {% for component_name, component_version in data.docker.components.items() %}
             * - {{ component_name }}
               - {{ component_version }}
             {% endfor %}
-   {% endfor %}
 
-.. _amd-primus-megatron-lm-model-support-v259:
+.. _amd-primus-megatron-lm-model-support-v2510:
 
 Supported models
 ================
@@ -111,7 +108,7 @@ To test for optimal performance, consult the recommended :ref:`System health ben
 <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
 system's configuration.
 
-.. _mi300x-amd-primus-megatron-lm-training-v259:
+.. _mi300x-amd-primus-megatron-lm-training-v2510:
 
 Environment setup
 =================
@@ -121,63 +118,49 @@ Environment setup
    Use the following instructions to set up the environment, configure the script to train models, and
    reproduce the benchmark results on AMD Instinct GPUs.
 
-.. _amd-primus-megatron-lm-requirements-v259:
+.. _amd-primus-megatron-lm-requirements-v2510:
 
 Pull the Docker image
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
+   {% set docker = data.docker %}
 
-   1. Pull the appropriate Docker image for your AMD GPU architecture from Docker Hub.
+   1. Pull the ``{{ docker.pull_tag }}`` Docker image from Docker Hub.
 
-      .. tab-set::
+      .. code-block:: shell
 
-         {% for supported_gpus, docker in dockers.items() %}
-         .. tab-item:: {{ supported_gpus }}
-            :sync: {{ supported_gpus }}
-
-            .. code-block:: shell
-
-               docker pull {{ docker.pull_tag }}
-         {% endfor %}
+         docker pull {{ docker.pull_tag }}
 
    2. Launch the Docker container.
 
-      .. tab-set::
+      .. code-block:: shell
 
-         {% for supported_gpus, docker in dockers.items() %}
-         .. tab-item:: {{ supported_gpus }}
-            :sync: {{ supported_gpus }}
+         docker run -it \
+             --device /dev/dri \
+             --device /dev/kfd \
+             --device /dev/infiniband \
+             --network host --ipc host \
+             --group-add video \
+             --cap-add SYS_PTRACE \
+             --security-opt seccomp=unconfined \
+             --privileged \
+             -v $HOME:$HOME \
+             --shm-size 128G \
+             --name primus_training_env \
+             {{ docker.pull_tag }}
 
-            .. code-block:: shell
+      Use these commands if you exit the ``primus_training_env`` container and need to return to it.
 
-               docker run -it \
-                   --device /dev/dri \
-                   --device /dev/kfd \
-                   --device /dev/infiniband \
-                   --network host --ipc host \
-                   --group-add video \
-                   --cap-add SYS_PTRACE \
-                   --security-opt seccomp=unconfined \
-                   --privileged \
-                   -v $HOME:$HOME \
-                   --shm-size 128G \
-                   --name primus_training_env \
-                   {{ docker.pull_tag }}
-         {% endfor %}
+      .. code-block:: shell
 
-3. Use these commands if you exit the ``primus_training_env`` container and need to return to it.
+         docker start primus_training_env
+         docker exec -it primus_training_env bash
 
-   .. code-block:: shell
+The Docker container hosts verified branch ``release/v25.10`` of the `Primus
+<https://github.com/AMD-AGI/Primus/tree/release/v25.10>`__ repository.
 
-      docker start primus_training_env
-      docker exec -it primus_training_env bash
-
-The Docker container hosts verified commit ``e16b27b`` of the `Primus
-<https://github.com/AMD-AGI/Primus/tree/e16b27b>`__ repository.
-
-.. _amd-primus-megatron-lm-environment-setup-v259:
+.. _amd-primus-megatron-lm-environment-setup-v2510:
 
 Configuration
 =============
@@ -224,7 +207,7 @@ You can use either mock data or real data for training.
 
   Ensure that the files are accessible inside the Docker container.
 
-.. _amd-primus-megatron-lm-tokenizer-v259:
+.. _amd-primus-megatron-lm-tokenizer-v2510:
 
 Tokenizer
 ---------
@@ -245,7 +228,7 @@ right permissions to access the tokenizer for each model.
    <https://github.com/AMD-AGI/Primus/blob/e16b27bf6c1b2798f38848fc574fee60d9a9b902/examples/megatron/configs/llama3.1_8B-pretrain.yaml>`__
    definition.
 
-.. _amd-primus-megatron-lm-run-training-v259:
+.. _amd-primus-megatron-lm-run-training-v2510:
 
 Run training
 ============
@@ -269,7 +252,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 3.3 70B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run pre-training for Llama 3.3 70B BF16, run:
 
@@ -280,7 +263,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/llama3.3_70B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 6 \
@@ -291,7 +274,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/llama3.3_70B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 2 \
@@ -301,7 +289,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 3.1 8B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run pre-training for Llama 3.1 8B FP8, run:
 
@@ -312,7 +300,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/llama3.1_8B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --fp8 hybrid \
@@ -324,7 +312,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/llama3.1_8B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --fp8 hybrid
@@ -338,7 +331,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/llama3.1_8B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 4 \
@@ -349,7 +342,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/llama3.1_8B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50
 
@@ -357,7 +355,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 3.1 70B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run pre-training for Llama 3.1 70B BF16, run:
 
@@ -368,7 +366,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/llama3.1_70B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                  --train_iters 50 \
                  --micro_batch_size 4 \
@@ -379,7 +377,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/llama3.1_70B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                  --train_iters 50
 
@@ -398,7 +401,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/llama3.1_70B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --fp8 hybrid \
@@ -411,7 +414,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/llama3.1_70B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --num_layers 40 \
@@ -422,7 +430,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 2 7B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run pre-training for Llama 2 7B FP8, run:
 
@@ -433,7 +441,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama2_7B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/llama2_7B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --fp8 hybrid \
@@ -445,7 +453,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama2_7B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/llama2_7B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --fp8 hybrid
@@ -459,7 +472,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama2_7B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/llama2_7B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 10 \
@@ -470,7 +483,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama2_7B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/llama2_7B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50
 
@@ -478,7 +496,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 2 70B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run pre-training for Llama 2 70B BF16, run:
 
@@ -489,7 +507,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/llama2_70B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 17 \
@@ -500,7 +518,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/llama2_70B-pretrain.yaml \
             bash ./examples/run_pretrain.sh \
                 --train_iters 50
 
@@ -508,7 +531,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to DeepSeek-V3.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run training on a single node for DeepSeek-V3 (MoE with expert parallel) BF16 with 3-layer proxy,
    use the following command:
@@ -520,7 +543,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/deepseek_v3-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/deepseek_v3-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --num_layers 3 \
                 --moe_layer_freq 1 \
@@ -533,17 +556,24 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/deepseek_v3-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/deepseek_v3-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --num_layers 3 \
                 --moe_layer_freq 1 \
+                --micro_batch_size 3 \
+                --global_batch_size 192 \
                 --train_iters 50
 
 .. container:: model-doc primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to DeepSeek-V2-Lite.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run training on a single node for DeepSeek-V2-Lite (MoE with expert parallel) BF16,
    use the following command:
@@ -555,7 +585,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/deepseek_v2_lite-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/deepseek_v2_lite-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 12 \
@@ -566,7 +596,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/deepseek_v2_lite-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/deepseek_v2_lite-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --global_batch_size 256
@@ -575,7 +610,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Mixtral 8x7B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run training on a single node for Mixtral 8x7B (MoE with expert parallel),
    use the following command:
@@ -587,7 +622,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/mixtral_8x7B_v0.1-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/mixtral_8x7B_v0.1-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 4 \
@@ -598,7 +633,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/mixtral_8x7B_v0.1-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/mixtral_8x7B_v0.1-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50
 
@@ -606,7 +646,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Mixtral 8x22B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run training on a single node for Mixtral 8x22B BF16 (MoE with expert parallel) 4-layer proxy,
    use the following command:
@@ -618,7 +658,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/mixtral_8x22B_v0.1-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/mixtral_8x22B_v0.1-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --num_layers 4 \
@@ -631,7 +671,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/mixtral_8x22B_v0.1-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/mixtral_8x22B_v0.1-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --num_layers 4 \
@@ -643,7 +688,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Qwen 2.5 7B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run training on a single node for Qwen 2.5 7B BF16, use the following
    command:
@@ -655,7 +700,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/qwen2.5_7B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/qwen2.5_7B-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 16 \
@@ -666,7 +711,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/qwen2.5_7B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/qwen2.5_7B-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50
 
@@ -679,7 +729,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/qwen2.5_7B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/qwen2.5_7B-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --fp8 hybrid
@@ -691,7 +741,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/qwen2.5_7B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/qwen2.5_7B-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --fp8 hybrid
@@ -700,7 +755,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Qwen 2.5 72B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To run the training on a single node for Qwen 2.5 72B BF16, use the following command.
 
@@ -711,7 +766,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/qwen2.5_72B-pretrain.yaml \
+            EXP=examples/megatron/configs/MI355X/qwen2.5_72B-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50 \
                 --micro_batch_size 16 \
@@ -722,11 +777,16 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
 
          .. code-block:: shell
 
-            EXP=examples/megatron/configs/qwen2.5_72B-pretrain.yaml \
+            # Set the variables for better performance
+            # only on MI325X and MI300X
+            export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+            export NVTE_CK_IS_V3_ATOMIC_FP32=1
+
+            EXP=examples/megatron/configs/MI300X/qwen2.5_72B-pretrain.yaml \
             bash examples/run_pretrain.sh \
                 --train_iters 50
 
-.. _amd-primus-megatron-multi-node-examples-v259:
+.. _amd-primus-megatron-multi-node-examples-v2510:
 
 Multi-node training examples
 ----------------------------
@@ -740,28 +800,27 @@ to launch the multi-node workload. Use the following steps to setup your environ
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
-   .. tab-set::
+   {% set docker = data.docker %}
+   .. code-block:: shell
 
-      {% for supported_gpus, docker in dockers.items() %}
-      .. tab-item:: {{ supported_gpus }}
-         :sync: {{ supported_gpus }}
+      git clone --recurse-submodules https://github.com/AMD-AGI/Primus.git
+      cd Primus
+      git checkout release/v25.10
+      git submodule update --init --recursive
 
-         .. code-block:: shell
+      export DOCKER_IMAGE={{ docker.pull_tag }}
+      export HF_TOKEN=<your_HF_token>
+      export HSA_NO_SCRATCH_RECLAIM=1
+      export NVTE_CK_USES_BWD_V3=1
+      export NCCL_IB_HCA=<your_NCCL_IB_HCA> # specify which RDMA interfaces to use for communication
+      export NCCL_SOCKET_IFNAME=<your_NCCL_SOCKET_IFNAME> # your Network Interface
+      export GLOO_SOCKET_IFNAME=<your_GLOO_SOCKET_IFNAME> # your Network Interface
+      export NCCL_IB_GID_INDEX=3 # Set InfiniBand GID index for NCCL communication. Default is 3 for ROCE
 
-            git clone --recurse-submodules https://github.com/AMD-AGI/Primus.git
-            cd Primus
-            git checkout e16b27b
-
-            export DOCKER_IMAGE={{ docker.pull_tag }}
-            export HF_TOKEN=<your_HF_token>
-            export HSA_NO_SCRATCH_RECLAIM=1
-            export NVTE_CK_USES_BWD_V3=1
-            export NCCL_IB_HCA=<your_NCCL_IB_HCA> # specify which RDMA interfaces to use for communication
-            export NCCL_SOCKET_IFNAME=<your_NCCL_SOCKET_IFNAME> # your Network Interface
-            export GLOO_SOCKET_IFNAME=<your_GLOO_SOCKET_IFNAME> # your Network Interface
-            export NCCL_IB_GID_INDEX=3 # Set InfiniBand GID index for NCCL communication. Default is 3 for ROCE
-      {% endfor %}
+      # Set the variables for better performance
+      # only on MI325X and MI300X
+      export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
+      export NVTE_CK_IS_V3_ATOMIC_FP32=1
 
 .. note::
 
@@ -769,13 +828,13 @@ to launch the multi-node workload. Use the following steps to setup your environ
    * If ``NCCL_IB_HCA`` and ``NCCL_SOCKET_IFNAME`` are not set, Primus will try to auto-detect. However, since NICs can vary accross different cluster, it is encouraged to explicitly export your NCCL parameters for the cluster.
    * To find your network interface, you can use ``ip a``.
    * To find RDMA interfaces, you can use ``ibv_devices`` to get the list of all the RDMA/IB  devices.
-   * Remember to set ``DOCKER_IMAGE`` and ``HF_TOKEN`` (see :ref:`amd-primus-megatron-lm-tokenizer-v259`) as appropriate.
+   * Remember to set ``DOCKER_IMAGE`` and ``HF_TOKEN`` (see :ref:`amd-primus-megatron-lm-tokenizer-v2510`) as appropriate.
 
 .. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-8b
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 3.1 8B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To train Llama 3.1 8B FP8 on 8 nodes, run:
 
@@ -793,7 +852,7 @@ to launch the multi-node workload. Use the following steps to setup your environ
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 2 7B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To train Llama 2 7B FP8 on 8 nodes, run:
 
@@ -811,7 +870,7 @@ to launch the multi-node workload. Use the following steps to setup your environ
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 3.1 70B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To train Llama 3.1 70B FP8 on 8 nodes, run:
 
@@ -843,7 +902,7 @@ to launch the multi-node workload. Use the following steps to setup your environ
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 2 70B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To train Llama 2 70B FP8 on 8 nodes, run:
 
@@ -875,7 +934,7 @@ to launch the multi-node workload. Use the following steps to setup your environ
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 3.3 70B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To train Llama 3.3 70B FP8 on 8 nodes, run:
 
@@ -907,7 +966,7 @@ to launch the multi-node workload. Use the following steps to setup your environ
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 2 70B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To train Mixtral 8x7B BF16 on 8 nodes, run:
 
@@ -925,7 +984,7 @@ to launch the multi-node workload. Use the following steps to setup your environ
 
    Once setup is complete, run the appropriate training command.
    The following run commands are tailored to Llama 2 70B.
-   See :ref:`amd-primus-megatron-lm-model-support-v259` to switch to another available model.
+   See :ref:`amd-primus-megatron-lm-model-support-v2510` to switch to another available model.
 
    To train Qwen2.5 72B FP8 on 8 nodes, run:
 
@@ -942,7 +1001,7 @@ to launch the multi-node workload. Use the following steps to setup your environ
           --no_fp8_weight_transpose_cache true \
           --fp8 hybrid
 
-.. _amd-primus-megatron-lm-benchmark-test-vars-v259:
+.. _amd-primus-megatron-lm-benchmark-test-vars-v2510:
 
 Key options
 -----------
@@ -987,7 +1046,10 @@ num_layers
 Known issues
 ============
 
-PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
+DeepSeekV3 proxy model and Mixtral 8x22B proxy model may exit with an error
+due to a memory free issue. However, this does not impacts training runs. All
+iterations, in this case 50, should have been completed before the exit and
+the results should be available in the end.
 
 Further reading
 ===============

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

@@ -29,12 +29,10 @@ with Primus Turbo optimizations.
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
    .. tab-set::
 
-   {% for supported_gpus, docker in dockers.items() %}
-      .. tab-item:: {{ supported_gpus }}
-         :sync: {{ supported_gpus }}
+      .. tab-item:: {{ data.docker.pull_tag }}
+         :sync: {{ data.docker.pull_tag }}
 
          .. list-table::
             :header-rows: 1
@@ -42,13 +40,12 @@ with Primus Turbo optimizations.
             * - Software component
               - Version
 
-            {% for component_name, component_version in docker.components.items() %}
+            {% for component_name, component_version in data.docker.components.items() %}
             * - {{ component_name }}
               - {{ component_version }}
             {% endfor %}
-   {% endfor %}
 
-.. _amd-primus-pytorch-model-support-v259:
+.. _amd-primus-pytorch-model-support-v2510:
 
 Supported models
 ================
@@ -67,7 +64,7 @@ vary by model -- select one to get started.
             <div class="col-2 me-1 px-2 model-param-head">Model</div>
             <div class="row col-10 pe-0">
       {% for model_group in model_groups %}
-               <div class="col-12 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+               <div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
       {% endfor %}
             </div>
          </div>
@@ -94,7 +91,7 @@ vary by model -- select one to get started.
    For additional workloads, including Llama 3.3, Llama 3.2, Llama 2, GPT OSS, Qwen, and Flux models,
    see the documentation :doc:`pytorch-training` (without Primus)
 
-.. _amd-primus-pytorch-performance-measurements-v259:
+.. _amd-primus-pytorch-performance-measurements-v2510:
 
 System validation
 =================
@@ -120,20 +117,11 @@ Pull the Docker image
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
-
    Use the following command to pull the Docker image from Docker Hub.
 
-   .. tab-set::
+   .. code-block:: shell
 
-      {% for supported_gpus, docker in dockers.items() %}
-      .. tab-item:: {{ supported_gpus }}
-         :sync: {{ supported_gpus }}
-
-         .. code-block:: shell
-
-            docker pull {{ docker.pull_tag }}
-      {% endfor %}
+      docker pull {{ data.docker.pull_tag }}
 
 Run training
 ============
@@ -145,7 +133,7 @@ tweak some configurations (such as batch sizes).
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
+   {% set docker = data.docker %}
    {% set model_groups = data.model_groups %}
 
    .. tab-set::
@@ -158,7 +146,7 @@ tweak some configurations (such as batch sizes).
          .. container:: model-doc {{ model.mad_tag }}
 
             The following run command is tailored to {{ model.model }}.
-            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
+            See :ref:`amd-primus-pytorch-model-support-v2510` to switch to another available model.
 
             1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
                directory and install the required packages on the host machine.
@@ -185,13 +173,6 @@ tweak some configurations (such as batch sizes).
                ``container_ci-{{ model.mad_tag }}``. The latency and throughput reports of the
                model are collected in ``~/MAD/perf.csv``.
 
-               .. note::
-
-                  Currently, Primus torchtitan models are run with Primus Turbo
-                  enabled for enhanced performance. To disable Primus Turbo,
-                  modify respective configuration file
-                  ``scripts/primus/pytorch_train/primus_torchtitan_scripts/llama3_[8B|70B]-[BF16|FP8].yaml``.
-
       {% endfor %}
    {% endfor %}
 
@@ -203,48 +184,34 @@ tweak some configurations (such as batch sizes).
          .. container:: model-doc {{ model.mad_tag }}
 
             The following run commands are tailored to {{ model.model }}.
-            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
+            See :ref:`amd-primus-pytorch-model-support-v2510` to switch to another available model.
 
             .. rubric:: Download the Docker image and required packages
 
-            1. Pull the appropriate Docker image for your AMD GPU architecture from Docker Hub.
+            1. Pull the ``{{ docker.pull_tag }}`` Docker image from Docker Hub.
 
-               .. tab-set::
+               .. code-block:: shell
 
-                  {% for supported_gpus, docker in dockers.items() %}
-                  .. tab-item:: {{ supported_gpus }}
-                     :sync: {{ supported_gpus }}
-
-                     .. code-block:: shell
-
-                        docker pull {{ docker.pull_tag }}
-                  {% endfor %}
+                  docker pull {{ docker.pull_tag }}
 
             2. Run the Docker container.
 
-               .. tab-set::
+               .. code-block:: shell
 
-                  {% for supported_gpus, docker in dockers.items() %}
-                  .. tab-item:: {{ supported_gpus }}
-                     :sync: {{ supported_gpus }}
-
-                     .. code-block:: shell
-
-                        docker run -it \
-                            --device /dev/dri \
-                            --device /dev/kfd \
-                            --network host \
-                            --ipc host \
-                            --group-add video \
-                            --cap-add SYS_PTRACE \
-                            --security-opt seccomp=unconfined \
-                            --privileged \
-                            -v $HOME:$HOME \
-                            -v $HOME/.ssh:/root/.ssh \
-                            --shm-size 64G \
-                            --name training_env \
-                            {{ docker.pull_tag }}
-                  {% endfor %}
+                  docker run -it \
+                      --device /dev/dri \
+                      --device /dev/kfd \
+                      --network host \
+                      --ipc host \
+                      --group-add video \
+                      --cap-add SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --privileged \
+                      -v $HOME:$HOME \
+                      -v $HOME/.ssh:/root/.ssh \
+                      --shm-size 64G \
+                      --name training_env \
+                      {{ docker.pull_tag }}
 
                Use these commands if you exit the ``training_env`` container and need to return to it.
 
@@ -283,37 +250,28 @@ tweak some configurations (such as batch sizes).
                .. tab-set::
 
                   .. tab-item:: MI355X and MI350X
-                     :sync: MI355X and MI300X
+                     :sync: MI355X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 5
+                        EXP=examples/torchtitan/configs/MI355X/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 6
 
                   .. tab-item:: MI325X
                      :sync: MI325X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 6
+                        EXP=examples/torchtitan/configs/MI300X/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 6
 
                   .. tab-item:: MI300X
-                     :sync: MI325X and MI300X
+                     :sync: MI300X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 4
+                        EXP=examples/torchtitan/configs/MI300X/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 4
 
 
                To train Llama 3.1 8B with FP8 precision, use the following command.
@@ -321,37 +279,28 @@ tweak some configurations (such as batch sizes).
                .. tab-set::
 
                   .. tab-item:: MI355X and MI350X
-                     :sync: MI355X and MI300X
+                     :sync: MI355X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 8
+                        EXP=examples/torchtitan/configs/MI355X/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 8
 
                   .. tab-item:: MI325X
                      :sync: MI325X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_8B-FP8-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 7
+                        EXP=examples/torchtitan/configs/MI300X/llama3.1_8B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 7
 
                   .. tab-item:: MI300X
-                     :sync: MI325X and MI300X
+                     :sync: MI300X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_8B-FP8-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 5
+                        EXP=examples/torchtitan/configs/MI300X/llama3.1_8B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 5
 
             .. container:: model-doc primus_pyt_train_llama-3.1-70b
 
@@ -364,36 +313,57 @@ tweak some configurations (such as batch sizes).
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 8
+                        EXP=examples/torchtitan/configs/MI355X/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 8
 
                   .. tab-item:: MI325X
                      :sync: MI325X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 6
+                        EXP=examples/torchtitan/configs/MI300X/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 6
 
                   .. tab-item:: MI300X
-                     :sync: MI325X and MI300X
+                     :sync: MI300X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 4
+                        EXP=examples/torchtitan/configs/MI300X/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 4
 
                To train Llama 3.1 70B with FP8 precision, use the following command.
 
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/MI355X/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 6
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/MI300X/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 5
+
+                  .. tab-item:: MI300X
+                     :sync: MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/MI300X/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 3
+
+            .. container:: model-doc primus_pyt_train_deepseek-v2
+
+               Use the following command to run train DeepSeek V2 16B with BF16 precision using Primus torchtitan.
+
                .. tab-set::
 
                   .. tab-item:: MI355X and MI350X
@@ -401,151 +371,55 @@ tweak some configurations (such as batch sizes).
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 6
+                        EXP=examples/torchtitan/configs/MI355X/deepseek_v3_16b-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 16
 
                   .. tab-item:: MI325X
                      :sync: MI325X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 5
+                        EXP=examples/torchtitan/configs/MI300X/deepseek_v3_16b-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 10
 
                   .. tab-item:: MI300X
-                     :sync: MI325X and MI300X
+                     :sync: MI300X
 
                      .. code-block:: shell
 
-                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
-                        bash examples/run_pretrain.sh \
-                            --metrics.enable_tensorboard false \
-                            --profiling.enable_profiling false \
-                            --training.batch_size 3
-      {% endfor %}
-   {% endfor %}
+                        EXP=examples/torchtitan/configs/MI300X/deepseek_v3_16b-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 8
 
-      .. tab-item:: Standalone torchtitan benchmarking
-
-   {% for model_group in model_groups %}
-      {% for model in model_group.models %}
-
-         .. container:: model-doc {{ model.mad_tag }}
-
-            The following run commands are tailored to {{ model.model }}.
-            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
-
-            .. rubric:: Download the Docker image and required packages
-
-            1. Pull the appropriate Docker image for your AMD GPU architecture from Docker Hub.
+               To train DeepSeek V2 16B with FP8 precision, use the following command.
 
                .. tab-set::
 
-                  {% for supported_gpus, docker in dockers.items() %}
-                  .. tab-item:: {{ supported_gpus }}
-                     :sync: {{ supported_gpus }}
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X
 
                      .. code-block:: shell
 
-                        docker pull {{ docker.pull_tag }}
-                  {% endfor %}
+                        EXP=examples/torchtitan/configs/MI355X/deepseek_v3_16b-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 16
 
-            2. Run the Docker container.
-
-               .. tab-set::
-
-                  {% for supported_gpus, docker in dockers.items() %}
-                  .. tab-item:: {{ supported_gpus }}
-                     :sync: {{ supported_gpus }}
+                  .. tab-item:: MI325X
+                     :sync: MI325X
 
                      .. code-block:: shell
 
-                        docker run -it \
-                            --device /dev/dri \
-                            --device /dev/kfd \
-                            --network host \
-                            --ipc host \
-                            --group-add video \
-                            --cap-add SYS_PTRACE \
-                            --security-opt seccomp=unconfined \
-                            --privileged \
-                            -v $HOME:$HOME \
-                            -v $HOME/.ssh:/root/.ssh \
-                            --shm-size 64G \
-                            --name training_env \
-                            {{ docker.pull_tag }}
-                  {% endfor %}
+                        EXP=examples/torchtitan/configs/MI300X/deepseek_v3_16b-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 8
 
-               Use these commands if you exit the ``training_env`` container and need to return to it.
+                  .. tab-item:: MI300X
+                     :sync: MI300X
 
-               .. code-block:: shell
+                     .. code-block:: shell
 
-                  docker start training_env
-                  docker exec -it training_env bash
-
-            3. Navigate to the ``torchtitan`` workspace directory.
-
-               .. code-block:: shell
-
-                  cd /workspace/torchtitan
-
-            .. rubric:: Download the tokenizer
-
-            1. The following benchmarking examples require downloading models and datasets
-               from Hugging Face. To ensure successful access to gated repos, set your
-               ``HF_TOKEN``.
-
-               .. code-block:: shell
-
-                  export HF_TOKEN=$your_personal_hugging_face_access_token
-
-            2. Download the tokenizer for your model.
-
-               .. container:: model-doc {{ model.mad_tag }}
-
-                  .. code-block:: shell
-
-                     python3 scripts/download_tokenizer.py \
-                        --repo_id {{ model.model_repo }} \
-                        --tokenizer_path "original" \
-                        --hf_token=${HF_TOKEN}
-
-            .. rubric:: Pretraining examples
-
-            Run the training script with the appropriate configuration file.
-
-            For train with BF16 precicion, use the following command:
-
-            .. container:: model-doc {{ model.mad_tag }}
-
-               .. code-block:: shell
-
-                  CONFIG_FILE={{ model.config_file.bf16 }} \
-                  .run_train.sh
-
-            For train with BF16 precicion, use the following command:
-
-            .. container:: model-doc {{ model.mad_tag }}
-
-               .. code-block:: shell
-
-                  CONFIG_FILE={{ model.config_file.fp8 }} \
-                  .run_train.sh
+                        EXP=examples/torchtitan/configs/MI300X/deepseek_v3_16b-pretrain.yaml \
+                        bash examples/run_pretrain.sh --training.local_batch_size 8
       {% endfor %}
    {% endfor %}
 
-Known issues
-============
-
-PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
-
-
 Further reading
 ===============
 

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

@@ -27,12 +27,10 @@ training workloads:
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
    .. tab-set::
 
-   {% for supported_gpus, docker in dockers.items() %}
-      .. tab-item:: {{ supported_gpus }}
-         :sync: {{ supported_gpus }}
+      .. tab-item:: {{ data.docker.pull_tag }}
+         :sync: {{ data.docker.pull_tag }}
 
          .. list-table::
             :header-rows: 1
@@ -40,13 +38,12 @@ training workloads:
             * - Software component
               - Version
 
-            {% for component_name, component_version in docker.components.items() %}
+            {% for component_name, component_version in data.docker.components.items() %}
             * - {{ component_name }}
               - {{ component_version }}
             {% endfor %}
-   {% endfor %}
 
-.. _amd-pytorch-training-model-support-v259:
+.. _amd-pytorch-training-model-support-v2510:
 
 Supported models
 ================
@@ -88,7 +85,7 @@ one to get started.
          </div>
       </div>
 
-.. _amd-pytorch-training-supported-training-modes-v259:
+.. _amd-pytorch-training-supported-training-modes-v2510:
 
 The following table lists supported training modes per model.
 
@@ -123,7 +120,7 @@ The following table lists supported training modes per model.
          unlisted fine-tuning methods by using an existing file in the
          ``/workspace/torchtune/recipes/configs`` directory as a template.
 
-.. _amd-pytorch-training-performance-measurements-v259:
+.. _amd-pytorch-training-performance-measurements-v2510:
 
 Performance measurements
 ========================
@@ -164,7 +161,7 @@ Run training
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
+   {% set docker = data.docker %}
    {% set model_groups = data.model_groups %}
 
    Once the setup is complete, choose between two options to start benchmarking training:
@@ -179,7 +176,7 @@ Run training
          .. container:: model-doc {{ model.mad_tag }}
 
             The following run command is tailored to {{ model.model }}.
-            See :ref:`amd-pytorch-training-model-support-v259` to switch to another available model.
+            See :ref:`amd-pytorch-training-model-support-v2510` to switch to another available model.
 
             1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
                directory and install the required packages on the host machine.
@@ -217,7 +214,7 @@ Run training
          .. container:: model-doc {{ model.mad_tag }}
 
             The following commands are tailored to {{ model.model }}.
-            See :ref:`amd-pytorch-training-model-support-v259` to switch to another available model.
+            See :ref:`amd-pytorch-training-model-support-v2510` to switch to another available model.
 
       {% endfor %}
    {% endfor %}
@@ -226,42 +223,28 @@ Run training
 
          1. Use the following command to pull the Docker image from Docker Hub.
 
-            .. tab-set::
+            .. code-block:: shell
 
-               {% for supported_gpus, docker in dockers.items() %}
-               .. tab-item:: {{ supported_gpus }}
-                  :sync: {{ supported_gpus }}
-
-                  .. code-block:: shell
-
-                     docker pull {{ docker.pull_tag }}
-               {% endfor %}
+               docker pull {{ docker.pull_tag }}
 
          2. Launch the Docker container.
 
-            .. tab-set::
+            .. code-block:: shell
 
-               {% for supported_gpus, docker in dockers.items() %}
-               .. tab-item:: {{ supported_gpus }}
-                  :sync: {{ supported_gpus }}
-
-                  .. code-block:: shell
-
-                     docker run -it \
-                         --device /dev/dri \
-                         --device /dev/kfd \
-                         --network host \
-                         --ipc host \
-                         --group-add video \
-                         --cap-add SYS_PTRACE \
-                         --security-opt seccomp=unconfined \
-                         --privileged \
-                         -v $HOME:$HOME \
-                         -v $HOME/.ssh:/root/.ssh \
-                         --shm-size 64G \
-                         --name training_env \
-                         {{ docker.pull_tag }}
-               {% endfor %}
+               docker run -it \
+                   --device /dev/dri \
+                   --device /dev/kfd \
+                   --network host \
+                   --ipc host \
+                   --group-add video \
+                   --cap-add SYS_PTRACE \
+                   --security-opt seccomp=unconfined \
+                   --privileged \
+                   -v $HOME:$HOME \
+                   -v $HOME/.ssh:/root/.ssh \
+                   --shm-size 64G \
+                   --name training_env \
+                   {{ docker.pull_tag }}
 
             Use these commands if you exit the ``training_env`` container and need to return to it.
 
@@ -419,11 +402,34 @@ Run training
 
          .. container:: model-doc {{ model.mad_tag }}
 
-            .. rubric:: Pre-training
+            .. rubric:: Pretraining
 
             To start the pre-training benchmark, use the following command with the
             appropriate options. See the following list of options and their descriptions.
 
+            {% if model.mad_tag == "pyt_train_dlrm" %}
+
+            1. Go to the DLRM directory.
+
+               .. code-block:: shell
+
+                  cd /workspace/DLRMBenchmark
+
+            2. To run the single node training benchmark for DLRM-v2 with TF32 precision,
+               run the following script.
+
+               .. code-block:: shell
+
+                  ./launch_training_single_node.sh
+
+               To run with MAD within the Docker container, use the following command.
+
+               .. code-block:: shell
+
+                  ./pytorch_benchmark_report.sh -t pretrain -m DLRM
+
+            {% else %}
+
             .. code-block:: shell
 
                ./pytorch_benchmark_report.sh -t {% if available_modes | length == 1 %}{{ available_modes[0] }}{% else %}$training_mode{% endif %} \
@@ -466,6 +472,7 @@ Run training
                * - ``$sequence_length``
                  - Sequence length for the language model.
                  - Between 2048 and 8192. 8192 by default.
+            {% endif %}
          {% endif %}
 
          {% set training_modes = model.training_modes %}
@@ -525,7 +532,7 @@ Run training
 
             To start the fine-tuning benchmark, use the following command with the
             appropriate options. See the following list of options and their descriptions.
-            See :ref:`supported training modes <amd-pytorch-training-supported-training-modes-v259>`.
+            See :ref:`supported training modes <amd-pytorch-training-supported-training-modes-v2510>`.
 
             .. code-block:: shell
 
@@ -590,7 +597,7 @@ Run training
 
             For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.
 
-.. _amd-pytorch-training-multinode-examples-v259:
+.. _amd-pytorch-training-multinode-examples-v2510:
 
 Multi-node training
 -------------------
@@ -639,11 +646,6 @@ To launch the training job on a SLURM cluster for Llama 3.3 70B, run the followi
 
 Once the run is finished, you can find the log files in the ``result_torchtune/`` directory.
 
-Known issues
-============
-
-PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
-
 Further reading
 ===============
 

docs/index.md

@@ -65,6 +65,8 @@ ROCm documentation is organized into the following categories:
 * [ROCm libraries](./reference/api-libraries.md)
 * [ROCm tools, compilers, and runtimes](./reference/rocm-tools.md)
 * [GPU hardware specifications](./reference/gpu-arch-specs.rst)
+* [Hardware atomics operation support](./reference/gpu-atomics-operation.rst)
+* [Environment variables](./reference/env-variables.rst)
 * [Data types and precision support](./reference/precision-support.rst)
 * [Graph safe support](./reference/graph-safe-support.rst)
 <!-- markdownlint-enable MD051 -->

docs/reference/env-variables.rst

@@ -0,0 +1,173 @@
+.. meta::
+    :description: Environment variables reference
+    :keywords: AMD, ROCm, environment variables, environment, reference, settings
+
+.. role:: cpp(code)
+   :language: cpp
+
+.. _env-variables-reference:
+
+*************************************************************
+ROCm environment variables
+*************************************************************
+
+ROCm provides a set of environment variables that allow users to configure and optimize their development
+and runtime experience. These variables define key settings such as installation paths, platform selection,
+and runtime behavior for applications running on AMD accelerators and GPUs.
+
+This page outlines commonly used environment variables across different components of the ROCm software stack,
+including HIP and ROCR-Runtime. Understanding these variables can help streamline software development and
+execution in ROCm-based environments.
+
+HIP environment variables
+=========================
+
+The following tables list the HIP environment variables.
+
+GPU isolation variables
+--------------------------------------------------------------------------------
+
+.. remote-content::
+   :repo: ROCm/rocm-systems
+   :path: /projects/hip/docs/reference/env_variables/gpu_isolation_hip_env.rst
+   :default_branch: develop
+   :tag_prefix: docs/
+
+
+Profiling variables
+--------------------------------------------------------------------------------
+
+.. remote-content::
+   :repo: ROCm/rocm-systems
+   :path: /projects/hip/docs/reference/env_variables/profiling_hip_env.rst
+   :default_branch: develop
+   :tag_prefix: docs/
+
+
+Debug variables
+--------------------------------------------------------------------------------
+
+.. remote-content::
+   :repo: ROCm/rocm-systems
+   :path: /projects/hip/docs/reference/env_variables/debug_hip_env.rst
+   :default_branch: develop
+   :tag_prefix: docs/
+
+Memory management related variables
+--------------------------------------------------------------------------------
+
+.. remote-content::
+   :repo: ROCm/rocm-systems
+   :path: /projects/hip/docs/reference/env_variables/memory_management_hip_env.rst
+   :default_branch: develop
+   :tag_prefix: docs/
+
+Other useful variables
+--------------------------------------------------------------------------------
+
+.. remote-content::
+   :repo: ROCm/rocm-systems
+   :path: /projects/hip/docs/reference/env_variables/miscellaneous_hip_env.rst
+   :default_branch: develop
+   :tag_prefix: docs/
+
+ROCR-Runtime environment variables
+==================================
+
+The following table lists the ROCR-Runtime environment variables:
+
+.. remote-content::
+   :repo: ROCm/rocm-systems
+   :path: /projects/rocr-runtime/runtime/docs/data/env_variables.rst
+   :default_branch: develop
+   :tag_prefix: docs/
+
+HIPCC environment variables
+===========================
+
+This topic provides descriptions of the HIPCC environment variables.
+
+.. remote-content::
+   :repo: ROCm/llvm-project
+   :path: amd/hipcc/docs/env.rst
+   :default_branch: amd-staging
+   :start_line: 14
+   :tag_prefix: docs/
+
+Environment variables in ROCm libraries
+=======================================
+
+Many ROCm libraries define environment variables for specific tuning, debugging,
+or behavioral control. The table below provides an overview and links to further
+documentation.
+
+.. list-table::
+    :header-rows: 1
+    :widths: 30, 70
+
+    * - Library
+      - Purpose of Environment Variables
+
+    * - :doc:`hipBLASLt <hipblaslt:reference/env-variables>`
+      - Manage logging, debugging, offline tuning, and stream-K configuration
+        for hipBLASLt.
+
+    * - :doc:`hipSPARSELt <hipsparselt:reference/env-variables>`
+      - Control logging, debugging and performance monitoring of hipSPARSELt.
+
+    * - :doc:`rocBLAS <rocblas:reference/env-variables>`
+      - Performance tuning, kernel selection, logging, and debugging for BLAS
+        operations.
+
+    * - :doc:`rocSolver <rocsolver:reference/env_variables>`
+      - Control logging of rocSolver.
+
+    * - :doc:`rocSPARSE <rocsparse:reference/env_variables>`
+      - Control logging of rocSPARSE.
+
+    * - :doc:`MIGraphX <amdmigraphx:reference/MIGraphX-dev-env-vars>`
+      - Control debugging, testing, and model performance tuning options for
+        MIGraphX.
+
+    * - :doc:`MIOpen <miopen:reference/env_variables>`
+      - Control MIOpen logging and debugging, find mode and algorithm behavior
+        and others.
+
+    * - :doc:`MIVisionX <mivisionx:reference/MIVisionX-env-variables>`
+      - Control core OpenVX, GPU/device and debugging/profiling, stitching and
+        chroma key configurations, file I/O operations, model deployment, and
+        neural network parameters of MIVisionX.
+
+    * - :doc:`RCCL <rccl:api-reference/env-variables>`
+      - Control the logging, debugging, compiler and assembly behavior, and
+        cache of RPP.
+
+    * - :doc:`RPP <rpp:reference/rpp-env-variables>`
+      - Logging, debugging, compiler and assembly management, and cache control in RPP
+
+    * - `Tensile <https://rocm.docs.amd.com/projects/Tensile/en/latest/src/reference/environment-variables.html>`_
+      - Enable testing, debugging, and experimental features for Tensile clients and applications
+
+Key single-variable details
+===========================
+
+This section provides detailed descriptions, in the standard format, for ROCm
+libraries that feature a single, key environment variable (or a very minimal set)
+which is documented directly on this page for convenience.
+
+.. _rocalution-vars-detail:
+
+rocALUTION
+----------
+
+.. list-table::
+    :header-rows: 1
+    :widths: 70,30
+
+    * - Environment variable
+      - Value
+
+    * - | ``ROCALUTION_LAYER``
+        | If set to ``1``, enable file logging. Logs each rocALUTION function call including object constructor/destructor, address of the object, memory allocation, data transfers, all function calls for matrices, vectors, solvers, and preconditioners. The log file is placed in the working directory.
+      - | ``1`` (Enable trace file logging)
+        | Default: Not set.

docs/reference/graph-safe-support.rst

@@ -93,7 +93,7 @@ The following table shows whether a ROCm library is graph-safe.
       - ⚠️ (experimental)
     * 
       - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - ❌ (see :doc:`details <rocthrust:hipgraph-support>`)
+      - ❌
     * 
       - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
       - ❌

docs/release/versions.md

@@ -10,6 +10,8 @@
 
 | Version | Release date |
 | ------- | ------------ |
+| [7.1.1](https://rocm.docs.amd.com/en/docs-7.1.1/) | November 26, 2025 |
+| [7.1.0](https://rocm.docs.amd.com/en/docs-7.1.0/) | October 30, 2025 |
 | [7.0.2](https://rocm.docs.amd.com/en/docs-7.0.2/) | October 10, 2025 |
 | [7.0.1](https://rocm.docs.amd.com/en/docs-7.0.1/) | September 17, 2025 |
 | [7.0.0](https://rocm.docs.amd.com/en/docs-7.0.0/) | September 16, 2025 |

docs/sphinx/_toc.yml.in

@@ -117,6 +117,8 @@ subtrees:
             title: SGLang inference performance testing
           - file: how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
             title: SGLang distributed inference with Mooncake
+          - file: how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst
+            title: xDiT diffusion inference
           - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
             title: Deploy your model
 
@@ -216,6 +218,8 @@ subtrees:
     title: ROCm tools, compilers, and runtimes
   - file: reference/gpu-arch-specs.rst
   - file: reference/gpu-atomics-operation.rst
+  - file: reference/env-variables.rst
+    title: Environment variables
   - file: reference/precision-support.rst
     title: Data types and precision support
   - file: reference/graph-safe-support.rst

docs/sphinx/requirements.in

@@ -1,4 +1,4 @@
-rocm-docs-core==1.27.0
+rocm-docs-core==1.31.1
 sphinx-reredirects
 sphinx-sitemap
 sphinxcontrib.datatemplates==0.11.0

docs/sphinx/requirements.txt

@@ -2,13 +2,13 @@
 # This file is autogenerated by pip-compile with Python 3.10
 # by the following command:
 #
-#    pip-compile docs/sphinx/requirements.in
+#    pip-compile requirements.in
 #
 accessible-pygments==0.0.5
     # via pydata-sphinx-theme
 alabaster==1.0.0
     # via sphinx
-asttokens==3.0.0
+asttokens==3.0.1
     # via stack-data
 attrs==25.4.0
     # via
@@ -23,21 +23,21 @@ beautifulsoup4==4.14.2
     # via pydata-sphinx-theme
 breathe==4.36.0
     # via rocm-docs-core
-certifi==2025.10.5
+certifi==2025.11.12
     # via requests
 cffi==2.0.0
     # via
     #   cryptography
     #   pynacl
-charset-normalizer==3.4.3
+charset-normalizer==3.4.4
     # via requests
-click==8.3.0
+click==8.3.1
     # via
     #   jupyter-cache
     #   sphinx-external-toc
 comm==0.2.3
     # via ipykernel
-cryptography==46.0.2
+cryptography==46.0.3
     # via pyjwt
 debugpy==1.8.17
     # via ipykernel
@@ -50,7 +50,7 @@ docutils==0.21.2
     #   myst-parser
     #   pydata-sphinx-theme
     #   sphinx
-exceptiongroup==1.3.0
+exceptiongroup==1.3.1
     # via ipython
 executing==2.2.1
     # via stack-data
@@ -64,7 +64,7 @@ gitpython==3.1.45
     # via rocm-docs-core
 greenlet==3.2.4
     # via sqlalchemy
-idna==3.10
+idna==3.11
     # via requests
 imagesize==1.4.1
     # via sphinx
@@ -72,7 +72,7 @@ importlib-metadata==8.7.0
     # via
     #   jupyter-cache
     #   myst-nb
-ipykernel==6.30.1
+ipykernel==7.1.0
     # via myst-nb
 ipython==8.37.0
     # via
@@ -94,7 +94,7 @@ jupyter-client==8.6.3
     # via
     #   ipykernel
     #   nbclient
-jupyter-core==5.8.1
+jupyter-core==5.9.1
     # via
     #   ipykernel
     #   jupyter-client
@@ -106,7 +106,7 @@ markdown-it-py==3.0.0
     #   myst-parser
 markupsafe==3.0.3
     # via jinja2
-matplotlib-inline==0.1.7
+matplotlib-inline==0.2.1
     # via
     #   ipykernel
     #   ipython
@@ -132,16 +132,17 @@ nest-asyncio==1.6.0
 packaging==25.0
     # via
     #   ipykernel
+    #   pydata-sphinx-theme
     #   sphinx
 parso==0.8.5
     # via jedi
 pexpect==4.9.0
     # via ipython
-platformdirs==4.4.0
+platformdirs==4.5.0
     # via jupyter-core
 prompt-toolkit==3.0.52
     # via ipython
-psutil==7.1.0
+psutil==7.1.3
     # via ipykernel
 ptyprocess==0.7.0
     # via pexpect
@@ -149,7 +150,7 @@ pure-eval==0.2.3
     # via stack-data
 pycparser==2.23
     # via cffi
-pydata-sphinx-theme==0.16.1
+pydata-sphinx-theme==0.15.4
     # via
     #   rocm-docs-core
     #   sphinx-book-theme
@@ -163,7 +164,7 @@ pygments==2.19.2
     #   sphinx
 pyjwt[crypto]==2.10.1
     # via pygithub
-pynacl==1.6.0
+pynacl==1.6.1
     # via pygithub
 python-dateutil==2.9.0.post0
     # via jupyter-client
@@ -179,7 +180,7 @@ pyzmq==27.1.0
     # via
     #   ipykernel
     #   jupyter-client
-referencing==0.36.2
+referencing==0.37.0
     # via
     #   jsonschema
     #   jsonschema-specifications
@@ -187,9 +188,9 @@ requests==2.32.5
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.27.0
+rocm-docs-core==1.31.1
     # via -r requirements.in
-rpds-py==0.27.1
+rpds-py==0.29.0
     # via
     #   jsonschema
     #   referencing
@@ -217,7 +218,7 @@ sphinx==8.1.3
     #   sphinx-reredirects
     #   sphinxcontrib-datatemplates
     #   sphinxcontrib-runcmd
-sphinx-book-theme==1.1.3
+sphinx-book-theme==1.1.4
     # via rocm-docs-core
 sphinx-copybutton==0.5.2
     # via rocm-docs-core
@@ -249,13 +250,13 @@ sphinxcontrib-runcmd==0.2.0
     # via sphinxcontrib-datatemplates
 sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
-sqlalchemy==2.0.43
+sqlalchemy==2.0.44
     # via jupyter-cache
 stack-data==0.6.3
     # via ipython
 tabulate==0.9.0
     # via jupyter-cache
-tomli==2.2.1
+tomli==2.3.0
     # via sphinx
 tornado==6.5.2
     # via

docs/sphinx/static/css/rocm_rn.css

@@ -124,3 +124,26 @@
 #rocm-rn-components:has(tbody.rocm-components-runtimes td:hover) tr:hover > td {
   background-color: var(--pst-color-table-row-hover-bg);
 }
+
+/* Left-align text + vertically center content for any table using this class */
+.table--middle-left {
+  border-collapse: collapse; /* optional but typical for docs tables */
+  width: 100%;
+}
+
+.table--middle-left th,
+.table--middle-left td {
+  text-align: left;
+  vertical-align: middle !important; /* override Bootstrap/Sphinx defaults */
+  padding: 0.5rem; /* optional: adjust to your spacing scale */
+}
+
+/* Normalize paragraphs inside cells so margins don't disrupt centering */
+.table--middle-left th p,
+.table--middle-left td p {
+  margin: 0;
+}
+
+div.sd-row ul {
+  padding-left: 2rem;
+}

docs/what-is-rocm.rst

@@ -123,8 +123,7 @@ Performance
 
 .. note::
 
-  `ROCprof Compute Viewer <https://rocm.docs.amd.com/projects/rocprof-compute-viewer/en/amd-mainline/>`_ is a tool for visualizing and analyzing GPU thread trace data collected using :doc:`rocprofv3 <rocprofiler-sdk:index>`.
-  Note that `ROCprof Compute Viewer <https://rocm.docs.amd.com/projects/rocprof-compute-viewer/en/amd-mainline/>`_ is in an early access state. Running production workloads is not recommended.
+  `ROCprof Compute Viewer <https://rocm.docs.amd.com/projects/rocprof-compute-viewer/en/amd-mainline/>`_ is a tool for visualizing and analyzing GPU thread trace data collected using :doc:`rocprofv3 <rocprofiler-sdk:index>`. Note that `ROCprof Compute Viewer <https://rocm.docs.amd.com/projects/rocprof-compute-viewer/en/amd-mainline/>`_ is in an early access state. Running production workloads is not recommended.
 
 Development
 ^^^^^^^^^^^

tools/rocm-build/rocm-7.1.0.xml

@@ -0,0 +1,57 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest>
+    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
+    <default revision="refs/tags/rocm-7.1.0"
+     remote="rocm-org"
+     sync-c="true"
+     sync-j="4" />
+<!--list of projects for ROCm-->
+    <project name="ROCK-Kernel-Driver" />
+    <project name="amdsmi" />
+    <project name="rocm_bandwidth_test" />
+    <project name="rocm-examples" />
+<!--HIP Projects-->
+    <project name="HIPIFY" />
+<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
+    <project name="half" />
+    <project name="llvm-project" />
+    <project name="spirv-llvm-translator" />
+<!-- gdb projects -->
+    <project name="ROCdbgapi" />
+    <project name="ROCgdb" />
+    <project name="rocr_debug_agent" />
+<!-- ROCm Libraries -->
+    <project groups="mathlibs" name="AMDMIGraphX" />
+    <project groups="mathlibs" name="MIVisionX" />
+    <project groups="mathlibs" name="ROCmValidationSuite" />
+    <project groups="mathlibs" name="composable_kernel" />
+    <project groups="mathlibs" name="hipTensor" />
+    <project groups="mathlibs" name="hipfort" />
+    <project groups="mathlibs" name="rccl" />
+    <project groups="mathlibs" name="rocAL" />
+    <project groups="mathlibs" name="rocALUTION" />
+    <project groups="mathlibs" name="rocDecode" />
+    <project groups="mathlibs" name="rocJPEG" />
+    <!-- The following components have been migrated to rocm-libraries:
+        hipBLAS-common hipBLAS hipBLASLt hipCUB
+        hipFFT hipRAND hipSPARSE hipSPARSELt
+        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="rocSHMEM" />
+    <project groups="mathlibs" name="rocWMMA" />
+    <project groups="mathlibs" name="rocm-cmake" />
+    <project groups="mathlibs" name="rpp" />
+    <project groups="mathlibs" name="TransferBench" />
+<!-- Projects for OpenMP-Extras -->
+    <project name="aomp" path="openmp-extras/aomp" />
+    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
+    <project name="flang" path="openmp-extras/flang" />
+</manifest>

tools/rocm-build/rocm-7.1.1.xml

@@ -0,0 +1,60 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest>
+    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
+    <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="amdsmi" />
+    <project name="rocm_bandwidth_test" />
+    <project name="rocm-examples" />
+<!--HIP Projects-->
+    <project name="HIPIFY" />
+<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
+    <project name="half" />
+    <project name="llvm-project" />
+    <project name="spirv-llvm-translator" />
+<!-- gdb projects -->
+    <project name="ROCdbgapi" />
+    <project name="ROCgdb" />
+    <project name="rocr_debug_agent" />
+<!-- ROCm Libraries -->
+    <project groups="mathlibs" name="AMDMIGraphX" />
+    <project groups="mathlibs" name="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="hipTensor" />
+    <project groups="mathlibs" name="hipfort" />
+    <project groups="mathlibs" name="rccl" />
+    <project groups="mathlibs" name="rocAL" />
+    <project groups="mathlibs" name="rocALUTION" />
+    <project groups="mathlibs" name="rocDecode" />
+    <project groups="mathlibs" name="rocJPEG" />
+    <!-- The following components have been migrated to rocm-libraries:
+        hipBLAS-common hipBLAS hipBLASLt hipCUB
+        hipFFT hipRAND hipSPARSE hipSPARSELt
+        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="rocSHMEM" />
+    <project groups="mathlibs" name="rocSOLVER" />
+    <project groups="mathlibs" name="rocWMMA" />
+    <project groups="mathlibs" name="rocm-cmake" />
+    <project groups="mathlibs" name="rpp" />
+    <project groups="mathlibs" name="TransferBench" />
+<!-- Projects for OpenMP-Extras -->
+    <project name="aomp" path="openmp-extras/aomp" />
+    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
+    <project name="flang" path="openmp-extras/flang" />
+</manifest>