Taichi removed (#5792 )

702 Libva known issue added (#5728 )
* 702 Libva known issue added * Review feedback added * Feedback incorporated * Minor change * Github issue added * Jeff's feedback added
2026-01-10 15:18:11 -05:00 · 2025-12-19 15:43:27 -05:00 · 2025-12-02 13:45:20 -05:00 · 2025-11-20 17:59:33 +01:00 · 2025-11-04 18:09:52 -05:00 · 2025-10-28 15:20:13 -04:00
58 changed files with 7079 additions and 3723 deletions
--- a/.azuredevops/components/HIPIFY.yml
+++ b/.azuredevops/components/HIPIFY.yml
@@ -79,7 +79,7 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - task: Bash@3
      displayName: Add lit to PATH
      inputs:
--- a/.azuredevops/components/MIOpen.yml
+++ b/.azuredevops/components/MIOpen.yml
@@ -131,7 +131,7 @@ jobs:
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
@@ -212,7 +212,7 @@ jobs:
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/aqlprofile.yml
+++ b/.azuredevops/components/aqlprofile.yml
@@ -0,0 +1,174 @@
+parameters:
+- name: componentName
+  type: string
+  default: aqlprofile
+- 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
+  type: boolean
+  default: false
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+    - python3-pip
+- name: rocmDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - ROCR-Runtime
+- name: rocmTestDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - ROCR-Runtime
+    - rocprofiler-register
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+    testJobs:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool: ${{ variables.MEDIUM_BUILD_POOL }}
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        consolidateBuildAndInstall: true
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/aqlprofile/cmake_modules
+          -DAQLPROFILE_BUILD_TESTS=ON
+          -DGPU_TARGETS=${{ job.target }}
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        gpuTarget: ${{ job.target }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          gpuTarget: ${{ job.target }}
+
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.os }}_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: $(Agent.BuildDirectory)/rocm/share/hsa-amd-aqlprofile/
+          testExecutable: ./run_tests.sh
+          testParameters: ''
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
--- a/.azuredevops/components/hipBLASLt.yml
+++ b/.azuredevops/components/hipBLASLt.yml
@@ -77,6 +77,7 @@ parameters:
    - clr
    - hipBLAS-common
    - llvm-project
+    - rocm-cmake
    - rocminfo
    - rocm_smi_lib
    - rocprofiler-register
@@ -144,7 +145,7 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/hipSPARSELt.yml
+++ b/.azuredevops/components/hipSPARSELt.yml
@@ -54,6 +54,7 @@ parameters:
    - hipSPARSE
    - llvm-project
    - rocBLAS
+    - rocm-cmake
    - rocm_smi_lib
    - rocminfo
    - rocprofiler-register
@@ -67,6 +68,7 @@ parameters:
    - llvm-project
    - hipBLAS-common
    - hipBLASLt
+    - rocm-cmake
    - rocBLAS
    - rocminfo
    - rocprofiler-register
@@ -110,7 +112,7 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/hipTensor.yml
+++ b/.azuredevops/components/hipTensor.yml
@@ -77,6 +77,7 @@ jobs:
        extraBuildFlags: >-
          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/rocm/llvm
          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
          -DROCM_PATH=$(Agent.BuildDirectory)/rocm
          -DCMAKE_BUILD_TYPE=Release
          -DHIPTENSOR_BUILD_TESTS=ON
--- a/.azuredevops/components/hipfort.yml
+++ b/.azuredevops/components/hipfort.yml
@@ -71,7 +71,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/origami.yml
+++ b/.azuredevops/components/origami.yml
@@ -39,6 +39,9 @@ parameters:
    - python3
    - python3-dev
    - python3-pip
+    - libgtest-dev
+    - libboost-filesystem-dev
+    - libboost-program-options-dev
 - name: pipModules
  type: object
  default:
@@ -107,8 +110,12 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
@@ -125,7 +132,7 @@ jobs:
      parameters:
        os: ${{ job.os }}
        extraBuildFlags: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
          -DORIGAMI_BUILD_SHARED_LIBS=ON
          -DORIGAMI_ENABLE_PYTHON=ON
@@ -206,7 +213,15 @@ jobs:
          ${{ if parameters.triggerDownstreamJobs }}:
            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './origami-tests'
+          testParameters: '--yaml origami-tests.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
      - script: |
+          set -e
          export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH

          echo "--- Running origami_test.py ---"
--- a/.azuredevops/components/rccl.yml
+++ b/.azuredevops/components/rccl.yml
@@ -83,7 +83,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/rdc.yml
+++ b/.azuredevops/components/rdc.yml
@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rdc
 - 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
@@ -33,6 +52,7 @@ parameters:
    - clr
    - hipBLAS-common
    - hipBLASLt
+    - hipRAND
    - llvm-project
    - rocBLAS
    - rocm-cmake
@@ -43,6 +63,7 @@ parameters:
    - rocprofiler
    - rocprofiler-register
    - rocprofiler-sdk
+    - rocRAND
    - ROCR-Runtime
 - name: rocmTestDependencies
  type: object
@@ -74,7 +95,11 @@ parameters:

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rdc_build_${{ 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
@@ -85,16 +110,22 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.25.0'
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
      parameters:
        checkoutRef: ${{ parameters.checkoutRef }}
        dependencyList: ${{ parameters.rocmDependencies }}
        gpuTarget: ${{ job.target }}
        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
  # Build grpc
    - task: Bash@3
      displayName: 'git clone grpc'
@@ -104,6 +135,7 @@ jobs:
        workingDirectory: $(Build.SourcesDirectory)
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
      parameters:
+        componentName: ${{ parameters.componentName }}
        cmakeBuildDir: $(Build.SourcesDirectory)/grpc/build
        cmakeSourceDir: $(Build.SourcesDirectory)/grpc
        installDir: $(Build.SourcesDirectory)/bin
@@ -117,6 +149,7 @@ jobs:
          -GNinja
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
      parameters:
+        componentName: ${{ parameters.componentName }}
        extraBuildFlags: >-
          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
          -DGRPC_ROOT="$(Build.SourcesDirectory)/bin"
@@ -126,9 +159,12 @@ jobs:
          -DAMDGPU_TARGETS=${{ job.target }}
    - 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
@@ -136,60 +172,64 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        gpuTarget: ${{ job.target }}

- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rdc_test_${{ job.target }}
-    dependsOn: rdc_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    - name: ROCM_PATH
-      value: $(Agent.BuildDirectory)/rocm
-    - name: ROCM_DIR
-      value: $(Agent.BuildDirectory)/rocm
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - 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 }}
-    - task: Bash@3
-      displayName: Setup test environment
-      inputs:
-        targetType: inline
-        script: |
-          sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rdcd /usr/sbin/rdcd
-          echo $(Agent.BuildDirectory)/rocm/lib/rdc/grpc/lib | sudo tee /etc/ld.so.conf.d/grpc.conf
-          sudo ldconfig -v
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - task: Bash@3
-      displayName: Test rdc
-      inputs:
-        targetType: inline
-        script: >-
-          $(Agent.BuildDirectory)/rocm/share/rdc/rdctst_tests/rdctst
-          --batch_mode
-          --start_rdcd
-          --unauth_comm
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
-        extraPaths: /home/user/workspace/rocm/bin
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_${{ job.target }}
+      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
+      - name: ROCM_PATH
+        value: $(Agent.BuildDirectory)/rocm
+      - name: ROCM_DIR
+        value: $(Agent.BuildDirectory)/rocm
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - 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 }}
+      - task: Bash@3
+        displayName: Setup test environment
+        inputs:
+          targetType: inline
+          script: |
+            sudo ln -s $(Agent.BuildDirectory)/rocm/bin/rdcd /usr/sbin/rdcd
+            echo $(Agent.BuildDirectory)/rocm/lib/rdc/grpc/lib | sudo tee /etc/ld.so.conf.d/grpc.conf
+            sudo ldconfig -v
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - task: Bash@3
+        displayName: Test rdc
+        inputs:
+          targetType: inline
+          script: >-
+            $(Agent.BuildDirectory)/rocm/share/rdc/rdctst_tests/rdctst
+            --batch_mode
+            --start_rdcd
+            --unauth_comm
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+          extraPaths: /home/user/workspace/rocm/bin
--- a/.azuredevops/components/rocBLAS.yml
+++ b/.azuredevops/components/rocBLAS.yml
@@ -70,6 +70,7 @@ parameters:
    - hipBLAS-common
    - hipBLASLt
    - llvm-project
+    - rocm-cmake
    - rocminfo
    - rocprofiler-register
    - rocm_smi_lib
@@ -154,7 +155,7 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/rocm-examples.yml
+++ b/.azuredevops/components/rocm-examples.yml
@@ -33,16 +33,20 @@ parameters:
    - hipRAND
    - hipSOLVER
    - hipSPARSE
+    - hipTensor
    - llvm-project
    - rocBLAS
    - rocFFT
+    - rocJPEG
    - rocPRIM
    - rocprofiler-register
+    - rocprofiler-sdk
    - ROCR-Runtime
    - rocRAND
    - rocSOLVER
    - rocSPARSE
    - rocThrust
+    - rocWMMA
 - name: rocmTestDependencies
  type: object
  default:
@@ -57,18 +61,22 @@ parameters:
    - hipRAND
    - hipSOLVER
    - hipSPARSE
+    - hipTensor
    - llvm-project
    - rocBLAS
    - rocFFT
    - rocminfo
    - rocPRIM
+    - rocJPEG
    - rocprofiler-register
+    - rocprofiler-sdk
    - ROCR-Runtime
    - rocRAND
    - rocSOLVER
    - rocSPARSE
    - rocThrust
    - roctracer
+    - rocWMMA

 - name: jobMatrix
  type: object
@@ -97,6 +105,9 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.25.0'
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
@@ -158,6 +169,9 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.25.0'
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/rocm-libraries.yml
+++ b/.azuredevops/components/rocm-libraries.yml
@@ -102,7 +102,7 @@ jobs:
    workspace:
      clean: all
    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
--- a/.azuredevops/components/rocprofiler-sdk.yml
+++ b/.azuredevops/components/rocprofiler-sdk.yml
@@ -213,6 +213,7 @@ jobs:
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
        parameters:
          componentName: ${{ parameters.componentName }}
+          testDir: $(Agent.BuildDirectory)/s/build
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
        parameters:
          aptPackages: ${{ parameters.aptPackages }}
--- a/.azuredevops/components/rocprofiler-systems.yml
+++ b/.azuredevops/components/rocprofiler-systems.yml
@@ -226,8 +226,11 @@ jobs:
            echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
        parameters:
+          cmakeSourceDir: $(Agent.BuildDirectory)/s/projects/rocprofiler-systems
    # build flags reference: https://rocm.docs.amd.com/projects/omnitrace/en/latest/install/install.html
          extraBuildFlags: >-
+            -DCMAKE_INSTALL_PREFIX=$(Agent.BuildDirectory)/rocprofiler-systems
+            -DROCPROFSYS_USE_PYTHON=ON
            -DROCPROFSYS_BUILD_TESTING=ON
            -DROCPROFSYS_BUILD_DYNINST=ON
            -DROCPROFSYS_BUILD_LIBUNWIND=ON
@@ -245,11 +248,13 @@ jobs:
        displayName: Set up rocprofiler-systems env
        inputs:
          targetType: inline
-          script: source share/rocprofiler-systems/setup-env.sh
-          workingDirectory: build
+          script: source $(Agent.BuildDirectory)/rocprofiler-systems/share/rocprofiler-systems/setup-env.sh
+          workingDirectory: $(Agent.BuildDirectory)/rocprofiler-systems/share/rocprofiler-systems
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
        parameters:
          componentName: ${{ parameters.componentName }}
+          testDir: $(Agent.BuildDirectory)/s/build/tests/
+          testParameters: '--output-on-failure'
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
        parameters:
          gpuTarget: ${{ job.target }}
--- a/.azuredevops/templates/steps/dependencies-cmake-custom.yml
+++ b/.azuredevops/templates/steps/dependencies-cmake-custom.yml
@@ -1,10 +1,15 @@
+parameters:
+  - name: cmakeVersion
+    type: string
+    default: '3.31.0'
+
 steps:
 - task: Bash@3
-  displayName: Install CMake 3.31
+  displayName: Install CMake ${{ parameters.cmakeVersion }}
  inputs:
    targetType: inline
    script: |
-      CMAKE_VERSION=3.31.0
+      CMAKE_VERSION=${{ parameters.cmakeVersion }}
      CMAKE_ROOT="$(Pipeline.Workspace)/cmake"

      echo "Downloading CMake $CMAKE_VERSION..."
--- a/.azuredevops/templates/steps/dependencies-rocm.yml
+++ b/.azuredevops/templates/steps/dependencies-rocm.yml
@@ -46,6 +46,10 @@ parameters:
      pipelineId: 115
      developBranch: aomp-dev
      hasGpuTarget: false
+    aqlprofile:
+      pipelineId: 365
+      developBranch: develop
+      hasGpuTarget: false
    clr:
      pipelineId: 335
      developBranch: develop
@@ -126,13 +130,17 @@ parameters:
      pipelineId: 80
      developBranch: develop
      hasGpuTarget: true
+    origami:
+      pipelineId: 364
+      developBranch: develop
+      hasGpuTarget: true
    rccl:
      pipelineId: 107
      developBranch: develop
      hasGpuTarget: true
    rdc:
-      pipelineId: 100
-      developBranch: amd-staging
+      pipelineId: 360
+      developBranch: develop
      hasGpuTarget: false
    rocAL:
      pipelineId: 151
@@ -219,8 +227,8 @@ parameters:
      developBranch: develop
      hasGpuTarget: true
    rocprofiler-systems:
-      pipelineId: 255
-      developBranch: amd-staging
+      pipelineId: 345
+      developBranch: develop
      hasGpuTarget: true
    rocPyDecode:
      pipelineId: 239
--- a/.wordlist.txt
+++ b/.wordlist.txt
@@ -27,6 +27,7 @@ ASICs
 ASan
 ASAN
 ASm
+Async
 ATI
 atomicRMW
 AddressSanitizer
@@ -130,6 +131,7 @@ ELMo
 ENDPGM
 EPYC
 ESXi
+EP
 EoS
 etcd
 fas
@@ -181,6 +183,7 @@ GPR
 GPT
 GPU
 GPU's
+GPUDirect
 GPUs
 Graphbolt
 GraphSage
@@ -299,6 +302,7 @@ Makefiles
 Matplotlib
 Matrox
 MaxText
+MBT
 Megablocks
 Megatrends
 Megatron
@@ -308,6 +312,7 @@ Meta's
 Miniconda
 MirroredStrategy
 Mixtral
+MLA
 MosaicML
 MoEs
 Mooncake
@@ -350,6 +355,7 @@ OFED
 OMM
 OMP
 OMPI
+OOM
 OMPT
 OMPX
 ONNX
@@ -396,6 +402,7 @@ Profiler's
 PyPi
 Pytest
 PyTorch
+QPS
 Qcycles
 Qwen
 RAII
@@ -669,12 +676,14 @@ denoised
 denoises
 denormalize
 dequantization
+dequantized
 dequantizes
 deserializers
 detections
 dev
 devicelibs
 devsel
+dgl
 dimensionality
 disambiguates
 distro
@@ -783,6 +792,7 @@ linalg
 linearized
 linter
 linux
+llm
 llvm
 lm
 localscratch
@@ -833,6 +843,7 @@ passthrough
 pe
 perfcounter
 performant
+piecewise
 perl
 pragma
 pre
@@ -979,6 +990,7 @@ tokenizer
 tokenizes
 toolchain
 toolchains
+topk
 toolset
 toolsets
 torchtitan
@@ -1006,6 +1018,7 @@ USM
 UTCL
 UTIL
 utils
+UX
 vL
 variational
 vdi
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,116 @@ 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 7.0.2
+
+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)
+for a complete overview of this release.
+
+### **AMD SMI** (26.0.2)
+
+#### Added
+
+* Added `bad_page_threshold_exceeded` field to `amd-smi static --ras`, which compares retired pages count against bad page threshold. This field displays `True` if retired pages exceed the threshold, `False` if within threshold, or `N/A` if threshold data is unavailable. Note that `sudo` is required to have the `bad_page_threshold_exceeded` field populated.
+
+#### Removed
+
+* Removed gpuboard and baseboard temperatures enums in amdsmi Python Library.
+    * `AmdSmiTemperatureType` had issues with referencing the correct attribute. As such, the following duplicate enums have been removed:
+        - `AmdSmiTemperatureType.GPUBOARD_NODE_FIRST`
+        - `AmdSmiTemperatureType.GPUBOARD_VR_FIRST`
+        - `AmdSmiTemperatureType.BASEBOARD_FIRST`
+
+#### Resolved Issues
+
+* Fixed `attribute error` in `amd-smi monitor` on Linux Guest systems, where the violations argument caused CLI to break.
+* Fixed certain output in `amd-smi monitor` when GPUs are partitioned.  
+  * It fixes the amd-smi monitor such as: `amd-smi monitor -Vqt`, `amd-smi monitor -g 0 -Vqt -w 1`, `amd-smi monitor -Vqt --file /tmp/test1`, etc. These commands will now be able to display as normal in partitioned GPU scenarios.
+
+* Fixed an issue where using `amd-smi ras --folder <folder_name>` was forcing the created folder's name to be lowercase. This fix also allows all string input options to be case insensitive.
+
+* Fixed an issue of some processes not being detected by AMD SMI despite making use of KFD resources. This fix, with the addition of KFD Fallback for process detection, ensures that all KFD processes will be detected.
+
+* Multiple CPER issues were fixed.  
+  - Issue of being unable to query for additional CPERs after 20 were generated on a single device.
+  - Issue where the RAS HBM CRC read was failing due to an incorrect AFID value.
+  - Issue where RAS injections were not consistently producing related CPERs.
+
+### **HIP** (7.0.2)
+
+#### Added
+
+* Support for the `hipMemAllocationTypeUncached` flag, enabling developers to allocate uncached memory. This flag is now supported in the following APIs:
+    - `hipMemGetAllocationGranularity` determines the recommended allocation granularity for uncached memory.
+    - `hipMemCreate` allocates memory with uncached properties.
+
+#### Resolved issues
+
+* A compilation failure affecting applications that compile kernels using `hiprtc` with the compiler option `std=c++11`.
+* A permission-related error occurred during the execution of `hipLaunchHostFunc`. This API is now supported and permitted to run during stream capture, aligning its behavior with CUDA.
+* A numerical error during graph capture of kernels that rely on a remainder in `globalWorkSize`, in frameworks like MIOpen and PyTorch, where the grid size is not a multiple of the block size. To ensure correct replay behavior, HIP runtime now stores this remainder in `hip::GraphKernelNode` during `hipExtModuleLaunchKernel` capture, enabling accurate execution and preventing corruption.
+* A page fault occurred during viewport rendering while running the file undo.blend in Blender. The issue was resolved by the HIP runtime, which reused the same context during image creation.
+* Resolved a segmentation fault in `gpu_metrics`, which is used in threshold logic for command submission patches to GPU device(s) during CPU synchronization.
+
+### **hipBLAS** (3.0.2)
+ 
+#### Added
+ 
+* Enabled support for gfx1150, gfx1151, gfx1200, and gfx1201 AMD hardware.
+
+### **RCCL** (2.26.6)
+
+#### Added
+
+* Enabled double-buffering in `reduceCopyPacks` to trigger pipelining, especially to overlap bf16 arithmetic.
+* Added `--force-reduce-pipeline` as an option that can be passed to the `install.sh` script. Passing this option will enable software-triggered pipelining `bfloat16` reductions (that is, `all_reduce`, `reduce_scatter`, and `reduce`).
+
+### **rocBLAS** (5.0.2)
+ 
+#### Added
+ 
+* Enabled gfx1150 and gfx1151.
+* The `ROCBLAS_USE_HIPBLASLT_BATCHED` variable to independently control the batched hipblaslt backend. Set `ROCBLAS_USE_HIPBLASLT_BATCHED=0` to disable batched GEMM use of the hipblaslt backend.
+
+#### Resolved issues
+ 
+* Set the imaginary portion of the main diagonal of the output matrix to zero in syrk and herk.
+
+### **ROCdbgapi** (0.77.4)
+
+#### Added
+
+* ROCdbgapi documentation link in the README.md file.
+
+### **ROCm Systems Profiler** (1.1.1)
+
+#### Resolved issues
+
+* Fixed an issue where ROC-TX ranges were displayed as two separate events instead of a single spanning event.
+
+### **rocPRIM** (4.0.1)
+
+#### Resolved issues
+
+* Fixed compilation issue when using `rocprim::texture_cache_iterator`.
+* Fixed a HIP version check used to determine whether `hipStreamLegacy` is supported. This resolves runtime errors that occur when `hipStreamLegacy` is used in ROCm 7.0.0 and later.
+
+### **rocSPARSE** (4.0.3)
+
+#### Resolved issues
+
+* Fixed an issue causing premature deallocation of internal buffers while still in use.
+
+### **rocSOLVER** (3.30.1)
+
+#### Optimized
+
+Improved the performance of:
+
+* LARFT and downstream functions such as GEQRF and ORMTR.
+* LARF and downstream functions such as GEQR2.
+* ORMTR and downstream functions such as SYEVD.
+* GEQR2 and downstream functions such as GEQRF.
+
 ## ROCm 7.0.1

 ROCm 7.0.1 is a quality release that resolves the existing issue. There is no change in component from the previous ROCm 7.0.0 release. See the [ROCm 7.0.1 release notes](https://rocm.docs.amd.com/en/docs-7.0.1/about/release-notes.html#rocm-7-0-1-release-notes) for a complete overview of this release.
@@ -802,11 +912,15 @@ HIP runtime has the following functional improvements which improves runtime per
 * Compatibility with NCCL 2.25.1.
 * Compatibility with NCCL 2.26.6.

+#### Optimized
+* Improved the performance of the `FP8` Sum operation by upcasting to `FP16`.
+
 #### Resolved issues

 * Resolved an issue when using more than 64 channels when multiple collectives are used in the same `ncclGroup()` call.
 * Fixed unit test failures in tests ending with the `ManagedMem` and `ManagedMemGraph` suffixes.
 * Fixed a suboptimal algorithmic switching point for AllReduce on the AMD Instinct MI300X.
+* Fixed broken functionality within the LL protocol on gfx950 by disabling inlining of LLGenericOp kernels.
 * Fixed the known issue "When splitting a communicator using `ncclCommSplit` in some GPU configurations, MSCCL initialization can cause a segmentation fault" with a design change to use `comm` instead of `rank` for `mscclStatus`. The global map for `comm` to `mscclStatus` is still not thread safe but should be explicitly handled by mutexes for read-write operations. This is tested for correctness, but there is a plan to use a thread-safe map data structure in an upcoming release.

 ### **rocAL** (2.3.0)
--- a/RELEASE.md
+++ b/RELEASE.md
--- a/default.xml
+++ b/default.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-7.0.1"
+    <default revision="refs/tags/rocm-7.0.2"
     remote="rocm-org"
     sync-c="true"
     sync-j="4" />
@@ -41,7 +41,6 @@
    <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" />
@@ -57,7 +56,6 @@
    <project groups="mathlibs" name="rocm-libraries" />
    <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" />
--- a/docs/compatibility/compatibility-matrix-historical-6.0.csv
+++ b/docs/compatibility/compatibility-matrix-historical-6.0.csv
@@ -1,136 +1,136 @@
-ROCm Version,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 24.04.2,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, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
-      ,,,,,,,,,,,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
-      ,"RHEL 9.6, 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-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, 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 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 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-630-past-60]_,Azure Linux 3.0 [#az-mi300x-630-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,,,,,,,,,,,,,,,,,,
-,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
-      ,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
-      ,RDNA4,RDNA4,RDNA4,RDNA4,,,,,,,,,,,,,,,
-      ,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
-      ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx950 [#mi350x-os-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-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-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,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,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,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,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
-      ,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>`,"2.7, 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]_","2.18.1, 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>`,0.6.0,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
-      :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,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,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,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,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,N/A,2.48.0.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]_,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,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>`_,1.22.0,1.20.0,1.20.0,1.20.0,1.20.0,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
-,,,,,,,,,,,,,,,,,,,
-      ,,,,,,,,,,,,,,,,,,,
-      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
-      `UCC <https://github.com/ROCm/ucc>`_,>=1.4.0,>=1.3.0,>=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,>=1.15.0,>=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,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      CUB,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-,,,,,,,,,,,,,,,,,,,
-     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>`,"30.10.1 [#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
-      :doc:`MIGraphX <amdmigraphx:index>`,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>`,3.5.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`MIVisionX <mivisionx:index>`,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
-      :doc:`rocAL <rocal:index>`,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`rocDecode <rocdecode:index>`,1.0.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
-      :doc:`rocJPEG <rocjpeg:index>`,1.1.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`rocPyDecode <rocpydecode:index>`,0.6.0,0.3.1,0.3.1,0.3.1,0.3.1,0.2.0,0.2.0,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`RPP <rpp:index>`,2.0.0,1.9.10,1.9.10,1.9.10,1.9.10,1.9.1,1.9.1,1.9.1,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
-      ,,,,,,,,,,,,,,,,,,,
-      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
-      :doc:`RCCL <rccl:index>`,2.26.6,2.22.3,2.22.3,2.22.3,2.22.3,2.21.5,2.21.5,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
-      :doc:`rocSHMEM <rocshmem:index>`,3.0.0,2.0.1,2.0.1,2.0.0,2.0.0,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
-      :doc:`hipBLAS <hipblas:index>`,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>`,1.0.0,0.12.1,0.12.1,0.12.1,0.12.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
-      :doc:`hipFFT <hipfft:index>`,1.0.20,1.0.18,1.0.18,1.0.18,1.0.18,1.0.17,1.0.17,1.0.17,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
-      :doc:`hipfort <hipfort:index>`,0.7.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.1,0.5.1,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
-      :doc:`hipRAND <hiprand:index>`,3.0.0,2.12.0,2.12.0,2.12.0,2.12.0,2.11.1,2.11.1,2.11.1,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
-      :doc:`hipSOLVER <hipsolver:index>`,3.0.0,2.4.0,2.4.0,2.4.0,2.4.0,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
-      :doc:`hipSPARSE <hipsparse:index>`,4.0.1,3.2.0,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.4,0.2.3,0.2.3,0.2.3,0.2.3,0.2.2,0.2.2,0.2.2,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
-      :doc:`rocALUTION <rocalution:index>`,4.0.0,3.2.3,3.2.3,3.2.3,3.2.2,3.2.1,3.2.1,3.2.1,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
-      :doc:`rocBLAS <rocblas:index>`,5.0.0,4.4.1,4.4.1,4.4.0,4.4.0,4.3.0,4.3.0,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
-      :doc:`rocFFT <rocfft:index>`,1.0.34,1.0.32,1.0.32,1.0.32,1.0.32,1.0.31,1.0.31,1.0.31,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
-      :doc:`rocRAND <rocrand:index>`,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
-      :doc:`rocSOLVER <rocsolver:index>`,3.30.0,3.28.2,3.28.2,3.28.0,3.28.0,3.27.0,3.27.0,3.27.0,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
-      :doc:`rocSPARSE <rocsparse:index>`,4.0.2,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
-      :doc:`rocWMMA <rocwmma:index>`,2.0.0,1.7.0,1.7.0,1.7.0,1.7.0,1.6.0,1.6.0,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
-      :doc:`Tensile <tensile:src/index>`,4.44.0,4.43.0,4.43.0,4.43.0,4.43.0,4.42.0,4.42.0,4.42.0,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
-      ,,,,,,,,,,,,,,,,,,,
-      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
-      :doc:`hipCUB <hipcub:index>`,4.0.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`hipTensor <hiptensor:index>`,2.0.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
-      :doc:`rocPRIM <rocprim:index>`,4.0.0,3.4.1,3.4.1,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`rocThrust <rocthrust:index>`,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      ,,,,,,,,,,,,,,,,,,,
-      SUPPORT LIBS,,,,,,,,,,,,,,,,,,,
-      `hipother <https://github.com/ROCm/hipother>`_,7.0.51830,6.4.43483,6.4.43483,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
-      `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]_,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>`,26.0.0,25.5.1,25.5.1,25.4.2,25.3.0,24.7.1,24.7.1,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
-      :doc:`ROCm Data Center Tool <rdc:index>`,1.1.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
-      :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
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,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>`,1.2.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60105,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
-      ,,,,,,,,,,,,,,,,,,,
-      PERFORMANCE TOOLS,,,,,,,,,,,,,,,,,,,
-      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
-      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.2.3,3.1.1,3.1.1,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.1.0,1.0.2,1.0.2,1.0.1,1.0.0,0.1.2,0.1.1,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70000,2.0.60403,2.0.60402,2.0.60401,2.0.60400,2.0.60303,2.0.60302,2.0.60301,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
-      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.0.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCTracer <roctracer:index>`,4.1.70000,4.1.60403,4.1.60402,4.1.60401,4.1.60400,4.1.60303,4.1.60302,4.1.60301,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
-      ,,,,,,,,,,,,,,,,,,,
-      DEVELOPMENT TOOLS,,,,,,,,,,,,,,,,,,,
-      :doc:`HIPIFY <hipify:index>`,20.0.0,19.0.0,19.0.0,19.0.0,19.0.0,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
-      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.3,0.77.2,0.77.2,0.77.2,0.77.2,0.77.0,0.77.0,0.77.0,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
-      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
-      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.0.4,2.0.4,2.0.4,2.0.4,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
-      ,,,,,,,,,,,,,,,,,,,
-      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,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
-      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      `Flang <https://github.com/ROCm/flang>`_,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`llvm-project <llvm-project:index>`,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-,,,,,,,,,,,,,,,,,,,
-      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      :doc:`HIP <hip:index>`,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `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
-      :doc:`ROCr Runtime <rocr-runtime:index>`,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,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 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:`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>`_,7.0.51831,7.0.51830,6.4.43483,6.4.43483,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
+      `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
--- a/docs/compatibility/compatibility-matrix.rst
+++ b/docs/compatibility/compatibility-matrix.rst
@@ -23,20 +23,20 @@ compatibility and system requirements.
 .. container:: format-big-table

  .. csv-table::
-      :header: "ROCm Version", "7.0.1/7.0.0", "6.4.3", "6.3.0"
+      :header: "ROCm Version", "7.0.2", "7.0.1/7.0.0", "6.4.0"
      :stub-columns: 1

-      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.3,Ubuntu 24.04.2,Ubuntu 24.04.2
+      :ref:`Operating systems & kernels <OS-kernel-versions>`,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 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.5, 9.4"
-      ,RHEL 8.10 [#rhel-700]_,RHEL 8.10,RHEL 8.10
-      ,SLES 15 SP7 [#sles-db-700]_,"SLES 15 SP7, SP6","SLES 15 SP6, SP5"
-      ,"Oracle Linux 9, 8 [#ol-700-mi300x]_","Oracle Linux 9, 8 [#ol-mi300x]_",Oracle Linux 8.10 [#ol-mi300x]_
-      ,Debian 12 [#sles-db-700]_,Debian 12 [#single-node]_,
-      ,Azure Linux 3.0 [#az-mi300x]_,Azure Linux 3.0 [#az-mi300x]_,
-      ,Rocky Linux 9 [#rl-700]_,,
+      ,"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]_,
      ,.. _architecture-support-compatibility-matrix:,,
-      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,,
+      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,CDNA4,
      ,CDNA3,CDNA3,CDNA3
      ,CDNA2,CDNA2,CDNA2
      ,CDNA,CDNA,CDNA
@@ -44,140 +44,140 @@ 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]_,,
-      ,gfx1201 [#RDNA-OS-700]_,gfx1201 [#RDNA-OS]_,
-      ,gfx1200 [#RDNA-OS-700]_,gfx1200 [#RDNA-OS]_,
-      ,gfx1101 [#RDNA-OS-700]_ [#rd-v710]_,gfx1101 [#RDNA-OS]_ [#7700XT-OS]_,
-      ,gfx1100 [#RDNA-OS-700]_,gfx1100,gfx1100
-      ,gfx1030 [#RDNA-OS-700]_ [#rd-v620]_,gfx1030,gfx1030
-      ,gfx942 [#mi325x-os]_ [#mi300x-os]_ [#mi300A-os]_,gfx942,gfx942
-      ,gfx90a [#mi200x-os]_,gfx90a,gfx90a
-      ,gfx908 [#mi100-os]_,gfx908,gfx908
+      :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
      ,,,
      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix:,,
-      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.7, 2.6, 2.5","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 2.1, 2.0, 1.13"
-      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.19.1, 2.18.1, 2.17.1 [#tf-mi350]_","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1"
-      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.6.0,0.4.35,0.4.31
-      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat]_,N/A,N/A,85f95ae
-      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat]_,N/A,N/A,0.7.0
-      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat]_,b6356,b6356,N/A
-      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.22.0,1.20.0,1.17.3
+      :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:`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
      ,,,
      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
-      `UCC <https://github.com/ROCm/ucc>`_,>=1.4.0,>=1.3.0,>=1.3.0
-      `UCX <https://github.com/ROCm/ucx>`_,>=1.17.0,>=1.15.0,>=1.15.0
+      `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,2.6.0,2.5.0,2.3.2
-      CUB,2.6.0,2.5.0,2.3.2
+      Thrust,2.6.0,2.6.0,2.5.0
+      CUB,2.6.0,2.6.0,2.5.0
      ,,,
      DRIVER & USER SPACE [#kfd_support]_,.. _kfd-userspace-support-compatibility-matrix:,,
-      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.10.1 [#driver_patch]_, 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"
+      :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"
      ,,,
      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>`,2.13.0,2.12.0,2.11.0
-      :doc:`MIOpen <miopen:index>`,3.5.0,3.4.0,3.3.0
-      :doc:`MIVisionX <mivisionx:index>`,3.3.0,3.2.0,3.1.0
-      :doc:`rocAL <rocal:index>`,2.3.0,2.2.0,2.1.0
-      :doc:`rocDecode <rocdecode:index>`,1.0.0,0.10.0,0.8.0
-      :doc:`rocJPEG <rocjpeg:index>`,1.1.0,0.8.0,0.6.0
-      :doc:`rocPyDecode <rocpydecode:index>`,0.6.0,0.3.1,0.2.0
-      :doc:`RPP <rpp:index>`,2.0.0,1.9.10,1.9.1
+      :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
      ,,,
      COMMUNICATION,.. _commlibs-support-compatibility-matrix:,,
-      :doc:`RCCL <rccl:index>`,2.26.6,2.22.3,2.21.5
-      :doc:`rocSHMEM <rocshmem:index>`,3.0.0,2.0.1,N/A
+      :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
      ,,,
      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>`,3.0.0,2.4.0,2.3.0
-      :doc:`hipBLASLt <hipblaslt:index>`,1.0.0,0.12.1,0.10.0
-      :doc:`hipFFT <hipfft:index>`,1.0.20,1.0.18,1.0.17
-      :doc:`hipfort <hipfort:index>`,0.7.0,0.6.0,0.5.0
-      :doc:`hipRAND <hiprand:index>`,3.0.0,2.12.0,2.11.0
-      :doc:`hipSOLVER <hipsolver:index>`,3.0.0,2.4.0,2.3.0
-      :doc:`hipSPARSE <hipsparse:index>`,4.0.1,3.2.0,3.1.2
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.4,0.2.3,0.2.2
-      :doc:`rocALUTION <rocalution:index>`,4.0.0,3.2.3,3.2.1
-      :doc:`rocBLAS <rocblas:index>`,5.0.0,4.4.1,4.3.0
-      :doc:`rocFFT <rocfft:index>`,1.0.34,1.0.32,1.0.31
-      :doc:`rocRAND <rocrand:index>`,4.0.0,3.3.0,3.2.0
-      :doc:`rocSOLVER <rocsolver:index>`,3.30.0,3.28.2,3.27.0
-      :doc:`rocSPARSE <rocsparse:index>`,4.0.2,3.4.0,3.3.0
-      :doc:`rocWMMA <rocwmma:index>`,2.0.0,1.7.0,1.6.0
-      :doc:`Tensile <tensile:src/index>`,4.44.0,4.43.0,4.42.0
+      :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:`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>`,4.0.0,3.4.0,3.3.0
-      :doc:`hipTensor <hiptensor:index>`,2.0.0,1.5.0,1.4.0
-      :doc:`rocPRIM <rocprim:index>`,4.0.0,3.4.1,3.3.0
-      :doc:`rocThrust <rocthrust:index>`,4.0.0,3.3.0,3.3.0
+      :doc:`hipCUB <hipcub:index>`,4.0.0,4.0.0,3.4.0
+      :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
      ,,,
      SUPPORT LIBS,,,
-      `hipother <https://github.com/ROCm/hipother>`_,7.0.51830,6.4.43483,6.3.42131
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.1/7.0.0,6.4.3,6.3.0
+      `hipother <https://github.com/ROCm/hipother>`_,7.0.51831,7.0.51830,6.4.43482
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.2,7.0.1/7.0.0,6.4.0
      `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>`,26.0.0,25.5.1,24.7.1
-      :doc:`ROCm Data Center Tool <rdc:index>`,1.1.0,0.3.0,0.3.0
+      :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:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.8.0,7.7.0,7.4.0
-      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.2.0,1.1.0,1.1.0
+      :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>`,2.6.0,1.4.0,1.4.0
-      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.2.3,3.1.1,3.0.0
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.1.0,1.0.2,0.1.0
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70000,2.0.60403,2.0.60300
-      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.0.0,0.6.0,0.5.0
-      :doc:`ROCTracer <roctracer:index>`,4.1.70000,4.1.60403,4.1.60300
+      :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:`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
      ,,,
      DEVELOPMENT TOOLS,,,
-      :doc:`HIPIFY <hipify:index>`,20.0.0,19.0.0,18.0.0.24455
+      :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>`,0.77.3,0.77.2,0.77.0
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,15.2.0,15.2.0
-      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.4.0,0.4.0
-      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.0.4,2.0.3
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.4,0.77.3,0.77.2
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,16.3.0,15.2.0
+      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.5.0,0.4.0
+      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.1.0,2.0.4
      ,,,
      COMPILERS,.. _compilers-support-compatibility-matrix:,,
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A
      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1
-      `Flang <https://github.com/ROCm/flang>`_,20.0.0.25314,19.0.0.25224,18.0.0.24455
-      :doc:`llvm-project <llvm-project:index>`,20.0.0.25314,19.0.0.25224,18.0.0.24491
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,20.0.0.25314,19.0.0.25224,18.0.0.24491
+      `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
      ,,,
      RUNTIMES,.. _runtime-support-compatibility-matrix:,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,7.0.51830,6.4.43484,6.3.42131
-      :doc:`HIP <hip:index>`,7.0.51830,6.4.43484,6.3.42131
+      :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
      `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>`,1.18.0,1.15.0,1.14.0
+      :doc:`ROCr Runtime <rocr-runtime:index>`,1.18.0,1.18.0,1.15.0

 .. rubric:: Footnotes

-.. [#rhel-700] RHEL 8.10 is only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, MI210, and MI100 GPUs.
-.. [#ol-700-mi300x] **For ROCm 7.0.x** - Oracle Linux 9 is supported only on AMD Instinct MI355X, MI350X, and MI300X GPUs. Oracle Linux 8 is supported only on AMD Instinct MI300X GPUs.
+.. [#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.
-.. [#sles-db-700] **For ROCm 7.0.x** - SLES 15 SP7 and Debian 12 are only supported 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.
-.. [#rl-700] Rocky Linux 9 is only supported on AMD Instinct MI300X and MI300A GPUs.
-.. [#single-node] **Prior to ROCm 7.0.0** - Debian 12 is supported only on AMD Instinct MI300X for single-node functionality.
-.. [#mi350x-os] AMD Instinct MI355X (gfx950) and MI350X(gfx950) GPUs are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, 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 7800 XT (gfx1101), AMD Radeon RX 7700 XT (gfx1101), AMD Radeon PRO W7700 (gfx1101), and AMD Radeon PRO W6800 (gfx1030) are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, and RHEL 9.6.
-.. [#RDNA-OS] **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] **For ROCm 7.0.x** - AMD Radeon PRO V710 (gfx1101) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and Azure Linux 3.0.
-.. [#rd-v620] **For ROCm 7.0.x** - AMD Radeon PRO V620 (gfx1030) is only supported on Ubuntu 24.04.3 and Ubuntu 22.04.5.
-.. [#mi325x-os] **For ROCm 7.0.x** - AMD Instinct MI325X GPU (gfx942) is only supported 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 GPU (gfx942) is supported on all listed :ref:`supported_distributions`.
-.. [#mi300A-os] **For ROCm 7.0.x** - AMD Instinct MI300A GPU (gfx942) is supported only on Ubuntu 24.04, Ubuntu 22.04, 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, Ubuntu 22.04, 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 GPU (gfx908) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
-.. [#7700XT-OS] **Prior ROCm 7.0.0** - Radeon RX 7700 XT (gfx1101) is supported only on Ubuntu 24.04.2 and RHEL 9.6.
-.. [#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.
-.. [#stanford-megatron-lm_compat] Stanford Megatron-LM is only supported on ROCm 6.3.0.
-.. [#megablocks_compat] Megablocks is only supported on ROCm 6.3.0.
-.. [#llama-cpp_compat] llama.cpp is only supported on ROCm 7.0.0 and 6.4.x.
+.. [#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.
+.. [#llama-cpp_compat] llama.cpp is supported only on ROCm 7.0.0 and ROCm 6.4.x.
 .. [#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.
@@ -201,6 +201,8 @@ Use this lookup table to confirm which operating system and kernel versions are
   ,,
   `Ubuntu <https://ubuntu.com/about/release-cycle#ubuntu-kernel-release-cycle>`_, 22.04.5, "5.15 [GA], 6.8 [HWE]", 2.35
   ,,
+   `Red Hat Enterprise Linux (RHEL 10) <https://access.redhat.com/articles/3078#RHEL9>`_, 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
   ,9.5, 5.14+, 2.34
   ,9.4, 5.14.0-427, 2.34
@@ -213,10 +215,12 @@ Use this lookup table to confirm which operating system and kernel versions are
   ,,
   `Rocky Linux <https://wiki.rockylinux.org/rocky/version/>`_, 9, 5.14.0-570, 2.34
   ,,
-   `Oracle Linux <https://blogs.oracle.com/scoter/post/oracle-linux-and-unbreakable-enterprise-kernel-uek-releases>`_, 9, 6.12.0 (UEK), 2.34
+   `Oracle Linux <https://blogs.oracle.com/scoter/post/oracle-linux-and-unbreakable-enterprise-kernel-uek-releases>`_, 10, 6.12.0 (UEK), 2.39
+   ,9, 6.12.0 (UEK), 2.34
   ,8, 5.15.0 (UEK), 2.28
   ,,
-   `Debian <https://www.debian.org/download>`_,12, 6.1.0, 2.36
+   `Debian <https://www.debian.org/download>`_,13, 6.12, 2.35
+   ,12, 6.1.0, 2.36
   ,,
   `Azure Linux <https://techcommunity.microsoft.com/blog/linuxandopensourceblog/azure-linux-3-0-now-in-preview-on-azure-kubernetes-service-v1-31/4287229>`_,3.0, 6.6.92, 2.38
   ,,
@@ -251,42 +255,45 @@ Expand for full historical view of:

   .. rubric:: Footnotes

-   .. [#rhel-700-past-60] **For ROCm 7.0.x** - RHEL 8.10 is only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, MI210, and MI100 GPUs.
-   .. [#ol-700-mi300x-past-60] **For ROCm 7.0.x** - Oracle Linux 9 is supported only on AMD Instinct MI300X, MI350X, and MI355X. Oracle Linux 8 is only supported on AMD Instinct MI300X.
-   .. [#mi300x-past-60] **Prior ROCm 7.0.0** - Oracle Linux is supported only on AMD Instinct MI300X.
-   .. [#sles-db-700-past-60] **For ROCm 7.0.x** - SLES 15 SP7 and Debian 12 are only supported 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 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.
-   .. [#az-mi300x-630-past-60] **Prior ROCm 6.4.0**- Azure Linux 3.0 is supported only on AMD Instinct MI300X.
-   .. [#rl-700-past-60] Rocky Linux 9 is only supported on AMD Instinct MI300X and MI300A GPUs.
-   .. [#mi350x-os-past-60] AMD Instinct MI355X (gfx950) and MI350X(gfx950) GPUs are only supported 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 7800 XT (gfx1101), AMD Radeon RX 7700 XT (gfx1101), AMD Radeon PRO W7700 (gfx1101), and AMD Radeon PRO W6800 (gfx1030) are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, and RHEL 9.6.
+   .. [#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 only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and Azure Linux 3.0.
-   .. [#rd-v620-past-60] **For ROCm 7.0.x** - AMD Radeon PRO V620 (gfx1030) is only supported 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 only supported on Ubuntu 24.04.3, 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, Ubuntu 22.04, 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, Ubuntu 22.04, 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 only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
-   .. [#7700XT-OS-past-60] Radeon RX 7700 XT (gfx1101) is supported only on Ubuntu 24.04.2 and RHEL 9.6.
+   .. [#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 only supported 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 only supported 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 only supported 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 only supported on Ubuntu 22.04.3.
-   .. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
-   .. [#tf-mi350-past-60] TensorFlow 2.17.1 is not supported on AMD Instinct MI350 series GPUs. Use TensorFlow 2.19.1 or 2.18.1 with MI350 series GPUs instead.
-   .. [#verl_compat-past-60] verl is only supported on ROCm 6.2.0.
-   .. [#stanford-megatron-lm_compat-past-60] Stanford Megatron-LM is only supported on ROCm 6.3.0.
-   .. [#dgl_compat-past-60] DGL is only supported on ROCm 6.4.0.
-   .. [#megablocks_compat-past-60] Megablocks is only supported on ROCm 6.3.0.
-   .. [#ray_compat-past-60] Ray is only supported on ROCm 6.4.1.
-   .. [#llama-cpp_compat-past-60] llama.cpp is only supported on ROCm 7.0.0 and 6.4.x.
-   .. [#flashinfer_compat-past-60] FlashInfer is only supported on ROCm 6.4.1.
+   .. [#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.
+   .. [#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.
+   .. [#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.
+   .. [#megablocks_compat-past-60] Megablocks is supported only on ROCm 6.3.0.
+   .. [#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.
   .. [#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.
--- a/docs/compatibility/ml-compatibility/jax-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/jax-compatibility.rst
@@ -50,9 +50,7 @@ with ROCm support:
 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.
+Portable JIT Runtime (PJRT) is an open, stable interface for device runtime and compiler. The table below shows the compatibility between the JAX Plugin–PJRT and JAX/JAXLIB.

 .. list-table::
    :header-rows: 1
@@ -62,7 +60,7 @@ between JAX Plugin–PJRT and JAX/JAXLIB.
      - ROCm
    * - 0.6.0
      - 0.6.2, 0.6.0
-      - 7.0.1, 7.0.0
+      - 7.0.2, 7.0.1, 7.0.0 

 Use cases and recommendations
 ================================================================================
--- a/docs/compatibility/ml-compatibility/pytorch-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/pytorch-compatibility.rst
@@ -407,7 +407,7 @@ 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 2.7/2.8 with ROCm 7.0
 ================================================================================

 - Enhanced TunableOp framework: Introduces ``tensorfloat32`` support for
@@ -463,7 +463,7 @@ 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
 ================================================================================

 - The ``matmul.allow_fp16_reduced_precision_reduction`` and
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -89,15 +89,15 @@ 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 = "7.0.1"
-release = "7.0.1"
+version = "7.0.2"
+release = "7.0.2"
 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": "2025-09-17"},
+    {"file": "about/release-notes", "os": ["linux"], "date": "2025-10-10"},
    {"file": "release/changelog", "os": ["linux"],},
    {"file": "compatibility/compatibility-matrix", "os": ["linux"]},
    {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
--- a/docs/data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
@@ -1,47 +1,16 @@
 dockers:
-  - pull_tag: rocm/jax-training:maxtext-v25.7-jax060
+  - pull_tag: rocm/jax-training:maxtext-v25.9
    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
    components:
-      ROCm: 6.4.1
-      JAX: 0.6.0
-      Python: 3.10.12
-      Transformer Engine: 2.1.0+90d703dd
-      hipBLASLt: 1.1.0-499ece1c21
-  - pull_tag: rocm/jax-training:maxtext-v25.7
-    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
-    components:
-      ROCm: 6.4.1
-      JAX: 0.5.0
-      Python: 3.10.12
-      Transformer Engine: 2.1.0+90d703dd
+      ROCm: 7.0.0
+      JAX: 0.6.2
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+c91bac54
      hipBLASLt: 1.x.x
 model_groups:
  - group: Meta Llama
    tag: llama
    models:
-      - model: Llama 3.3 70B
-        mad_tag: jax_maxtext_train_llama-3.3-70b
-        model_repo: Llama-3.3-70B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3.1 8B
-        mad_tag: jax_maxtext_train_llama-3.1-8b
-        model_repo: Llama-3.1-8B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3.1 70B
-        mad_tag: jax_maxtext_train_llama-3.1-70b
-        model_repo: Llama-3.1-70B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3 8B
-        mad_tag: jax_maxtext_train_llama-3-8b
-        multinode_training_script: llama3_8b_multinode.sh
-        doc_options: ["multi-node"]
-      - model: Llama 3 70B
-        mad_tag: jax_maxtext_train_llama-3-70b
-        multinode_training_script: llama3_70b_multinode.sh
-        doc_options: ["multi-node"]
      - model: Llama 2 7B
        mad_tag: jax_maxtext_train_llama-2-7b
        model_repo: Llama-2-7B
@@ -54,6 +23,29 @@ model_groups:
        precision: bf16
        multinode_training_script: llama2_70b_multinode.sh
        doc_options: ["single-node", "multi-node"]
+      - model: Llama 3 8B (multi-node)
+        mad_tag: jax_maxtext_train_llama-3-8b
+        multinode_training_script: llama3_8b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3 70B (multi-node)
+        mad_tag: jax_maxtext_train_llama-3-70b
+        multinode_training_script: llama3_70b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3.1 8B
+        mad_tag: jax_maxtext_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 70B
+        mad_tag: jax_maxtext_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.3 70B
+        mad_tag: jax_maxtext_train_llama-3.3-70b
+        model_repo: Llama-3.3-70B
+        precision: bf16
+        doc_options: ["single-node"]
  - group: DeepSeek
    tag: deepseek
    models:
--- a/docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
@@ -1,14 +1,21 @@
 dockers:
-  - pull_tag: rocm/megatron-lm:v25.8_py310
-    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
+  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
-      hipBLASLt: d1b517fc7a
-      Triton: 3.3.0
-      RCCL: 2.22.3
+      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
@@ -19,8 +26,6 @@ model_groups:
        mad_tag: pyt_megatron_lm_train_llama-3.1-8b
      - model: Llama 3.1 70B
        mad_tag: pyt_megatron_lm_train_llama-3.1-70b
-      - model: Llama 3.1 70B (proxy)
-        mad_tag: pyt_megatron_lm_train_llama-3.1-70b-proxy
      - model: Llama 2 7B
        mad_tag: pyt_megatron_lm_train_llama-2-7b
      - model: Llama 2 70B
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v25.7-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v25.7-benchmark-models.yaml
@@ -0,0 +1,72 @@
+dockers:
+  - pull_tag: rocm/jax-training:maxtext-v25.7-jax060
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
+    components:
+      ROCm: 6.4.1
+      JAX: 0.6.0
+      Python: 3.10.12
+      Transformer Engine: 2.1.0+90d703dd
+      hipBLASLt: 1.1.0-499ece1c21
+  - pull_tag: rocm/jax-training:maxtext-v25.7
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
+    components:
+      ROCm: 6.4.1
+      JAX: 0.5.0
+      Python: 3.10.12
+      Transformer Engine: 2.1.0+90d703dd
+      hipBLASLt: 1.x.x
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: jax_maxtext_train_llama-3.3-70b
+        model_repo: Llama-3.3-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 8B
+        mad_tag: jax_maxtext_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 70B
+        mad_tag: jax_maxtext_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3 8B
+        mad_tag: jax_maxtext_train_llama-3-8b
+        multinode_training_script: llama3_8b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3 70B
+        mad_tag: jax_maxtext_train_llama-3-70b
+        multinode_training_script: llama3_70b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 2 7B
+        mad_tag: jax_maxtext_train_llama-2-7b
+        model_repo: Llama-2-7B
+        precision: bf16
+        multinode_training_script: llama2_7b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+      - model: Llama 2 70B
+        mad_tag: jax_maxtext_train_llama-2-70b
+        model_repo: Llama-2-70B
+        precision: bf16
+        multinode_training_script: llama2_70b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V2-Lite (16B)
+        mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
+        model_repo: DeepSeek-V2-lite
+        precision: bf16
+        doc_options: ["single-node"]
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: jax_maxtext_train_mixtral-8x7b
+        model_repo: Mixtral-8x7B
+        precision: bf16
+        doc_options: ["single-node"]
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.8-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.8-benchmark-models.yaml
@@ -0,0 +1,48 @@
+dockers:
+  - pull_tag: rocm/megatron-lm:v25.8_py310
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      hipBLASLt: d1b517fc7a
+      Triton: 3.3.0
+      RCCL: 2.22.3
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: pyt_megatron_lm_train_llama-3.3-70b
+      - model: Llama 3.1 8B
+        mad_tag: pyt_megatron_lm_train_llama-3.1-8b
+      - model: Llama 3.1 70B
+        mad_tag: pyt_megatron_lm_train_llama-3.1-70b
+      - model: Llama 3.1 70B (proxy)
+        mad_tag: pyt_megatron_lm_train_llama-3.1-70b-proxy
+      - model: Llama 2 7B
+        mad_tag: pyt_megatron_lm_train_llama-2-7b
+      - model: Llama 2 70B
+        mad_tag: pyt_megatron_lm_train_llama-2-70b
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: pyt_megatron_lm_train_deepseek-v3-proxy
+      - model: DeepSeek-V2-Lite
+        mad_tag: pyt_megatron_lm_train_deepseek-v2-lite-16b
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: pyt_megatron_lm_train_mixtral-8x7b
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-7b
+      - model: Qwen 2.5 72B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-72b
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
@@ -0,0 +1,58 @@
+dockers:
+  - pull_tag: rocm/megatron-lm:v25.8_py310
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
+    components:
+      ROCm: 6.4.3
+      Primus: 927a717
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      hipBLASLt: d1b517fc7a
+      Triton: 3.3.0
+      RCCL: 2.22.3
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
+        config_name: llama3.3_70B-pretrain.yaml
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
+        config_name: llama3.1_70B-pretrain.yaml
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
+        config_name: llama3.1_8B-pretrain.yaml
+      - model: Llama 2 7B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
+        config_name: llama2_7B-pretrain.yaml
+      - model: Llama 2 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
+        config_name: llama2_70B-pretrain.yaml
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
+        config_name: deepseek_v3-pretrain.yaml
+      - model: DeepSeek-V2-Lite
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
+        config_name: deepseek_v2_lite-pretrain.yaml
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
+        config_name: mixtral_8x7B_v0.1-pretrain.yaml
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+        config_name: mixtral_8x22B_v0.1-pretrain.yaml
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
+        config_name: primus_qwen2.5_7B-pretrain.yaml
+      - model: Qwen 2.5 72B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
+        config_name: qwen2.5_72B-pretrain.yaml
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml
@@ -0,0 +1,24 @@
+dockers:
+  - pull_tag: rocm/pytorch-training:v25.8
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+a1e66aae
+      Flash Attention: 3.0.0.post1
+      hipBLASLt: 1.1.0-d1b517fc7a
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 3.1 8B
+      mad_tag: primus_pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+    - model: Llama 3.1 70B
+      mad_tag: primus_pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B
+      precision: BF16
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.8-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.8-benchmark-models.yaml
@@ -0,0 +1,178 @@
+dockers:
+  - pull_tag: rocm/pytorch-training:v25.8
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+a1e66aae
+      Flash Attention: 3.0.0.post1
+      hipBLASLt: 1.1.0-d1b517fc7a
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 4 Scout 17B-16E
+      mad_tag: pyt_train_llama-4-scout-17b-16e
+      model_repo: Llama-4-17B_16E
+      url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.3 70B
+      mad_tag: pyt_train_llama-3.3-70b
+      model_repo: Llama-3.3-70B
+      url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 3.2 1B
+      mad_tag: pyt_train_llama-3.2-1b
+      model_repo: Llama-3.2-1B
+      url: https://huggingface.co/meta-llama/Llama-3.2-1B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 3B
+      mad_tag: pyt_train_llama-3.2-3b
+      model_repo: Llama-3.2-3B
+      url: https://huggingface.co/meta-llama/Llama-3.2-3B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 Vision 11B
+      mad_tag: pyt_train_llama-3.2-vision-11b
+      model_repo: Llama-3.2-Vision-11B
+      url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.2 Vision 90B
+      mad_tag: pyt_train_llama-3.2-vision-90b
+      model_repo: Llama-3.2-Vision-90B
+      url: https://huggingface.co/meta-llama/Llama-3.2-90B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.1 8B
+      mad_tag: pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+      training_modes: [pretrain, finetune_fw, finetune_lora, HF_pretrain]
+    - model: Llama 3.1 70B
+      mad_tag: pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+      precision: BF16
+      training_modes: [pretrain, finetune_fw, finetune_lora]
+    - model: Llama 3.1 405B
+      mad_tag: pyt_train_llama-3.1-405b
+      model_repo: Llama-3.1-405B
+      url: https://huggingface.co/meta-llama/Llama-3.1-405B
+      precision: BF16
+      training_modes: [finetune_qlora]
+    - model: Llama 3 8B
+      mad_tag: pyt_train_llama-3-8b
+      model_repo: Llama-3-8B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3 70B
+      mad_tag: pyt_train_llama-3-70b
+      model_repo: Llama-3-70B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-70B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 7B
+      mad_tag: pyt_train_llama-2-7b
+      model_repo: Llama-2-7B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 2 13B
+      mad_tag: pyt_train_llama-2-13b
+      model_repo: Llama-2-13B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 70B
+      mad_tag: pyt_train_llama-2-70b
+      model_repo: Llama-2-70B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_lora, finetune_qlora]
+  - group: OpenAI
+    tag: openai
+    models:
+    - model: GPT OSS 20B
+      mad_tag: pyt_train_gpt_oss_20b
+      model_repo: GPT-OSS-20B
+      url: https://huggingface.co/openai/gpt-oss-20b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+    - model: GPT OSS 120B
+      mad_tag: pyt_train_gpt_oss_120b
+      model_repo: GPT-OSS-120B
+      url: https://huggingface.co/openai/gpt-oss-120b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+  - group: Qwen
+    tag: qwen
+    models:
+    - model: Qwen 3 8B
+      mad_tag: pyt_train_qwen3-8b
+      model_repo: Qwen3-8B
+      url: https://huggingface.co/Qwen/Qwen3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 3 32B
+      mad_tag: pyt_train_qwen3-32b
+      model_repo: Qwen3-32
+      url: https://huggingface.co/Qwen/Qwen3-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 32B
+      mad_tag: pyt_train_qwen2.5-32b
+      model_repo: Qwen2.5-32B
+      url: https://huggingface.co/Qwen/Qwen2.5-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 72B
+      mad_tag: pyt_train_qwen2.5-72b
+      model_repo: Qwen2.5-72B
+      url: https://huggingface.co/Qwen/Qwen2.5-72B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2 1.5B
+      mad_tag: pyt_train_qwen2-1.5b
+      model_repo: Qwen2-1.5B
+      url: https://huggingface.co/Qwen/Qwen2-1.5B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 2 7B
+      mad_tag: pyt_train_qwen2-7b
+      model_repo: Qwen2-7B
+      url: https://huggingface.co/Qwen/Qwen2-7B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+  - group: Stable Diffusion
+    tag: sd
+    models:
+    - model: Stable Diffusion XL
+      mad_tag: pyt_huggingface_stable_diffusion_xl_2k_lora_finetuning
+      model_repo: SDXL
+      url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+      precision: BF16
+      training_modes: [finetune_lora]
+  - group: Flux
+    tag: flux
+    models:
+    - model: FLUX.1-dev
+      mad_tag: pyt_train_flux
+      model_repo: Flux
+      url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+      precision: BF16
+      training_modes: [pretrain]
+  - group: NCF
+    tag: ncf
+    models:
+    - model: NCF
+      mad_tag: pyt_ncf_training
+      model_repo:
+      url: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Recommendation/NCF
+      precision: FP32
--- a/docs/data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
@@ -1,15 +1,22 @@
 dockers:
-  - pull_tag: rocm/megatron-lm:v25.8_py310
-    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
-    components:
-      ROCm: 6.4.3
-      Primus: 927a717
-      PyTorch: 2.8.0a0+gitd06a406
+  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
-      hipBLASLt: d1b517fc7a
-      Triton: 3.3.0
-      RCCL: 2.22.3
+      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
--- a/docs/data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
@@ -1,24 +1,39 @@
 dockers:
-  - pull_tag: rocm/pytorch-training:v25.8
-    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
-      Python: 3.10.18
-      Transformer Engine: 2.2.0.dev0+a1e66aae
-      Flash Attention: 3.0.0.post1
-      hipBLASLt: 1.1.0-d1b517fc7a
+  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: 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: 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"
--- a/docs/data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
@@ -1,13 +1,21 @@
 dockers:
-  - pull_tag: rocm/pytorch-training:v25.8
-    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
-      Python: 3.10.18
-      Transformer Engine: 2.2.0.dev0+a1e66aae
-      Flash Attention: 3.0.0.post1
-      hipBLASLt: 1.1.0-d1b517fc7a
+  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
@@ -158,7 +166,7 @@ model_groups:
      model_repo: SDXL
      url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
      precision: BF16
-      training_modes: [finetune_lora]
+      training_modes: [posttrain-p]
  - group: Flux
    tag: flux
    models:
@@ -167,7 +175,7 @@ model_groups:
      model_repo: Flux
      url: https://huggingface.co/black-forest-labs/FLUX.1-dev
      precision: BF16
-      training_modes: [pretrain]
+      training_modes: [posttrain-p]
  - group: NCF
    tag: ncf
    models:
--- a/docs/how-to/rocm-for-ai/inference-optimization/vllm-optimization.rst
+++ b/docs/how-to/rocm-for-ai/inference-optimization/vllm-optimization.rst
--- a/docs/how-to/rocm-for-ai/inference-optimization/workload.rst
+++ b/docs/how-to/rocm-for-ai/inference-optimization/workload.rst
@@ -15,10 +15,9 @@ using PyTorch. It delves into specific workloads such as
 :ref:`model inference <mi300x-vllm-optimization>`, offering strategies to
 enhance efficiency.

-The following topics highlight :ref:`auto-tunable configurations <mi300x-auto-tune>`
-that streamline optimization as well as advanced techniques like
-:ref:`Triton kernel optimization <mi300x-triton-kernel-performance-optimization>` for
-meticulous tuning.
+The following topics highlight :ref:`auto-tunable configurations <mi300x-auto-tune>` as
+well as :ref:`Triton kernel optimization <mi300x-triton-kernel-performance-optimization>`
+for meticulous tuning.

 Workload tuning strategy
 ========================
@@ -86,27 +85,28 @@ Optimize model inference with vLLM
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

 vLLM provides tools and techniques specifically designed for efficient model
-inference on AMD Instinct MI300X accelerators. See :ref:`fine-tuning-llms-vllm`
-for installation guidance. Optimizing performance with vLLM
-involves configuring tensor parallelism, leveraging advanced features, and
-ensuring efficient execution. Here’s how to optimize vLLM performance:
+inference on AMD Instinct GPUs. See the official `vLLM installation docs
+<https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html>`__ for
+installation guidance. Optimizing performance with vLLM involves configuring
+tensor parallelism, leveraging advanced features, and ensuring efficient
+execution.

-* Tensor parallelism: Configure the
-  :ref:`tensor-parallel-size parameter <mi300x-vllm-multiple-gpus>` to distribute
-  tensor computations across multiple GPUs. Adjust parameters such as
-  ``batch-size``, ``input-len``, and ``output-len`` based on your workload.
-
-* Configuration for vLLM: Set :ref:`parameters <mi300x-vllm-optimization>`
-  according to workload requirements. Benchmark performance to understand
-  characteristics and identify bottlenecks.
+* Configuration for vLLM: Set engine arguments according to workload
+  requirements.

 * Benchmarking and performance metrics: Measure latency and throughput to
  evaluate performance.

+.. seealso::
+
+   See :doc:`vllm-optimization` to learn more about vLLM performance
+   optimization techniques.
+
 .. _mi300x-auto-tune:

 Auto-tunable configurations
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
 Auto-tunable configurations can significantly streamline performance
 optimization by automatically adjusting parameters based on workload
 characteristics. For example:
@@ -120,8 +120,7 @@ characteristics. For example:
  your specific hardware.

 * Triton: Use :ref:`Triton’s auto-tuning features <mi300x-autotunable-kernel-config>`
-  to explore various kernel configurations and automatically select the
-  best-performing ones.
+  to explore various kernel configurations and select the best-performing ones.

 Manual tuning
 ^^^^^^^^^^^^^
@@ -328,380 +327,21 @@ hardware counters are also included.

   ROCm Systems Profiler timeline trace example.

-.. _mi300x-vllm-optimization:
-
 vLLM performance optimization
 =============================

-vLLM is a high-throughput and memory efficient inference and serving engine for large language models that has gained traction in the AI community for
-its performance and ease of use. See :ref:`fine-tuning-llms-vllm` for a primer on vLLM with ROCm.
-
-Performance environment variables
---------------------------------
-
-The following performance tips are not *specific* to vLLM -- they are general
-but relevant in this context. You can tune the following vLLM parameters to
-achieve optimal request latency and throughput performance.
-
-* As described in `Environment variables (MI300X)
-  <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html#environment-variables>`_,
-  the environment variable ``HIP_FORCE_DEV_KERNARG`` can improve vLLM
-  performance. Set it to ``export HIP_FORCE_DEV_KERNARG=1``.
-
-* Set the :ref:`RCCL environment variable <mi300x-rccl>` ``NCCL_MIN_NCHANNELS``
-  to ``112`` to increase the number of channels on MI300X to potentially improve
-  performance.
-
-* Set the environment variable ``TORCH_BLAS_PREFER_HIPBLASLT=1`` to use hipBLASLt to improve performance.
-
-Auto-tuning using PyTorch TunableOp
------------------------------------
-
-Since vLLM is based on the PyTorch framework, PyTorch TunableOp can be used for auto-tuning. 
-You can run auto-tuning with TunableOp in two simple steps without modifying your code:
-
-* Enable TunableOp and tuning. Optionally, enable verbose mode:
-
-  .. code-block:: shell
-
-     PYTORCH_TUNABLEOP_ENABLED=1 PYTORCH_TUNABLEOP_VERBOSE=1 your_vllm_script.sh
-
-* Enable TunableOp and disable tuning and measure.
-
-  .. code-block:: shell
-
-     PYTORCH_TUNABLEOP_ENABLED=1 PYTORCH_TUNABLEOP_TUNING=0 your_vllm_script.sh
-
-Learn more about TunableOp in the :ref:`PyTorch TunableOp <mi300x-tunableop>` section.
-
-Performance tuning based on vLLM engine configurations
-------------------------------------------------------
-
-The following subsections describe vLLM-specific configurations for performance tuning.
-You can tune the following vLLM parameters to achieve optimal performance.
-
-*  ``tensor_parallel_size``
-
-*  ``gpu_memory_utilization``
-
-*  ``dtype``
-
-*  ``enforce_eager``
-
-*  ``kv_cache_dtype``
-
-*  ``input_len``
-
-*  ``output_len``
-
-*  ``max_num_seqs``
-
-*  ``num_scheduler_steps``
-
-*  ``max_model_len``
-
-*  ``enable_chunked_prefill``
-
-*  ``distributed_executor_backend``
-
-*  ``max_seq_len_to_capture``
-
-Refer to `vLLM documentation <https://docs.vllm.ai/en/latest/models/performance.html>`_
-for additional performance tips. :ref:`fine-tuning-llms-vllm` describes vLLM
-usage with ROCm.
-
-ROCm provides a prebuilt optimized Docker image for validating the performance
-of LLM inference with vLLM on MI300X series accelerators. The Docker image includes
-ROCm, vLLM, and PyTorch. For more information, see
-:doc:`/how-to/rocm-for-ai/inference/benchmark-docker/vllm`.
-
-.. _mi300x-vllm-throughput-measurement:
-
-Evaluating performance by throughput measurement
-------------------------------------------------
-
-This tuning guide evaluates the performance of LLM inference workloads by measuring throughput in tokens per second (TPS). Throughput can be assessed using both real-world and synthetic data, depending on your evaluation goals.
-
-Refer to the benchmarking script located at ``benchmarks/benchmark_throughput.py`` in the `vLLM repository <https://github.com/ROCm/vllm/blob/main/benchmarks/benchmark_throughput.py>`_.
-Use this script to measure throughput effectively. You can assess throughput using real-world and synthetic data, depending on your evaluation goals.
-
-* For realistic performance evaluation, you can use datasets like Hugging Face's
-  ``ShareGPT_V3_unfiltered_cleaned_split.json``. This dataset includes real-world conversational
-  data, making it a good representation of typical use cases for language models. Download it using
-  the following command:
-
-  .. code-block:: shell
-
-     wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
-
-* For standardized benchmarking, you can set fixed input and output token
-  lengths. Synthetic prompts provide consistent benchmarking runs, making it
-  easier to compare performance across different models or configurations.
-  Additionally, a controlled environment simplifies analysis.
-
-By balancing real-world data and synthetic data approaches, you can get a well-rounded understanding of model performance in varied scenarios.
-
-.. _mi300x-vllm-single-node:
-
-Maximizing vLLM instances on a single node
------------------------------------------
-
-The general guideline is to maximize per-node throughput by running as many vLLM instances as possible.
-However, running too many instances might lead to insufficient memory for the KV-cache, which can affect performance.
-
-The Instinct MI300X accelerator is equipped with 192GB of HBM3 memory capacity and bandwidth.
-For models that fit in one GPU -- to maximize the accumulated throughput -- you can run as many as eight vLLM instances
-simultaneously on one MI300X node (with eight GPUs). To do so, use the GPU isolation environment
-variable ``CUDA_VISIBLE_DEVICES``.
-
-For example, this script runs eight instances of vLLM for throughput benchmarking at the same time
-with a model that can fit in one GPU:
-
-.. code-block:: shell
-
-   for i in $(seq 0 7);
-   do
-       CUDA_VISIBLE_DEVICES="$i" python3 /app/vllm/benchmarks/benchmark_throughput.py -tp 1 --dataset "/path/to/dataset/ShareGPT_V3_unfiltered_cleaned_split.json" --model /path/to/model &
-   done
-
-The total throughput achieved by running ``N`` instances of vLLM is generally much higher than running a
-single vLLM instance across ``N`` GPUs simultaneously (that is, configuring ``tensor_parallel_size`` as N or
-using the ``-tp`` N option, where ``1 < N ≤ 8``).
-
-vLLM on MI300X accelerators can run a variety of model weights, including Llama 2 (7b, 13b, 70b), Llama 3 (8b, 70b), Qwen2 (7b, 72b), Mixtral-8x7b, Mixtral-8x22b, and so on.
-Notable configurations include Llama2-70b and Llama3-70b models on a single MI300X GPU, and the Llama3.1 405b model can fit on one single node with 8 MI300X GPUs.
-
-.. _mi300x-vllm-gpu-memory-utilization:
-
-Configure the gpu_memory_utilization parameter
----------------------------------------------
-
-There are two ways to increase throughput by configuring ``gpu-memory-utilization`` parameter.
-
-1. Increase ``gpu-memory-utilization`` to improve the throughput for a single instance as long as
-   it does not incur HIP or CUDA Out Of Memory. The default ``gpu-memory-utilization`` is 0.9.
-   You can set it to ``>0.9`` and ``<1``.
-
-   For example, below benchmarking command set the ``gpu-memory-utilization`` as 0.98, or 98%.
-
-   .. code-block:: shell
-
-      /vllm-workspace/benchmarks/benchmark_throughput.py --gpu-memory-utilization 0.98 --input-len 1024 --output-len 128 --model /path/to/model
-
-2. Decrease ``gpu-memory-utilization`` to maximize the number of vLLM instances on the same GPU.
-
-   Specify GPU memory utilization to run as many instances of vLLM as possible on a single
-   GPU. However, too many instances can result in no memory for KV-cache. For small models, run
-   multiple instances of vLLM on the same GPU by specifying a smaller ``gpu-memory-utilization`` -- as
-   long as it would not cause HIP Out Of Memory. 
-
-   For example, run two instances of the Llama3-8b model at the same time on a single GPU by specifying
-   ``--gpu-memory-utilization`` to 0.4 (40%) as follows (on GPU ``0``):
-
-   .. code-block:: shell
-
-      CUDA_VISIBLE_DEVICES=0 python3 /vllm-workspace/benchmarks/benchmark_throughput.py --gpu-memory-utilization 0.4 
-      --dataset "/path/to/dataset/ShareGPT_V3_unfiltered_cleaned_split.json" --model /path/to/model &
-
-      CUDA_VISIBLE_DEVICES=0 python3 /vllm-workspace/benchmarks/benchmark_throughput.py --gpu-memory-utilization 0.4 
-      --dataset "/path/to/dataset/ShareGPT_V3_unfiltered_cleaned_split.json" --model /path/to/model &
-
-See :ref:`vllm-engine-args` for other performance suggestions.
-
-.. _mi300x-vllm-multiple-gpus:
-
-Run vLLM on multiple GPUs
-------------------------
-
-The two main reasons to use multiple GPUs are:
-
-*  The model size is too big to run vLLM using one GPU as it results HIP Out of Memory.
-
-*  To achieve better latency when using a single GPU is not desirable.
-
-To run one vLLM instance on multiple GPUs, use the ``-tp`` or ``--tensor-parallel-size`` option to
-specify multiple GPUs. Optionally, use the ``CUDA_VISIBLE_DEVICES`` environment variable to specify
-the GPUs.
-
-For example, you can use two GPUs to start an API server on port 8000:
-
-.. code-block:: shell
-
-   python -m vllm.entrypoints.api_server --model /path/to/model --dtype
-   float16 -tp 2 --port 8000 &
-
-To achieve both latency and throughput performance for serving, you can run multiple API servers on
-different GPUs by specifying different ports for each server and use ``CUDA_VISIBLE_DEVICES`` to
-specify the GPUs for each server, for example:
-
-.. code-block:: shell
-
-   CUDA_VISIBLE_DEVICES=0,1 python -m vllm.entrypoints.api_server --model
-   /path/to/model --dtype float16 -tp 2 --port 8000 &
-
-   CUDA_VISIBLE_DEVICES=2,3 python -m vllm.entrypoints.api_server --model
-   /path/to/model --dtype float16 -tp 2 --port 8001 &
-
-Choose an attention backend
---------------------------
-
-vLLM on ROCm supports two attention backends, each suitable for different use cases and performance
-requirements:
-
- **Triton Flash Attention** - For benchmarking, run vLLM scripts at
-  least once as a warm-up step so Triton can perform auto-tuning before
-  collecting benchmarking numbers. This is the default setting.
-
- **Composable Kernel (CK) Flash Attention** - To use CK Flash Attention, specify
-  the environment variable as ``export VLLM_USE_TRITON_FLASH_ATTN=0``.
-
-
-Refer to :ref:`Model acceleration libraries <acceleration-flash-attention>`
-to learn more about Flash Attention with Triton or CK backends.
-
-.. _vllm-engine-args:
-
-vLLM engine arguments
---------------------
-
-The following are configuration suggestions to potentially improve performance with vLLM. See
-`vLLM's engine arguments documentation <https://docs.vllm.ai/en/latest/serving/engine_args.html>`_
-for a full list of configurable engine arguments.
-
-Configure the max-num-seqs parameter
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Increase the ``max-num-seqs`` parameter from the default ``256`` to ``512`` (``--max-num-seqs
-512``). This increases the maximum number of sequences per iteration and can improve throughput.
-
-Use the float16 dtype
-^^^^^^^^^^^^^^^^^^^^^
-
-The default data type (``dtype``) is specified in the model’s configuration file. For instance, some models use ``torch.bfloat16`` as their default ``dtype``.
-Use float16 (``--dtype float16``) for better performance.
-
-Multi-step scheduling
-^^^^^^^^^^^^^^^^^^^^^
-
-Setting ``num-scheduler-steps`` for multi-step scheduling can increase performance. Set it between 10 to 15 (``--num-scheduler-steps 10``).
-
-Distributed executor backend
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-The vLLM supports two modes of distributed executor backend: ``ray`` and ``mp``. When using the `<https://github.com/ROCm/vllm>`__ fork, using the ``mp``
-backend (``--distributed_executor_backend mp``) is recommended.
-
-Graph mode max-seq-len-to-capture
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Maximum sequence length covered by CUDA graphs. In the default mode (where ``enforce_eager`` is ``False``), when a sequence has context length
-larger than this, vLLM engine falls back to eager mode. The default is 8192.
-
-When working with models that support long context lengths, set the parameter ``--max-seq-len-to-capture`` to 16384.
-See this `vLLM blog <https://blog.vllm.ai/2024/10/23/vllm-serving-amd.html>`__ for details.
-
-An example of long context length model is Qwen2-7b.
-
-Whether to enable chunked prefill
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Another vLLM performance tip is to enable chunked prefill to improve
-throughput. Chunked prefill allows large prefills to be chunked into
-smaller chunks and batched together with decode requests.
-
-You can enable the feature by specifying ``--enable-chunked-prefill`` in the
-command line or setting ``enable_chunked_prefill=True`` in the LLM
-constructor. 
-
-As stated in `vLLM's documentation, <https://docs.vllm.ai/en/latest/models/performance.html#chunked-prefill>`__,
-you can tune the performance by changing ``max_num_batched_tokens``. By
-default, it is set to 512 and optimized for ITL (inter-token latency).
-Smaller ``max_num_batched_tokens`` achieves better ITL because there are
-fewer prefills interrupting decodes.
-Higher ``max_num_batched_tokens`` achieves better TTFT (time to the first
-token) as you can put more prefill to the batch.
-
-You might experience noticeable throughput improvements when
-benchmarking on a single GPU or 8 GPUs using the vLLM throughput
-benchmarking script along with the ShareGPT dataset as input.
-
-In the case of fixed ``input-len``/``output-len``, for some configurations,
-enabling chunked prefill increases the throughput. For some other
-configurations, the throughput may be worse and elicit a need to tune
-parameter ``max_num_batched_tokens`` (for example, increasing ``max_num_batched_tokens`` value to 4096 or larger).
-
-.. note::
-
-   Chunked prefill is no longer recommended. See the vLLM blog: `Serving LLMs on AMD MI300X: Best Practices <https://blog.vllm.ai/2024/10/23/vllm-serving-amd.html>`_ (October 2024).
-
-Quantization support
---------------------
-
-Quantization reduces the precision of the model’s weights and activations, which significantly decreases the memory footprint.
-``fp8(w8a8)`` and ``AWQ`` quantization are supported for ROCm.
-
-FP8 quantization
-^^^^^^^^^^^^^^^^^
-
-`<https://github.com/ROCm/vllm>`__ supports FP8 (8-bit floating point) weight and activation quantization using hardware acceleration on the Instinct MI300X.
-Quantization of models with FP8 allows for a 2x reduction in model memory requirements and up to a 1.6x improvement in throughput with minimal impact on accuracy.
-
-AMD publishes Quark Quantized OCP FP8 models on Hugging Face. For example:
-
-* `Llama-3.1-8B-Instruct-FP8-KV <https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV>`__
-* `Llama-3.1-70B-Instruct-FP8-KV <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`__
-* `Llama-3.1-405B-Instruct-FP8-KV <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`__
-* `Mixtral-8x7B-Instruct-v0.1-FP8-KV <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`__
-* `Mixtral-8x22B-Instruct-v0.1-FP8-KV <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`__
-
-To enable vLLM benchmarking to run on fp8 quantized models, use the ``--quantization`` parameter with value ``fp8`` (``--quantization fp8``).
-
-AWQ quantization
-^^^^^^^^^^^^^^^^
-
-You can quantize your own models by installing AutoAWQ or picking one of the 400+ models on Hugging Face. Be aware that
-that AWQ support in vLLM is currently underoptimized.
-
-To enable vLLM to run on ``awq`` quantized models, using ``--quantization`` parameter with ``awq`` (``--quantization awq``).
-
-You can find more specifics in the `vLLM AutoAWQ documentation <https://docs.vllm.ai/en/stable/quantization/auto_awq.html>`_.
-
-fp8 kv-cached-dtype
-^^^^^^^^^^^^^^^^^^^^^^^
-
-Using ``fp8 kv-cache dtype`` can improve performance as it reduces the size
-of ``kv-cache``. As a result, it reduces the cost required for reading and
-writing the ``kv-cache``.
-
-To use this feature, specify ``--kv-cache-dtype`` as ``fp8``.
-
-To specify the quantization scaling config, use the
-``--quantization-param-path`` parameter. If the parameter is not specified,
-the default scaling factor of ``1`` is used, which can lead to less accurate
-results. To generate ``kv-cache`` scaling JSON file, see `FP8 KV
-Cache <https://github.com/vllm-project/llm-compressor/blob/main/examples/quantization_kv_cache/README.md>`__
-in the vLLM GitHub repository.
-
-Two sample Llama scaling configuration files are in vLLM for ``llama2-70b`` and
-``llama2-7b``.
-
-If building the vLLM using
-`Dockerfile.rocm <https://github.com/vllm-project/vllm/blob/main/docker/Dockerfile.rocm>`_
-for ``llama2-70b`` scale config, find the file at
-``/vllm-workspace/tests/fp8_kv/llama2-70b-fp8-kv/kv_cache_scales.json`` at
-runtime.
-
-Below is a sample command to run benchmarking with this feature enabled
-for the ``llama2-70b`` model:
-
-.. code-block:: shell
-
-   python3 /vllm-workspace/benchmarks/benchmark_throughput.py --model \
-   /path/to/llama2-70b-model --kv-cache-dtype "fp8" \
-   --quantization-param-path \
-   "/vllm-workspace/tests/fp8_kv/llama2-70b-fp8-kv/kv_cache_scales.json" \
-   --input-len 512 --output-len 256 --num-prompts 500
-
+vLLM is a high-throughput and memory efficient inference and serving engine for
+large language models that has gained traction in the AI community for its
+performance and ease of use. See :doc:`vllm-optimization`, where you'll learn
+how to:
+
+* Enable AITER (AI Tensor Engine for ROCm) to speed up on LLM models.
+* Configure environment variables for optimal HIP, RCCL, and Quick Reduce performance.
+* Select the right attention backend for your workload (AITER MHA/MLA vs. Triton).
+* Choose parallelism strategies (tensor, pipeline, data, expert) for multi-GPU deployments.
+* Apply quantization (``FP8``/``FP4``) to reduce memory usage by 2-4× with minimal accuracy loss.
+* Tune engine arguments (batch size, memory utilization, graph modes) for your use case.
+* Benchmark and scale across single-node and multi-node configurations.

 .. _mi300x-tunableop:

@@ -946,33 +586,33 @@ for details.

  .. code-block:: shell

-     HIP_FORCE_DEV_KERNARG=1  hipblaslt-bench --alpha 1 --beta 0 -r f16_r \
+     HIP_FORCE_DEV_KERNARG=1  hipblaslt-bench --alpha 1 --beta 0 -r f16_r \
     --a_type f16_r --b_type f8_r --compute_type f32_f16_r \
-     --initialization trig_float  --cold_iters 100 --iters 1000 --rotating 256
+     --initialization trig_float  --cold_iters 100 --iters 1000 --rotating 256

 * Example 2: Benchmark forward epilogues and backward epilogues

-  *  ``HIPBLASLT_EPILOGUE_RELU: "--activation_type relu";``
+  *  ``HIPBLASLT_EPILOGUE_RELU: "--activation_type relu";``

-  *  ``HIPBLASLT_EPILOGUE_BIAS: "--bias_vector";``
+  *  ``HIPBLASLT_EPILOGUE_BIAS: "--bias_vector";``

-  *  ``HIPBLASLT_EPILOGUE_RELU_BIAS: "--activation_type relu --bias_vector";``
+  *  ``HIPBLASLT_EPILOGUE_RELU_BIAS: "--activation_type relu --bias_vector";``

-  *  ``HIPBLASLT_EPILOGUE_GELU: "--activation_type gelu";``
+  *  ``HIPBLASLT_EPILOGUE_GELU: "--activation_type gelu";``

  *  ``HIPBLASLT_EPILOGUE_DGELU": --activation_type gelu --gradient";``

-  *  ``HIPBLASLT_EPILOGUE_GELU_BIAS: "--activation_type gelu --bias_vector";``
+  *  ``HIPBLASLT_EPILOGUE_GELU_BIAS: "--activation_type gelu --bias_vector";``

-  *  ``HIPBLASLT_EPILOGUE_GELU_AUX: "--activation_type gelu --use_e";``
+  *  ``HIPBLASLT_EPILOGUE_GELU_AUX: "--activation_type gelu --use_e";``

-  *  ``HIPBLASLT_EPILOGUE_GELU_AUX_BIAS: "--activation_type gelu --bias_vector --use_e";``
+  *  ``HIPBLASLT_EPILOGUE_GELU_AUX_BIAS: "--activation_type gelu --bias_vector --use_e";``

-  *  ``HIPBLASLT_EPILOGUE_DGELU_BGRAD: "--activation_type gelu --bias_vector --gradient";``
+  *  ``HIPBLASLT_EPILOGUE_DGELU_BGRAD: "--activation_type gelu --bias_vector --gradient";``

-  *  ``HIPBLASLT_EPILOGUE_BGRADA: "--bias_vector --gradient --bias_source a";``
+  *  ``HIPBLASLT_EPILOGUE_BGRADA: "--bias_vector --gradient --bias_source a";``

-  *  ``HIPBLASLT_EPILOGUE_BGRADB:  "--bias_vector --gradient --bias_source b";``
+  *  ``HIPBLASLT_EPILOGUE_BGRADB:  "--bias_vector --gradient --bias_source b";``


 hipBLASLt auto-tuning using hipblaslt-bench
@@ -1031,26 +671,26 @@ The tuning tool is a two-step tool. It first runs the benchmark, then it creates

  .. code-block:: python

-     defaultBenchOptions = {"ProblemType": {
-         "TransposeA": 0,
-         "TransposeB": 0,
-         "ComputeInputDataType": "s",
-         "ComputeDataType": "s",
-         "DataTypeC": "s",
-         "DataTypeD": "s",
-         "UseBias": False
-     }, "TestConfig": {
-         "ColdIter": 20,
-         "Iter": 100,
-         "AlgoMethod": "all",
-         "RequestedSolutions": 2, # Only works in AlgoMethod heuristic
-         "SolutionIndex": None, # Only works in AlgoMethod index
-         "ApiMethod": "cpp",
-         "RotatingBuffer": 0,
-     }, "TuningParameters": {
-         "SplitK": [0]
-     }, "ProblemSizes": []}
-     defaultCreateLogicOptions = {}  # Currently unused
+     defaultBenchOptions = {"ProblemType": {
+         "TransposeA": 0,
+         "TransposeB": 0,
+         "ComputeInputDataType": "s",
+         "ComputeDataType": "s",
+         "DataTypeC": "s",
+         "DataTypeD": "s",
+         "UseBias": False
+     }, "TestConfig": {
+         "ColdIter": 20,
+         "Iter": 100,
+         "AlgoMethod": "all",
+         "RequestedSolutions": 2, # Only works in AlgoMethod heuristic
+         "SolutionIndex": None, # Only works in AlgoMethod index
+         "ApiMethod": "cpp",
+         "RotatingBuffer": 0,
+     }, "TuningParameters": {
+         "SplitK": [0]
+     }, "ProblemSizes": []}
+     defaultCreateLogicOptions = {}  # Currently unused

 * ``TestConfig``
   1. ``ColdIter``: This is number the warm-up iterations before starting the kernel benchmark.
@@ -1230,7 +870,7 @@ command:

 .. code-block:: shell

-   merge.py original_dir new_tuned_yaml_dir output_dir 
+   merge.py original_dir new_tuned_yaml_dir output_dir 

 The following table describes the logic YAML files.

@@ -1833,7 +1473,7 @@ de-quantize the ``int4`` key-value from the ``int4`` data type to ``fp16``.

 From the IR snippet, you can see ``i32`` data is loaded from global memory to
 registers (``%190``). With a few element-wise operations in registers, it is
-stored in shared memory (``%269``) for the transpose operation (``%270``), which
+stored in shared memory (``%269``) for the transpose operation (``%270``), which
 needs data movement across different threads. With the transpose done, it is
 loaded from LDS to register again (``%276``), and with a few more
 element-wise operations, it is stored to LDS again (``%298``). The last step
@@ -1967,7 +1607,7 @@ something similar to the following:
   loaded at: [0x7fd4f100c000-0x7fd4f100e070]

 The kernel name and the code object file should be listed. In the
-example above, the kernel name is vector_add_assert_trap, but this might
+example above, the kernel name is vector_add_assert_trap, but this might
 also look like:

 .. code-block:: text
@@ -2081,3 +1721,8 @@ Hardware efficiency is maximized with 4 or fewer HIP streams. These environment
 configuration to two compute streams and two RCCL streams, aligning with this best practice.
 Additionally, RCCL is often pre-optimized for MI300 systems in production by querying the node
 topology during startup, reducing the need for extensive manual tuning.
+
+Further reading
+===============
+
+* :doc:`vllm-optimization`
--- a/docs/how-to/rocm-for-ai/system-setup/system-health-check.rst
+++ b/docs/how-to/rocm-for-ai/system-setup/system-health-check.rst
@@ -92,7 +92,7 @@ GPUs, which can impact end-to-end latency.
 .. _healthcheck-install-transferbench:

 1. To get started, use the instructions in the `TransferBench documentation
-   <https://rocm.docs.amd.com/projects/TransferBench/en/latest/install/install.html#install-transferbench>`_
+   <https://rocm.docs.amd.com/projects/TransferBench/en/latest/install/install.html#install-transferbench>`__
   or use the following commands:

   .. code:: shell
@@ -102,5 +102,5 @@ GPUs, which can impact end-to-end latency.
      CC=hipcc make

 2. Run the suggested TransferBench tests -- see `TransferBench benchmarking
-   <https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/performance-bench.html#transferbench-benchmarking-results>`_
+   <https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/system-validation.html#transferbench>`__
   in the Instinct performance benchmarking documentation for instructions.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
@@ -6,14 +6,8 @@
 Training a model with JAX MaxText on ROCm
 ******************************************

-MaxText is a high-performance, open-source framework built on the Google JAX
-machine learning library to train LLMs at scale. The MaxText framework for
-ROCm is an optimized fork of the upstream
-`<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
-on AMD MI300X series GPUs.
-
 The MaxText for ROCm training Docker image
-provides a prebuilt environment for training on AMD Instinct MI300X and MI325X GPUs,
+provides a prebuilt environment for training on AMD Instinct MI355X, MI350X, MI325X, and MI300X GPUs,
 including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
 It includes the following software components:

@@ -61,15 +55,15 @@ MaxText with on ROCm provides the following key features to train large language

 - Multi-node support

- NANOO FP8 quantization support
+- NANOO FP8 (for MI300X series GPUs) and FP8 (for MI355X and MI350X) quantization support

-.. _amd-maxtext-model-support-v257:
+.. _amd-maxtext-model-support-v259:

 Supported models
 ================

-The following models are pre-optimized for performance on AMD Instinct MI300
-series GPUs. Some instructions, commands, and available training
+The following models are pre-optimized for performance on AMD Instinct
+GPUs. Some instructions, commands, and available training
 configurations in this documentation might vary by model -- select one to get
 started.

@@ -139,22 +133,13 @@ Use the following command to pull the Docker image from Docker Hub.

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

-   {% set dockers = data.dockers %}
-   .. tab-set::
+   {% set docker = data.dockers[0] %}

-      {% for docker in dockers %}
-      {% set jax_version = docker.components["JAX"] %}
+   .. code-block:: shell

-      .. tab-item:: JAX {{ jax_version }}
-         :sync: {{ docker.pull_tag }}
+      docker pull {{ docker.pull_tag }}

-         .. code-block:: shell
-
-            docker pull {{ docker.pull_tag }}
-
-      {% endfor %}
-
-.. _amd-maxtext-multi-node-setup-v257:
+.. _amd-maxtext-multi-node-setup-v259:

 Multi-node configuration
 ------------------------
@@ -162,7 +147,7 @@ Multi-node configuration
 See :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your
 environment for multi-node training.

-.. _amd-maxtext-get-started-v257:
+.. _amd-maxtext-get-started-v259:

 Benchmarking
 ============
@@ -174,7 +159,7 @@ benchmark results:

   .. _vllm-benchmark-mad:

-   {% set dockers = data.dockers %}
+   {% set docker = data.dockers[0] %}
   {% set model_groups = data.model_groups %}
   {% for model_group in model_groups %}
      {% for model in model_group.models %}
@@ -186,6 +171,9 @@ benchmark results:
         {% if model.mad_tag and "single-node" in model.doc_options %}
         .. tab-item:: MAD-integrated benchmarking

+            The following run command is tailored to {{ model.model }}.
+            See :ref:`amd-maxtext-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.

@@ -214,22 +202,19 @@ benchmark results:

         .. tab-item:: Standalone benchmarking

+            The following commands are optimized for {{ model.model }}. See
+            :ref:`amd-maxtext-model-support-v259` to switch to another
+            available model. Some instructions and resources might not be
+            available for all models and configurations.
+
            .. rubric:: Download the Docker image and required scripts

            Run the JAX MaxText benchmark tool independently by starting the
            Docker container as shown in the following snippet.

-            .. tab-set::
-               {% for docker in dockers %}
-               {% set jax_version = docker.components["JAX"] %}
+            .. code-block:: shell

-               .. tab-item:: JAX {{ jax_version }}
-                  :sync: {{ docker.pull_tag }}
-
-                  .. code-block:: shell
-
-                     docker pull {{ docker.pull_tag }}
-               {% endfor %}
+               docker pull {{ docker.pull_tag }}

            {% if model.model_repo and "single-node" in model.doc_options %}
            .. rubric:: Single node training
@@ -250,33 +235,25 @@ benchmark results:

            2. Launch the Docker container.

-               .. tab-set::
-                  {% for docker in dockers %}
-                  {% set jax_version = docker.components["JAX"] %}
+               .. code-block:: shell

-                  .. tab-item:: JAX {{ jax_version }}
-                     :sync: {{ docker.pull_tag }}
-
-                     .. 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 \
-                            -v $HF_HOME:/hf_cache \
-                            -e HF_HOME=/hf_cache \
-                            -e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
-                            --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 \
+                      -v $HF_HOME:/hf_cache \
+                      -e HF_HOME=/hf_cache \
+                      -e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
+                      --shm-size 64G \
+                      --name training_env \
+                      {{ docker.pull_tag }}

            3. In the Docker container, clone the ROCm MAD repository and navigate to the
               benchmark scripts directory at ``MAD/scripts/jax-maxtext``.
@@ -299,11 +276,27 @@ benchmark results:

                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }}

-               For quantized training, use the following command:
+               For quantized training, run the script with the appropriate option for your Instinct GPU.

-               .. code-block:: shell
+               .. tab-set::

-                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8
+                  .. tab-item:: MI355X and MI350X
+
+                     For ``fp8`` quantized training on MI355X and MI350X GPUs, use the following command:
+
+                     .. code-block:: shell
+
+                        ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q fp8
+
+                  {% if model.model_repo not in ["Llama-3.1-70B", "Llama-3.3-70B"] %}
+                  .. tab-item:: MI325X and MI300X
+
+                     For ``nanoo_fp8`` quantized training on MI300X series GPUs, use the following command:
+
+                     .. code-block:: shell
+
+                        ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8
+                  {% endif %}

            {% endif %}
            {% if model.multinode_training_script and "multi-node" in model.doc_options %}
@@ -335,7 +328,7 @@ benchmark results:
         {% else %}
            .. rubric:: Multi-node training

-            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v257`
+            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v259`
            with an available `multi-node training script <https://github.com/ROCm/MAD/tree/develop/scripts/jax-maxtext/gpu-rocm>`__.
         {% endif %}
      {% endfor %}
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst
@@ -10,6 +10,12 @@ Training a model with Megatron-LM on ROCm

 .. caution::

+   For a unified training solution on AMD GPUs with ROCm, the `rocm/megatron-lm
+   <https://hub.docker.com/r/rocm/megatron-lm/>`__ 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 Megatron-LM and :doc:`torchtitan <primus-pytorch>`.
+
   Primus with Megatron is designed to replace this ROCm Megatron-LM training workflow.
   To learn how to migrate workloads from Megatron-LM to Primus with Megatron,
   see :doc:`previous-versions/megatron-lm-primus-migration-guide`.
@@ -17,30 +23,25 @@ Training a model with Megatron-LM on ROCm
 The `Megatron-LM framework for ROCm <https://github.com/ROCm/Megatron-LM>`_ is
 a specialized fork of the robust Megatron-LM, designed to enable efficient
 training of large-scale language models on AMD GPUs. By leveraging AMD
-Instinct™ MI300X series GPUs, Megatron-LM delivers enhanced
-scalability, performance, and resource utilization for AI workloads. It is
+Instinct™ GPUs, Megatron-LM delivers enhanced scalability, performance, and
+resource utilization for AI workloads. It is
 purpose-built to support models like Llama, DeepSeek, and Mixtral,
 enabling developers to train next-generation AI models more
 efficiently.

-AMD provides ready-to-use Docker images for MI300X series GPUs containing
-essential components, including PyTorch, ROCm libraries, and Megatron-LM
-utilities. It contains the following software components to accelerate training
-workloads:
-
-.. note::
-
-   This Docker environment is based on Python 3.10 and Ubuntu 22.04. For an alternative environment with
-   Python 3.12 and Ubuntu 24.04, see the :doc:`previous ROCm Megatron-LM v25.6 Docker release <previous-versions/megatron-lm-v25.6>`.
+AMD provides ready-to-use Docker images for MI355X, MI350X, MI325X, and MI300X
+GPUs containing essential components, including PyTorch, ROCm libraries, and
+Megatron-LM utilities. It contains the following software components to
+accelerate training workloads:

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

   {% set dockers = data.dockers %}
   .. tab-set::

-      {% for docker in dockers %}
-      .. tab-item:: ``{{ docker.pull_tag }}``
-         :sync: {{ docker.pull_tag }}
+   {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}

         .. list-table::
            :header-rows: 1
@@ -51,10 +52,8 @@ workloads:
            {% for component_name, component_version in docker.components.items() %}
            * - {{ component_name }}
              - {{ component_version }}
-
            {% endfor %}
-      {% endfor %}
-
+   {% endfor %}
   .. _amd-megatron-lm-model-support:

   Supported models
@@ -151,33 +150,24 @@ Download the Docker image
   {% set dockers = data.dockers %}
   1. Use the following command to pull the Docker image from Docker Hub.

-      {% if dockers|length > 1 %}
      .. tab-set::

-         {% for docker in data.dockers %}
-         .. tab-item:: {{ docker.doc_name }}
-            :sync: {{ docker.pull_tag }}
+         {% for supported_gpus, docker in dockers.items() %}
+         .. tab-item:: {{ supported_gpus }}
+            :sync: {{ supported_gpus }}

            .. code-block:: shell

               docker pull {{ docker.pull_tag }}
-
         {% endfor %}
-      {% elif dockers|length == 1 %}
-      {% set docker = dockers[0] %}
-      .. code-block:: shell

-         docker pull {{ docker.pull_tag }}
-
-      {% endif %}
   2. Launch the Docker container.

-      {% if dockers|length > 1 %}
      .. tab-set::

-         {% for docker in dockers %}
-         .. tab-item:: {{ docker.doc_name }}
-            :sync: {{ docker.pull_tag }}
+         {% for supported_gpus, docker in dockers.items() %}
+         .. tab-item:: {{ supported_gpus }}
+            :sync: {{ supported_gpus }}

            .. code-block:: shell

@@ -195,28 +185,7 @@ Download the Docker image
                   --shm-size 128G \
                   --name megatron_training_env \
                   {{ docker.pull_tag }}
-
         {% endfor %}
-      {% elif dockers|length == 1 %}
-      {% set docker = dockers[0] %}
-      .. 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 }}
-
-      {% endif %}

 3. Use these commands if you exit the ``megatron_training_env`` container and need to return to it.

@@ -234,8 +203,8 @@ Download the Docker image
      pip uninstall megatron-core
      pip install -e .

-The Docker container hosts
-`<https://github.com/ROCm/Megatron-LM/tree/rocm_dev>`__ at verified commit ``e8e9edc``.
+The Docker container hosts a verified commit of
+`<https://github.com/ROCm/Megatron-LM/tree/rocm_dev>`__.

 .. _amd-megatron-lm-environment-setup:

@@ -572,31 +541,73 @@ Single node training
   To run training on a single node for Llama 3.1 8B FP8, navigate to the Megatron-LM folder and use the
   following command.

-   .. code-block:: shell
+   .. tab-set::

-      TEE_OUTPUT=1 \
-      MBS=2 \
-      BS=128 \
-      TP=1 \
-      TE_FP8=1 \
-      SEQ_LENGTH=8192 \
-      MODEL_SIZE=8 \
-      TOTAL_ITERS=50 \
-      bash examples/llama/train_llama3.sh
+      .. tab-item:: MI355X and MI350X
+         :sync: MI355X and MI350X
+
+         .. code-block:: shell
+
+            TEE_OUTPUT=1 \
+            MBS=4 \
+            BS=512 \
+            TP=1 \
+            TE_FP8=1 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=8 \
+            TOTAL_ITERS=10 \
+            GEMM_TUNING=0 \
+            bash examples/llama/train_llama3.sh
+
+      .. tab-item:: MI300X
+         :sync: MI325X and MI300X
+
+         .. code-block:: shell
+
+            TEE_OUTPUT=1 \
+            MBS=2 \
+            BS=128 \
+            TP=1 \
+            TE_FP8=1 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=8 \
+            TOTAL_ITERS=50 \
+            bash examples/llama/train_llama3.sh

   For Llama 3.1 8B BF16, use the following command:

-   .. code-block:: shell
+   .. tab-set::

-      TEE_OUTPUT=1 \
-      MBS=2 \
-      BS=128 \
-      TP=1 \
-      TE_FP8=0 \
-      SEQ_LENGTH=8192 \
-      MODEL_SIZE=8 \
-      TOTAL_ITERS=50 \
-      bash examples/llama/train_llama3.sh
+      .. tab-item:: MI355X and MI350X
+         :sync: MI355X and MI350X
+
+         .. code-block:: shell
+
+            TEE_OUTPUT=1 \
+            MBS=4 \
+            BS=512 \
+            TP=1 \
+            TE_FP8=0 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=8 \
+            TOTAL_ITERS=10 \
+            GEMM_TUNING=1 \
+            bash examples/llama/train_llama3.sh
+
+      .. tab-item:: MI300X
+         :sync: MI325X and MI300X
+
+         .. code-block:: shell
+
+            TEE_OUTPUT=1 \
+            MBS=2 \
+            BS=128 \
+            TP=1 \
+            TE_FP8=0 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=8 \
+            TOTAL_ITERS=50 \
+            bash examples/llama/train_llama3.sh

 .. container:: model-doc pyt_megatron_lm_train_llama-3.1-70b

@@ -625,29 +636,60 @@ Single node training
      parallelism, MCore's distributed optimizer, gradient accumulation fusion,
      or FP16.

-.. container:: model-doc pyt_megatron_lm_train_llama-3.1-70b-proxy
-
-   To run the training on a single node for Llama 3.1 70B with proxy, use the following command.
-
-   .. code-block:: shell
-
-      CKPT_FORMAT=torch_dist \
-      TEE_OUTPUT=1 \
-      RECOMPUTE=1 \
-      MBS=3 \
-      BS=24 \
-      TP=1 \
-      TE_FP8=1 \
-      SEQ_LENGTH=8192 \
-      MODEL_SIZE=70 \
-      FSDP=1 \
-      TOTAL_ITERS=10 \
-      NUM_LAYERS=40 \
-      bash examples/llama/train_llama3.sh
+   To run the training on a single node for Llama 3.1 70B FP8, use the
+   following command.

   .. note::

-      Use two or more nodes to run the *full* Llama 70B model with FP8 precision.
+      The MI300X configuration uses a proxy model. On MI300X GPUs, use two or more nodes
+      to run the full Llama 3.1 70B model with FP8 precision. MI355X and MI350X GPUs
+      can support the full 70B model with FP8 precision on a single node.
+
+   .. tab-set::
+
+      .. tab-item:: MI355X and MI350X
+         :sync: MI355X and MI350X
+
+         .. code-block:: shell
+
+            CKPT_FORMAT=torch_dist \
+            TEE_OUTPUT=1 \
+            RECOMPUTE=1 \
+            MBS=3 \
+            BS=24 \
+            TP=1 \
+            TE_FP8=1 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=70 \
+            FSDP=1 \
+            TOTAL_ITERS=10 \
+            bash examples/llama/train_llama3.sh
+
+      .. tab-item:: MI300X
+         :sync: MI325X and MI300X
+
+         .. code-block:: shell
+
+            FP8_WEIGHT_TRANSPOSE_CACHE=0 \
+            CKPT_FORMAT=torch_dist \
+            TEE_OUTPUT=1 \
+            RECOMPUTE=1 \
+            MBS=3 \
+            BS=24 \
+            TP=1 \
+            TE_FP8=1 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=70 \
+            FSDP=1 \
+            TOTAL_ITERS=10 \
+            NUM_LAYERS=40 \
+            bash examples/llama/train_llama3.sh
+
+   .. note::
+
+      The MI300X configuration uses a proxy model. On MI300X GPUs, use two or more nodes
+      to run the full Llama 3.1 70B model with FP8 precision. MI355X and MI350X GPUs
+      can support the full 70B model with FP8 precision on a single node.

   .. note::

@@ -987,6 +1029,11 @@ 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
 =================

--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-history.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-history.rst
@@ -17,27 +17,35 @@ previous releases of the ``ROCm/jax-training`` Docker image on `Docker Hub <http
     - Components
     - Resources

-   * - 25.7 (latest)
-     - 
+   * - 25.9 (latest)
+     -
+       * ROCm 7.0.0
+       * JAX 0.6.2
+     -
+       * :doc:`Documentation <../jax-maxtext>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7-jax060/images/sha256-7352212ae033a76dca2b9dceffc23c1b5f1a61a7a560082cf747a9bf1acfc9ce>`__
+
+   * - 25.7
+     -
       * ROCm 6.4.1
       * JAX 0.6.0, 0.5.0
-     - 
-       * :doc:`Documentation <../jax-maxtext>`
+     -
+       * :doc:`Documentation <jax-maxtext-v25.7>`
       * `Docker Hub (JAX 0.6.0) <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7-jax060/images/sha256-7352212ae033a76dca2b9dceffc23c1b5f1a61a7a560082cf747a9bf1acfc9ce>`__
       * `Docker Hub (JAX 0.5.0) <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025>`__

   * - 25.5
-     - 
+     -
       * ROCm 6.3.4
       * JAX 0.4.35
-     - 
+     -
       * :doc:`Documentation <jax-maxtext-v25.5>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.5/images/sha256-4e0516358a227cae8f552fb866ec07e2edcf244756f02e7b40212abfbab5217b>`__

   * - 25.4
-     - 
+     -
       * ROCm 6.3.0
       * JAX 0.4.31
-     - 
+     -
       * :doc:`Documentation <jax-maxtext-v25.4>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.4/images/sha256-fb3eb71cd74298a7b3044b7130cf84113f14d518ff05a2cd625c11ea5f6a7b01>`__
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.7.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.7.rst
@@ -0,0 +1,366 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using JAX MaxText for ROCm.
+   :keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
+
+******************************************
+Training a model with JAX MaxText on ROCm
+******************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm JAX MaxText
+   training performance documentation. See :doc:`../jax-maxtext` for the latest version.
+
+MaxText is a high-performance, open-source framework built on the Google JAX
+machine learning library to train LLMs at scale. The MaxText framework for
+ROCm is an optimized fork of the upstream
+`<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
+on AMD MI300X series GPUs.
+
+The MaxText for ROCm training Docker image
+provides a prebuilt environment for training on AMD Instinct MI300X and MI325X GPUs,
+including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
+It includes the following software components:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   .. tab-set::
+
+      {% for docker in dockers %}
+      {% set jax_version = docker.components["JAX"] %}
+
+      .. tab-item:: ``{{ docker.pull_tag }}``
+         :sync: {{ 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 %}
+         {% if jax_version == "0.6.0" %}
+         .. note::
+
+            Shardy is a new config in JAX 0.6.0. You might get related errors if it's
+            not configured correctly. For now you can turn it off by setting
+            ``shardy=False`` during the training run. You can also follow the `migration
+            guide <https://docs.jax.dev/en/latest/shardy_jax_migration.html>`__ to enable
+            it.
+         {% endif %}
+
+      {% endfor %}
+
+MaxText with on ROCm provides the following key features to train large language models efficiently:
+
+- Transformer Engine (TE)
+
+- Flash Attention (FA) 3 -- with or without sequence input packing
+
+- GEMM tuning
+
+- Multi-node support
+
+- NANOO FP8 quantization support
+
+.. _amd-maxtext-model-support-v257:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on AMD Instinct MI300
+series GPUs. Some instructions, commands, and available training
+configurations in this documentation might vary by model -- select one to get
+started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-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>
+
+.. note::
+
+   Some models, such as Llama 3, require an external license agreement through
+   a third party (for example, Meta).
+
+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.
+
+Environment setup
+=================
+
+This Docker image is optimized for specific model configurations outlined
+as follows. Performance can vary for other training workloads, as AMD
+doesn’t validate configurations and run conditions outside those described.
+
+Pull the Docker image
+---------------------
+
+Use the following command to pull the Docker image from Docker Hub.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   .. tab-set::
+
+      {% for docker in dockers %}
+      {% set jax_version = docker.components["JAX"] %}
+
+      .. tab-item:: JAX {{ jax_version }}
+         :sync: {{ docker.pull_tag }}
+
+         .. code-block:: shell
+
+            docker pull {{ docker.pull_tag }}
+
+      {% endfor %}
+
+.. _amd-maxtext-multi-node-setup-v257:
+
+Multi-node configuration
+------------------------
+
+See :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your
+environment for multi-node training.
+
+.. _amd-maxtext-get-started-v257:
+
+Benchmarking
+============
+
+Once the setup is complete, choose between two options to reproduce the
+benchmark results:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+
+   .. _vllm-benchmark-mad:
+
+   {% set dockers = data.dockers %}
+   {% set model_groups = data.model_groups %}
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         {% if model.mad_tag and "single-node" in model.doc_options %}
+         .. tab-item:: MAD-integrated benchmarking
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. Use this command to run the performance benchmark test on the {{ model.model }} model
+               using one GPU with the :literal:`{{model.precision}}` data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{model.mad_tag}} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
+            model are collected in the following path: ``~/MAD/perf.csv/``.
+         {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            .. rubric:: Download the Docker image and required scripts
+
+            Run the JAX MaxText benchmark tool independently by starting the
+            Docker container as shown in the following snippet.
+
+            .. tab-set::
+               {% for docker in dockers %}
+               {% set jax_version = docker.components["JAX"] %}
+
+               .. tab-item:: JAX {{ jax_version }}
+                  :sync: {{ docker.pull_tag }}
+
+                  .. code-block:: shell
+
+                     docker pull {{ docker.pull_tag }}
+               {% endfor %}
+
+            {% if model.model_repo and "single-node" in model.doc_options %}
+            .. rubric:: Single node training
+
+            1. Set up environment variables.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN=<Your Hugging Face token>
+                  export HF_HOME=<Location of saved/cached Hugging Face models>
+
+               ``MAD_SECRETS_HFTOKEN`` is your Hugging Face access token to access models, tokenizers, and data.
+               See `User access tokens <https://huggingface.co/docs/hub/en/security-tokens>`__.
+
+               ``HF_HOME`` is where ``huggingface_hub`` will store local data. See `huggingface_hub CLI <https://huggingface.co/docs/huggingface_hub/main/en/guides/cli#huggingface-cli-download>`__.
+               If you already have downloaded or cached Hugging Face artifacts, set this variable to that path.
+               Downloaded files typically get cached to ``~/.cache/huggingface``.
+
+            2. Launch the Docker container.
+
+               .. tab-set::
+                  {% for docker in dockers %}
+                  {% set jax_version = docker.components["JAX"] %}
+
+                  .. tab-item:: JAX {{ jax_version }}
+                     :sync: {{ docker.pull_tag }}
+
+                     .. 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 \
+                            -v $HF_HOME:/hf_cache \
+                            -e HF_HOME=/hf_cache \
+                            -e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
+                            --shm-size 64G \
+                            --name training_env \
+                            {{ docker.pull_tag }}
+                  {% endfor %}
+
+            3. In the Docker container, clone the ROCm MAD repository and navigate to the
+               benchmark scripts directory at ``MAD/scripts/jax-maxtext``.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD/scripts/jax-maxtext
+
+            4. Run the setup scripts to install libraries and datasets needed
+               for benchmarking.
+
+               .. code-block:: shell
+
+                  ./jax-maxtext_benchmark_setup.sh -m {{ model.model_repo }}
+
+            5. To run the training benchmark without quantization, use the following command:
+
+               .. code-block:: shell
+
+                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }}
+
+               For quantized training, use the following command:
+
+               .. code-block:: shell
+
+                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8
+
+            {% endif %}
+            {% if model.multinode_training_script and "multi-node" in model.doc_options %}
+            .. rubric:: Multi-node training
+
+            The following examples use SLURM to run on multiple nodes.
+
+            .. note::
+
+               The following scripts will launch the Docker container and run the
+               benchmark. Run them outside of any Docker container.
+
+            1. Make sure ``$HF_HOME`` is set before running the test. See
+               `ROCm benchmarking <https://github.com/ROCm/MAD/blob/develop/scripts/jax-maxtext/gpu-rocm/readme.md>`__
+               for more details on downloading the Llama models before running the
+               benchmark.
+
+            2. To run multi-node training for {{ model.model }},
+               use the
+               `multi-node training script <https://github.com/ROCm/MAD/blob/develop/scripts/jax-maxtext/gpu-rocm/{{ model.multinode_training_script }}>`__
+               under the ``scripts/jax-maxtext/gpu-rocm/`` directory.
+
+            3. Run the multi-node training benchmark script.
+
+               .. code-block:: shell
+
+                  sbatch -N <num_nodes> {{ model.multinode_training_script }}
+
+         {% else %}
+            .. rubric:: Multi-node training
+
+            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v257`
+            with an available `multi-node training script <https://github.com/ROCm/MAD/tree/develop/scripts/jax-maxtext/gpu-rocm>`__.
+         {% 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>`__.
+
+- 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:`jax-maxtext-history` to find documentation for previous releases
+of the ``ROCm/jax-training`` Docker image.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-history.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-history.rst
@@ -16,62 +16,73 @@ previous releases of the ``ROCm/megatron-lm`` Docker image on `Docker Hub <https
     - Components
     - Resources

-   * - v25.8 (latest)
-     - 
-       * ROCm 6.4.3
-       * PyTorch 2.8.0a0+gitd06a406
-     - 
+   * - v25.9 (latest)
+     -
+       * 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>`
-       * `Docker Hub (py310) <https://hub.docker.com/r/rocm/megatron-lm/tags>`__
+       * `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>`__
+
+   * - v25.8
+     -
+       * ROCm 6.4.3
+       * PyTorch 2.8.0a0+gitd06a406
+     -
+       * :doc:`Primus Megatron documentation <primus-megatron-v25.8>`
+       * :doc:`Megatron-LM (legacy) documentation <megatron-lm-v25.8>`
+       * `Docker Hub (py310) <https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-0030c4a3dcb233c66dd5f61135821f9f5c4e321cbe0a2cdc74f110752f28c869>`__

   * - v25.7
-     - 
+     -
       * ROCm 6.4.2
       * PyTorch 2.8.0a0+gitd06a406
-     - 
+     -
       * :doc:`Primus Megatron documentation <primus-megatron-v25.7>`
       * :doc:`Megatron-LM (legacy) documentation <megatron-lm-v25.7>`
       * `Docker Hub (py310) <https://hub.docker.com/layers/rocm/megatron-lm/v25.7_py310/images/sha256-6189df849feeeee3ae31bb1e97aef5006d69d2b90c134e97708c19632e20ab5a>`__

   * - v25.6
-     - 
+     -
       * ROCm 6.4.1
       * PyTorch 2.8.0a0+git7d205b2
-     - 
+     -
       * :doc:`Documentation <megatron-lm-v25.6>`
       * `Docker Hub (py312) <https://hub.docker.com/layers/rocm/megatron-lm/v25.6_py312/images/sha256-482ff906532285bceabdf2bda629bd32cb6174d2d07f4243a736378001b28df0>`__
       * `Docker Hub (py310) <https://hub.docker.com/layers/rocm/megatron-lm/v25.6_py310/images/sha256-9627bd9378684fe26cb1a10c7dd817868f553b33402e49b058355b0f095568d6>`__

   * - v25.5
-     - 
+     -
       * ROCm 6.3.4
       * PyTorch 2.8.0a0+gite2f9759
-     - 
+     -
       * :doc:`Documentation <megatron-lm-v25.5>`
       * `Docker Hub (py312) <https://hub.docker.com/layers/rocm/megatron-lm/v25.5_py312/images/sha256-4506f18ba188d24189c6b1f95130b425f52c528a543bb3f420351824edceadc2>`__
       * `Docker Hub (py310) <https://hub.docker.com/layers/rocm/megatron-lm/v25.5_py310/images/sha256-743fbf1ceff7a44c4452f938d783a7abf143737d1c15b2b95f6f8a62e0fd048b>`__

   * - v25.4
-     - 
+     -
       * ROCm 6.3.0
-       * PyTorch 2.7.0a0+git637433 
-     - 
+       * PyTorch 2.7.0a0+git637433
+     -
       * :doc:`Documentation <megatron-lm-v25.4>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/v25.4/images/sha256-941aa5387918ea91c376c13083aa1e6c9cab40bb1875abbbb73bbb65d8736b3f>`__

   * - v25.3
-     - 
+     -
       * ROCm 6.3.0
-       * PyTorch 2.7.0a0+git637433 
-     - 
+       * PyTorch 2.7.0a0+git637433
+     -
       * :doc:`Documentation <megatron-lm-v25.3>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/v25.3/images/sha256-1e6ed9bdc3f4ca397300d5a9907e084ab5e8ad1519815ee1f868faf2af1e04e2>`__

   * - v24.12-dev
-     - 
+     -
       * ROCm 6.1.0
       * PyTorch 2.4.0
-     - 
+     -
       * :doc:`Documentation <megatron-lm-v24.12-dev>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/24.12-dev/images/sha256-5818c50334ce3d69deeeb8f589d83ec29003817da34158ebc9e2d112b929bf2e>`__
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.8.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.8.rst
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.8.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.8.rst
@@ -0,0 +1,667 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using Megatron-LM for ROCm.
+   :keywords: ROCm, AI, LLM, train, Megatron-LM, megatron, Llama, tutorial, docker, torch
+
+********************************************
+Training a model with Primus and Megatron-LM
+********************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm Megatron-LM
+   training performance documentation. See :doc:`../primus-megatron` 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 is backend-agnostic and supports multiple training engines -- including Megatron.
+
+.. note::
+
+   Primus with Megatron is designed to replace the :doc:`ROCm Megatron-LM training <../megatron-lm>` workflow.
+   To learn how to migrate workloads from Megatron-LM to Primus with Megatron,
+   see :doc:`megatron-lm-primus-migration-guide`.
+
+For ease of use, AMD provides a ready-to-use Docker image for MI300 series GPUs
+containing essential components for Primus and Megatron-LM. This Docker is powered by Primus
+Turbo optimizations for performance; this release adds support for Primus Turbo
+with optimized attention and grouped GEMM kernels.
+
+.. note::
+
+   This Docker environment is based on Python 3.10 and Ubuntu 22.04. For an alternative environment with
+   Python 3.12 and Ubuntu 24.04, see the :doc:`previous ROCm Megatron-LM v25.6 Docker release <megatron-lm-v25.6>`.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+.. _amd-primus-megatron-lm-model-support:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on AMD Instinct MI300X series GPUs.
+Some instructions, commands, and training examples in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-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-3 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>
+
+.. note::
+
+   Some models, such as Llama, require an external license agreement through
+   a third party (for example, Meta).
+
+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.
+
+.. _mi300x-amd-primus-megatron-lm-training:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+      {% set docker = dockers[0] %}
+
+   Environment setup
+   =================
+
+   Use the following instructions to set up the environment, configure the script to train models, and
+   reproduce the benchmark results on MI300X series GPUs with the ``{{ docker.pull_tag }}`` image.
+
+   .. _amd-primus-megatron-lm-requirements:
+
+   Download the Docker image
+   -------------------------
+
+   1. Use the following command to pull the Docker image from Docker Hub.
+
+      .. code-block:: shell
+
+         docker pull {{ docker.pull_tag }}
+
+   2. Launch the Docker container.
+
+      .. code-block:: shell
+
+         docker run -it \
+             --device /dev/dri \
+             --device /dev/kfd \
+             --device /dev/infiniband \
+             --network host --ipc host \
+             --group-add video \
+             --cap-add SYS_PTRACE \
+             --security-opt seccomp=unconfined \
+             --privileged \
+             -v $HOME:$HOME \
+             --shm-size 128G \
+             --name primus_training_env \
+             {{ docker.pull_tag }}
+
+3. Use these commands if you exit the ``primus_training_env`` container and need to return to it.
+
+   .. code-block:: shell
+
+      docker start primus_training_env
+      docker exec -it primus_training_env bash
+
+The Docker container hosts verified commit ``927a717`` of the `Primus
+<https://github.com/AMD-AGI/Primus/tree/927a71702784347a311ca48fd45f0f308c6ef6dd>`__ repository.
+
+.. _amd-primus-megatron-lm-environment-setup:
+
+Configuration
+=============
+
+Primus defines a training configuration in YAML for each model in
+`examples/megatron/configs <https://github.com/AMD-AGI/Primus/tree/927a71702784347a311ca48fd45f0f308c6ef6dd/examples/megatron/configs>`__.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+   .. container:: model-doc {{ model.mad_tag }}
+
+      To update training parameters for {{ model.model }}, you can update ``examples/megatron/configs/{{ model.config_name }}``.
+      Note that training configuration YAML files for other models follow this naming convention.
+
+      {% endfor %}
+   {% endfor %}
+
+.. note::
+
+   See :ref:`Key options <amd-primus-megatron-lm-benchmark-test-vars>` for more information on configuration options.
+
+Dataset options
+---------------
+
+You can use either mock data or real data for training.
+
+* Mock data can be useful for testing and validation. Use the ``mock_data`` field to toggle between mock and real data. The default
+  value is ``true`` for enabled.
+
+  .. code-block:: yaml
+
+     mock_data: true
+
+* If you're using a real dataset, update the ``train_data_path`` field to point to the location of your dataset.
+
+  .. code-block:: bash
+
+     mock_data: false
+     train_data_path: /path/to/your/dataset
+
+  Ensure that the files are accessible inside the Docker container.
+
+.. _amd-primus-megatron-lm-tokenizer:
+
+Tokenizer
+---------
+
+Set the ``HF_TOKEN`` environment variable with
+right permissions to access the tokenizer for each model.
+
+.. code-block:: bash
+
+   # Export your HF_TOKEN in the workspace
+   export HF_TOKEN=<your_hftoken>
+
+.. note::
+
+   In Primus, each model uses a tokenizer from Hugging Face. For example, Llama
+   3.1 8B model uses ``tokenizer_model: meta-llama/Llama-3.1-8B`` and
+   ``tokenizer_type: Llama3Tokenizer`` defined in the `llama3.1-8B model
+   <https://github.com/AMD-AGI/Primus/blob/927a71702784347a311ca48fd45f0f308c6ef6dd/examples/megatron/configs/llama3.1_8B-pretrain.yaml>`__
+   definition.
+
+.. _amd-primus-megatron-lm-run-training:
+
+Run training
+============
+
+Use the following example commands to set up the environment, configure
+:ref:`key options <amd-primus-megatron-lm-benchmark-test-vars>`, and run training on
+MI300X series GPUs with the AMD Megatron-LM environment.
+
+Single node training
+--------------------
+
+To run training on a single node, navigate to ``/workspace/Primus`` and use the following setup command:
+
+.. code-block:: shell
+
+   pip install -r requirements.txt
+   export HSA_NO_SCRATCH_RECLAIM=1
+   export NVTE_CK_USES_BWD_V3=1
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.3-70b
+
+   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` to switch to another available model.
+
+   To run pre-training for Llama 3.3 70B BF16, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+          --micro_batch_size 2 \
+          --global_batch_size 16 \
+          --train_iters 50
+
+.. 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` to switch to another available model.
+
+   To run pre-training for Llama 3.1 8B FP8, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+          --train_iters 50 \
+          --fp8 hybrid
+
+   For Llama 3.1 8B BF16, use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-70b
+
+   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` to switch to another available model.
+
+   To run pre-training for Llama 3.1 70B BF16, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+           --train_iters 50
+
+   To run the training on a single node for Llama 3.1 70B FP8 with proxy, use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+          --train_iters 50 \
+          --num_layers 40 \
+          --fp8 hybrid
+
+   .. note::
+
+      Use two or more nodes to run the *full* Llama 70B model with FP8 precision.
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-7b
+
+   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` to switch to another available model.
+
+   To run pre-training for Llama 2 7B FP8, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama2_7B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+          --train_iters 50 \
+          --fp8 hybrid
+
+   To run pre-training for Llama 2 7B BF16, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama2_7B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-70b
+
+   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` to switch to another available model.
+
+   To run pre-training for Llama 2 70B BF16, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_deepseek-v3-proxy
+
+   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` to switch to another available model.
+
+   To run training on a single node for DeepSeek-V3 (MoE with expert parallel) with 3-layer proxy,
+   use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/deepseek_v3-pretrain.yaml \
+      bash examples/run_pretrain.sh \
+          --num_layers 3 \
+          --moe_layer_freq 1 \
+          --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` to switch to another available model.
+
+   To run training on a single node for DeepSeek-V2-Lite (MoE with expert parallel),
+   use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/deepseek_v2_lite-pretrain.yaml \
+      bash examples/run_pretrain.sh \
+          --global_batch_size 256 \
+          --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x7b
+
+   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` to switch to another available model.
+
+   To run training on a single node for Mixtral 8x7B (MoE with expert parallel),
+   use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/mixtral_8x7B_v0.1-pretrain.yaml \
+      bash examples/run_pretrain.sh --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+
+   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` to switch to another available model.
+
+   To run training on a single node for Mixtral 8x22B (MoE with expert parallel) with 4-layer proxy,
+   use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/mixtral_8x22B_v0.1-pretrain.yaml \
+      bash examples/run_pretrain.sh \
+          --num_layers 4 \
+          --pipeline_model_parallel_size 1 \
+          --micro_batch_size 1 \
+          --global_batch_size 16 \
+          --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_qwen2.5-7b
+
+   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` to switch to another available model.
+
+   To run training on a single node for Qwen 2.5 7B BF16, use the following
+   command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/qwen2.5_7B-pretrain.yaml \
+      bash examples/run_pretrain.sh --train_iters 50
+
+   For FP8, use the following command.
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/qwen2.5_7B-pretrain.yaml \
+      bash examples/run_pretrain.sh \
+          --train_iters 50 \
+          --fp8 hybrid
+
+.. container:: model-doc primus_pyt_megatron_lm_train_qwen2.5-72b
+
+   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` to switch to another available model.
+
+   To run the training on a single node for Qwen 2.5 72B BF16, use the following command.
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/qwen2.5_72B-pretrain.yaml \
+      bash examples/run_pretrain.sh --train_iters 50
+
+.. _amd-primus-megatron-multi-node-examples:
+
+Multi-node training examples
+----------------------------
+
+Refer to :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your environment for multi-node
+training.
+
+To run training on multiple nodes, you can use the
+`run_slurm_pretrain.sh <https://github.com/AMD-AGI/Primus/blob/927a71702784347a311ca48fd45f0f308c6ef6dd/examples/run_slurm_pretrain.sh>`__
+to launch the multi-node workload. Use the following steps to setup your environment:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+
+   .. code-block:: shell
+
+      cd /workspace/Primus/
+      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
+
+.. note::
+
+   * Make sure correct network drivers are installed on the nodes. If inside a Docker, either install the drivers inside the Docker container or pass the network drivers from the host while creating Docker container.
+   * 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.
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.3-70b
+
+   To train Llama 3.3 70B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 1 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --fp8 hybrid
+
+   To train Llama 3.3 70B BF16 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 1 \
+          --global_batch_size 256 \
+          --recompute_num_layers 12
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-8b
+
+   To train Llama 3.1 8B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      # Adjust the training parameters. For e.g., `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case
+      NNODES=8 EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+      bash ./examples/run_slurm_pretrain.sh \
+          --global_batch_size 1024 \
+          --fp8 hybrid
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-70b
+
+   To train Llama 3.1 70B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 1 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --fp8 hybrid
+
+   To train Llama 3.1 70B BF16 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 1 \
+          --global_batch_size 256 \
+          --recompute_num_layers 12
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-7b
+
+   To train Llama 2 8B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      # Adjust the training parameters. For e.g., `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case
+      NNODES=8 EXP=examples/megatron/configs/llama2_7B-pretrain.yaml bash ./examples/run_slurm_pretrain.sh --global_batch_size 2048 --fp8 hybrid
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-70b
+
+   To train Llama 2 70B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 2 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --fp8 hybrid
+
+   To train Llama 2 70B BF16 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
+      bash ./examples/run_slurm_pretrain.sh \
+          --micro_batch_size 2 \
+          --global_batch_size 1536 \
+          --recompute_num_layers 12
+
+.. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x7b
+
+   To train Mixtral 8x7B BF16 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/mixtral_8x7B_v0.1-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 2 \
+          --global_batch_size 256
+
+.. container:: model-doc primus_pyt_megatron_lm_train_qwen2.5-72b
+
+   To train Qwen2.5 72B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/qwen2.5_72B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 4 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --fp8 hybrid
+
+.. _amd-primus-megatron-lm-benchmark-test-vars:
+
+Key options
+-----------
+
+The following are key options to take note of
+
+fp8
+  ``hybrid`` enables FP8 GEMMs.
+
+use_torch_fsdp2
+  ``use_torch_fsdp2: 1``  enables torch fsdp-v2. If FSDP is enabled,
+  set ``use_distributed_optimizer`` and ``overlap_param_gather`` to ``false``.
+
+profile
+  To enable PyTorch profiling, set these parameters:
+
+  .. code-block:: yaml
+
+     profile: true
+     use_pytorch_profiler: true
+     profile_step_end: 7
+     profile_step_start: 6
+
+train_iters
+  The total number of iterations (default: 50).
+
+mock_data
+  True by default.
+
+micro_batch_size
+  Micro batch size.
+
+global_batch_size
+  Global batch size.
+
+recompute_granularity
+  For activation checkpointing.
+
+num_layers
+  For using a reduced number of layers as with proxy models.
+
+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 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:`megatron-lm-history` to find documentation for previous releases
+of the ``ROCm/megatron-lm`` Docker image.
+
+This training environment now uses Primus with Megatron as the primary
+configuration. Limited support for the legacy ROCm Megatron-LM is still
+available; see the :doc:`../megatron-lm` documentation.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-pytorch-v25.8.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-pytorch-v25.8.rst
@@ -0,0 +1,312 @@
+: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::
+
+   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.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+   For ease of use, AMD provides a ready-to-use Docker image -- ``{{
+   docker.pull_tag }}`` -- for MI300X series GPUs containing essential
+   components for Primus and PyTorch training with
+   Primus Turbo optimizations.
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+.. _amd-primus-pytorch-model-support-v258:
+
+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-v25.8-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0" style="display: none;">
+            <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-3 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">Model</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-v258:
+
+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.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+
+   Pull the Docker image
+   =====================
+
+   Use the following command to pull the `Docker image <{{ unified_docker.docker_hub_url }}>`_ from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ unified_docker.pull_tag }}
+
+   Run training
+   ============
+
+   {% set model_groups = data.model_groups %}
+
+   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).
+
+   .. 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-v258` 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 run commands are tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available model.
+
+            .. rubric:: Download the Docker image and required packages
+
+            1. Use the following command to pull the Docker image from Docker Hub.
+
+               .. code-block:: shell
+
+                  docker pull {{ unified_docker.pull_tag }}
+
+            2. Run the Docker container.
+
+               .. code-block:: shell
+
+                  docker run -it \
+                      --device /dev/dri \
+                      --device /dev/kfd \
+                      --network host \
+                      --ipc host \
+                      --group-add video \
+                      --cap-add SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --privileged \
+                      -v $HOME:$HOME \
+                      -v $HOME/.ssh:/root/.ssh \
+                      --shm-size 64G \
+                      --name training_env \
+                      {{ unified_docker.pull_tag }}
+
+               Use these commands if you exit the ``training_env`` container and need to return to it.
+
+               .. code-block:: shell
+
+                  docker start training_env
+                  docker exec -it training_env bash
+
+            3. In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
+               repository and navigate to the benchmark scripts directory
+               ``/workspace/MAD/scripts/pytorch_train``.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD/scripts/pytorch_train
+
+            .. rubric:: Prepare training datasets and dependencies
+
+            1. The following benchmarking examples require downloading models and datasets
+               from Hugging Face. To ensure successful access to gated repos, set your
+               ``HF_TOKEN``.
+
+               .. code-block:: shell
+
+                  export HF_TOKEN=$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
+
+            .. rubric:: Pretraining
+
+            To start the pretraining 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 pretrain \
+                   -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 %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if model.mad_tag == "primus_pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Currently, only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+
+            .. rubric:: Benchmarking examples
+
+            Use the following command to run train {{ model.model }} with BF16 precision using Primus torchtitan.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -m {{ model.model_repo }}
+
+            To train {{ model.model }} with FP8 precision, use the following command.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -m {{ model.model_repo }} -p FP8
+      {% endfor %}
+   {% endfor %}
+
+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.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-history.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-history.rst
@@ -16,51 +16,62 @@ previous releases of the ``ROCm/pytorch-training`` Docker image on `Docker Hub <
     - Components
     - Resources

-   * - v25.8 (latest)
-     - 
-       * ROCm 6.4.3
-       * PyTorch 2.8.0a0+gitd06a406
-     - 
+   * - v25.9 (latest)
+     -
+       * 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>`
-       * `Docker Hub <https://hub.docker.com/r/rocm/pytorch-training/tags>`__
+       * `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>`__
+
+   * - v25.8
+     -
+       * ROCm 6.4.3
+       * PyTorch 2.8.0a0+gitd06a406
+     -
+       * :doc:`Primus PyTorch Training documentation <primus-pytorch-v25.8>`
+       * :doc:`PyTorch training (legacy) documentation <pytorch-training-v25.8>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5>`__

   * - v25.7
-     - 
+     -
       * ROCm 6.4.2
       * PyTorch 2.8.0a0+gitd06a406
-     - 
+     -
       * :doc:`Documentation <pytorch-training-v25.7>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.7/images/sha256-cc6fd840ab89cb81d926fc29eca6d075aee9875a55a522675a4b9231c9a0a712>`__

   * - v25.6
-     - 
+     -
       * ROCm 6.3.4
       * PyTorch 2.8.0a0+git7d205b2
-     - 
+     -
       * :doc:`Documentation <pytorch-training-v25.6>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.6/images/sha256-a4cea3c493a4a03d199a3e81960ac071d79a4a7a391aa9866add3b30a7842661>`__

   * - v25.5
-     - 
+     -
       * ROCm 6.3.4
       * PyTorch 2.7.0a0+git637433
-     - 
+     -
       * :doc:`Documentation <pytorch-training-v25.5>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.5/images/sha256-d47850a9b25b4a7151f796a8d24d55ea17bba545573f0d50d54d3852f96ecde5>`__

   * - v25.4
-     - 
+     -
       * ROCm 6.3.0
       * PyTorch 2.7.0a0+git637433
-     - 
+     -
       * :doc:`Documentation <pytorch-training-v25.4>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.4/images/sha256-fa98a9aa69968e654466c06f05aaa12730db79b48b113c1ab4f7a5fe6920a20b>`__

   * - v25.3
-     - 
+     -
       * ROCm 6.3.0
       * PyTorch 2.7.0a0+git637433
-     - 
+     -
       * :doc:`Documentation <pytorch-training-v25.3>`
       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.3/images/sha256-0ffdde1b590fd2787b1c7adf5686875b100980b0f314090901387c44253e709b>`__
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.7.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.7.rst
@@ -10,7 +10,7 @@ Training a model with PyTorch for ROCm

 .. caution::

-   This documentation does not reflect the latest version of ROCm vLLM
+   This documentation does not reflect the latest version of ROCm PyTorch training
   performance benchmark documentation. See :doc:`../pytorch-training` for the latest version.

 PyTorch is an open-source machine learning framework that is widely used for
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.8.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.8.rst
@@ -0,0 +1,588 @@
+: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.
+
+PyTorch is an open-source machine learning framework that is widely used for
+model training with GPU-optimized components for transformer-based models.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+   The `PyTorch for ROCm training Docker <{{ docker.docker_hub_url }}>`__
+   (``{{ docker.pull_tag }}``) 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:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+.. _amd-pytorch-training-model-support:
+
+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/pytorch-training-v25.8-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% 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:
+
+   The following table lists supported training modes per model.
+
+   .. 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:
+
+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-v25.8-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% 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` 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` 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.
+
+            .. code-block:: shell
+
+               docker pull {{ unified_docker.pull_tag }}
+
+         2. Run the Docker container.
+
+            .. code-block:: shell
+
+               docker run -it \
+                   --device /dev/dri \
+                   --device /dev/kfd \
+                   --network host \
+                   --ipc host \
+                   --group-add video \
+                   --cap-add SYS_PTRACE \
+                   --security-opt seccomp=unconfined \
+                   --privileged \
+                   -v $HOME:$HOME \
+                   -v $HOME/.ssh:/root/.ssh \
+                   --shm-size 64G \
+                   --name training_env \
+                   {{ unified_docker.pull_tag }}
+
+            Use these commands if you exit the ``training_env`` container and need to return to it.
+
+            .. code-block:: shell
+
+               docker start training_env
+               docker exec -it training_env bash
+
+         3. In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
+            repository and navigate to the benchmark scripts directory
+            ``/workspace/MAD/scripts/pytorch_train``.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/pytorch_train
+
+         .. rubric:: Prepare training datasets and dependencies
+
+         1. The following benchmarking examples require downloading models and datasets
+            from Hugging Face. To ensure successful access to gated repos, set your
+            ``HF_TOKEN``.
+
+            .. code-block:: shell
+
+               export HF_TOKEN=$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:
+
+            * `bghira/pseudo-camera-10k <https://huggingface.co/datasets/bghira/pseudo-camera-10k>`__
+
+   {% 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 $sequence_length
+
+            {% if model.mad_tag == "pyt_train_flux" %}
+            .. container:: model-doc {{ model.mad_tag }}
+
+               .. note::
+
+                  Currently, FLUX models are not supported out-of-the-box on {{ unified_docker.pull_tag }}.
+                  To use FLUX, refer to ``rocm/pytorch-training`` Docker: :doc:`pytorch-training-v25.6`
+
+                  Occasionally, downloading the Flux dataset might fail. In the event of this
+                  error, manually download it from Hugging Face at
+                  `black-forest-labs/FLUX.1-dev <https://huggingface.co/black-forest-labs/FLUX.1-dev>`_
+                  and save it to `/workspace/FluxBenchmark`. This ensures that the test script can access
+                  the required dataset.
+            {% endif %}
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$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_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>`.
+
+            .. 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:
+
+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.
+
+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.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
@@ -13,30 +13,42 @@ Primus now supports the PyTorch torchtitan backend.

 .. note::

-   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.
+   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/primus-pytorch-benchmark-models.yaml

   {% set dockers = data.dockers %}
-   {% set docker = dockers[0] %}
-   For ease of use, AMD provides a ready-to-use Docker image -- ``{{
-   docker.pull_tag }}`` -- for MI300X series GPUs containing essential
-   components for Primus and PyTorch training with
-   Primus Turbo optimizations.
+   .. tab-set::

-   .. list-table::
-      :header-rows: 1
+   {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}

-      * - Software component
-        - Version
+         .. list-table::
+            :header-rows: 1

-      {% for component_name, component_version in docker.components.items() %}
-      * - {{ component_name }}
-        - {{ component_version }}
-      {% endfor %}
+            * - Software component
+              - Version

-.. _amd-primus-pytorch-model-support-v258:
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}
+   {% endfor %}
+
+.. _amd-primus-pytorch-model-support-v259:

 Supported models
 ================
@@ -47,22 +59,21 @@ vary by model -- select one to get started.

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

-   {% set unified_docker = data.dockers[0] %}
   {% set model_groups = data.model_groups %}
   .. raw:: html

      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
-         <div class="row gx-0" style="display: none;">
+         <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-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+               <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">Model</div>
+            <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 %}
@@ -83,7 +94,7 @@ 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-v258:
+.. _amd-primus-pytorch-performance-measurements-v259:

 System validation
 =================
@@ -109,25 +120,34 @@ Pull the Docker image

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

-   {% set unified_docker = data.dockers[0] %}
+   {% set dockers = data.dockers %}

-   Use the following command to pull the `Docker image <{{ unified_docker.docker_hub_url }}>`_ from Docker Hub.
+   Use the following command to pull the Docker image from Docker Hub.

-   .. code-block:: shell
+   .. tab-set::

-      docker pull {{ unified_docker.pull_tag }}
+      {% 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/primus-pytorch-benchmark-models.yaml

-   {% set unified_docker = data.dockers[0] %}
+   {% set dockers = data.dockers %}
   {% set model_groups = data.model_groups %}

-   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).
-
   .. tab-set::

      .. tab-item:: MAD-integrated benchmarking
@@ -138,7 +158,7 @@ Run training
         .. container:: model-doc {{ model.mad_tag }}

            The following run command is tailored to {{ model.model }}.
-            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available 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.
@@ -165,10 +185,17 @@ Run training
               ``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:: Standalone benchmarking
+      .. tab-item:: Primus benchmarking

   {% for model_group in model_groups %}
      {% for model in model_group.models %}
@@ -176,34 +203,48 @@ Run training
         .. container:: model-doc {{ model.mad_tag }}

            The following run commands are tailored to {{ model.model }}.
-            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available model.
+            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.

            .. rubric:: Download the Docker image and required packages

-            1. Use the following command to pull the Docker image from Docker Hub.
+            1. Pull the appropriate Docker image for your AMD GPU architecture from Docker Hub.

-               .. code-block:: shell
+               .. tab-set::

-                  docker pull {{ unified_docker.pull_tag }}
+                  {% 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.

-               .. code-block:: shell
+               .. tab-set::

-                  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 \
-                      {{ unified_docker.pull_tag }}
+                  {% 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.

@@ -212,16 +253,249 @@ Run training
                  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``.
+            .. 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

-                  git clone https://github.com/ROCm/MAD
-                  cd MAD/scripts/pytorch_train
+                  docker start training_env
+                  docker exec -it training_env bash

-            .. rubric:: Prepare training datasets and dependencies
+            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
@@ -231,62 +505,47 @@ Run training

                  export HF_TOKEN=$your_personal_hugging_face_access_token

-            2. Run the setup script to install libraries and datasets needed for benchmarking.
+            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

-                  ./pytorch_benchmark_setup.sh
+                  CONFIG_FILE={{ model.config_file.bf16 }} \
+                  .run_train.sh

-            .. rubric:: Pretraining
+            For train with BF16 precicion, use the following command:

-            To start the pretraining benchmark, use the following command with the
-            appropriate options. See the following list of options and their descriptions.
+            .. container:: model-doc {{ model.mad_tag }}

-            .. code-block:: shell
+               .. code-block:: shell

-               ./pytorch_benchmark_report.sh -t pretrain \
-                   -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 %}
-
-               * - ``$datatype``
-                 - ``BF16``{% if model.mad_tag == "primus_pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
-                 - Currently, only Llama 3.1 8B supports FP8 precision.
-
-               * - ``$sequence_length``
-                 - Sequence length for the language model.
-                 - Between 2048 and 8192. 8192 by default.
-
-            .. rubric:: Benchmarking examples
-
-            Use the following command to run train {{ model.model }} with BF16 precision using Primus torchtitan.
-
-            .. code-block:: shell
-
-               ./pytorch_benchmark_report.sh -m {{ model.model_repo }}
-
-            To train {{ model.model }} with FP8 precision, use the following command.
-
-            .. code-block:: shell
-
-               ./pytorch_benchmark_report.sh -m {{ model.model_repo }} -p FP8
+                  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
 ===============

--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
@@ -10,44 +10,54 @@ Training a model with PyTorch on ROCm

 .. note::

-   Primus with the PyTorch torchtitan backend is designed to replace :doc:`ROCm PyTorch training <pytorch-training>` workflow.
+   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/pytorch-training-benchmark-models.yaml

   {% set dockers = data.dockers %}
-   {% set docker = dockers[0] %}
-   The `PyTorch for ROCm training Docker <{{ docker.docker_hub_url }}>`__
-   (``{{ docker.pull_tag }}``) 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:
+   .. tab-set::

-   .. list-table::
-      :header-rows: 1
+   {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}

-      * - Software component
-        - Version
+         .. list-table::
+            :header-rows: 1

-      {% for component_name, component_version in docker.components.items() %}
-      * - {{ component_name }}
-        - {{ component_version }}
-      {% endfor %}
+            * - Software component
+              - Version

-.. _amd-pytorch-training-model-support:
+            {% 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 MI325X and MI300X GPUs.
-Some instructions, commands, and training recommendations in this documentation might
-vary by model -- select one to get started.
+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/pytorch-training-benchmark-models.yaml

-   {% set unified_docker = data.dockers[0] %}
   {% set model_groups = data.model_groups %}
   .. raw:: html

@@ -78,11 +88,13 @@ vary by model -- select one to get started.
         </div>
      </div>

+.. _amd-pytorch-training-supported-training-modes-v259:

-   .. _amd-pytorch-training-supported-training-modes:
+The following table lists supported training modes per model.

-   The following table lists supported training modes per model.
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml

+   {% set model_groups = data.model_groups %}
   .. dropdown:: Supported training modes

      .. list-table::
@@ -111,7 +123,7 @@ vary by model -- select one to get started.
         unlisted fine-tuning methods by using an existing file in the
         ``/workspace/torchtune/recipes/configs`` directory as a template.

-.. _amd-pytorch-training-performance-measurements:
+.. _amd-pytorch-training-performance-measurements-v259:

 Performance measurements
 ========================
@@ -152,7 +164,7 @@ Run training

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

-   {% set unified_docker = data.dockers[0] %}
+   {% set dockers = data.dockers %}
   {% set model_groups = data.model_groups %}

   Once the setup is complete, choose between two options to start benchmarking training:
@@ -167,7 +179,7 @@ Run training
         .. container:: model-doc {{ model.mad_tag }}

            The following run command is tailored to {{ model.model }}.
-            See :ref:`amd-pytorch-training-model-support` to switch to another available 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.
@@ -205,7 +217,7 @@ Run training
         .. container:: model-doc {{ model.mad_tag }}

            The following commands are tailored to {{ model.model }}.
-            See :ref:`amd-pytorch-training-model-support` to switch to another available model.
+            See :ref:`amd-pytorch-training-model-support-v259` to switch to another available model.

      {% endfor %}
   {% endfor %}
@@ -214,28 +226,42 @@ Run training

         1. Use the following command to pull the Docker image from Docker Hub.

-            .. code-block:: shell
+            .. tab-set::

-               docker pull {{ unified_docker.pull_tag }}
+               {% for supported_gpus, docker in dockers.items() %}
+               .. tab-item:: {{ supported_gpus }}
+                  :sync: {{ supported_gpus }}

-         2. Run the Docker container.
+                  .. code-block:: shell

-            .. code-block:: shell
+                     docker pull {{ 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 \
-                   {{ unified_docker.pull_tag }}
+         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.

@@ -379,7 +405,7 @@ Run training

            ``pytorch_benchmark_setup.sh`` downloads the following datasets from Hugging Face:

-            * `bghira/pseudo-camera-10k <https://huggingface.co/datasets/bghira/pseudo-camera-10k>`__
+            * `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 %}
@@ -410,7 +436,7 @@ Run training

               .. note::

-                  Currently, FLUX models are not supported out-of-the-box on {{ unified_docker.pull_tag }}.
+                  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
@@ -442,6 +468,49 @@ Run training
                 - 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).",
@@ -456,7 +525,7 @@ 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>`.
+            See :ref:`supported training modes <amd-pytorch-training-supported-training-modes-v259>`.

            .. code-block:: shell

@@ -521,7 +590,7 @@ 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:
+.. _amd-pytorch-training-multinode-examples-v259:

 Multi-node training
 -------------------
@@ -570,6 +639,11 @@ 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
 ===============

--- a/docs/how-to/rocm-for-ai/training/scale-model-training.rst
+++ b/docs/how-to/rocm-for-ai/training/scale-model-training.rst
@@ -46,7 +46,7 @@ In DDP training, each process or worker owns a replica of the model and processe

 See the following developer blogs for more in-depth explanations and examples.

-*  `Multi GPU training with DDP — PyTorch Tutorials <https://pytorch.org/tutorials/beginner/ddp_series_multigpu.html>`_
+*  `Multi GPU training with DDP — PyTorch Tutorials <https://docs.pytorch.org/tutorials/beginner/ddp_series_multigpu.html>`__

 *  `Building a decoder transformer model on AMD GPUs — ROCm Blogs
   <https://rocm.blogs.amd.com/artificial-intelligence/decoder-transformer/README.html#distributed-training-on-multiple-gpus>`_
--- a/docs/reference/gpu-arch-specs.rst
+++ b/docs/reference/gpu-arch-specs.rst
@@ -628,6 +628,24 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 32
          - 12
          - 0
+        *
+          - Radeon RX 9060
+          - RDNA4
+          - gfx1200
+          - 8
+          - 28
+          - 32 or 64
+          - 128
+          - 32
+          - 4
+          - N/A
+          - 32
+          - 16
+          - 32
+          - 768
+          - 32
+          - 12
+          - 0
        *
          - Radeon RX 7900 XTX
          - RDNA3
--- a/docs/release/versions.md
+++ b/docs/release/versions.md
@@ -10,6 +10,7 @@

 | Version | Release date |
 | ------- | ------------ |
+| [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 |
 | [6.4.3](https://rocm.docs.amd.com/en/docs-6.4.3/) | August 7, 2025 |
--- a/docs/sphinx/_toc.yml.in
+++ b/docs/sphinx/_toc.yml.in
@@ -132,6 +132,8 @@ subtrees:
            title: Profile and debug
          - file: how-to/rocm-for-ai/inference-optimization/workload.rst
            title: Workload optimization
+          - file: how-to/rocm-for-ai/inference-optimization/vllm-optimization.rst
+            title: vLLM V1 performance optimization

      - url: https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/
        title: AI tutorials
--- a/tools/rocm-build/rocm-7.0.2.xml
+++ b/tools/rocm-build/rocm-7.0.2.xml
@@ -0,0 +1,68 @@
+<?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"
+     remote="rocm-org"
+     sync-c="true"
+     sync-j="4" />
+<!--list of projects for ROCm-->
+    <project name="ROCm" revision="roc-7.0.x" />
+    <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" />
+    <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" />
+    <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>
Author	SHA1	Message	Date
Pratik Basyal	44ce37475c	Taichi removed (#5792 )	2025-12-19 15:43:27 -05:00
Pratik Basyal	2a026856d3	702 Libva known issue added (#5728 ) * 702 Libva known issue added * Review feedback added * Feedback incorporated * Minor change * Github issue added * Jeff's feedback added	2025-12-02 13:45:20 -05:00
Gulsum Gudukbay Akbulut	f4d9a2e479	Update jax-compatibility.rst (#5609 ) * Update jax-compatibility.rst * Apply review suggestions Co-authored-by: Istvan Kiss <istvan.kiss@amd.com> * Update jax-compatibility.rst * Broken table fixed * JAX PJRT and JAXLIB compatibility table updated * Linting error fixed * Update docs/compatibility/ml-compatibility/jax-compatibility.rst * Update docs/compatibility/ml-compatibility/jax-compatibility.rst --------- Co-authored-by: Pratik Basyal <prbasyal@amd.com> Co-authored-by: Istvan Kiss <istvan.kiss@amd.com>	2025-11-20 17:59:33 +01:00
Pratik Basyal	52f6f0cbc4	Release date for PLDM updated (#5627 )	2025-11-04 18:09:52 -05:00
Pratik Basyal	f71614de00	7.0.2 Broken link, version and known issue update (#5591 ) (#5592 ) * Version and known issue update * Historical compatibility updated	2025-10-28 15:20:13 -04:00
Istvan Kiss	1b2d5924f2	Remove CentOS Stream mention from PyTorch release notes. (#5583 )	2025-10-28 14:14:15 +01:00
peterjunpark	e3704ad70e	Revert "Add xdit diffusion docs (#5576 ) (#5578 )" (#5579 ) This reverts commit `a38b2865f0`.	2025-10-27 16:21:10 -04:00
peterjunpark	a38b2865f0	Add xdit diffusion docs (#5576 ) (#5578 ) (cherry picked from commit `4132a2609c`) Co-authored-by: Kristoffer <kristoffer.torp@amd.com>	2025-10-27 15:41:29 -04:00
peterjunpark	dfdff755ef	Fix broken links under rocm-for-ai/ (#5564 ) (#5565 ) (cherry picked from commit `35ca027aa4`)	2025-10-23 15:18:08 -04:00
peterjunpark	8d2d5abdae	add xref to vllm v1 optimization guide in workload.rst (#5560 ) (#5561 ) (cherry picked from commit `90c1d9068f`)	2025-10-23 11:51:55 -04:00
peterjunpark	b30b8b43e0	Updates to the vLLM optimization guide for MI300X/MI355X (#5554 ) * Expand vLLM optimization guide for MI300X/MI355X with comprehensive AITER coverage. attention backend selection, environment variables (HIP/RCCL/Quick Reduce), parallelism strategies, quantization (FP8/FP4), engine tuning, CUDA graph modes, and multi-node scaling. Co-authored-by: PinSiang <pinsiang.tan@embeddedllm.com> Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com> Co-authored-by: pinsiangamd <pinsiang.tan@amd.com> Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> (cherry picked from commit `cb8d21a0df`)	2025-10-22 13:01:57 -04:00
Pratik Basyal	47421ef7cc	PLDM version update for MI350 series [Develop] (#5547 ) (#5548 ) * PLDM version update for MI350 series * Minor update	2025-10-20 14:42:33 -04:00
Pratik Basyal	a4ac854834	PLDM update for MI250 and MI210 [Develop] (#5537 ) (#5538 ) * PLDM update for MI250 and MI210 * PLDM update	2025-10-17 17:32:57 -04:00
peterjunpark	79acda6775	JAX Maxtext v25.9 doc update (#5532 ) (#5533 ) * archive previous version (25.7) * update docker components list for 25.9 * update template * update docker pull tag * update * fix intro (cherry picked from commit `a613bd6824`)	2025-10-17 11:54:39 -04:00
peterjunpark	811fa5c87a	Update Megatron/PyTorch Primus 25.9 docs (#5528 ) (#5529 ) * add previous versions * Fix heading levels in pages using embedded templates (#5468) * update primus-megatron doc update megatron-lm doc update templates fix tab update primus-megatron model configs Update primus-pytorch model configs fix css class add posttrain to pytorch-training template update data sheets update update update update docker tags * Add known issue and update Primus/Turbo versions * add primus ver to histories * update primus ver to 0.1.1 * fix leftovers from merge conflict (cherry picked from commit `14bb59fca9`)	2025-10-16 13:27:40 -04:00
Pratik Basyal	6796381dd5	GitHub issue added to 702 known issues (#5520 ) (#5521 ) * GitHub issue added to 702 known issues * Added missing RCCL changelog	2025-10-15 10:03:07 -04:00
Pratik Basyal	0ada3a8fef	ROCm for HPC topic updated Develop (#5504 ) (#5505 ) * ROCm for HPC topic updated * ROCm for HPC topic udpated * Minor editorial	2025-10-10 22:39:31 -04:00
Pratik Basyal	5c0b5d08da	Post GA 702 footnote (#5503 ) * Footnote updated * Merge conflict updated	2025-10-10 21:35:33 -04:00
peterjunpark	c9dbb72806	Merge pull request #5497 from ROCm/develop [docs/7.0.2] Fix documented AMD SMI version (ROCm 7.0.2) (#5496)	2025-10-10 15:10:39 -04:00
peterjunpark	3a70d75f5e	Fix documented AMD SMI version (ROCm 7.0.2) (#5496 )	2025-10-10 15:09:20 -04:00
Istvan Kiss	02ac6124de	Update PyTorch compatibilty page version number (#5494 ) * Update PyTorch compatibilty page version number * Apply suggestions from code review Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com> --------- Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>	2025-10-10 19:11:16 +02:00
Istvan Kiss	c0e317de22	Fix broken environment variable links in release notes (#5493 )	2025-10-10 18:23:00 +02:00
Alex Xu	92f950e6ff	Merge branch 'roc-7.0.x' into docs/7.0.2	2025-10-10 11:55:35 -04:00
Alex Xu	07bf4643bc	Merge branch 'develop' into roc-7.0.x	2025-10-10 11:55:18 -04:00
Alex Xu	4786abd1ac	Merge branch 'roc-7.0.x' into docs/7.0.2	2025-10-10 11:49:20 -04:00
Alex Xu	0ba8fdc9fd	Merge branch 'develop' into roc-7.0.x	2025-10-10 11:48:32 -04:00
alexxu-amd	61e1f088a1	Merge pull request #5492 from ROCm/sync-dev-from-internal Sync dev from internal for 7.0.2 GA	2025-10-10 11:17:32 -04:00
Pratik Basyal	1f6e5c5e04	Update compatibility-matrix.rst	2025-10-10 11:10:48 -04:00
Pratik Basyal	e8a0769842	Update RELEASE.md	2025-10-10 11:07:51 -04:00
Alex Xu	6f9579d052	Merge remote-tracking branch 'internal/develop' into sync-dev-from-internal	2025-10-10 11:02:33 -04:00
Pratik Basyal	245d53a021	Merge pull request #579 from prbasyal-amd/post-rc3-702-update GPU resiliency highlight updated 702	2025-10-10 11:00:59 -04:00
Alex Xu	35dbbb22bc	fix linting	2025-10-10 10:29:13 -04:00
alexxu-amd	03dc8cee00	Merge pull request #584 from ROCm/sync-dev-from-external Sync dev from external	2025-10-10 10:14:56 -04:00
Alex Xu	323e5fd27a	Merge remote-tracking branch 'external/develop' into sync-dev-from-external	2025-10-10 10:13:08 -04:00
alexxu-amd	b11fd7b492	Update versions.md (#583 )	2025-10-10 09:31:24 -04:00
alexxu-amd	d5f13a9290	Sync develop into docs/7.0.2	2025-10-10 09:26:44 -04:00
srayasam-amd	5e2efa05a6	7.0.2 GA update (#5491 ) * 7.0.2 GA update * Create rocm-7.0.2.xml	2025-10-10 18:47:48 +05:30
alexxu-amd	8088f74594	Sync develop into docs/7.0.2	2025-10-09 16:44:29 -04:00
randyh62	c06242bb89	Update RELEASE.md (#581 ) * Update RELEASE.md Remove support for rocBlas and hipBlasLt * Update CHANGELOG.md Removed from the Changelog as well.	2025-10-09 13:15:08 -07:00
peterjunpark	68e8453ca5	Update vLLM doc for 10/6 release and bump rocm-docs-core to 1.26.0 (#5481 ) * archive previous doc version * update model/docker data and doc templates * Update "Reproducing the Docker image" * fix: truncated commit hash doesn't work for some reason * bump rocm-docs-core to 1.26.0 * fix numbering fix * update docker tag * update .wordlist.txt	2025-10-08 16:23:40 -04:00
Pratik Basyal	503b8bcc86	Framework and changelog updated (#5483 ) * Framework and chaneglog updated * Wordlist updated	2025-10-08 15:05:11 -04:00
amd-hsivasun	e3d97d339a	[Ex CI] Added rocJPEG and rocprofiler-sdk	2025-10-08 14:47:44 -04:00
alexxu-amd	978c58d196	Merge pull request #577 from ROCm/sync-develop-from-external Sync develop from external	2025-10-08 14:25:03 -04:00
alexxu-amd	a366048b64	Merge branch 'develop' into sync-develop-from-external	2025-10-08 14:12:14 -04:00
Pratik Basyal	4c3e33c291	Compatibility matrix and changelog synced for ROCm 7.0.2 (#576 ) * Compatibility matrix and changelog synced * Indentation updated * OS updated	2025-10-08 14:11:15 -04:00
Alex Xu	89758e67d8	Merge remote-tracking branch 'external/develop' into sync-develop-from-external	2025-10-08 14:03:34 -04:00
Pratik Basyal	5d0f201b4d	7.0.2 review update (#575 ) * 7.0.2 review update * Tensorflow footnote updated * Wordlist added	2025-10-08 12:35:14 -04:00
Pratik Basyal	e3677d89a6	PLDM bundle info updated for 7.0.2 (#574 ) * PLDM bundle info updated * Driver dependency added to GPU resiliency * Known issue for Migrpahx added * Footnote added * Known issue for OpenCV updated * Leo's feedback incorporated * Radeon 9060 updated * Known issues updated	2025-10-08 11:00:42 -04:00
amd-hsivasun	f20edab8fc	[Ex CI] Update CMake Flags for hipTensor	2025-10-07 15:21:39 -04:00
Pratik Basyal	6f84d50011	ROCm 7.0.2 Post RC3 update (#573 ) * Space minimized * OS support updated * Minor change	2025-10-06 14:08:01 -04:00
Pratik Basyal	57dd082f28	Post RC2 7.0.2 review feedback updated (#571 ) * Known issue updated * Space optimized * Changelog updated * Apply suggestions from code review Leo's review feedback incorporated Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com> * Highlight changes * Highlight and OS support updated * GPU resiliency highlight updated * Highlights updated * ROCm-EP deprecation added * Apply suggestions from code review leo's feedback incorporated Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com> * PLDM update --------- Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>	2025-10-06 12:04:09 -04:00
peterjunpark	eeea0d2180	Fix heading levels in pages using embedded templates (#5468 )	2025-10-03 13:33:14 -04:00
anisha-amd	93c6d17922	Docs: frameworks 25.09 - compatibility - FlashInfer and llama.cpp (#5462 )	2025-10-02 13:51:36 -04:00
amd-hsivasun	f91c2b9b4a	Update dependencies-rocm.yml	2025-10-01 15:31:35 -04:00
amd-hsivasun	5e6b66ca39	Remove tasks to locate test dir	2025-10-01 15:30:37 -04:00
amd-hsivasun	6b8b359d03	Updated test dir to s/build/tests	2025-10-01 15:30:37 -04:00
amd-hsivasun	38e659e5f0	Update testDir	2025-10-01 15:30:37 -04:00
amd-hsivasun	0894547f5a	Update setupenv	2025-10-01 15:30:37 -04:00
amd-hsivasun	aca31170c4	Update setupenv	2025-10-01 15:30:37 -04:00
amd-hsivasun	d21ec9eea5	Updated testDir	2025-10-01 15:30:37 -04:00
amd-hsivasun	189c269350	Added Debug	2025-10-01 15:30:37 -04:00
amd-hsivasun	774cb7a1b3	Changed testDir	2025-10-01 15:30:37 -04:00
amd-hsivasun	024cb4db76	Added testDir	2025-10-01 15:30:37 -04:00
amd-hsivasun	945fb286f7	Find tests Task	2025-10-01 15:30:37 -04:00
amd-hsivasun	ee93101541	Change list files	2025-10-01 15:30:37 -04:00
amd-hsivasun	e31841312b	Update testDir	2025-10-01 15:30:37 -04:00
amd-hsivasun	41b5298659	Added a list for all rp-systems files	2025-10-01 15:30:37 -04:00
amd-hsivasun	58790154b2	Add a script to look for setup-env.sh	2025-10-01 15:30:37 -04:00
amd-hsivasun	6f7f73ac0b	Update workingDirectories	2025-10-01 15:30:37 -04:00
amd-hsivasun	b2e3bc8565	[Ex CI] Updated rp-systems CMakeBuildDir	2025-10-01 15:30:37 -04:00
amd-hsivasun	52979e2fdb	[Ex CI] Updated testDir for rp-systems tests	2025-10-01 15:30:37 -04:00
peterjunpark	0ea5216ace	docs: update article_info in conf.py (#5454 )	2025-10-01 13:17:50 -04:00
peterjunpark	2e1b4dd5ee	Add multi-node setup instructions for training perf Dockers (#5449 ) --------- Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>	2025-09-30 14:53:38 -04:00
Pratik Basyal	5c7b993c0c	7.0.2 release changes (#568 ) * Initial changes for 7.0.2 * Heading level updated * Release notes changes * rocsolver added * Known issues updated * Highlights updated * RN changes * Release highlights for AI applications updated * AI developer contents added * leo's review feedback added * Compatibility matrix updated * GPU driver support	2025-09-30 14:02:04 -04:00
amd-hsivasun	2d79b3c4bd	[Ex CI] Added rocm-cmake dependency	2025-09-30 14:00:16 -04:00
Peter Park	fd59b5fbac	fix links in docs (#5446 )	2025-09-29 15:27:32 -04:00
amd-hsivasun	0a643f4686	[Ex CI] Enable aqlprofile	2025-09-26 14:42:15 -04:00
amd-hsivasun	d9e5744f7a	Update testExecutable	2025-09-26 14:01:02 -04:00
amd-hsivasun	ccb849ec02	Added python3-pip to aptModules	2025-09-26 14:01:02 -04:00
amd-hsivasun	42d4867964	Removed more aptPackages	2025-09-26 14:01:02 -04:00
amd-hsivasun	375359a5dd	Added ninja to aptPackages	2025-09-26 14:01:02 -04:00
amd-hsivasun	e92745f1ff	Removed apt and pip modules	2025-09-26 14:01:02 -04:00
amd-hsivasun	0fa72358d3	Remove registerROCm packages flag	2025-09-26 14:01:02 -04:00
amd-hsivasun	6fec268a4e	Removed package manager	2025-09-26 14:01:02 -04:00
amd-hsivasun	ff14cd1ff5	Added pyyaml	2025-09-26 14:01:02 -04:00
amd-hsivasun	8f65688653	Added registerROCmPackages	2025-09-26 14:01:02 -04:00
amd-hsivasun	33d1493adb	Removed dependencies	2025-09-26 14:01:02 -04:00
amd-hsivasun	4b6c7776a2	Updated parameters	2025-09-26 14:01:02 -04:00
amd-hsivasun	af811daa1b	Added GPUTarget	2025-09-26 14:01:02 -04:00
amd-hsivasun	d6c045e482	Update test parameters	2025-09-26 14:01:02 -04:00
amd-hsivasun	78b24cad39	Update test pool	2025-09-26 14:01:02 -04:00
amd-hsivasun	753a94c0bb	Add test step to buildjob	2025-09-26 14:01:02 -04:00
amd-hsivasun	6ecad57c62	Revert pool changes	2025-09-26 14:01:02 -04:00
amd-hsivasun	977554809a	Changed cmake prefix path	2025-09-26 14:01:02 -04:00
amd-hsivasun	7b00f4493b	Removed module and prefix path	2025-09-26 14:01:02 -04:00
amd-hsivasun	95c439a272	Removed Compiler Path	2025-09-26 14:01:02 -04:00
amd-hsivasun	94e04fbdc0	Updated testpool	2025-09-26 14:01:02 -04:00
amd-hsivasun	7ab59de8af	Update testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	175c817563	Change testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	25516d312e	Updated testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	30c345629a	Changed testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	210dc94bbb	Removed testExecutable	2025-09-26 14:01:02 -04:00
amd-hsivasun	a54023ccb8	Changed testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	17e3362dc7	Add Checkout to testjob	2025-09-26 14:01:02 -04:00
amd-hsivasun	0f9c0d884d	Updated testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	c890de4b16	Added Path to Gtest	2025-09-26 14:01:02 -04:00
amd-hsivasun	4ea77ab515	Added Tests	2025-09-26 14:01:02 -04:00
amd-hsivasun	c0512612f4	Updated testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	1c81ac3747	Updated testdir path	2025-09-26 14:01:02 -04:00
amd-hsivasun	4bafa42e52	Updated test parameters	2025-09-26 14:01:02 -04:00
amd-hsivasun	493801e670	Updated testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	1a5152b7b3	Removed testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	874c881012	Fixed testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	bdcaeea74c	Updated testdir	2025-09-26 14:01:02 -04:00
amd-hsivasun	b02669acf7	Fixed Dependencies	2025-09-26 14:01:02 -04:00
amd-hsivasun	844f10b2b1	Updated denendecies-other variables	2025-09-26 14:01:02 -04:00
amd-hsivasun	d6c14920b4	External CI: Build pipeline for aqlprofile	2025-09-26 14:01:02 -04:00
amd-hsivasun	4affe10a7c	[Ex CI] Update pipeline Id for rdc to monorepo	2025-09-26 12:38:57 -04:00
amd-hsivasun	81341ef435	Add New Line	2025-09-26 11:41:21 -04:00
amd-hsivasun	abacd328f9	[Ex CI] Added rocRand to rocmDependencies	2025-09-26 11:41:21 -04:00
amd-hsivasun	80b2fb6e26	[Ex CI] Add hipRAND to rocmDependencies	2025-09-26 11:41:21 -04:00
amd-hsivasun	b53e8decfc	[Ex CI] Enable rdc monorepo	2025-09-26 11:41:21 -04:00
amd-hsivasun	5fcc2eafde	[Ex CI] Update pipeline Id for rocprofiler-sdk to monorepo	2025-09-25 16:49:07 -04:00
amd-hsivasun	2eb0d77bc6	Updated testDir	2025-09-25 13:20:37 -04:00
amd-hsivasun	d84b41908f	Changed Testdir	2025-09-25 13:20:37 -04:00
amd-hsivasun	986f8284d1	[Ex CI] Update testDir for rocprofiler-sdk	2025-09-25 13:20:37 -04:00
Pratik Basyal	d92d9268dc	Use of Radeon and Ryzen reference updated [Develop] (#5432 ) * Use of Radeon and Ryzen reference updated * Pytorch link update	2025-09-24 19:07:41 -05:00
Ibrahim Wani	1629d3f0ea	Add origami yaml based tests to azure pipelines (#5431 ) * Add origami yaml tests * Dependency fix in origami.yml * Fix almalinux dependency; get publish test results step working * Fix almalinux dependency issue	2025-09-24 14:49:51 -06:00
Pratik Basyal	6cf6b34b2e	TOC for ROCm on Radeon and Ryzen updated (#5429 )	2025-09-24 13:58:26 -05:00
Pratik Basyal	c35a0a121a	ROR link and text updated (#5426 )	2025-09-24 13:28:13 -05:00
amd-hsivasun	412e383654	[Ex CI] Update pipeline Id for rocprofiler-sdk	2025-09-23 15:56:49 -04:00
Pratik Basyal	39f6fc187d	rocm-core version updated (#5418 )	2025-09-23 15:49:33 -04:00
amd-hsivasun	05b480fb28	Update rocm-examples.yml	2025-09-23 12:10:11 -04:00
amd-hsivasun	4fa44d90db	Updated dependencies-cmake-custom.yml default ver	2025-09-23 12:10:11 -04:00
amd-hsivasun	c9ef13d823	Added Custom Cmake to testjobs	2025-09-23 12:10:11 -04:00
amd-hsivasun	f02172050b	Added rocWMMA dependency	2025-09-23 12:10:11 -04:00
amd-hsivasun	154dbe297a	Updated File to take custom cmake version	2025-09-23 12:10:11 -04:00
amd-hsivasun	993a0a4fd4	[Ex CI] Update cmake	2025-09-23 12:10:11 -04:00
amd-hsivasun	c03662f410	[Ex CI] Update pipeline Id for origami to monorepo	2025-09-23 11:17:39 -04:00
Peter Park	442d7e4750	Add env var note to vllm.rst for MoE models and fix links in docs (#5415 ) * docs(vllm.rst): add performance note for MoE models * docs: fix links update vllm readme link 20250521 fix links	2025-09-22 15:58:43 -04:00
Pratik Basyal	a09a8f517e	PLDM version for 7.0.0 updated (#5412 )	2025-09-22 11:14:07 -04:00
Pratik Basyal	0bbaab645d	rocSHMEM and ROCprofiler-SDK highlight update (#5408 ) (#5409 ) * rocSHMEM and ROCprofiler-SDK highlight update (#5408) * Update RELEASE.md	2025-09-22 10:26:12 -04:00
Ibrahim Wani	4b80405e2e	Add set -e to exit when test fails (#5398 )	2025-09-19 10:43:35 -06:00
Peter Park	d92e5b6c12	Update Primus Megatron doc v25.8 (#5396 ) * megatron: update previous versions list update wording * megatron: update rst and yaml update primus repo link update mig guide * update headings and anchors * megatron: update doc * update docker hub urls	2025-09-19 08:09:21 -04:00
Pratik Basyal	91fce2e134	rocpd highlight updated (#5393 )	2025-09-18 19:00:36 -04:00
Peter Park	27d53cf082	Remove duplicate ML FW docker image support table (#5389 )	2025-09-18 17:06:53 -04:00
Pratik Basyal	bc084246be	Reference to AMD GPU Driver 30.10 release notes updated (#5380 )	2025-09-18 13:34:46 -05:00