adding aqlprofile

* Add origami yaml pipeline.

* Unindent lines.

* Add cmake dependency step to origami yml.

* Add pybind dep

* Fix pipeline failures.

* Quick fix

* Fix pybind11 dep for almalinux

* Fix pybind11 dep for almalinux again

* Test

* [Ex CI] don't create symlink if more than one sparse checkout dir

* hipBLASLt multi sparse

* Replace pybind with nanobind.

* Quick fix

* Testing nanobind install in pipelines

* Run origami binding tests

* Change build path for tests

* Change build path for tests again

* Add missing dep for CI

* Add archs to buildJobs

* Fix CI error.

* Test

* Test job target

* Adding job target to hipblaslt dependant builds

* Check devices on machine

* Add gpu to pipeline

* Add more gpu targets

* test

* Add test job to origami

* Update test jobs

* Finding test dir

* Fix sparse checkout

* Find build dir

* Try to find build dir

* Clean up

* Test

* Change test dir

* Build origami in test job

* Try removing job.target from params

* Package bindings in build artifacts

* Download build as artifact.

* Comment out block

* Fix checkout in test job

* Test1

* Echo to list dir

* Sparse checkout origami/python

* Download python bindings as artifact

* Try ctest instead of running test files directly

* Only download artifacts for ubuntu

* Add missing cd

* Run individual tests not ctest.

* Fix hipblaslt build failures

* Resolve more ci failures in hipblaslt

* Add old changes back in

* Fix hipblaslt ci errors

* Clean up

* Add nanobind to array

* Add nanobind to array correctly

* Remove nanobind install script

* Quick fix

* Add pip module installs to test job

---------

Co-authored-by: Daniel Su <danielsu@amd.com>

.azuredevops/components/hipBLASLt.yml

@@ -178,7 +178,7 @@ jobs:
           mkdir -p $(Agent.BuildDirectory)/temp-deps
           cd $(Agent.BuildDirectory)/temp-deps
           # position-independent LAPACK is required for almalinux8 builds
-          cmake -DBUILD_GTEST=OFF -DBUILD_LAPACK=ON -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/s/deps
+          cmake -DBUILD_GTEST=OFF -DBUILD_LAPACK=ON -DCMAKE_POSITION_INDEPENDENT_CODE=ON $(Agent.BuildDirectory)/sparse/projects/hipblaslt/deps
           make -j
           sudo make install
     - script: |
@@ -197,6 +197,8 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}
+        cmakeSourceDir: $(Agent.BuildDirectory)/sparse/projects/hipblaslt
+        cmakeBuildDir: $(Agent.BuildDirectory)/sparse/projects/hipblaslt/build
         extraBuildFlags: >-
           -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
           -DCMAKE_INCLUDE_PATH=$(Agent.BuildDirectory)/rocm/llvm/include

.azuredevops/components/origami.yml

@@ -0,0 +1,236 @@
+parameters:
+- name: componentName
+  type: string
+  default: origami
+- 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
+    - wget
+    - python3
+    - python3-dev
+    - python3-pip
+- name: pipModules
+  type: object
+  default:
+    - nanobind>=2.0.0
+- name: rocmDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - rocm-cmake
+    - rocminfo
+    - ROCR-Runtime
+    - rocprofiler-register
+- name: rocmTestDependencies
+  type: object
+  default:
+    - clr
+    - llvm-project
+    - rocm-cmake
+    - rocminfo
+    - ROCR-Runtime
+    - rocprofiler-register
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt }
+      - { os: almalinux8, packageManager: dnf }
+    testJobs:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - hipBLASLt:
+      name: hipBLASLt
+      sparseCheckoutDir: projects/hipblaslt
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - origami_build
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: origami_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: ROCM_PATH
+      value: $(Agent.BuildDirectory)/rocm
+    pool:
+      vmImage: ${{ variables.BASE_BUILD_POOL }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        extraBuildFlags: >-
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+          -DORIGAMI_BUILD_SHARED_LIBS=ON
+          -DORIGAMI_ENABLE_PYTHON=ON
+          -DORIGAMI_BUILD_TESTING=ON
+          -GNinja
+    - ${{ if ne(job.os, 'almalinux8') }}:
+      - task: PublishPipelineArtifact@1
+        displayName: 'Publish Build Directory Artifact'
+        inputs:
+          targetPath: '$(Agent.BuildDirectory)/s/build'
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
+          publishLocation: 'pipeline'
+      - task: PublishPipelineArtifact@1
+        displayName: 'Publish Python Source Artifact'
+        inputs:
+          targetPath: '$(Agent.BuildDirectory)/s/python'
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
+          publishLocation: 'pipeline'
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+        os: ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}
+        componentName: ${{ parameters.componentName }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: origami_test_${{ job.os }}_${{ job.target }}
+      timeoutInMinutes: 120
+      dependsOn: origami_build_${{ job.os }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+      - task: DownloadPipelineArtifact@2
+        displayName: 'Download Build Directory Artifact'
+        inputs:
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
+          path: '$(Agent.BuildDirectory)/s/build'
+      - task: DownloadPipelineArtifact@2
+        displayName: 'Download Python Source Artifact'
+        inputs:
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
+          path: '$(Agent.BuildDirectory)/s/python'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          os: ${{ job.os }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - script: |
+          export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH
+
+          echo "--- Running origami_test.py ---"
+          python3 $(Agent.BuildDirectory)/s/python/origami_test.py
+          
+          echo "--- Running origami_grid_test.py ---"
+          python3 $(Agent.BuildDirectory)/s/python/origami_grid_test.py
+        displayName: 'Run Python Binding Tests'
+        condition: succeeded()
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rocDecode.yml

@@ -8,6 +8,25 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
+- name: rocPyDecodeRepo
+  type: string
+  default: rocpydecode_repo
+# 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
@@ -56,10 +75,23 @@ parameters:
     testJobs:
       - { os: ubuntu2204, packageManager: apt, target: gfx942 }
       - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocPyDecode:
+      name: rocPyDecode
+      sparseCheckoutDir: ''
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocDecode_build
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -83,12 +115,15 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         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 }}
@@ -169,3 +204,15 @@ jobs:
         registerROCmPackages: true
         environment: test
         gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.rocPyDecodeRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}

.azuredevops/components/rocPyDecode.yml

@@ -5,6 +5,22 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -47,19 +63,19 @@ parameters:
   type: object
   default:
     buildJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
     testJobs:
-      - gfx942:
-        target: gfx942
-      - gfx90a:
-        target: gfx90a
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rocPyDecode_build_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml
@@ -74,16 +90,20 @@ jobs:
       parameters:
         aptPackages: ${{ parameters.aptPackages }}
         pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        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 }}
     - task: Bash@3
       displayName: 'Save Python Package Paths'
       inputs:

.azuredevops/components/rocm-core.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocm-core
 - 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
@@ -27,6 +46,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rocm_core_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+        dependsOn:
+          - ${{ each build in parameters.buildDependsOn }}:
+            - ${{ build }}_${{ job.os }}
     pool:
       ${{ if eq(job.os, 'ubuntu2404') }}:
         vmImage: 'ubuntu-24.04'
@@ -50,8 +73,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
@@ -65,9 +90,12 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml

.azuredevops/components/rocm_smi_lib.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocm-smi-lib
 - 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
@@ -32,6 +51,10 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rocm_smi_lib_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     pool:
       ${{ if eq(job.os, 'ubuntu2404') }}:
         vmImage: 'ubuntu-24.04'
@@ -55,8 +78,10 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
@@ -65,51 +90,56 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     #   parameters:
     #     aptPackages: ${{ parameters.aptPackages }}
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
-    dependsOn: rocm_smi_lib_build_${{ job.os }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-      parameters:
-        runRocminfo: false
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocm_smi_lib
-        testDir: '$(Agent.BuildDirectory)'
-        testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
-        testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: rocm_smi_lib_test_${{ job.os }}_${{ job.target }}
+      dependsOn: rocm_smi_lib_build_${{ job.os }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ 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:
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+        parameters:
+          runRocminfo: false
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)'
+          testExecutable: 'sudo ./rocm/share/rocm_smi/rsmitst_tests/rsmitst'
+          testParameters: '--gtest_output=xml:./test_output.xml --gtest_color=yes'
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/rocminfo.yml

@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: rocminfo
 - 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
@@ -40,7 +59,11 @@ parameters:
 
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocminfo_build_${{ job.os }}
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
     pool:
       vmImage: 'ubuntu-22.04'
     ${{ if eq(job.os, 'almalinux8') }}:
@@ -62,14 +85,18 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}
         dependencyList: ${{ parameters.rocmDependencies }}
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         os: ${{ job.os }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
         useAmdclang: false
         extraBuildFlags: >-
@@ -78,65 +105,71 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
       parameters:
+        componentName: ${{ parameters.componentName }}
         os: ${{ job.os }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
 
-- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocminfo_test_${{ job.target }}
-    dependsOn: rocminfo_build_${{ job.os }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        packageManager: ${{ job.packageManager }}
-        registerROCmPackages: true
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-      parameters:
-        runRocminfo: false
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocminfo
-        testDir: '$(Agent.BuildDirectory)'
-        testExecutable: './rocm/bin/rocminfo'
-        testParameters: ''
-        testPublishResults: false
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: rocm_agent_enumerator
-        testDir: '$(Agent.BuildDirectory)'
-        testExecutable: './rocm/bin/rocm_agent_enumerator'
-        testParameters: ''
-        testPublishResults: false
-        os: ${{ job.os }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        registerROCmPackages: true
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: rocminfo_test_${{ job.target }}
+      dependsOn: rocminfo_build_${{ job.os }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          packageManager: ${{ job.packageManager }}
+          registerROCmPackages: true
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          os: ${{ job.os }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+        parameters:
+          runRocminfo: false
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)'
+          testExecutable: './rocm/bin/rocminfo'
+          testParameters: ''
+          testPublishResults: false
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: rocm_agent_enumerator
+          testDir: '$(Agent.BuildDirectory)'
+          testExecutable: './rocm/bin/rocm_agent_enumerator'
+          testParameters: ''
+          testPublishResults: false
+          os: ${{ job.os }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          registerROCmPackages: true
+          environment: test
+          gpuTarget: ${{ job.target }}

.azuredevops/components/rocprofiler-compute.yml

@@ -55,6 +55,7 @@ parameters:
     - pymongo
     - pyyaml
     - setuptools
+    - sqlalchemy
     - tabulate
     - textual
     - textual_plotext

.azuredevops/dependencies/catch2.yml

@@ -0,0 +1,63 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: catch2Version
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: catch2_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone catch2 ${{ parameters.catch2Version }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/catchorg/Catch2.git -b ${{ parameters.catch2Version }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/Catch2/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/Catch2
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/tag-builds/catch2.yml

@@ -0,0 +1,23 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: catch2Version
+  type: string
+  default: "v3.7.0"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/catch2.yml
+    parameters:
+      catch2Version: ${{ parameters.catch2Version }}

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

@@ -171,16 +171,16 @@ parameters:
       developBranch: develop
       hasGpuTarget: false
     rocm-core:
-      pipelineId: 103
-      developBranch: master
+      pipelineId: 349
+      developBranch: develop
       hasGpuTarget: false
     rocm-examples:
       pipelineId: 216
       developBranch: amd-staging
       hasGpuTarget: true
     rocminfo:
-      pipelineId: 91
-      developBranch: amd-staging
+      pipelineId: 356
+      developBranch: develop
       hasGpuTarget: false
     rocMLIR:
       pipelineId: 229
@@ -251,8 +251,8 @@ parameters:
       developBranch: develop
       hasGpuTarget: true
     roctracer:
-      pipelineId: 141
-      developBranch: amd-staging
+      pipelineId: 331
+      developBranch: develop
       hasGpuTarget: true
     rocWMMA:
       pipelineId: 109

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

@@ -8,11 +8,13 @@ parameters:
   type: object
   default:
     boost: 250
+    catch2: 343
     fmtlib: 341
     grpc: 72
     gtest: 73
     half560: 68
     lapack: 69
+    libdivide: 342
     spdlog: 340
 
 steps:
@@ -31,7 +33,7 @@ steps:
     inputs:
       archiveFilePatterns: '$(Pipeline.Workspace)/d/**/*.tar.gz'
       destinationFolder: $(Agent.BuildDirectory)/vendor
-      cleanDestinationFolder: true
+      cleanDestinationFolder: false
       overwriteExistingFiles: true
   - task: DeleteFiles@1
     displayName: Clean up ${{ dependency }}

.wordlist.txt

@@ -156,6 +156,7 @@ GEMMs
 GFLOPS
 GFortran
 GFXIP
+GGUF
 Gemma
 GiB
 GIM
@@ -293,6 +294,7 @@ Multicore
 Multithreaded
 MyEnvironment
 MyST
+NANOO
 NBIO
 NBIOs
 NCCL
@@ -500,6 +502,7 @@ Unhandled
 VALU
 VBIOS
 VCN
+verl's
 VGPR
 VGPRs
 VM
@@ -742,6 +745,7 @@ logits
 lossy
 macOS
 matchers
+maxtext
 megatron
 microarchitecture
 migraphx
@@ -918,6 +922,7 @@ toolchain
 toolchains
 toolset
 toolsets
+torchtitan
 torchvision
 tqdm
 tracebacks

RELEASE.md

@@ -57,9 +57,8 @@ ROCm documentation continues to be updated to provide clearer and more comprehen
  
     For more information about the changes, see [Changelog for the AI Developer Hub](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/changelog.html).
 
-* ROCm provides a comprehensive ecosystem for deep learning development. For more details, see [Deep learning frameworks for ROCm](https://rocm.docs.amd.com/en/docs-6.4.3/how-to/deep-learning-rocm.html). AMD ROCm adds support for the following deep learning frameworks:
+* ROCm provides a comprehensive ecosystem for deep learning development. For more details, see [Deep learning frameworks for ROCm](https://rocm.docs.amd.com/en/docs-6.4.3/how-to/deep-learning-rocm.html). AMD ROCm adds support for the following deep learning framework:
 
-    * Taichi is an open-source, imperative, and parallel programming language designed for high-performance numerical computation. Embedded in Python, it leverages just-in-time (JIT) compilation frameworks such as LLVM to accelerate compute-intensive Python code by compiling it to native GPU or CPU instructions. It is currently supported on ROCm 6.3.2. For more information, see [Taichi compatibility](https://rocm.docs.amd.com/en/docs-6.4.3/compatibility/ml-compatibility/taichi-compatibility.html).
     * Megablocks is a light-weight library for mixture-of-experts (MoE) training. The core of the system is efficient "dropless-MoE" and standard MoE layers. Megablocks is integrated with Megatron-LM, where data and pipeline parallel training of MoEs is supported. It is currently supported on ROCm 6.3.0. For more information, see [Megablocks compatibility](https://rocm.docs.amd.com/en/docs-6.4.3/compatibility/ml-compatibility/megablocks-compatibility.html).
 
 * The [Data types and precision support](https://rocm.docs.amd.com/en/latest/reference/precision-support.html) topic now includes new hardware and library support information.

default.xml

@@ -1,12 +1,12 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
     <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.4.3"
+    <default revision="refs/tags/20250912-42"
      remote="rocm-org"
      sync-c="true"
      sync-j="4" />
 <!--list of projects for ROCm-->
-    <project name="ROCK-Kernel-Driver" />
+    <project name="aqlprofile" />
     <project name="ROCR-Runtime" />
     <project name="amdsmi" />
     <project name="rdc" />
@@ -37,36 +37,37 @@
     <project name="rocr_debug_agent" />
 <!-- ROCm Libraries -->
     <project groups="mathlibs" name="AMDMIGraphX" />
-    <project groups="mathlibs" name="MIOpen" />
     <project groups="mathlibs" name="MIVisionX" />
     <project groups="mathlibs" name="ROCmValidationSuite" />
-    <project groups="mathlibs" name="Tensile" />
     <project groups="mathlibs" name="composable_kernel" />
-    <project groups="mathlibs" name="hipBLAS-common" />
-    <project groups="mathlibs" name="hipBLAS" />
-    <project groups="mathlibs" name="hipBLASLt" />
-    <project groups="mathlibs" name="hipCUB" />
-    <project groups="mathlibs" name="hipFFT" />
-    <project groups="mathlibs" name="hipRAND" />
     <project groups="mathlibs" name="hipSOLVER" />
-    <project groups="mathlibs" name="hipSPARSE" />
-    <project groups="mathlibs" name="hipSPARSELt" />
     <project groups="mathlibs" name="hipTensor" />
     <project groups="mathlibs" name="hipfort" />
     <project groups="mathlibs" name="rccl" />
     <project groups="mathlibs" name="rocAL" />
     <project groups="mathlibs" name="rocALUTION" />
-    <project groups="mathlibs" name="rocBLAS" />
     <project groups="mathlibs" name="rocDecode" />
     <project groups="mathlibs" name="rocJPEG" />
+    <project groups="mathlibs" name="rocm-libraries">
+        <linkfile src="projects/hipcub" dest="hipCUB"/>
+        <linkfile src="projects/rocprim" dest="rocPRIM"/>
+        <linkfile src="projects/hiprand" dest="hipRAND"/>
+        <linkfile src="projects/rocrand" dest="rocRAND"/>
+        <linkfile src="projects/rocthrust" dest="rocThrust"/>
+        <linkfile src="projects/hipblas-common" dest="hipBLAS-common"/>
+        <linkfile src="projects/hipblaslt" dest="hipBLASLt"/>
+        <linkfile src="projects/rocblas" dest="rocBLAS"/>
+        <linkfile src="projects/hipsparselt" dest="hipSPARSELt"/>
+        <linkfile src="projects/rocsparse" dest="rocSPARSE"/>
+        <linkfile src="projects/hipsparse" dest="hipSPARSE"/>
+        <linkfile src="projects/hipblas" dest="hipBLAS"/>
+        <linkfile src="projects/miopen" dest="MIOpen"/>
+        <linkfile src="projects/hipfft" dest="hipFFT"/>
+        <linkfile src="projects/rocfft" dest="rocFFT"/>
+    </project>
     <project groups="mathlibs" name="rocPyDecode" />
-    <project groups="mathlibs" name="rocFFT" />
-    <project groups="mathlibs" name="rocPRIM" />
-    <project groups="mathlibs" name="rocRAND" />
     <project groups="mathlibs" name="rocSHMEM" />
     <project groups="mathlibs" name="rocSOLVER" />
-    <project groups="mathlibs" name="rocSPARSE" />
-    <project groups="mathlibs" name="rocThrust" />
     <project groups="mathlibs" name="rocWMMA" />
     <project groups="mathlibs" name="rocm-cmake" />
     <project groups="mathlibs" name="rpp" />

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

@@ -35,6 +35,8 @@ ROCm Version,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6
       :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,
       :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
       :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat]_,N/A,N/A,N/A,N/A,N/A,1.8.0b1,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat]_,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
+      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat]_,N/A,N/A,N/A,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
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.2,1.2,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
 ,,,,,,,,,,,,,,,,,,
       ,,,,,,,,,,,,,,,,,,

docs/compatibility/compatibility-matrix.rst

@@ -246,6 +246,8 @@ Expand for full historical view of:
    .. [#dgl_compat] DGL is only supported on ROCm 6.4.0.
    .. [#megablocks_compat] Megablocks is only supported on ROCm 6.3.0.
    .. [#taichi_compat] Taichi is only supported on ROCm 6.3.2.
+   .. [#ray_compat] Ray is only supported on ROCm 6.4.1.
+   .. [#llama-cpp_compat] llama.cpp is only supported on ROCm 6.4.0.
    .. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
    .. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
    

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

@@ -0,0 +1,156 @@
+:orphan:
+
+.. meta::
+    :description: llama.cpp deep learning framework compatibility
+    :keywords: GPU, GGML, llama.cpp compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+llama.cpp compatibility
+********************************************************************************
+
+`llama.cpp <https://github.com/ggml-org/llama.cpp>`__ is an open-source framework 
+for Large Language Model (LLM) inference that runs on both central processing units 
+(CPUs) and graphics processing units (GPUs). It is written in plain C/C++, providing 
+a simple, dependency-free setup. 
+
+The framework supports multiple quantization options, from 1.5-bit to 8-bit integers, 
+to speed up inference and reduce memory usage. Originally built as a CPU-first library, 
+llama.cpp is easy to integrate with other programming environments and is widely 
+adopted across diverse platforms, including consumer devices. 
+
+ROCm support for llama.cpp is upstreamed, and you can build the official source code
+with ROCm support:
+
+- ROCm support for llama.cpp is hosted in the official `https://github.com/ROCm/llama.cpp 
+  <https://github.com/ROCm/llama.cpp>`_ repository.
+
+- Due to independent compatibility considerations, this location differs from the 
+  `https://github.com/ggml-org/llama.cpp <https://github.com/ggml-org/llama.cpp>`_ upstream repository.
+
+- To install llama.cpp, use the prebuilt :ref:`Docker image <llama-cpp-docker-compat>`, 
+  which includes ROCm, llama.cpp, and all required dependencies.
+
+  - See the :doc:`ROCm llama.cpp installation guide <rocm-install-on-linux:install/3rd-party/llama-cpp-install>` 
+    to install and get started.
+
+  - See the `Installation guide <https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#hip>`__ 
+    in the upstream llama.cpp documentation.
+
+.. note::
+
+  llama.cpp is supported on ROCm 6.4.0.
+
+Supported devices
+================================================================================
+
+**Officially Supported**: AMD Instinct™ MI300X, MI210
+
+
+Use cases and recommendations
+================================================================================
+
+llama.cpp can be applied in a variety of scenarios, particularly when you need to meet one or more of the following requirements:
+
+- Plain C/C++ implementation with no external dependencies
+- Support for 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory usage
+- Custom HIP (Heterogeneous-compute Interface for Portability) kernels for running large language models (LLMs) on AMD GPUs (graphics processing units)
+- CPU (central processing unit) + GPU (graphics processing unit) hybrid inference for partially accelerating models larger than the total available VRAM (video random-access memory)
+
+llama.cpp is also used in a range of real-world applications, including:
+
+- Games such as `Lucy's Labyrinth <https://github.com/MorganRO8/Lucys_Labyrinth>`__:
+  A simple maze game where AI-controlled agents attempt to trick the player.
+- Tools such as `Styled Lines <https://marketplace.unity.com/packages/tools/ai-ml-integration/style-text-webgl-ios-stand-alone-llm-llama-cpp-wrapper-292902>`__:
+  A proprietary, asynchronous inference wrapper for Unity3D game development, including pre-built mobile and web platform wrappers and a model example.
+- Various other AI applications use llama.cpp as their inference engine;  
+  for a detailed list, see the `user interfaces (UIs) section <https://github.com/ggml-org/llama.cpp?tab=readme-ov-file#description>`__.
+
+For more use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for llama.cpp examples and best practices to optimize your workloads on AMD GPUs.
+
+- The `Llama.cpp Meets Instinct: A New Era of Open-Source AI Acceleration <https://rocm.blogs.amd.com/ecosystems-and-partners/llama-cpp/README.html>`__, 
+  blog post outlines how the open-source llama.cpp framework enables efficient LLM inference—including interactive inference with ``llama-cli``, 
+  server deployment with ``llama-server``, GGUF model preparation and quantization, performance benchmarking, and optimizations tailored for 
+  AMD Instinct GPUs within the ROCm ecosystem. 
+
+.. _llama-cpp-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `ROCm llama.cpp Docker images <https://hub.docker.com/r/rocm/llama.cpp>`__
+with ROCm backends on Docker Hub. The following Docker image tags and associated
+inventories were tested on `ROCm 6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. important::
+
+   Tag endings of ``_full``, ``_server``, and ``_light`` serve different purposes for entrypoints as follows:
+
+   - Full: This image includes both the main executable file and the tools to convert ``LLaMA`` models into ``ggml`` and convert into 4-bit quantization.
+   - Server: This image only includes the server executable file.
+   - Light: This image only includes the main executable file.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Full Docker
+      - Server Docker
+      - Light Docker
+      - llama.cpp
+      - Ubuntu
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_full/images/sha256-f78f6c81ab2f8e957469415fe2370a1334fe969c381d1fe46050c85effaee9d5"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_server/images/sha256-275ad9e18f292c26a00a2de840c37917e98737a88a3520bdc35fd3fc5c9a6a9b"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_light/images/sha256-cc324e6faeedf0e400011f07b49d2dc41a16bae257b2b7befa0f4e2e97231320"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b5997 <https://github.com/ROCm/llama.cpp/tree/release/b5997>`__
+      - 24.04
+
+Key ROCm libraries for llama.cpp
+================================================================================
+
+llama.cpp functionality on ROCm is determined by its underlying library
+dependencies. These ROCm components affect the capabilities, performance, and
+feature set available to developers.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - Version
+      - Purpose
+      - Usage
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`__
+      - :version-ref:`hipBLAS rocm_version`
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Supports operations such as matrix multiplication, matrix-vector
+        products, and tensor contractions. Utilized in both dense and batched
+        linear algebra operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`__
+      - :version-ref:`hipBLASLt rocm_version`
+      - hipBLASLt is an extension of the hipBLAS library, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+      - By setting the flag ``ROCBLAS_USE_HIPBLASLT``, you can dispatch hipblasLt
+        kernels where possible.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`__
+      - :version-ref:`rocWMMA rocm_version`
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+      - Can be used to enhance the flash attention performance on AMD compute, by enabling
+        the flag during compile time.

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

@@ -0,0 +1,111 @@
+:orphan:
+
+.. meta::
+    :description: Ray deep learning framework compatibility
+    :keywords: GPU, Ray compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+Ray compatibility
+*******************************************************************************
+
+Ray is a unified framework for scaling AI and Python applications from your laptop 
+to a full cluster, without changing your code. Ray consists of `a core distributed 
+runtime  <https://docs.ray.io/en/latest/ray-core/walkthrough.html>`_ and a set of 
+`AI libraries <https://docs.ray.io/en/latest/ray-air/getting-started.html>`_ for 
+simplifying machine learning computations.
+
+Ray is a general-purpose framework that runs many types of workloads efficiently. 
+Any Python application can be scaled with Ray, without extra infrastructure.
+
+ROCm support for Ray is upstreamed, and you can build the official source code
+with ROCm support: 
+
+- ROCm support for Ray is hosted in the official `https://github.com/ROCm/ray 
+  <https://github.com/ROCm/ray>`_ repository.
+
+- Due to independent compatibility considerations, this location differs from the 
+  `https://github.com/ray-project/ray <https://github.com/ray-project/ray>`_ upstream repository.
+
+- To install Ray, use the prebuilt :ref:`Docker image <ray-docker-compat>` 
+  which includes ROCm, Ray, and all required dependencies.
+
+  - See the :doc:`ROCm Ray installation guide <rocm-install-on-linux:install/3rd-party/ray-install>` 
+    for instructions to get started.
+
+  - See the `Installation section <https://docs.ray.io/en/latest/ray-overview/installation.html>`_ 
+    in the upstream Ray documentation.
+
+  - The Docker image provided is based on the upstream Ray `Daily Release (Nightly) wheels <https://docs.ray.io/en/latest/ray-overview/installation.html#daily-releases-nightlies>`__ 
+    corresponding to commit `005c372 <https://github.com/ray-project/ray/commit/005c372262e050d5745f475e22e64305fa07f8b8>`__.
+
+.. note::
+
+  Ray is supported on ROCm 6.4.1.
+
+Supported devices
+================================================================================
+
+**Officially Supported**: AMD Instinct™ MI300X, MI210
+
+
+Use cases and recommendations
+================================================================================
+
+* The `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm 
+  Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__  
+  blog provides an overview of Volcano Engine Reinforcement Learning (verl) 
+  for large language models (LLMs) and discusses its benefits in large-scale 
+  reinforcement learning from human feedback (RLHF). It uses Ray as part of a 
+  hybrid orchestration engine to schedule and coordinate training and inference 
+  tasks in parallel, enabling optimized resource utilization and potential overlap 
+  between these phases. This dynamic resource allocation strategy significantly 
+  improves overall system efficiency. The blog presents verl’s performance results, 
+  focusing on throughput and convergence accuracy achieved on AMD Instinct™ MI300X 
+  GPUs. Follow this guide to get started with verl on AMD Instinct GPUs and 
+  accelerate your RLHF training with ROCm-optimized performance.
+
+* The `Exploring Use Cases for Scalable AI: Implementing Ray with ROCm Support for Efficient ML Workflows 
+  <https://rocm.blogs.amd.com/artificial-intelligence/rocm-ray/README.html>`__
+  blog post describes key use cases such as training and inference for large language models (LLMs), 
+  model serving, hyperparameter tuning, reinforcement learning, and the orchestration of large-scale 
+  workloads using Ray in the ROCm environment.
+
+For more use cases and recommendations, see the AMD GPU tabs in the `Accelerator Support 
+topic <https://docs.ray.io/en/latest/ray-core/scheduling/accelerators.html#accelerator-support>`__ 
+of the Ray core documentation and refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for Ray examples and best practices to optimize your workloads on AMD GPUs.
+
+.. _ray-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes ready-made `ROCm Ray Docker images <https://hub.docker.com/r/rocm/ray/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and
+associated inventories represent the latest Ray version from the official Docker Hub and are validated for
+`ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`_. Click the |docker-icon|
+icon to view the image on Docker Hub.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - Ray
+      - Pytorch
+      - Ubuntu
+      - Python
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.48.0.post0_rocm6.4.1_ubuntu24.04_py3.12_pytorch2.6.0/images/sha256-0d166fe6bdced38338c78eedfb96eff92655fb797da3478a62dd636365133cc0"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `2.48.0.post0 <https://github.com/ROCm/ray/tree/release/2.48.0.post0>`_
+      - 2.6.0+git684f6f2
+      - 24.04
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_

docs/conf.py

@@ -108,6 +108,8 @@ article_pages = [
     {"file": "compatibility/ml-compatibility/dgl-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/megablocks-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/taichi-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/ray-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/llama-cpp-compatibility", "os": ["linux"]},
     {"file": "how-to/deep-learning-rocm", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},
@@ -124,11 +126,15 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.3", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.4", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.5", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.6", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-primus-migration-guide", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/primus-megatron", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/pytorch-training", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-history", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.3", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.4", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.5", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.6", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-history", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.4", "os": ["linux"]},

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

@@ -78,7 +78,11 @@ vllm_benchmark:
         model_repo: Qwen/QwQ-32B
         url: https://huggingface.co/Qwen/QwQ-32B
         precision: float16
-        tunableop: true
+      - model: Qwen3 30B A3B
+        mad_tag: pyt_vllm_qwen3-30b-a3b
+        model_repo: Qwen/Qwen3-30B-A3B
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B
+        precision: float16
     - group: Microsoft Phi
       tag: phi
       models:

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

@@ -0,0 +1,72 @@
+dockers:
+  - 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
+  - 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
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: jax_maxtext_train_llama-3.3-70b
+        model_repo: Llama-3.3-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 8B
+        mad_tag: jax_maxtext_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 70B
+        mad_tag: jax_maxtext_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3 8B
+        mad_tag: jax_maxtext_train_llama-3-8b
+        multinode_training_script: llama3_8b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3 70B
+        mad_tag: jax_maxtext_train_llama-3-70b
+        multinode_training_script: llama3_70b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 2 7B
+        mad_tag: jax_maxtext_train_llama-2-7b
+        model_repo: Llama-2-7B
+        precision: bf16
+        multinode_training_script: llama2_7b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+      - model: Llama 2 70B
+        mad_tag: jax_maxtext_train_llama-2-70b
+        model_repo: Llama-2-70B
+        precision: bf16
+        multinode_training_script: llama2_70b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V2-Lite (16B)
+        mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
+        model_repo: DeepSeek-V2-lite
+        precision: bf16
+        doc_options: ["single-node"]
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: jax_maxtext_train_mixtral-8x7b
+        model_repo: Mixtral-8x7B
+        precision: bf16
+        doc_options: ["single-node"]

docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.6-benchmark-models.yaml

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

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

@@ -1,38 +1,17 @@
-unified_docker:
-  latest:
-    pull_tag: rocm/pytorch-training:v25.6
-    docker_hub_url: https://hub.docker.com/r/rocm/pytorch-training/tags
-    rocm_version: 6.4.1
-    pytorch_version: 2.8.0a0+git7d205b2
-    python_version: 3.10.17
-    transformer_engine_version: 1.14.0+2f85f5f2
-    flash_attention_version: 3.0.0.post1
-    hipblaslt_version: 0.15.0-8c6919d
-    triton_version: 3.3.0
+dockers:
+  - pull_tag: rocm/pytorch-training:v25.7
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.7/images/sha256-cc6fd840ab89cb81d926fc29eca6d075aee9875a55a522675a4b9231c9a0a712
+    components:
+      ROCm: 6.4.2
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+94e53dd8
+      Flash Attention: 3.0.0.post1
+      hipBLASLt: 1.1.0-4b9a52edfc
+      Triton: 3.3.0
 model_groups:
-  - group: Pre-training
-    tag: pre-training
-    models:
-    - model: Llama 3.1 8B
-      mad_tag: pyt_train_llama-3.1-8b
-      model_repo: Llama-3.1-8B
-      url: https://huggingface.co/meta-llama/Llama-3.1-8B
-      precision: BF16
-      training_modes: [pretrain]
-    - model: Llama 3.1 70B
-      mad_tag: pyt_train_llama-3.1-70b
-      model_repo: Llama-3.1-70B
-      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
-      precision: BF16
-      training_modes: [pretrain]
-    - model: FLUX.1-dev
-      mad_tag: pyt_train_flux
-      model_repo: Flux
-      url: https://huggingface.co/black-forest-labs/FLUX.1-dev
-      precision: BF16
-      training_modes: [pretrain]
-  - group: Fine-tuning
-    tag: fine-tuning
+  - group: Meta Llama
+    tag: llama
     models:
     - model: Llama 4 Scout 17B-16E
       mad_tag: pyt_train_llama-4-scout-17b-16e
@@ -75,19 +54,19 @@ model_groups:
       model_repo: Llama-3.1-8B
       url: https://huggingface.co/meta-llama/Llama-3.1-8B
       precision: BF16
-      training_modes: [finetune_fw, finetune_lora]
+      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
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
       precision: BF16
-      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+      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, HF_finetune_lora]
+      training_modes: [finetune_qlora]
     - model: Llama 3 8B
       mad_tag: pyt_train_llama-3-8b
       model_repo: Llama-3-8B
@@ -117,4 +96,67 @@ model_groups:
       model_repo: Llama-2-70B
       url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
       precision: BF16
-      training_modes: [finetune_lora, finetune_qlora, HF_finetune_lora]
+      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: 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]

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

@@ -23,93 +23,114 @@ The table below summarizes information about ROCm-enabled deep learning framewor
       - Installation options
       - GitHub
 
-    * - `PyTorch <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/pytorch-compatibility.html>`_
+    * - `PyTorch <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/pytorch-compatibility.html>`__
       - .. raw:: html
-         
+
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html#using-a-docker-image-with-pytorch-pre-installed>`_ 
-        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html#using-a-wheels-package>`_
-        - `ROCm Base Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html#using-the-pytorch-rocm-base-docker-image>`_ 
-        - `Upstream Docker file <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html#using-the-pytorch-upstream-dockerfile>`_
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html#using-a-docker-image-with-pytorch-pre-installed>`__
+        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html#using-a-wheels-package>`__
+        - `ROCm Base Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html#using-the-pytorch-rocm-base-docker-image>`__
+        - `Upstream Docker file <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html#using-the-pytorch-upstream-dockerfile>`__
       - .. raw:: html
-         
+
           <a href="https://github.com/ROCm/pytorch"><i class="fab fa-github fa-lg"></i></a>
-   
-    * - `TensorFlow <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/tensorflow-compatibility.html>`_
+
+    * - `TensorFlow <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/tensorflow-compatibility.html>`__
       - .. raw:: html
-         
+
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/tensorflow-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/tensorflow-install.html#using-a-docker-image-with-tensorflow-pre-installed>`_
-        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/tensorflow-install.html#using-a-wheels-package>`_
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/tensorflow-install.html#using-a-docker-image-with-tensorflow-pre-installed>`__
+        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/tensorflow-install.html#using-a-wheels-package>`__
 
       - .. raw:: html
-         
+
           <a href="https://github.com/ROCm/tensorflow-upstream"><i class="fab fa-github fa-lg"></i></a> 
 
-    * - `JAX <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/jax-compatibility.html>`_
+    * - `JAX <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/jax-compatibility.html>`__
       - .. raw:: html
-         
+
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/jax-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/jax-install.html#using-a-prebuilt-docker-image>`_
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/jax-install.html#using-a-prebuilt-docker-image>`__
       - .. raw:: html
-         
+
           <a href="https://github.com/ROCm/jax"><i class="fab fa-github fa-lg"></i></a>
-   
-    * - `verl <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/verl-compatibility.html>`_
+
+    * - `verl <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/verl-compatibility.html>`__
       - .. raw:: html
-         
+
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/verl-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/verl-install.html#use-a-prebuilt-docker-image-with-verl-pre-installed>`_
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/verl-install.html#use-a-prebuilt-docker-image-with-verl-pre-installed>`__
       - .. raw:: html
-         
+
           <a href="https://github.com/ROCm/verl"><i class="fab fa-github fa-lg"></i></a>
 
-    * - `Stanford Megatron-LM <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/stanford-megatron-lm-compatibility.html>`_
+    * - `Stanford Megatron-LM <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/stanford-megatron-lm-compatibility.html>`__
       - .. raw:: html
-         
+
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/stanford-megatron-lm-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/stanford-megatron-lm-install.html#use-a-prebuilt-docker-image-with-stanford-megatron-lm-pre-installed>`_
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/stanford-megatron-lm-install.html#use-a-prebuilt-docker-image-with-stanford-megatron-lm-pre-installed>`__
       - .. raw:: html
-         
+
           <a href="https://github.com/ROCm/Stanford-Megatron-LM"><i class="fab fa-github fa-lg"></i></a>
-   
-    * - `DGL <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/dgl-compatibility.html>`_
+
+    * - `DGL <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/dgl-compatibility.html>`__
       - .. raw:: html
-         
+
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/dgl-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/dgl-install.html#use-a-prebuilt-docker-image-with-dgl-pre-installed>`_
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/dgl-install.html#use-a-prebuilt-docker-image-with-dgl-pre-installed>`__
       - .. raw:: html
-         
+
           <a href="https://github.com/ROCm/dgl"><i class="fab fa-github fa-lg"></i></a> 
 
-    * - `Megablocks <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/megablocks-compatibility.html>`_
+    * - `Megablocks <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/megablocks-compatibility.html>`__
       - .. raw:: html
-         
+
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/megablocks-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/megablocks-install.html#using-a-prebuilt-docker-image-with-megablocks-pre-installed>`_
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/megablocks-install.html#using-a-prebuilt-docker-image-with-megablocks-pre-installed>`__
       - .. raw:: html
-         
+
           <a href="https://github.com/ROCm/megablocks"><i class="fab fa-github fa-lg"></i></a>
-   
-    * - `Taichi <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/taichi-compatibility.html>`_
+
+    * - `Taichi <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/taichi-compatibility.html>`__
       - .. raw:: html
-         
+
           <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/taichi-install.html"><i class="fas fa-link fa-lg"></i></a>
       - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/taichi-install.html#use-a-prebuilt-docker-image-with-taichi-pre-installed>`_ 
-        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/taichi-install.html#use-a-wheels-package>`_
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/taichi-install.html#use-a-prebuilt-docker-image-with-taichi-pre-installed>`__
+        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/taichi-install.html#use-a-wheels-package>`__
 
       - .. raw:: html
-         
-          <a href="https://github.com/ROCm/taichi"><i class="fab fa-github fa-lg"></i></a>      
 
+          <a href="https://github.com/ROCm/taichi"><i class="fab fa-github fa-lg"></i></a>
+
+    * - `Ray <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/ray-compatibility.html>`__
+      - .. raw:: html
+
+          <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/ray-install.html"><i class="fas fa-link fa-lg"></i></a>
+      - 
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/ray-install.html#using-a-prebuilt-docker-image-with-ray-pre-installed>`__
+        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/ray-install.html#install-ray-on-bare-metal-or-a-custom-container>`__
+        - `ROCm Base Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/ray-install.html#build-your-own-docker-image>`__
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/ray"><i class="fab fa-github fa-lg"></i></a>
+
+    * - `llama.cpp <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/llama-cpp-compatibility.html>`__
+      - .. raw:: html
+
+          <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/llama-cpp-install.html"><i class="fas fa-link fa-lg"></i></a>
+      - 
+        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/llama-cpp-install.html#use-a-prebuilt-docker-image-with-llama-cpp-pre-installed>`__
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/llama.cpp"><i class="fab fa-github fa-lg"></i></a>
 
 Learn how to use your ROCm deep learning environment for training, fine-tuning, inference, and performance optimization
 through the following guides.
@@ -124,10 +145,3 @@ through the following guides.
 
 * :doc:`Use ROCm for AI inference optimization <rocm-for-ai/inference-optimization/index>`
 
-
-
-
-
-
-
-

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

@@ -939,7 +939,7 @@ hipBLASLt benchmarking
 The GEMM library
 `hipBLASLt <https://rocm.docs.amd.com/projects/hipBLASLt/en/latest/index.html>`_
 provides a benchmark tool for its supported operations. Refer to the
-`documentation <https://github.com/ROCm/hipBLASLt/blob/develop/clients/benchmarks/README.md>`_
+`documentation <https://github.com/ROCm/hipBLASLt/blob/develop/clients/bench/README.md>`_
 for details.
 
 * Example 1: Benchmark mix fp8 GEMM

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

@@ -46,7 +46,7 @@ vLLM inference performance testing
         - {{ unified_docker.hipblaslt_version }}
 
 With this Docker image, you can quickly test the :ref:`expected
-inference performance numbers <vllm-benchmark-performance-measurements>` for
+inference performance numbers <vllm-benchmark-performance-measurements-715>` for
 MI300X series accelerators.
 
 What's new
@@ -219,7 +219,7 @@ system's configuration.
             ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
             model are collected in the following path: ``~/MAD/reports_{{model.precision}}/``.
 
-            Although the :ref:`available models <vllm-benchmark-available-models>` are preconfigured
+            Although the :ref:`available models <vllm-benchmark-available-models-715>` are preconfigured
             to collect latency and throughput performance data, you can also change the benchmarking
             parameters. See the standalone benchmarking tab for more information.
 

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

@@ -39,7 +39,7 @@ vLLM inference performance testing
         - {{ unified_docker.hipblaslt_version }}
 
 With this Docker image, you can quickly test the :ref:`expected
-inference performance numbers <vllm-benchmark-performance-measurements>` for
+inference performance numbers <vllm-benchmark-performance-measurements-812>` for
 MI300X series accelerators.
 
 What's new
@@ -208,7 +208,7 @@ system's configuration.
             and ``{{ model.mad_tag }}_serving.csv``.
 
             Although the :ref:`available models
-            <vllm-benchmark-available-models>` are preconfigured to collect
+            <vllm-benchmark-available-models-812>` are preconfigured to collect
             offline throughput and online serving performance data, you can
             also change the benchmarking parameters. See the standalone
             benchmarking tab for more information.

docs/how-to/rocm-for-ai/install.rst

@@ -22,9 +22,9 @@ If you’re new to ROCm, refer to the :doc:`ROCm quick start install guide for L
 <rocm-install-on-linux:install/quick-start>`.
 
 If you’re using a Radeon GPU for graphics-accelerated applications, refer to the
-`Radeon installation instructions <https://rocm.docs.amd.com/projects/radeon/en/docs-6.1.3/docs/install/native_linux/install-radeon.html>`_.
+`Radeon installation instructions <https://rocm.docs.amd.com/projects/radeon/en/latest/docs/install/native_linux/howto_native_linux.html>`_.
 
-You can install ROCm on :ref:`compatible systems <rocm-install-on-linux:reference/system-requirements>` via your Linux
+You can install ROCm on :doc:`compatible systems <rocm-install-on-linux:reference/system-requirements>` via your Linux
 distribution's package manager. See the following documentation resources to get started:
 
 * :doc:`ROCm installation overview <rocm-install-on-linux:install/install-overview>`

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

@@ -2,9 +2,9 @@
    :description: How to train a model using JAX MaxText for ROCm.
    :keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
 
-**************************************
-Training a model with MaxText for ROCm
-**************************************
+******************************************
+Training a model with JAX MaxText for 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
@@ -12,70 +12,108 @@ ROCm is an optimized fork of the upstream
 `<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
 on AMD MI300X series accelerators.
 
-The MaxText for ROCm training Docker (``rocm/jax-training:maxtext-v25.5``) image
+The MaxText for ROCm training Docker image
 provides a prebuilt environment for training on AMD Instinct MI300X and MI325X accelerators,
 including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
 It includes the following software components:
 
-+--------------------------+--------------------------------+
-| Software component       | Version                        |
-+==========================+================================+
-| ROCm                     | 6.3.4                          |
-+--------------------------+--------------------------------+
-| JAX                      | 0.4.35                         |
-+--------------------------+--------------------------------+
-| Python                   | 3.10.12                        |
-+--------------------------+--------------------------------+
-| Transformer Engine       | 1.12.0.dev0+b8b92dc            |
-+--------------------------+--------------------------------+
-| hipBLASLt                | 0.13.0-ae9c477a                |
-+--------------------------+--------------------------------+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
 
-Supported features and models
-=============================
+   {% set dockers = data.dockers %}
+   .. tab-set::
 
-MaxText provides the following key features to train large language models efficiently:
+      {% for docker in dockers %}
+      {% set jax_version = docker.components["JAX"] %}
+
+      .. tab-item:: JAX {{ jax_version }}
+         :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.
+
+            The provided multi-node training scripts in this documentation are
+            not currently supported with JAX 0.6.0. For multi-node training, use the JAX 0.5.0
+            Docker image.
+         {% endif %}
+
+      {% endfor %}
+
+MaxText with on ROCm provides the following key features to train large language models efficiently:
 
 - Transformer Engine (TE)
 
-- Flash Attention (FA) 3
+- Flash Attention (FA) 3 -- with or without sequence input packing
 
 - GEMM tuning
 
 - Multi-node support
 
-.. _amd-maxtext-model-support:
+- NANOO FP8 quantization support
 
-The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+.. _amd-maxtext-model-support-v257:
 
-* Llama 3.3 70B
+Supported models
+================
 
-* Llama 3.1 8B
+The following models are pre-optimized for performance on AMD Instinct MI300
+series accelerators. Some instructions, commands, and available training
+configurations in this documentation might vary by model -- select one to get
+started.
 
-* Llama 3.1 70B
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
 
-* Llama 3 8B
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
 
-* Llama 3 70B
+         <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+           <div class="row">
+             <div class="col-2 me-2 model-param-head">Model</div>
+             <div class="row col-10">
+      {% for model_group in model_groups %}
+               <div class="col-4 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+             </div>
+           </div>
 
-* Llama 2 7B
-
-* Llama 2 70B
-
-* DeepSeek-V2-Lite
+           <div class="row mt-1">
+             <div class="col-2 me-2 model-param-head">Model variant</div>
+             <div class="row col-10">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+             </div>
+           </div>
+         </div>
 
 .. note::
 
    Some models, such as Llama 3, require an external license agreement through
    a third party (for example, Meta).
 
-Unsupported features
---------------------
-
-Currently, MaxText's default packed input format is not supported. Using this format
-with the current Docker image results in incorrect attention calculations
-across different input sequences. Support for packed input format is planned for a future release.
-
 System validation
 =================
 
@@ -98,14 +136,14 @@ This Docker image is optimized for specific model configurations outlined
 as follows. Performance can vary for other training workloads, as AMD
 doesn’t validate configurations and run conditions outside those described.
 
-.. _amd-maxtext-multi-node-setup:
+.. _amd-maxtext-multi-node-setup-v257:
 
 Multi-node setup
 ----------------
 
 For multi-node environments, ensure you have all the necessary packages for
 your network device, such as, RDMA. If you're not using a multi-node setup
-with RDMA, skip ahead to :ref:`amd-maxtext-download-docker`.
+with RDMA, skip ahead to :ref:`amd-maxtext-get-started-v257`.
 
 1. Install the following packages to build and install the RDMA driver.
 
@@ -180,196 +218,203 @@ with RDMA, skip ahead to :ref:`amd-maxtext-download-docker`.
          # If using Mellanox NIC
          export NCCL_IB_HCA=mlx5_0,mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_8,mlx5_9
 
-.. _amd-maxtext-download-docker:
+.. _amd-maxtext-get-started-v257:
 
-Pull the Docker image
----------------------
+Benchmarking
+============
 
-1. Use the following command to pull the Docker image from Docker Hub.
+Once the setup is complete, choose between two options to reproduce the
+benchmark results:
 
-   .. code-block:: shell
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
 
-      docker pull rocm/jax-training:maxtext-v25.5
+   .. _vllm-benchmark-mad:
 
-2. Use the following command to launch the Docker container. Note that the benchmarking scripts
-   used in the :ref:`following section <amd-maxtext-get-started>` automatically launch the Docker container
-   and execute the benchmark.
+   {% set dockers = data.dockers %}
+   {% set model_groups = data.model_groups %}
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
 
-   .. code-block:: shell
+   .. container:: model-doc {{model.mad_tag}}
 
-      docker run -it --device /dev/dri --device /dev/kfd --network host --ipc host --group-add video --cap-add SYS_PTRACE --security-opt seccomp=unconfined --privileged -v $HOME/.ssh:/root/.ssh --shm-size 128G --name maxtext_training rocm/jax-training:maxtext-v25.5
+      .. tab-set::
 
-.. _amd-maxtext-get-started:
+         {% if model.mad_tag and "single-node" in model.doc_options %}
+         .. tab-item:: MAD-integrated benchmarking
 
-Getting started
+            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
+
+               .. important::
+
+                  Quantized training is not supported with the JAX 0.6.0 Docker image; support
+                  will be added in a future release. For quantized training, use the JAX 0.5.0
+                  Docker image: ``rocm/jax-training:maxtext-v25.7``.
+
+            {% 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/maxtext/blob/main/benchmarks/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
 ===============
 
-The following examples demonstrate how to get started with single node
-and multi-node training using the benchmarking scripts provided at
-`<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__.
+- See the ROCm/maxtext benchmarking README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/readme.md>`__.
 
-.. important::
+- 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>`__.
 
-   The provided scripts launch a Docker container and execute a benchmark. Ensure you run these commands outside of any existing Docker container.
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
-Before running any benchmarks, ensure the ``$HF_HOME`` environment variable is
-set correctly and points to your Hugging Face cache directory. Refer to the
-README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__
-for more detailed instructions.
-
-Single node training benchmarking examples
-------------------------------------------
-
-* Example 1: Single node training with Llama 2 7B
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b.sh
-
-  Run the single node training benchmark:
-
-  .. code-block:: shell
-
-     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama2_7b.sh
-
-* Example 2: Single node training with Llama 2 70B
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b.sh
-
-  Run the single node training benchmark:
-
-  .. code-block:: shell
-
-     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama2_70b.sh
-
-* Example 3: Single node training with Llama 3 8B
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b.sh
-
-  Run the single node training benchmark:
-
-  .. code-block:: shell
-
-     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3_8b.sh
-
-* Example 4: Single node training with Llama 3 70B
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b.sh
-
-  Run the single node training benchmark:
-
-  .. code-block:: shell
-
-     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3_70b.sh
-
-* Example 5: Single node training with Llama 3.3 70B
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3.3_70b.sh
-
-  Run the single node training benchmark:
-
-  .. code-block:: shell
-
-     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3.3_70b.sh
-
-* Example 6: Single node training with DeepSeek V2 16B
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/deepseek_v2_16b.sh
-
-  Run the single node training benchmark:
-
-  .. code-block:: shell
-
-     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./deepseek_v2_16b.sh
-
-  .. note::
-
-     The reported TFLOP/s by MaxText for DeepSeek is not accurate. Use
-     the tokens/s as a performance indicator.
-
-Multi-node training benchmarking examples
------------------------------------------
-
-The following examples use SLURM for running on multiple nodes -- the commands might need to be adjusted for your
-own cluster setup.
-
-* Example 1: Multi-node training with Llama 2 7B
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b_multinode.sh
-
-  Run the multi-node training benchmark. For example:
-
-  .. code-block:: shell
-
-     sbatch -N <num_nodes> llama2_7b_multinode.sh
-
-* Example 2: Multi-node training with Llama 2 70B
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b_multinode.sh
-
-  Run the multi-node training benchmark. For example:
-
-  .. code-block:: shell
-
-     sbatch -N <num_nodes> llama2_70b_multinode.sh
-
-* Example 3: Multi-node training with Llama 3 8B model
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b_multinode.sh
-
-  Run the multi-node training benchmark. For example:
-
-  .. code-block:: shell
-
-     sbatch -N <num_nodes> llama3_8b_multinode.sh
-
-* Example 4: Multi-node training with Llama 3 70B model
-
-  Download the benchmarking script:
-
-  .. code-block:: shell
-
-     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b_multinode.sh
-
-  Run the multi-node training benchmark. For example:
-
-  .. code-block:: shell
-
-     sbatch -N <num_nodes> llama3_70b_multinode.sh
+- 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
 =================

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

@@ -17,12 +17,21 @@ previous releases of the ``ROCm/jax-training`` Docker image on `Docker Hub <http
      - Components
      - Resources
 
-   * - 25.5 (latest)
+   * - 25.7 (latest)
+     - 
+       * ROCm 6.4.1
+       * JAX 0.6.0, 0.5.0
+     - 
+       * :doc:`Documentation <../jax-maxtext>`
+       * `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>`
+       * :doc:`Documentation <jax-maxtext-v25.5>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.5/images/sha256-4e0516358a227cae8f552fb866ec07e2edcf244756f02e7b40212abfbab5217b>`__
 
    * - 25.4

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

@@ -51,7 +51,7 @@ MaxText provides the following key features to train large language models effic
 
 - Multi-node support
 
-.. _amd-maxtext-model-support:
+.. _amd-maxtext-model-support-v254:
 
 The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.5.rst

@@ -0,0 +1,385 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using JAX MaxText for ROCm.
+   :keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
+
+**************************************
+Training a model with MaxText for ROCm
+**************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm JAX MaxText
+   training performance documentation. See :doc:`../jax-maxtext` for the latest version.
+
+MaxText is a high-performance, open-source framework built on the Google JAX
+machine learning library to train LLMs at scale. The MaxText framework for
+ROCm is an optimized fork of the upstream
+`<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
+on AMD MI300X series accelerators.
+
+The MaxText for ROCm training Docker (``rocm/jax-training:maxtext-v25.5``) image
+provides a prebuilt environment for training on AMD Instinct MI300X and MI325X accelerators,
+including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
+It includes the following software components:
+
++--------------------------+--------------------------------+
+| Software component       | Version                        |
++==========================+================================+
+| ROCm                     | 6.3.4                          |
++--------------------------+--------------------------------+
+| JAX                      | 0.4.35                         |
++--------------------------+--------------------------------+
+| Python                   | 3.10.12                        |
++--------------------------+--------------------------------+
+| Transformer Engine       | 1.12.0.dev0+b8b92dc            |
++--------------------------+--------------------------------+
+| hipBLASLt                | 0.13.0-ae9c477a                |
++--------------------------+--------------------------------+
+
+Supported features and models
+=============================
+
+MaxText provides the following key features to train large language models efficiently:
+
+- Transformer Engine (TE)
+
+- Flash Attention (FA) 3
+
+- GEMM tuning
+
+- Multi-node support
+
+.. _amd-maxtext-model-support-v255:
+
+The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+
+* Llama 3.3 70B
+
+* Llama 3.1 8B
+
+* Llama 3.1 70B
+
+* Llama 3 8B
+
+* Llama 3 70B
+
+* Llama 2 7B
+
+* Llama 2 70B
+
+* DeepSeek-V2-Lite
+
+.. note::
+
+   Some models, such as Llama 3, require an external license agreement through
+   a third party (for example, Meta).
+
+Unsupported features
+--------------------
+
+Currently, MaxText's default packed input format is not supported. Using this format
+with the current Docker image results in incorrect attention calculations
+across different input sequences. Support for packed input format is planned for a future release.
+
+System validation
+=================
+
+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.
+
+.. _amd-maxtext-multi-node-setup-v255:
+
+Multi-node setup
+----------------
+
+For multi-node environments, ensure you have all the necessary packages for
+your network device, such as, RDMA. If you're not using a multi-node setup
+with RDMA, skip ahead to :ref:`amd-maxtext-download-docker`.
+
+1. Install the following packages to build and install the RDMA driver.
+
+   .. code-block:: shell
+
+      sudo apt install iproute2 -y
+      sudo apt install -y linux-headers-"$(uname-r)" libelf-dev
+      sudo apt install -y gcc make libtool autoconf librdmacm-dev rdmacm-utils infiniband-diags ibverbs-utils perftest ethtool libibverbs-dev rdma-core strace libibmad5 libibnetdisc5 ibverbs-providers libibumad-dev libibumad3 libibverbs1 libnl-3-dev libnl-route-3-dev
+
+   Refer to your NIC manufacturer's documentation for further steps on
+   compiling and installing the RoCE driver. For example, for Broadcom,
+   see `Compiling Broadcom NIC software from source <https://docs.broadcom.com/doc/957608-AN2XX#G3.484341>`_
+   in `Ethernet networking guide for AMD Instinct MI300X GPU clusters <https://docs.broadcom.com/doc/957608-AN2XX>`_.
+
+2. Set the following environment variables.
+
+   a. Master address
+
+      Change ``localhost`` to the master node's resolvable hostname or IP address:
+
+      .. code-block:: bash
+
+         export MASTER_ADDR="${MASTER_ADDR:-localhost}"
+
+   b. Number of nodes
+
+      Set the number of nodes you want to train on (for example, ``2``, ``4``, or ``8``):
+
+      .. code-block:: bash
+
+         export NNODES="${NNODES:-1}"
+
+   c. Node ranks
+
+      Set the rank of each node (``0`` for master, ``1`` for the first worker node, and so on)
+      Node ranks should be unique across all nodes in the cluster.
+
+      .. code-block:: bash
+
+         export NODE_RANK="${NODE_RANK:-0}"
+
+   d. Network interface
+
+      Update the network interface in the script to match your system's network interface. To
+      find your network interface, run the following (outside of any Docker container):
+
+      .. code-block:: bash
+
+         ip a
+
+      Look for an active interface with an IP address in the same subnet as
+      your other nodes. Then, update the following variable in the script, for
+      example:
+
+      .. code-block:: bash
+
+         export NCCL_SOCKET_IFNAME=ens50f0np0
+
+      This variable specifies which network interface to use for inter-node communication.
+      Setting this variable to the incorrect interface can result in communication failures
+      or significantly reduced performance.
+
+   e. RDMA interface
+
+      Ensure the :ref:`required packages <amd-maxtext-multi-node-setup>` are installed on all nodes.
+      Then, set the RDMA interfaces to use for communication.
+
+      .. code-block:: bash
+
+         # If using Broadcom NIC
+         export NCCL_IB_HCA=rdma0,rdma1,rdma2,rdma3,rdma4,rdma5,rdma6,rdma7
+         # If using Mellanox NIC
+         export NCCL_IB_HCA=mlx5_0,mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_8,mlx5_9
+
+.. _amd-maxtext-download-docker-v255:
+
+Pull the Docker image
+---------------------
+
+1. Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/jax-training:maxtext-v25.5
+
+2. Use the following command to launch the Docker container. Note that the benchmarking scripts
+   used in the :ref:`following section <amd-maxtext-get-started>` automatically launch the Docker container
+   and execute the benchmark.
+
+   .. code-block:: shell
+
+      docker run -it --device /dev/dri --device /dev/kfd --network host --ipc host --group-add video --cap-add SYS_PTRACE --security-opt seccomp=unconfined --privileged -v $HOME/.ssh:/root/.ssh --shm-size 128G --name maxtext_training rocm/jax-training:maxtext-v25.5
+
+.. _amd-maxtext-get-started-v255:
+
+Getting started
+===============
+
+The following examples demonstrate how to get started with single node
+and multi-node training using the benchmarking scripts provided at
+`<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__.
+
+.. important::
+
+   The provided scripts launch a Docker container and execute a benchmark. Ensure you run these commands outside of any existing Docker container.
+
+Before running any benchmarks, ensure the ``$HF_HOME`` environment variable is
+set correctly and points to your Hugging Face cache directory. Refer to the
+README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__
+for more detailed instructions.
+
+Single node training benchmarking examples
+------------------------------------------
+
+* Example 1: Single node training with Llama 2 7B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama2_7b.sh
+
+* Example 2: Single node training with Llama 2 70B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama2_70b.sh
+
+* Example 3: Single node training with Llama 3 8B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3_8b.sh
+
+* Example 4: Single node training with Llama 3 70B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3_70b.sh
+
+* Example 5: Single node training with Llama 3.3 70B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3.3_70b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./llama3.3_70b.sh
+
+* Example 6: Single node training with DeepSeek V2 16B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/deepseek_v2_16b.sh
+
+  Run the single node training benchmark:
+
+  .. code-block:: shell
+
+     IMAGE="rocm/jax-training:maxtext-v25.5" bash ./deepseek_v2_16b.sh
+
+  .. note::
+
+     The reported TFLOP/s by MaxText for DeepSeek is not accurate. Use
+     the tokens/s as a performance indicator.
+
+Multi-node training benchmarking examples
+-----------------------------------------
+
+The following examples use SLURM for running on multiple nodes -- the commands might need to be adjusted for your
+own cluster setup.
+
+* Example 1: Multi-node training with Llama 2 7B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_7b_multinode.sh
+
+  Run the multi-node training benchmark. For example:
+
+  .. code-block:: shell
+
+     sbatch -N <num_nodes> llama2_7b_multinode.sh
+
+* Example 2: Multi-node training with Llama 2 70B
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama2_70b_multinode.sh
+
+  Run the multi-node training benchmark. For example:
+
+  .. code-block:: shell
+
+     sbatch -N <num_nodes> llama2_70b_multinode.sh
+
+* Example 3: Multi-node training with Llama 3 8B model
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_8b_multinode.sh
+
+  Run the multi-node training benchmark. For example:
+
+  .. code-block:: shell
+
+     sbatch -N <num_nodes> llama3_8b_multinode.sh
+
+* Example 4: Multi-node training with Llama 3 70B model
+
+  Download the benchmarking script:
+
+  .. code-block:: shell
+
+     wget https://raw.githubusercontent.com/ROCm/maxtext/refs/heads/main/benchmarks/gpu-rocm/llama3_70b_multinode.sh
+
+  Run the multi-node training benchmark. For example:
+
+  .. code-block:: shell
+
+     sbatch -N <num_nodes> llama3_70b_multinode.sh
+
+Previous versions
+=================
+
+See :doc:`jax-maxtext-history` to find documentation for previous releases
+of the ``ROCm/jax-training`` Docker image.

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

@@ -18,7 +18,7 @@ Training a model with ROCm Megatron-LM
 The ROCm Megatron-LM framework is a specialized fork of the robust Megatron-LM, designed to
 enable efficient training of large-scale language models on AMD GPUs. By leveraging AMD Instinct™ MI300X
 accelerators, AMD Megatron-LM delivers enhanced scalability, performance, and resource utilization for AI
-workloads. It is purpose-built to :ref:`support models <amd-megatron-lm-model-support>`
+workloads. It is purpose-built to :ref:`support models <amd-megatron-lm-model-support-24-12>`
 like Meta's Llama 2, Llama 3, and Llama 3.1, enabling developers to train next-generation AI models with greater
 efficiency. See the GitHub repository at `<https://github.com/ROCm/Megatron-LM>`__.
 
@@ -67,7 +67,7 @@ Megatron-LM provides the following key features to train large language models e
 
 - Pre-training
 
-.. _amd-megatron-lm-model-support:
+.. _amd-megatron-lm-model-support-24-12:
 
 The following models are pre-optimized for performance on the AMD Instinct MI300X accelerator.
 

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

@@ -67,7 +67,7 @@ Megatron-LM provides the following key features to train large language models e
 
 - Pre-training
 
-.. _amd-megatron-lm-model-support:
+.. _amd-megatron-lm-model-support-25-3:
 
 The following models are pre-optimized for performance on the AMD Instinct MI300X accelerator.
 
@@ -278,7 +278,7 @@ handle a variety of input sequences, including unseen words or domain-specific t
    .. tab-item:: Llama
       :sync: llama
 
-      To train any of the Llama 2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support>`, use the ``Llama2Tokenizer``.
+      To train any of the Llama 2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support-25-3>`, use the ``Llama2Tokenizer``.
 
       To train any of Llama 3 and Llama 3.1 models that this Docker image supports, use the ``HuggingFaceTokenizer``.
       Set the Hugging Face model link in the ``TOKENIZER_MODEL`` variable.
@@ -292,7 +292,7 @@ handle a variety of input sequences, including unseen words or domain-specific t
    .. tab-item:: DeepSeek V2
       :sync: deepseek
 
-      To train any of the DeepSeek V2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support>`, use the ``DeepSeekV2Tokenizer``.
+      To train any of the DeepSeek V2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support-25-3>`, use the ``DeepSeekV2Tokenizer``.
 
 Multi-node training
 ^^^^^^^^^^^^^^^^^^^

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

@@ -67,7 +67,7 @@ Megatron-LM provides the following key features to train large language models e
 
 - Pre-training
 
-.. _amd-megatron-lm-model-support:
+.. _amd-megatron-lm-model-support-25-4:
 
 The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
 
@@ -291,7 +291,7 @@ or ``${DATA_DIR}/tokenizer_llama2``.
    .. tab-item:: Llama
       :sync: llama
 
-      To train any of the Llama 2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support>`, use the ``Llama2Tokenizer``
+      To train any of the Llama 2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support-25-4>`, use the ``Llama2Tokenizer``
       or the default ``HuggingFaceTokenizer``.
 
       To train any of Llama 3 and Llama 3.1 models that this Docker image supports, use the ``HuggingFaceTokenizer``.
@@ -320,7 +320,7 @@ or ``${DATA_DIR}/tokenizer_llama2``.
    .. tab-item:: DeepSeek V2
       :sync: deepseek
 
-      To train any of the DeepSeek V2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support>`, use the ``DeepSeekV2Tokenizer``.
+      To train any of the DeepSeek V2 models that :ref:`this Docker image supports <amd-megatron-lm-model-support-25-4>`, use the ``DeepSeekV2Tokenizer``.
 
 Multi-node training
 ^^^^^^^^^^^^^^^^^^^

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

@@ -16,12 +16,20 @@ previous releases of the ``ROCm/pytorch-training`` Docker image on `Docker Hub <
      - Components
      - Resources
 
+   * - v25.7
+     - 
+       * ROCm 6.4.2
+       * PyTorch 2.8.0a0+gitd06a406
+     - 
+       * :doc:`Documentation <../pytorch-training>`
+       * `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>`
+       * :doc:`Documentation <pytorch-training-v25.6>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.6/images/sha256-a4cea3c493a4a03d199a3e81960ac071d79a4a7a391aa9866add3b30a7842661>`__
 
    * - v25.5

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.5.rst

@@ -437,3 +437,8 @@ Once the setup is complete, choose between two options to start benchmarking:
 
            ./pytorch_benchmark_report.sh -t HF_finetune_lora -p BF16 -m Llama-2-70B
 
+Previous versions
+=================
+
+See :doc:`pytorch-training-history` to find documentation for previous releases
+of the ``ROCm/pytorch-training`` Docker image.

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

@@ -0,0 +1,456 @@
+: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 for ROCm
+**************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   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.
+
+The `PyTorch for ROCm training Docker <https://hub.docker.com/layers/rocm/pytorch-training/v25.6/images/sha256-a4cea3c493a4a03d199a3e81960ac071d79a4a7a391aa9866add3b30a7842661>`_
+(``rocm/pytorch-training:v25.6``) image provides a prebuilt optimized environment for fine-tuning and pretraining a
+model on AMD Instinct MI325X and MI300X accelerators. It includes the following software components to accelerate
+training workloads:
+
++--------------------------+--------------------------------+
+| Software component       | Version                        |
++==========================+================================+
+| ROCm                     | 6.3.4                          |
++--------------------------+--------------------------------+
+| PyTorch                  | 2.8.0a0+git7d205b2             |
++--------------------------+--------------------------------+
+| Python                   | 3.10.17                        |
++--------------------------+--------------------------------+
+| Transformer Engine       | 1.14.0+2f85f5f2                |
++--------------------------+--------------------------------+
+| Flash Attention          | 3.0.0.post1                    |
++--------------------------+--------------------------------+
+| hipBLASLt                | 0.15.0-8c6919d                 |
++--------------------------+--------------------------------+
+| Triton                   | 3.3.0                          |
++--------------------------+--------------------------------+
+
+.. _amd-pytorch-training-model-support-v256:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X accelerators.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.6-benchmark-models.yaml
+
+   {% set unified_docker = data.unified_docker.latest %}
+   {% set model_groups = data.model_groups %}
+
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+        <div class="row">
+          <div class="col-2 me-2 model-param-head">Workload</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+            <div class="col-6 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+   {% endfor %}
+          </div>
+        </div>
+
+        <div class="row mt-1">
+          <div class="col-2 me-2 model-param-head">Model</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+      {% set models = model_group.models %}
+      {% for model in models %}
+         {% if models|length % 3 == 0 %}
+            <div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% else %}
+            <div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+          </div>
+        </div>
+      </div>
+
+   .. note::
+
+      Some models require an external license agreement through a third party (for example, Meta).
+
+   .. _amd-pytorch-training-performance-measurements-v256:
+
+   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 accelerators or ROCm software.
+
+   System validation
+   =================
+
+   Before running AI workloads, it's important to validate that your AMD hardware is configured
+   correctly and performing optimally.
+
+   If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+   can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+   optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+   before starting training.
+
+   To test for optimal performance, consult the recommended :ref:`System health benchmarks
+   <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+   system's configuration.
+
+   This Docker image is optimized for specific model configurations outlined
+   below. Performance can vary for other training workloads, as AMD
+   doesn’t validate configurations and run conditions outside those described.
+
+   Benchmarking
+   ============
+
+   Once the setup is complete, choose between two options to start benchmarking:
+
+   .. tab-set::
+
+      .. tab-item:: MAD-integrated benchmarking
+
+         Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+         directory and install the required packages on the host machine.
+
+         .. code-block:: shell
+
+            git clone https://github.com/ROCm/MAD
+            cd MAD
+            pip install -r requirements.txt
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            For example, use this command to run the performance benchmark test on the {{ model.model }} model
+            using one GPU with the {{ model.precision }} data type on the host machine.
+
+            .. code-block:: shell
+
+               export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+               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 }}``, for example. The latency and throughput reports of the
+            model are collected in the following path: ``~/MAD/perf.csv``.
+
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Standalone benchmarking
+
+         .. rubric:: Download the Docker image and required packages
+
+         Use the following command to pull the Docker image from Docker Hub.
+
+         .. code-block:: shell
+
+            docker pull {{ unified_docker.pull_tag }}
+
+         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  $HOME/.ssh:/root/.ssh --shm-size 64G --name training_env {{ unified_docker.pull_tag }}
+
+         Use these commands if you exit the ``training_env`` container and need to return to it.
+
+         .. code-block:: shell
+
+            docker start training_env
+            docker exec -it training_env bash
+
+         In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
+         repository and navigate to the benchmark scripts directory
+         ``/workspace/MAD/scripts/pytorch_train``.
+
+         .. code-block:: shell
+
+            git clone https://github.com/ROCm/MAD
+            cd MAD/scripts/pytorch_train
+
+         .. rubric:: Prepare training datasets and dependencies
+
+         The following benchmarking examples require downloading models and datasets
+         from Hugging Face. To ensure successful access to gated repos, set your
+         ``HF_TOKEN``.
+
+         .. code-block:: shell
+
+            export HF_TOKEN=$your_personal_hugging_face_access_token
+
+         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://pytorch.org/data/beta/index.html>`_
+
+               * - ``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 %}
+         {% if model_group.tag == "pre-training" and model.mad_tag in ["pyt_train_llama-3.1-8b", "pyt_train_llama-3.1-70b", "pyt_train_flux"] %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Pretraining
+
+            To start the pre-training benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t pretrain -m {{ model.model_repo }} -p $datatype -s $sequence_length
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+            {% if model.mad_tag == "pyt_train_llama-3.1-8b" %}
+               * - ``$datatype``
+                 - ``BF16`` or ``FP8``
+                 - Only Llama 3.1 8B supports FP8 precision.
+            {% else %}
+               * - ``$datatype``
+                 - ``BF16``
+                 - Only Llama 3.1 8B supports FP8 precision.
+            {% endif %}
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+
+            {% if model.mad_tag == "pyt_train_flux" %}
+            .. container:: model-doc {{ model.mad_tag }}
+
+               .. note::
+
+                  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 %}
+         {% endif %}
+
+         {% if model_group.tag == "fine-tuning" %}
+         .. 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.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t $training_mode -m {{ model.model_repo }} -p BF16 -s $sequence_length
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               * - ``$training_mode``
+                 - ``finetune_fw``
+                 - Full weight fine-tuning (BF16 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
+
+               * - ``$datatype``
+                 - ``BF16``
+                 - All models support BF16.
+
+               * - ``$sequence_length``
+                 - Between 2048 and 16384.
+                 - Sequence length for the language model.
+
+            .. note::
+
+               {{ model.model }} currently supports the following fine-tuning methods:
+
+            {% for method in model.training_modes %}
+               * ``{{ method }}``
+            {% endfor %}
+            {% if model.training_modes|length < 4 %}
+
+               The upstream `torchtune <https://github.com/pytorch/torchtune>`_ repository
+               does not currently provide YAML configuration files for other combinations of
+               model to fine-tuning method
+               However, you can still configure your own YAML files to enable support for
+               fine-tuning methods not listed here by following existing patterns in the
+               ``/workspace/torchtune/recipes/configs`` directory.
+            {% 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>`__.
+
+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 accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`pytorch-training-history` to find documentation for previous releases
+of the ``ROCm/pytorch-training`` Docker image.

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

@@ -9,28 +9,25 @@ Training a model with PyTorch for ROCm
 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 <https://hub.docker.com/r/rocm/pytorch-training/tags>`_
-(``rocm/pytorch-training:v25.6``) image provides a prebuilt optimized environment for fine-tuning and pretraining a
-model on AMD Instinct MI325X and MI300X accelerators. It includes the following software components to accelerate
-training workloads:
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
 
-+--------------------------+--------------------------------+
-| Software component       | Version                        |
-+==========================+================================+
-| ROCm                     | 6.3.4                          |
-+--------------------------+--------------------------------+
-| PyTorch                  | 2.8.0a0+git7d205b2             |
-+--------------------------+--------------------------------+
-| Python                   | 3.10.17                        |
-+--------------------------+--------------------------------+
-| Transformer Engine       | 1.14.0+2f85f5f2                |
-+--------------------------+--------------------------------+
-| Flash Attention          | 3.0.0.post1                    |
-+--------------------------+--------------------------------+
-| hipBLASLt                | 0.15.0-8c6919d                 |
-+--------------------------+--------------------------------+
-| Triton                   | 3.3.0                          |
-+--------------------------+--------------------------------+
+   {% 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 accelerators. 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:
 
@@ -38,26 +35,27 @@ Supported models
 ================
 
 The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X accelerators.
+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.unified_docker.latest %}
+   {% 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">
-          <div class="col-2 me-2 model-param-head">Workload</div>
+          <div class="col-2 me-2 model-param-head">Model group</div>
           <div class="row col-10">
    {% for model_group in model_groups %}
-            <div class="col-6 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+            <div class="col-3 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
    {% endfor %}
           </div>
         </div>
 
         <div class="row mt-1">
-          <div class="col-2 me-2 model-param-head">Model</div>
+          <div class="col-2 me-2 model-param-head">Model variant</div>
           <div class="row col-10">
    {% for model_group in model_groups %}
       {% set models = model_group.models %}
@@ -73,84 +71,116 @@ The following models are pre-optimized for performance on the AMD Instinct MI325
         </div>
       </div>
 
-   .. note::
 
-      Some models require an external license agreement through a third party (for example, Meta).
+   .. _amd-pytorch-training-supported-training-modes:
 
-   .. _amd-pytorch-training-performance-measurements:
+   The following table lists supported training modes per model.
 
-   Performance measurements
-   ========================
+   .. dropdown:: Supported training modes
 
-   To evaluate performance, the
+      .. list-table::
+         :header-rows: 1
+
+         * - Model
+           - Supported training modes
+
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+         * - {{ model.model }}
+           - ``{{ model.training_modes | join('``, ``') }}``
+
+         {% 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>`_
-   page provides reference throughput and latency measurements for training
-   popular AI models.
+   should not be interpreted as the peak performance achievable by AMD
+   Instinct MI325X and MI300X accelerators or ROCm software.
 
-   .. note::
+System validation
+=================
 
-      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 accelerators or ROCm software.
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
 
-   System validation
-   =================
+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.
 
-   Before running AI workloads, it's important to validate that your AMD hardware is configured
-   correctly and performing optimally.
+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.
 
-   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.
+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.
 
-   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.
+Run training
+============
 
-   This Docker image is optimized for specific model configurations outlined
-   below. Performance can vary for other training workloads, as AMD
-   doesn’t validate configurations and run conditions outside those described.
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
 
-   Benchmarking
-   ============
+   {% set unified_docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
 
-   Once the setup is complete, choose between two options to start benchmarking:
+   Once the setup is complete, choose between two options to start benchmarking training:
 
    .. tab-set::
 
       .. tab-item:: MAD-integrated benchmarking
 
-         Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
-         directory and install the required packages on the host machine.
+         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
+            .. code-block:: shell
 
-            git clone https://github.com/ROCm/MAD
-            cd MAD
-            pip install -r requirements.txt
+               git clone https://github.com/ROCm/MAD
+               cd MAD
+               pip install -r requirements.txt
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
 
          .. container:: model-doc {{ model.mad_tag }}
 
-            For example, use this command to run the performance benchmark test on the {{ model.model }} model
-            using one GPU with the {{ model.precision }} data type on the host machine.
+            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
+               .. 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
+                  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 }}``, for example. The latency and throughput reports of the
-            model are collected in the following path: ``~/MAD/perf.csv``.
+               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 %}
@@ -159,222 +189,213 @@ The following models are pre-optimized for performance on the AMD Instinct MI325
 
          .. rubric:: Download the Docker image and required packages
 
-         Use the following command to pull the Docker image from Docker Hub.
+         1. Use the following command to pull the Docker image from Docker Hub.
 
-         .. code-block:: shell
+            .. code-block:: shell
 
-            docker pull {{ unified_docker.pull_tag }}
+               docker pull {{ unified_docker.pull_tag }}
 
-         Run the Docker container.
+         2. Run the Docker container.
 
-         .. code-block:: shell
+            .. 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 }}
+               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.
+            Use these commands if you exit the ``training_env`` container and need to return to it.
 
-         .. code-block:: shell
+            .. code-block:: shell
 
-            docker start training_env
-            docker exec -it training_env bash
+               docker start training_env
+               docker exec -it training_env bash
 
-         In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
-         repository and navigate to the benchmark scripts directory
-         ``/workspace/MAD/scripts/pytorch_train``.
+         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
+            .. code-block:: shell
 
-            git clone https://github.com/ROCm/MAD
-            cd MAD/scripts/pytorch_train
+               git clone https://github.com/ROCm/MAD
+               cd 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``.
+         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
+            .. code-block:: shell
 
-            export HF_TOKEN=$your_personal_hugging_face_access_token
+               export HF_TOKEN=$your_personal_hugging_face_access_token
 
-         Run the setup script to install libraries and datasets needed for benchmarking.
+         2. Run the setup script to install libraries and datasets needed for benchmarking.
 
-         .. code-block:: shell
+            .. code-block:: shell
 
-            ./pytorch_benchmark_setup.sh
+               ./pytorch_benchmark_setup.sh
 
-         .. container:: model-doc pyt_train_llama-3.1-8b
+            .. container:: model-doc pyt_train_llama-3.1-8b
 
-            ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 8B:
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 8B:
 
-            .. list-table::
-               :header-rows: 1
+               .. list-table::
+                  :header-rows: 1
 
-               * - Library
-                 - Reference
+                  * - Library
+                    - Reference
 
-               * - ``accelerate``
-                 - `Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_
+                  * - ``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
+                  * - ``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
+            .. container:: model-doc pyt_train_llama-3.1-70b
 
-            ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 70B:
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 70B:
 
-            .. list-table::
-               :header-rows: 1
+               .. list-table::
+                  :header-rows: 1
 
-               * - Library
-                 - Reference
+                  * - Library
+                    - Reference
 
-               * - ``datasets``
-                 - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
 
-               * - ``torchdata``
-                 - `TorchData <https://pytorch.org/data/beta/index.html>`_
+                  * - ``torchdata``
+                    - `TorchData <https://pytorch.org/data/beta/index.html>`_
 
-               * - ``tomli``
-                 - `Tomli <https://pypi.org/project/tomli/>`_
+                  * - ``tomli``
+                    - `Tomli <https://pypi.org/project/tomli/>`_
 
-               * - ``tiktoken``
-                 - `tiktoken <https://github.com/openai/tiktoken>`_
+                  * - ``tiktoken``
+                    - `tiktoken <https://github.com/openai/tiktoken>`_
 
-               * - ``blobfile``
-                 - `blobfile <https://pypi.org/project/blobfile/>`_
+                  * - ``blobfile``
+                    - `blobfile <https://pypi.org/project/blobfile/>`_
 
-               * - ``tabulate``
-                 - `tabulate <https://pypi.org/project/tabulate/>`_
+                  * - ``tabulate``
+                    - `tabulate <https://pypi.org/project/tabulate/>`_
 
-               * - ``wandb``
-                 - `Weights & Biases <https://github.com/wandb/wandb>`_
+                  * - ``wandb``
+                    - `Weights & Biases <https://github.com/wandb/wandb>`_
 
-               * - ``sentencepiece``
-                 - `SentencePiece <https://github.com/google/sentencepiece>`_ 0.2.0
+                  * - ``sentencepiece``
+                    - `SentencePiece <https://github.com/google/sentencepiece>`_ 0.2.0
 
-               * - ``tensorboard``
-                 - `TensorBoard <https://www.tensorflow.org/tensorboard>`_ 2.18.0
+                  * - ``tensorboard``
+                    - `TensorBoard <https://www.tensorflow.org/tensorboard>`_ 2.18.0
 
-         .. container:: model-doc pyt_train_flux
+            .. container:: model-doc pyt_train_flux
 
-            ``pytorch_benchmark_setup.sh`` installs the following libraries for FLUX:
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for FLUX:
 
-            .. list-table::
-               :header-rows: 1
+               .. list-table::
+                  :header-rows: 1
 
-               * - Library
-                 - Reference
+                  * - Library
+                    - Reference
 
-               * - ``accelerate``
-                 - `Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_
+                  * - ``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
+                  * - ``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
+                  * - ``sentencepiece``
+                    - `SentencePiece <https://github.com/google/sentencepiece>`_ 0.2.0
 
-               * - ``tensorboard``
-                 - `TensorBoard <https://www.tensorflow.org/tensorboard>`_ 2.18.0
+                  * - ``tensorboard``
+                    - `TensorBoard <https://www.tensorflow.org/tensorboard>`_ 2.18.0
 
-               * - ``csvkit``
-                 - `csvkit <https://csvkit.readthedocs.io/en/latest/>`_ 2.0.1
+                  * - ``csvkit``
+                    - `csvkit <https://csvkit.readthedocs.io/en/latest/>`_ 2.0.1
 
-               * - ``deepspeed``
-                 - `DeepSpeed <https://github.com/deepspeedai/DeepSpeed>`_ 0.16.2
+                  * - ``deepspeed``
+                    - `DeepSpeed <https://github.com/deepspeedai/DeepSpeed>`_ 0.16.2
 
-               * - ``diffusers``
-                 - `Hugging Face Diffusers <https://huggingface.co/docs/diffusers/en/index>`_ 0.31.0
+                  * - ``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
+                  * - ``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
+                  * - ``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
+                  * - ``peft``
+                    - `PEFT <https://huggingface.co/docs/peft/en/index>`_ 0.14.0
 
-               * - ``protobuf``
-                 - `Protocol Buffers <https://github.com/protocolbuffers/protobuf>`_ 5.29.2
+                  * - ``protobuf``
+                    - `Protocol Buffers <https://github.com/protocolbuffers/protobuf>`_ 5.29.2
 
-               * - ``pytest``
-                 - `PyTest <https://docs.pytest.org/en/stable/>`_ 8.3.4
+                  * - ``pytest``
+                    - `PyTest <https://docs.pytest.org/en/stable/>`_ 8.3.4
 
-               * - ``python-dotenv``
-                 - `python-dotenv <https://pypi.org/project/python-dotenv/>`_ 1.0.1
+                  * - ``python-dotenv``
+                    - `python-dotenv <https://pypi.org/project/python-dotenv/>`_ 1.0.1
 
-               * - ``seaborn``
-                 - `Seaborn <https://seaborn.pydata.org/>`_ 0.13.2
+                  * - ``seaborn``
+                    - `Seaborn <https://seaborn.pydata.org/>`_ 0.13.2
 
-               * - ``transformers``
-                 - `Transformers <https://huggingface.co/docs/transformers/en/index>`_ 4.47.0
+                  * - ``transformers``
+                    - `Transformers <https://huggingface.co/docs/transformers/en/index>`_ 4.47.0
 
-         ``pytorch_benchmark_setup.sh`` downloads the following datasets from Hugging Face:
+            ``pytorch_benchmark_setup.sh`` downloads the following datasets from Hugging Face:
 
-         * `bghira/pseudo-camera-10k <https://huggingface.co/datasets/bghira/pseudo-camera-10k>`_
+            * `bghira/pseudo-camera-10k <https://huggingface.co/datasets/bghira/pseudo-camera-10k>`_
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
-         {% if model_group.tag == "pre-training" and model.mad_tag in ["pyt_train_llama-3.1-8b", "pyt_train_llama-3.1-70b", "pyt_train_flux"] %}
+         {% 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:: Pretraining
+            .. 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 pretrain -m {{ model.model_repo }} -p $datatype -s $sequence_length
-
-            .. list-table::
-               :header-rows: 1
-
-               * - Name
-                 - Options
-                 - Description
-
-            {% if model.mad_tag == "pyt_train_llama-3.1-8b" %}
-               * - ``$datatype``
-                 - ``BF16`` or ``FP8``
-                 - Only Llama 3.1 8B supports FP8 precision.
-            {% else %}
-               * - ``$datatype``
-                 - ``BF16``
-                 - Only Llama 3.1 8B supports FP8 precision.
-            {% endif %}
-
-               * - ``$sequence_length``
-                 - Sequence length for the language model.
-                 - Between 2048 and 8192. 8192 by default.
+               ./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 the previous version of the ``pytorch-training`` Docker: :doc:`previous-versions/pytorch-training-v25.6`
+
                   Occasionally, downloading the Flux dataset might fail. In the event of this
                   error, manually download it from Hugging Face at
                   `black-forest-labs/FLUX.1-dev <https://huggingface.co/black-forest-labs/FLUX.1-dev>`_
                   and save it to `/workspace/FluxBenchmark`. This ensures that the test script can access
                   the required dataset.
             {% endif %}
-         {% endif %}
-
-         {% if model_group.tag == "fine-tuning" %}
-         .. 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.
-
-            .. code-block:: shell
-
-               ./pytorch_benchmark_report.sh -t $training_mode -m {{ model.model_repo }} -p BF16 -s $sequence_length
 
             .. list-table::
                :header-rows: 1
@@ -383,53 +404,143 @@ The following models are pre-optimized for performance on the AMD Instinct MI325
                  - Options
                  - Description
 
-               * - ``$training_mode``
-                 - ``finetune_fw``
-                 - Full weight fine-tuning (BF16 supported)
-
-               * -
-                 - ``finetune_lora``
-                 - LoRA fine-tuning (BF16 supported)
-
-               * -
-                 - ``finetune_qlora``
-                 - QLoRA fine-tuning (BF16 supported)
-
-               * -
-                 - ``HF_finetune_lora``
-                 - LoRA fine-tuning with Hugging Face PEFT
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
 
                * - ``$datatype``
-                 - ``BF16``
-                 - All models support BF16.
+                 - ``BF16``{% if model.mad_tag == "pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$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::
 
-               {{ model.model }} currently supports the following fine-tuning methods:
+               For LoRA and QLoRA support with vision models (Llama 3.2 11B and 90B),
+               use the following torchtune commit for compatibility:
 
-            {% for method in model.training_modes %}
-               * ``{{ method }}``
-            {% endfor %}
-            {% if model.training_modes|length < 4 %}
+               .. 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.
 
-               The upstream `torchtune <https://github.com/pytorch/torchtune>`_ repository
-               does not currently provide YAML configuration files for other combinations of
-               model to fine-tuning method
-               However, you can still configure your own YAML files to enable support for
-               fine-tuning methods not listed here by following existing patterns in the
-               ``/workspace/torchtune/recipes/configs`` directory.
             {% endif %}
          {% endif %}
       {% endfor %}
    {% endfor %}
 
-               .. rubric:: Benchmarking examples
+            .. rubric:: Benchmarking examples
 
-               For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.
+            For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.
+
+Multi-node training
+-------------------
+
+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
 ===============

docs/sphinx/_toc.yml.in

@@ -32,19 +32,23 @@ subtrees:
       - file: compatibility/ml-compatibility/pytorch-compatibility.rst
         title: PyTorch compatibility
       - file: compatibility/ml-compatibility/tensorflow-compatibility.rst
-        title: TensorFlow compatibility  
+        title: TensorFlow compatibility
       - file: compatibility/ml-compatibility/jax-compatibility.rst
         title: JAX compatibility
       - file: compatibility/ml-compatibility/verl-compatibility.rst
-        title: verl compatibility  
+        title: verl compatibility
       - file: compatibility/ml-compatibility/stanford-megatron-lm-compatibility.rst
         title: Stanford Megatron-LM compatibility
       - file: compatibility/ml-compatibility/dgl-compatibility.rst
-        title: DGL compatibility  
+        title: DGL compatibility
       - file: compatibility/ml-compatibility/megablocks-compatibility.rst
         title: Megablocks compatibility
       - file: compatibility/ml-compatibility/taichi-compatibility.rst
-        title: Taichi compatibility 
+        title: Taichi compatibility
+      - file: compatibility/ml-compatibility/ray-compatibility.rst
+        title: Ray compatibility
+      - file: compatibility/ml-compatibility/llama-cpp-compatibility.rst
+        title: llama.cpp compatibility
   - file: how-to/build-rocm.rst
     title: Build ROCm from source
 

tools/rocm-build/default.xml

@@ -0,0 +1,79 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest>
+    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
+    <default revision="refs/tags/20250912-42"
+     remote="rocm-org"
+     sync-c="true"
+     sync-j="4" />
+<!--list of projects for ROCm-->
+    <project name="aqlprofile" />
+    <project name="ROCR-Runtime" />
+    <project name="amdsmi" />
+    <project name="rdc" />
+    <project name="rocm_bandwidth_test" />
+    <project name="rocm_smi_lib" />
+    <project name="rocm-core" />
+    <project name="rocm-examples" />
+    <project name="rocminfo" />
+    <project name="rocprofiler" />
+    <project name="rocprofiler-register" />
+    <project name="rocprofiler-sdk" />
+    <project name="rocprofiler-compute" />
+    <project name="rocprofiler-systems" />
+    <project name="roctracer" />
+<!--HIP Projects-->
+    <project name="HIP" />
+    <project name="hip-tests" />
+    <project name="HIPIFY" />
+    <project name="clr" />
+    <project name="hipother" />
+<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
+    <project name="half" />
+    <project name="llvm-project" />
+    <project name="spirv-llvm-translator" />
+<!-- gdb projects -->
+    <project name="ROCdbgapi" />
+    <project name="ROCgdb" />
+    <project name="rocr_debug_agent" />
+<!-- ROCm Libraries -->
+    <project groups="mathlibs" name="AMDMIGraphX" />
+    <project groups="mathlibs" name="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" />
+    <project groups="mathlibs" name="rocAL" />
+    <project groups="mathlibs" name="rocALUTION" />
+    <project groups="mathlibs" name="rocDecode" />
+    <project groups="mathlibs" name="rocJPEG" />
+    <project groups="mathlibs" name="rocm-libraries">
+        <linkfile src="projects/hipcub" dest="hipCUB"/>
+        <linkfile src="projects/rocprim" dest="rocPRIM"/>
+        <linkfile src="projects/hiprand" dest="hipRAND"/>
+        <linkfile src="projects/rocrand" dest="rocRAND"/>
+        <linkfile src="projects/rocthrust" dest="rocThrust"/>
+        <linkfile src="projects/hipblas-common" dest="hipBLAS-common"/>
+        <linkfile src="projects/hipblaslt" dest="hipBLASLt"/>
+        <linkfile src="projects/rocblas" dest="rocBLAS"/>
+        <linkfile src="projects/hipsparselt" dest="hipSPARSELt"/>
+        <linkfile src="projects/rocsparse" dest="rocSPARSE"/>
+        <linkfile src="projects/hipsparse" dest="hipSPARSE"/>
+        <linkfile src="projects/hipblas" dest="hipBLAS"/>
+        <linkfile src="projects/miopen" dest="MIOpen"/>
+        <linkfile src="projects/hipfft" dest="hipFFT"/>
+        <linkfile src="projects/rocfft" dest="rocFFT"/>
+    </project>
+    <project groups="mathlibs" name="rocPyDecode" />
+    <project groups="mathlibs" name="rocSHMEM" />
+    <project groups="mathlibs" name="rocSOLVER" />
+    <project groups="mathlibs" name="rocWMMA" />
+    <project groups="mathlibs" name="rocm-cmake" />
+    <project groups="mathlibs" name="rpp" />
+    <project groups="mathlibs" name="TransferBench" />
+<!-- Projects for OpenMP-Extras -->
+    <project name="aomp" path="openmp-extras/aomp" />
+    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
+    <project name="flang" path="openmp-extras/flang" />
+</manifest>