Use intersphinx links for deep learning (#5859 )

* Use intersphinx links for deep learning * Update deep-learning-rocm.rst remove Taichi * Update deep-learning-rocm.rst Change Install link to "link" * Apply suggestion from @randyh62 OK
Add missing APU entries to GPU hardware specifications (#646 ) (#5862 ) (#5863 )
2026-01-22 21:18:02 -05:00 · 2026-01-20 09:17:37 -08:00 · 2026-01-16 13:02:06 -05:00 · 2026-01-15 11:34:02 -05:00 · 2026-01-14 11:26:11 -05:00 · 2026-01-08 12:29:00 -05:00
29 changed files with 1222 additions and 832 deletions
--- a/.azuredevops/components/HIP.yml
+++ b/.azuredevops/components/HIP.yml
@@ -34,7 +34,6 @@ parameters:
  default:
    - cmake
    - libnuma-dev
-    - libsimde-dev
    - mesa-common-dev
    - ninja-build
    - ocl-icd-libopencl1
--- a/.azuredevops/components/origami.yml
+++ b/.azuredevops/components/origami.yml
@@ -39,7 +39,6 @@ parameters:
    - python3
    - python3-dev
    - python3-pip
-    - python3-venv
    - libgtest-dev
    - libboost-filesystem-dev
    - libboost-program-options-dev
@@ -47,8 +46,6 @@ parameters:
  type: object
  default:
    - nanobind>=2.0.0
-    - pytest
-    - pytest-cov
 - name: rocmDependencies
  type: object
  default:
@@ -75,10 +72,8 @@ parameters:
      - { os: ubuntu2204, packageManager: apt }
      - { os: almalinux8, packageManager: dnf }
    testJobs:
+      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
-      # - { os: ubuntu2204, packageManager: apt, target: gfx1151 }
-      # - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
 - name: downstreamComponentMatrix
  type: object
  default:
@@ -121,11 +116,6 @@ jobs:
      parameters:
        dependencyList:
          - gtest
-    - ${{ if ne(job.os, 'almalinux8') }}:
-      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
-        parameters:
-          dependencyList:
-            - catch2
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
@@ -147,7 +137,6 @@ jobs:
          -DORIGAMI_BUILD_SHARED_LIBS=ON
          -DORIGAMI_ENABLE_PYTHON=ON
          -DORIGAMI_BUILD_TESTING=ON
-          -DORIGAMI_ENABLE_FETCH=ON
          -GNinja
    - ${{ if ne(job.os, 'almalinux8') }}:
      - task: PublishPipelineArtifact@1
@@ -180,6 +169,7 @@ jobs:
      dependsOn: origami_build_${{ job.os }}
      condition:
        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
          eq(${{ parameters.aggregatePipeline }}, False)
        )
@@ -190,30 +180,30 @@ jobs:
      workspace:
        clean: all
      steps:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
        parameters:
          aptPackages: ${{ parameters.aptPackages }}
          pipModules: ${{ parameters.pipModules }}
          packageManager: ${{ job.packageManager }}
-      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-        parameters:
-          checkoutRepo: ${{ parameters.checkoutRepo }}
-          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
-      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
-        parameters:
-          dependencyList:
-            - gtest
-      - ${{ if ne(job.os, 'almalinux8') }}:
-        - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
-          parameters:
-            dependencyList:
-              - catch2
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
        parameters:
          preTargetFilter: ${{ parameters.componentName }}
          os: ${{ job.os }}
+      - task: DownloadPipelineArtifact@2
+        displayName: 'Download Build Directory Artifact'
+        inputs:
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
+          path: '$(Agent.BuildDirectory)/s/build'
+      - task: DownloadPipelineArtifact@2
+        displayName: 'Download Python Source Artifact'
+        inputs:
+          artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
+          path: '$(Agent.BuildDirectory)/s/python'
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
        parameters:
          checkoutRef: ${{ parameters.checkoutRef }}
@@ -222,72 +212,25 @@ jobs:
          gpuTarget: ${{ job.target }}
          ${{ if parameters.triggerDownstreamJobs }}:
            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
-      - task: CMake@1
-        displayName: 'Origami Test CMake Configuration'
-        inputs:
-          cmakeArgs: >-
-            -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
-            -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-            -DORIGAMI_BUILD_SHARED_LIBS=ON
-            -DORIGAMI_ENABLE_PYTHON=ON
-            -DORIGAMI_BUILD_TESTING=ON
-            -GNinja
-            $(Agent.BuildDirectory)/s
-      - task: Bash@3
-        displayName: 'Build Origami Tests and Python Bindings'
-        inputs:
-          targetType: inline
-          workingDirectory: build
-          script: |
-            cmake --build . --target origami-tests origami_python -- -j$(nproc)
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-      # Run tests using CTest (discovers and runs both C++ and Python tests)
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
        parameters:
          componentName: ${{ parameters.componentName }}
          os: ${{ job.os }}
-          testDir: 'build'
-          testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml'
-      # Test pip install workflow
-      # - task: Bash@3
-      #   displayName: 'Test Pip Install'
-      #   inputs:
-      #     targetType: inline
-      #     script: |
-      #       set -e
-            
-      #       echo "==================================================================="
-      #       echo "Testing pip install workflow (pip install -e .)"
-      #       echo "==================================================================="
-            
-      #       # Set environment variables for pip install CMake build
-      #       export ROCM_PATH=$(Agent.BuildDirectory)/rocm
-      #       export CMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm:$(Agent.BuildDirectory)/vendor
-      #       export CMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
-            
-      #       echo "ROCM_PATH: $ROCM_PATH"
-      #       echo "CMAKE_PREFIX_PATH: $CMAKE_PREFIX_PATH"
-      #       echo "CMAKE_CXX_COMPILER: $CMAKE_CXX_COMPILER"
-      #       echo ""
-            
-      #       # Install from source directory
-      #       cd "$(Agent.BuildDirectory)/s/python"
-      #       pip install -e .
-            
-      #       # Verify import works
-      #       echo ""
-      #       echo "Verifying origami can be imported..."
-      #       python3 -c "import origami; print('✓ Successfully imported origami')"
-            
-      #       # Run pytest on installed package
-      #       echo ""
-      #       echo "Running pytest tests..."
-      #       python3 -m pytest tests/ -v -m "not slow" --tb=short
-            
-      #       echo ""
-      #       echo "==================================================================="
-      #       echo "Pip install test completed successfully"
-      #       echo "==================================================================="
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './origami-tests'
+          testParameters: '--yaml origami-tests.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - script: |
+          set -e
+          export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH
+
+          echo "--- Running origami_test.py ---"
+          python3 $(Agent.BuildDirectory)/s/python/origami_test.py
+          
+          echo "--- Running origami_grid_test.py ---"
+          python3 $(Agent.BuildDirectory)/s/python/origami_grid_test.py
+        displayName: 'Run Python Binding Tests'
+        condition: succeeded()
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
        parameters:
          aptPackages: ${{ parameters.aptPackages }}
--- a/.azuredevops/components/rocm-examples.yml
+++ b/.azuredevops/components/rocm-examples.yml
@@ -30,7 +30,6 @@ parameters:
    - python3-pip
    - protobuf-compiler
    - libprotoc-dev
-    - libopencv-dev
 - name: pipModules
  type: object
  default:
@@ -65,7 +64,6 @@ parameters:
    - MIVisionX
    - rocm_smi_lib
    - rccl
-    - rocAL
    - rocALUTION
    - rocBLAS
    - rocDecode
@@ -105,7 +103,6 @@ parameters:
    - MIVisionX
    - rocm_smi_lib
    - rccl
-    - rocAL
    - rocALUTION
    - rocBLAS
    - rocDecode
--- a/.wordlist.txt
+++ b/.wordlist.txt
@@ -36,6 +36,7 @@ Andrej
 Arb
 Autocast
 autograd
+Backported
 BARs
 BatchNorm
 BLAS
@@ -203,9 +204,11 @@ GenAI
 GenZ
 GitHub
 Gitpod
+hardcoded
 HBM
 HCA
 HGX
+HLO
 HIPCC
 hipDataType
 HIPExtension
@@ -333,6 +336,7 @@ MoEs
 Mooncake
 Mpops
 Multicore
+multihost
 Multithreaded
 mx
 MXFP
@@ -1027,6 +1031,7 @@ uncacheable
 uncorrectable
 underoptimized
 unhandled
+unfused
 uninstallation
 unmapped
 unsqueeze
--- a/RELEASE.md
+++ b/RELEASE.md
@@ -270,26 +270,26 @@ The [ROCm examples repository](https://github.com/ROCm/rocm-examples) has been e
 :margin: auto 0 auto auto
 :::{grid}
 :margin: auto 0 auto auto
-* [hipBLASLt](https://rocm.docs.amd.com/projects/hipBLASLt/en/latest/)
-* [hipSPARSE](https://rocm.docs.amd.com/projects/hipSPARSE/en/latest/)
-* [hipSPARSELt](https://rocm.docs.amd.com/projects/hipSPARSELt/en/latest/)
-* [hipTensor](https://rocm.docs.amd.com/projects/hipTensor/en/latest/)
+* [hipBLASLt](https://github.com/ROCm/rocm-examples/tree/amd-staging/Libraries/hipBLASLt)
+* [hipSPARSE](https://github.com/ROCm/rocm-examples/tree/amd-staging/Libraries/hipSPARSE)
+* [hipSPARSELt](https://github.com/ROCm/rocm-examples/tree/amd-staging/Libraries/hipSPARSELt)
+* [hipTensor](https://github.com/ROCm/rocm-examples/tree/amd-staging/Libraries/hipTensor)
 :::
 :::{grid}
 :margin: auto 0 auto auto
-* [rocALUTION](https://rocm.docs.amd.com/projects/rocALUTION/en/latest/)
-* [ROCprofiler-SDK](https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/latest/)
-* [rocWMMA](https://rocm.docs.amd.com/projects/rocWMMA/en/latest/)
+* [rocALUTION](https://github.com/ROCm/rocm-examples/tree/amd-staging/Libraries/rocALUTION)
+* [ROCprofiler-SDK](https://github.com/ROCm/rocm-examples/tree/amd-staging/Libraries/rocProfiler-SDK)
+* [rocWMMA](https://github.com/ROCm/rocm-examples/tree/amd-staging/Libraries/rocWMMA)
 :::
 ::::

 Usage examples are now available for the following performance analysis tools:

-* [ROCm Compute Profiler](https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/index.html)
-* [ROCm Systems Profiler](https://rocm.docs.amd.com/projects/rocprofiler-systems/en/latest/index.html)
-* [rocprofv3](https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/latest/how-to/using-rocprofv3.html)
+* [ROCm Compute Profiler](https://github.com/ROCm/rocm-examples/tree/amd-staging/Tools/rocprof-compute)
+* [ROCm Systems Profiler](https://github.com/ROCm/rocm-examples/tree/amd-staging/Tools/rocprof-systems)
+* [rocprofv3](https://github.com/ROCm/rocm-examples/tree/amd-staging/Tools/rocprofv3)

-The complete source code for the [HIP Graph Tutorial](https://rocm.docs.amd.com/projects/HIP/en/latest/tutorial/graph_api.html) is also available as part of the ROCm examples.
+The complete source code for the [HIP Graph Tutorial](https://github.com/ROCm/rocm-examples/tree/amd-staging/HIP-Doc/Tutorials/graph_api) is also available as part of the ROCm examples.

 ### ROCm documentation updates

--- a/docs/compatibility/compatibility-matrix-historical-6.0.csv
+++ b/docs/compatibility/compatibility-matrix-historical-6.0.csv
@@ -37,7 +37,7 @@ ROCm Version,7.1.1,7.1.0,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6
      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat-past-60]_,N/A,N/A,N/A,2.4.0,2.4.0,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,2.48.0.post0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,N/A,2.51.1,N/A,N/A,2.48.0.post0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat-past-60]_,N/A,N/A,N/A,b6652,b6356,b6356,b6356,b5997,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
      :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>` [#flashinfer_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,v0.2.5,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.1,1.22.0,1.22.0,1.22.0,1.20.0,1.20.0,1.20.0,1.20.0,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
--- a/docs/compatibility/compatibility-matrix.rst
+++ b/docs/compatibility/compatibility-matrix.rst
@@ -157,8 +157,8 @@ compatibility and system requirements.

 .. [#os-compatibility] Some operating systems are supported on limited GPUs. For detailed information, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-operating-systems>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-operating-systems>`__.
 .. [#gpu-compatibility] Some GPUs have limited operating system support. For detailed information, see the latest :ref:`supported_GPUs`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-gpus>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-gpus>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-gpus>`__.
-.. [#dgl_compat] DGL is supported only on ROCm 7.0.0, ROCm 6.4.3 and ROCm 6.4.0.
-.. [#llama-cpp_compat] llama.cpp is supported only on ROCm 7.0.0 and ROCm 6.4.x.
+.. [#dgl_compat] DGL is only supported on ROCm 7.0.0, ROCm 6.4.3 and ROCm 6.4.0.
+.. [#llama-cpp_compat] llama.cpp is only supported on ROCm 7.0.0 and ROCm 6.4.x.
 .. [#mi325x_KVM] For AMD Instinct MI325X KVM SR-IOV users, do not use AMD GPU Driver (amdgpu) 30.20.0.
 .. [#driver_patch] AMD GPU Driver (amdgpu) 30.10.1 is a quality release that resolves an issue identified in the 30.10 release. There are no other significant changes or feature additions in ROCm 7.0.1 from ROCm 7.0.0. AMD GPU Driver (amdgpu) 30.10.1 is compatible with ROCm 7.0.1 and ROCm 7.0.0.
 .. [#kfd_support] As of ROCm 6.4.0, forward and backward compatibility between the AMD GPU Driver (amdgpu) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and AMD GPU Driver support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
@@ -204,13 +204,13 @@ Expand for full historical view of:
   .. [#os-compatibility-past-60] Some operating systems are supported on limited GPUs. For detailed information, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-operating-systems>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-operating-systems>`__.
   .. [#gpu-compatibility-past-60] Some GPUs have limited operating system support. For detailed information, see the latest :ref:`supported_GPUs`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-gpus>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-gpus>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-gpus>`__.
   .. [#tf-mi350-past-60] TensorFlow 2.17.1 is not supported on AMD Instinct MI350 Series GPUs. Use TensorFlow 2.19.1 or 2.18.1 with MI350 Series GPUs instead.
-   .. [#verl_compat-past-60] verl is supported only on ROCm 7.0.0 and 6.2.0.
-   .. [#stanford-megatron-lm_compat-past-60] Stanford Megatron-LM is supported only on ROCm 6.3.0.
-   .. [#dgl_compat-past-60] DGL is supported only on ROCm 7.0.0, ROCm 6.4.3 and ROCm 6.4.0.
-   .. [#megablocks_compat-past-60] Megablocks is supported only on ROCm 6.3.0.
-   .. [#ray_compat-past-60] Ray is supported only on ROCm 6.4.1.
-   .. [#llama-cpp_compat-past-60] llama.cpp is supported only on ROCm 7.0.0 and 6.4.x.
-   .. [#flashinfer_compat-past-60] FlashInfer is supported only on ROCm 6.4.1.
+   .. [#verl_compat-past-60] verl is only supported on ROCm 7.0.0 and 6.2.0.
+   .. [#stanford-megatron-lm_compat-past-60] Stanford Megatron-LM is only supported on ROCm 6.3.0.
+   .. [#dgl_compat-past-60] DGL is only supported on ROCm 7.0.0, ROCm 6.4.3 and ROCm 6.4.0.
+   .. [#megablocks_compat-past-60] Megablocks is only supported on ROCm 6.3.0.
+   .. [#ray_compat-past-60] Ray is only supported on ROCm 7.0.0 and 6.4.1.
+   .. [#llama-cpp_compat-past-60] llama.cpp is only supported on ROCm 7.0.0 and 6.4.x.
+   .. [#flashinfer_compat-past-60] FlashInfer is only supported on ROCm 6.4.1.
   .. [#mi325x_KVM-past-60] For AMD Instinct MI325X KVM SR-IOV users, do not use AMD GPU Driver (amdgpu) 30.20.0.
   .. [#driver_patch-past-60] AMD GPU Driver (amdgpu) 30.10.1 is a quality release that resolves an issue identified in the 30.10 release. There are no other significant changes or feature additions in ROCm 7.0.1 from ROCm 7.0.0. AMD GPU Driver (amdgpu) 30.10.1 is compatible with ROCm 7.0.1 and ROCm 7.0.0.
   .. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD GPU Driver (amdgpu) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and AMD GPU Driver support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
--- a/docs/compatibility/ml-compatibility/dgl-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/dgl-compatibility.rst
@@ -36,63 +36,9 @@ Support overview
  - You can also consult the upstream `Installation guide <https://www.dgl.ai/pages/start.html>`__ 
    for additional context.

-Version support
--------------------------------------------------------------------------------
-
-DGL is supported on `ROCm 7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__, 
-`ROCm 6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__, and `ROCm 6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__.
-
-Supported devices
--------------------------------------------------------------------------------
-
-**Officially Supported**: AMD Instinct™ MI300X, MI250X
-
-.. _dgl-recommendations:
-
-Use cases and recommendations
-================================================================================
-
-DGL can be used for Graph Learning, and building popular graph models like  
-GAT, GCN, and GraphSage. Using these models, a variety of use cases are supported:
-
- Recommender systems
- Network Optimization and Analysis
- 1D (Temporal) and 2D (Image) Classification
- Drug Discovery
-
-For use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
-where you can search for DGL examples and best practices to optimize your workloads on AMD GPUs.
-
-* Although multiple use cases of DGL have been tested and verified, a few have been  
-  outlined in the `DGL in the Real World: Running GNNs on Real Use Cases 
-  <https://rocm.blogs.amd.com/artificial-intelligence/dgl_blog2/README.html>`__ blog 
-  post, which walks through four real-world graph neural network (GNN) workloads 
-  implemented with the Deep Graph Library on ROCm. It covers tasks ranging from 
-  heterogeneous e-commerce graphs and multiplex networks (GATNE) to molecular graph 
-  regression (GNN-FiLM) and EEG-based neurological diagnosis (EEG-GCNN). For each use 
-  case, the authors detail: the dataset and task, how DGL is used, and their experience 
-  porting to ROCm. It is shown that DGL codebases often run without modification, with 
-  seamless integration of graph operations, message passing, sampling, and convolution. 
-
-* The `Graph Neural Networks (GNNs) at Scale: DGL with ROCm on AMD Hardware 
-  <https://rocm.blogs.amd.com/artificial-intelligence/why-graph-neural/README.html>`__ 
-  blog post introduces the Deep Graph Library (DGL) and its enablement on the AMD ROCm platform, 
-  bringing high-performance graph neural network (GNN) training to AMD GPUs. DGL bridges 
-  the gap between dense tensor frameworks and the irregular nature of graph data through a 
-  graph-first, message-passing abstraction. Its design ensures scalability, flexibility, and 
-  interoperability across frameworks like PyTorch and TensorFlow. AMD’s ROCm integration 
-  enables DGL to run efficiently on HIP-based GPUs, supported by prebuilt Docker containers 
-  and open-source repositories. This marks a major step in AMD's mission to advance open, 
-  scalable AI ecosystems beyond traditional architectures.
-
-You can pre-process datasets and begin training on AMD GPUs through:
-
-* Single-GPU training/inference
-* Multi-GPU training
-
 .. _dgl-docker-compat:

-Docker image compatibility
+Compatibility matrix
 ================================================================================

 .. |docker-icon| raw:: html
@@ -114,6 +60,7 @@ Click the |docker-icon| to view the image on Docker Hub.
      - PyTorch
      - Ubuntu
      - Python
+      - GPU

    * - .. raw:: html

@@ -124,6 +71,7 @@ Click the |docker-icon| to view the image on Docker Hub.
      - `2.8.0 <https://github.com/pytorch/pytorch/releases/tag/v2.8.0>`__
      - 24.04
      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X

    * - .. raw:: html

@@ -134,6 +82,7 @@ Click the |docker-icon| to view the image on Docker Hub.
      - `2.6.0 <https://github.com/pytorch/pytorch/releases/tag/v2.6.0>`__
      - 24.04
      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X

    * - .. raw:: html

@@ -144,6 +93,7 @@ Click the |docker-icon| to view the image on Docker Hub.
      - `2.7.1 <https://github.com/pytorch/pytorch/releases/tag/v2.7.1>`__
      - 22.04
      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`__
+      - MI300X, MI250X

    * - .. raw:: html

@@ -154,6 +104,7 @@ Click the |docker-icon| to view the image on Docker Hub.
      - `2.6.0 <https://github.com/pytorch/pytorch/releases/tag/v2.6.0>`__
      - 24.04
      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X

    * - .. raw:: html

@@ -164,6 +115,7 @@ Click the |docker-icon| to view the image on Docker Hub.
      - `2.6.0 <https://github.com/pytorch/pytorch/releases/tag/v2.6.0>`__
      - 24.04
      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X, MI250X

    * - .. raw:: html

@@ -174,7 +126,7 @@ Click the |docker-icon| to view the image on Docker Hub.
      - `2.4.1 <https://github.com/pytorch/pytorch/releases/tag/v2.4.1>`__
      - 24.04
      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`__
-
+      - MI300X, MI250X

    * - .. raw:: html

@@ -185,7 +137,7 @@ Click the |docker-icon| to view the image on Docker Hub.
      - `2.4.1 <https://github.com/pytorch/pytorch/releases/tag/v2.4.1>`__
      - 22.04
      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`__
-
+      - MI300X, MI250X

    * - .. raw:: html

@@ -196,7 +148,10 @@ Click the |docker-icon| to view the image on Docker Hub.
      - `2.3.0 <https://github.com/pytorch/pytorch/releases/tag/v2.3.0>`__
      - 22.04
      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`__
-      
+      - MI300X, MI250X
+
+
+.. _dgl-key-rocm-libraries:

 Key ROCm libraries for DGL
 ================================================================================
@@ -310,8 +265,9 @@ If you prefer to build it yourself, ensure the following dependencies are instal
        multiplication (GEMM) and accumulation operations with mixed precision
        support.

+.. _dgl-supported-features-latest:

-Supported features
+Supported features with ROCm 7.0.0
 ================================================================================

 Many functions and methods available upstream are also supported in DGL on ROCm.
@@ -335,14 +291,17 @@ Instead of listing them all, support is grouped into the following categories to
 * DGL Sparse
 * GraphBolt

-Unsupported features
+.. _dgl-unsupported-features-latest:
+
+Unsupported features with ROCm 7.0.0
 ================================================================================

 * TF32 Support (only supported for PyTorch 2.7 and above)
 * Kineto/ROCTracer integration

+.. _dgl-unsupported-functions:

-Unsupported functions
+Unsupported functions with ROCm 7.0.0
 ================================================================================

 * ``bfs``
@@ -355,6 +314,50 @@ Unsupported functions
 * ``sample_labors_noprob``
 * ``sparse_admin``

+.. _dgl-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+DGL can be used for Graph Learning, and building popular graph models like  
+GAT, GCN, and GraphSage. Using these models, a variety of use cases are supported:
+
+- Recommender systems
+- Network Optimization and Analysis
+- 1D (Temporal) and 2D (Image) Classification
+- Drug Discovery
+
+For use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for DGL examples and best practices to optimize your workloads on AMD GPUs.
+
+* Although multiple use cases of DGL have been tested and verified, a few have been  
+  outlined in the `DGL in the Real World: Running GNNs on Real Use Cases 
+  <https://rocm.blogs.amd.com/artificial-intelligence/dgl_blog2/README.html>`__ blog 
+  post, which walks through four real-world graph neural network (GNN) workloads 
+  implemented with the Deep Graph Library on ROCm. It covers tasks ranging from 
+  heterogeneous e-commerce graphs and multiplex networks (GATNE) to molecular graph 
+  regression (GNN-FiLM) and EEG-based neurological diagnosis (EEG-GCNN). For each use 
+  case, the authors detail: the dataset and task, how DGL is used, and their experience 
+  porting to ROCm. It is shown that DGL codebases often run without modification, with 
+  seamless integration of graph operations, message passing, sampling, and convolution. 
+
+* The `Graph Neural Networks (GNNs) at Scale: DGL with ROCm on AMD Hardware 
+  <https://rocm.blogs.amd.com/artificial-intelligence/why-graph-neural/README.html>`__ 
+  blog post introduces the Deep Graph Library (DGL) and its enablement on the AMD ROCm platform, 
+  bringing high-performance graph neural network (GNN) training to AMD GPUs. DGL bridges 
+  the gap between dense tensor frameworks and the irregular nature of graph data through a 
+  graph-first, message-passing abstraction. Its design ensures scalability, flexibility, and 
+  interoperability across frameworks like PyTorch and TensorFlow. AMD’s ROCm integration 
+  enables DGL to run efficiently on HIP-based GPUs, supported by prebuilt Docker containers 
+  and open-source repositories. This marks a major step in AMD's mission to advance open, 
+  scalable AI ecosystems beyond traditional architectures.
+
+You can pre-process datasets and begin training on AMD GPUs through:
+
+* Single-GPU training/inference
+* Multi-GPU training
+
+
 Previous versions
 ===============================================================================
 See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/dgl-history` to find documentation for previous releases
--- a/docs/compatibility/ml-compatibility/flashinfer-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/flashinfer-compatibility.rst
@@ -42,38 +42,9 @@ Support overview
  - You can also consult the upstream `Installation guide <https://docs.flashinfer.ai/installation.html>`__ 
    for additional context.

-Version support
--------------------------------------------------------------------------------
-
-FlashInfer is supported on `ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__.
-
-Supported devices
--------------------------------------------------------------------------------
-
-**Officially Supported**: AMD Instinct™ MI300X
-
-
-.. _flashinfer-recommendations:
-
-Use cases and recommendations
-================================================================================
-
-This release of FlashInfer on ROCm provides the decode functionality for LLM inferencing.
-In the decode phase, tokens are generated sequentially, with the model predicting each new 
-token based on the previously generated tokens and the input context.
-
-FlashInfer on ROCm brings over upstream features such as load balancing, sparse and dense 
-attention optimizations, and batching support, enabling efficient execution on AMD Instinct™ MI300X GPUs.
-
-Because large LLMs often require substantial KV caches or long context windows, FlashInfer on ROCm 
-also implements cascade attention from upstream to reduce memory usage. 
-
-For currently supported use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
-where you can search for examples and best practices to optimize your workloads on AMD GPUs.
-
 .. _flashinfer-docker-compat:

-Docker image compatibility
+Compatibility matrix
 ================================================================================

 .. |docker-icon| raw:: html
@@ -95,6 +66,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - PyTorch
      - Ubuntu
      - Python
+      - GPU

    * - .. raw:: html

@@ -104,5 +76,23 @@ Click |docker-icon| to view the image on Docker Hub.
      - `2.7.1 <https://github.com/ROCm/pytorch/releases/tag/v2.7.1>`__
      - 24.04
      - `3.12 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X

+.. _flashinfer-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+The release of FlashInfer on ROCm provides the decode functionality for LLM inferencing.
+In the decode phase, tokens are generated sequentially, with the model predicting each new 
+token based on the previously generated tokens and the input context.
+
+FlashInfer on ROCm brings over upstream features such as load balancing, sparse and dense 
+attention optimizations, and batching support, enabling efficient execution on AMD Instinct™ MI300X GPUs.
+
+Because large LLMs often require substantial KV caches or long context windows, FlashInfer on ROCm 
+also implements cascade attention from upstream to reduce memory usage. 
+
+For currently supported use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for examples and best practices to optimize your workloads on AMD GPUs.

--- a/docs/compatibility/ml-compatibility/jax-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/jax-compatibility.rst
@@ -269,6 +269,33 @@ For a complete and up-to-date list of JAX public modules (for example, ``jax.num
  JAX API modules are maintained by the JAX project and is subject to change.
  Refer to the official Jax documentation for the most up-to-date information.

+Key features and enhancements for ROCm 7.1
+===============================================================================
+
+- Enabled compilation of multihost HLO runner Python bindings.
+
+  - Backported multihost HLO runner bindings and some related changes to
+    :code:`FunctionalHloRunner`.
+
+  - Added :code:`requirements_lock_3_12` to enable building for Python 3.12.
+
+- Removed hardcoded NHWC convolution layout for ``fp16`` precision to address the performance drops for ``fp16`` precision on gfx12xx GPUs.
+
+
+- ROCprofiler-SDK integration:
+
+  - Integrated ROCprofiler-SDK (v3) to XLA to improve profiling of GPU events,
+    support both time-based and step-based profiling.
+
+  - Added unit tests for :code:`rocm_collector` and :code:`rocm_tracer`.
+
+- Added Triton unsupported conversion from ``f8E4M3FNUZ`` to ``fp16`` with
+  rounding mode.
+
+- Introduced :code:`CudnnFusedConvDecomposer` to revert fused convolutions
+  when :code:`ConvAlgorithmPicker` fails to find a fused algorithm, and removed
+  unfused fallback paths from :code:`RocmFusedConvRunner`.
+
 Key features and enhancements for ROCm 7.0
 ===============================================================================

--- a/docs/compatibility/ml-compatibility/llama-cpp-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/llama-cpp-compatibility.rst
@@ -36,47 +36,9 @@ Support overview
  - You can also consult the upstream `Installation guide <https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md>`__ 
    for additional context.

-Version support
--------------------------------------------------------------------------------
-
-llama.cpp is supported on `ROCm 7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__ and 
-`ROCm 6.4.x <https://repo.radeon.com/rocm/apt/6.4/>`__.
-
-Supported devices
--------------------------------------------------------------------------------
-
-**Officially Supported**: AMD Instinct™ MI325X, 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
+Compatibility matrix
 ================================================================================

 .. |docker-icon| raw:: html
@@ -106,6 +68,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - llama.cpp
      - ROCm
      - Ubuntu
+      - GPU

    * - .. raw:: html

@@ -119,6 +82,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b6652 <https://github.com/ROCm/llama.cpp/tree/release/b6652>`__
      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
      - 24.04
+      - MI325X, MI300X, MI210

    * - .. raw:: html

@@ -132,6 +96,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b6652 <https://github.com/ROCm/llama.cpp/tree/release/b6652>`__
      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
      - 22.04
+      - MI325X, MI300X, MI210

    * - .. raw:: html

@@ -145,6 +110,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
      - 24.04
+      - MI325X, MI300X, MI210

    * - .. raw:: html

@@ -158,7 +124,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
      - 22.04
-
+      - MI325X, MI300X, MI210

    * - .. raw:: html

@@ -172,6 +138,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
      - `6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__
      - 24.04
+      - MI325X, MI300X, MI210

    * - .. raw:: html

@@ -185,7 +152,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
      - `6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__
      - 22.04
-
+      - MI325X, MI300X, MI210

    * - .. raw:: html

@@ -199,6 +166,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
      - 24.04
+      - MI325X, MI300X, MI210

    * - .. raw:: html

@@ -212,6 +180,7 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
      - 22.04
+      - MI325X, MI300X, MI210

    * - .. raw:: html

@@ -225,7 +194,9 @@ Click |docker-icon| to view the image on Docker Hub.
      - `b5997 <https://github.com/ROCm/llama.cpp/tree/release/b5997>`__
      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__
      - 24.04
+      - MI300X, MI210

+.. _llama-cpp-key-rocm-libraries:

 Key ROCm libraries for llama.cpp
 ================================================================================
@@ -268,6 +239,36 @@ your corresponding ROCm version.
      - Can be used to enhance the flash attention performance on AMD compute, by enabling
        the flag during compile time.

+.. _llama-cpp-uses-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+llama.cpp can be applied in a variety of scenarios, particularly when you need to meet one or more of the following requirements:
+
+- Plain C/C++ implementation with no external dependencies
+- Support for 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory usage
+- Custom HIP (Heterogeneous-compute Interface for Portability) kernels for running large language models (LLMs) on AMD GPUs (graphics processing units)
+- CPU (central processing unit) + GPU (graphics processing unit) hybrid inference for partially accelerating models larger than the total available VRAM (video random-access memory)
+
+llama.cpp is also used in a range of real-world applications, including:
+
+- Games such as `Lucy's Labyrinth <https://github.com/MorganRO8/Lucys_Labyrinth>`__:
+  A simple maze game where AI-controlled agents attempt to trick the player.
+- Tools such as `Styled Lines <https://marketplace.unity.com/packages/tools/ai-ml-integration/style-text-webgl-ios-stand-alone-llm-llama-cpp-wrapper-292902>`__:
+  A proprietary, asynchronous inference wrapper for Unity3D game development, including pre-built mobile and web platform wrappers and a model example.
+- Various other AI applications use llama.cpp as their inference engine;  
+  for a detailed list, see the `user interfaces (UIs) section <https://github.com/ggml-org/llama.cpp?tab=readme-ov-file#description>`__.
+
+For more use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for llama.cpp examples and best practices to optimize your workloads on AMD GPUs.
+
+- The `Llama.cpp Meets Instinct: A New Era of Open-Source AI Acceleration <https://rocm.blogs.amd.com/ecosystems-and-partners/llama-cpp/README.html>`__ 
+  blog post outlines how the open-source llama.cpp framework enables efficient LLM inference—including interactive inference with ``llama-cli``, 
+  server deployment with ``llama-server``, GGUF model preparation and quantization, performance benchmarking, and optimizations tailored for 
+  AMD Instinct GPUs within the ROCm ecosystem. 
+
+
 Previous versions
 ===============================================================================
 See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/llama-cpp-history` to find documentation for previous releases
--- a/docs/compatibility/ml-compatibility/megablocks-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/megablocks-compatibility.rst
@@ -33,19 +33,44 @@ Support overview
  - You can also consult the upstream `Installation guide <https://github.com/databricks/megablocks>`__ 
    for additional context.

-Version support
--------------------------------------------------------------------------------
+.. _megablocks-docker-compat:

-Megablocks is supported on `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`__.
+Compatibility matrix
+================================================================================

-Supported devices
--------------------------------------------------------------------------------
+.. |docker-icon| raw:: html

- **Officially Supported**: AMD Instinct™ MI300X
- **Partially Supported** (functionality or performance limitations): AMD Instinct™ MI250X, MI210
+   <i class="fab fa-docker"></i>

-Supported models and features
--------------------------------------------------------------------------------
+AMD validates and publishes `Megablocks images <https://hub.docker.com/r/rocm/megablocks/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tag and associated
+inventories represent the latest available Megablocks version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Megablocks
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/megablocks/megablocks-0.7.0_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-372ff89b96599019b8f5f9db469c84add2529b713456781fa62eb9a148659ab4"><i class="fab fa-docker fa-lg"></i> rocm/megablocks</a>
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `0.7.0 <https://github.com/databricks/megablocks/releases/tag/v0.7.0>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - MI300X
+
+Supported models and features with ROCm 6.3.0
+================================================================================

 This section summarizes the Megablocks features supported by ROCm.

@@ -77,38 +102,3 @@ It features how to pre-process datasets and how to begin pre-training on AMD GPU
 * Single-GPU pre-training
 * Multi-GPU pre-training

-.. _megablocks-docker-compat:
-
-Docker image compatibility
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes `Megablocks images <https://hub.docker.com/r/rocm/megablocks/tags>`__
-with ROCm backends on Docker Hub. The following Docker image tag and associated
-inventories represent the latest available Megablocks version from the official Docker Hub. 
-Click |docker-icon| to view the image on Docker Hub.
-
-.. list-table:: 
-    :header-rows: 1
-    :class: docker-image-compatibility
-
-    * - Docker image
-      - ROCm
-      - Megablocks
-      - PyTorch
-      - Ubuntu
-      - Python
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/megablocks/megablocks-0.7.0_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-372ff89b96599019b8f5f9db469c84add2529b713456781fa62eb9a148659ab4"><i class="fab fa-docker fa-lg"></i> rocm/megablocks</a>
-      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
-      - `0.7.0 <https://github.com/databricks/megablocks/releases/tag/v0.7.0>`_
-      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
-      - 24.04
-      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
-
-
--- a/docs/compatibility/ml-compatibility/ray-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/ray-compatibility.rst
@@ -12,8 +12,8 @@ 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 
+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. 
@@ -29,25 +29,57 @@ Support overview
 - To get started and install Ray on ROCm, use the prebuilt :ref:`Docker image <ray-docker-compat>`, 
  which includes ROCm, Ray, and all required dependencies.

-  - 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>`__.
-
-  - See the :doc:`ROCm Ray installation guide <rocm-install-on-linux:install/3rd-party/ray-install>` 
+  - See the :doc:`ROCm Ray installation guide <rocm-install-on-linux:install/3rd-party/ray-install>`
    for installation and setup instructions.

  - You can also consult the upstream `Installation guide <https://docs.ray.io/en/latest/ray-overview/installation.html>`__ 
    for additional context.

-Version support
--------------------------------------------------------------------------------
+.. _ray-docker-compat:

-Ray is supported on `ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__.
+Compatibility matrix
+================================================================================

-Supported devices
--------------------------------------------------------------------------------
+.. |docker-icon| raw:: html

-**Officially Supported**: AMD Instinct™ MI300X, MI210
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `ROCm Ray Docker images <https://hub.docker.com/r/rocm/ray/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and
+associated inventories represent the latest Ray version from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Ray
+      - Pytorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.51.1_rocm7.0.0_ubuntu22.04_py3.12_pytorch2.9.0/images/sha256-a02f6766b4ba406f88fd7e85707ec86c04b569834d869a08043ec9bcbd672168"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - `2.51.1 <https://github.com/ROCm/ray/tree/release/2.51.1>`__
+      - 2.9.0a0+git1c57644
+      - 22.04
+      - `3.12.12 <https://www.python.org/downloads/release/python-31212/>`__
+      - MI300X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.48.0.post0_rocm6.4.1_ubuntu24.04_py3.12_pytorch2.6.0/images/sha256-0d166fe6bdced38338c78eedfb96eff92655fb797da3478a62dd636365133cc0"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - `2.48.0.post0 <https://github.com/ROCm/ray/tree/release/2.48.0.post0>`__
+      - 2.6.0+git684f6f2
+      - 24.04
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - MI300X, MI210

 Use cases and recommendations
 ================================================================================
@@ -76,36 +108,7 @@ topic <https://docs.ray.io/en/latest/ray-core/scheduling/accelerators.html#accel
 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.
-Click the |docker-icon| icon to view the image on Docker Hub.
-
-.. list-table::
-    :header-rows: 1
-    :class: docker-image-compatibility
-
-    * - Docker image
-      - ROCm
-      - 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>
-      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__.
-      - `2.48.0.post0 <https://github.com/ROCm/ray/tree/release/2.48.0.post0>`_
-      - 2.6.0+git684f6f2
-      - 24.04
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/ray-history` to find documentation for previous releases
+of the ``ROCm/ray`` Docker image.
--- a/docs/compatibility/ml-compatibility/stanford-megatron-lm-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/stanford-megatron-lm-compatibility.rst
@@ -35,19 +35,45 @@ Support overview
  - You can also consult the upstream `Installation guide <https://github.com/NVIDIA/Megatron-LM>`__ 
    for additional context.

-Version support
--------------------------------------------------------------------------------
+.. _megatron-lm-docker-compat:

-Stanford Megatron-LM is supported on `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`__.
+Compatibility matrix
+================================================================================

-Supported devices
--------------------------------------------------------------------------------
+.. |docker-icon| raw:: html

- **Officially Supported**: AMD Instinct™ MI300X
- **Partially Supported** (functionality or performance limitations): AMD Instinct™ MI250X, MI210
+   <i class="fab fa-docker"></i>

-Supported models and features
--------------------------------------------------------------------------------
+AMD validates and publishes `Stanford Megatron-LM images <https://hub.docker.com/r/rocm/stanford-megatron-lm/tags>`_
+with ROCm and Pytorch backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest Stanford Megatron-LM version from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Stanford Megatron-LM
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/stanford-megatron-lm/stanford-megatron-lm85f95ae_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-070556f078be10888a1421a2cb4f48c29f28b02bfeddae02588d1f7fc02a96a6"><i class="fab fa-docker fa-lg"></i> rocm/stanford-megatron-lm</a>
+
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `85f95ae <https://github.com/stanford-futuredata/Megatron-LM/commit/85f95aef3b648075fe6f291c86714fdcbd9cd1f5>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - MI300X
+
+Supported models and features with ROCm 6.3.0
+================================================================================

 This section details models & features that are supported by the ROCm version on Stanford Megatron-LM.

@@ -88,41 +114,3 @@ It features how to pre-process datasets and how to begin pre-training on AMD GPU

 * Single-GPU pre-training
 * Multi-GPU pre-training
-
-.. _megatron-lm-docker-compat:
-
-Docker image compatibility
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes `Stanford Megatron-LM images <https://hub.docker.com/r/rocm/stanford-megatron-lm/tags>`_
-with ROCm and Pytorch backends on Docker Hub. The following Docker image tags and associated
-inventories represent the latest Stanford Megatron-LM version from the official Docker Hub.
-Click |docker-icon| to view the image on Docker Hub.
-
-.. list-table:: 
-    :header-rows: 1
-    :class: docker-image-compatibility
-
-    * - Docker image
-      - ROCm
-      - Stanford Megatron-LM
-      - PyTorch
-      - Ubuntu
-      - Python
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/stanford-megatron-lm/stanford-megatron-lm85f95ae_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-070556f078be10888a1421a2cb4f48c29f28b02bfeddae02588d1f7fc02a96a6"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
-      - `85f95ae <https://github.com/stanford-futuredata/Megatron-LM/commit/85f95aef3b648075fe6f291c86714fdcbd9cd1f5>`_
-      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
-      - 24.04
-      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
-
-      
-
--- a/docs/compatibility/ml-compatibility/verl-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/verl-compatibility.rst
@@ -37,67 +37,9 @@ Support overview
  - You can also consult the upstream `verl documentation <https://verl.readthedocs.io/en/latest/>`__ 
    for additional context.

-Version support
--------------------------------------------------------------------------------
-
-verl is supported on `ROCm 7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__ and
-`ROCm 6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`__.
-
-Supported devices
--------------------------------------------------------------------------------
-
-**Officially Supported**: AMD Instinct™ MI300X
-
-.. _verl-recommendations:
-
-Use cases and recommendations
-================================================================================
-
-* The benefits of verl in large-scale reinforcement learning from human feedback 
-  (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD 
-  GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__ 
-  blog. The blog post outlines how the Volcano Engine Reinforcement Learning 
-  (verl) framework integrates with the AMD ROCm platform to optimize training on 
-  AMD Instinct™ GPUs. The guide details the process of building a Docker image, 
-  setting up single-node and multi-node training environments, and highlights 
-  performance benchmarks demonstrating improved throughput and convergence accuracy. 
-  This resource serves as a comprehensive starting point for deploying verl on AMD GPUs, 
-  facilitating efficient RLHF training workflows.
-
-.. _verl-supported_features:
-
-Supported features
-===============================================================================
-
-The following table shows verl on ROCm support for GPU-accelerated modules.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Module
-      - Description
-      - verl version
-      - ROCm version
-    * - ``FSDP``
-      - Training engine
-      - 
-       * 0.6.0
-       * 0.3.0.post0
-      - 
-       * 7.0.0
-       * 6.2.0
-    * - ``vllm``
-      - Inference engine
-      - 
-       * 0.6.0
-       * 0.3.0.post0
-      - 
-       * 7.0.0
-       * 6.2.0
-
 .. _verl-docker-compat:

-Docker image compatibility
+Compatibility matrix
 ================================================================================

 .. |docker-icon| raw:: html
@@ -120,6 +62,7 @@ Click |docker-icon| to view the image on Docker Hub.
     - PyTorch
     - Python
     - vllm
+     - GPU

   * - .. raw:: html

@@ -130,6 +73,7 @@ Click |docker-icon| to view the image on Docker Hub.
     - `2.9.0 <https://github.com/ROCm/pytorch/tree/release/2.9-rocm7.x-gfx115x>`__
     - `3.12.11 <https://www.python.org/downloads/release/python-31211/>`__
     - `0.11.0 <https://github.com/vllm-project/vllm/releases/tag/v0.11.0>`__
+     - MI300X

   * - .. raw:: html

@@ -140,7 +84,33 @@ Click |docker-icon| to view the image on Docker Hub.
     - `2.5.0 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
     - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`__
     - `0.6.3 <https://github.com/vllm-project/vllm/releases/tag/v0.6.3>`__
+     - MI300X

+.. _verl-supported_features:
+
+Supported modules with verl on ROCm
+===============================================================================
+
+The following GPU-accelerated modules are supported with verl on ROCm:
+
+- ``FSDP``: Training engine
+- ``vllm``: Inference engine
+
+.. _verl-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+* The benefits of verl in large-scale reinforcement learning from human feedback 
+  (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD 
+  GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__ 
+  blog. The blog post outlines how the Volcano Engine Reinforcement Learning 
+  (verl) framework integrates with the AMD ROCm platform to optimize training on 
+  AMD Instinct™ GPUs. The guide details the process of building a Docker image, 
+  setting up single-node and multi-node training environments, and highlights 
+  performance benchmarks demonstrating improved throughput and convergence accuracy. 
+  This resource serves as a comprehensive starting point for deploying verl on AMD GPUs, 
+  facilitating efficient RLHF training workflows.

 Previous versions
 ===============================================================================
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -268,6 +268,3 @@ html_context = {
    "granularity_type" : [('Coarse-grained', 'coarse-grained'), ('Fine-grained', 'fine-grained')],
    "scope_type" : [('Device', 'device'), ('System', 'system')]
 }
-
-# Disable figure and table numbering
-numfig = False
--- a/docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
@@ -8,6 +8,303 @@ dockers:
      hipBLASLt: 1.0.0
    dockerfile:
      commit: 8398684622109c806a35d660647060b0b9910663
+
+configs:
+  default:
+    ## DeepSeek AITER MLA currently only supports --block-size 1
+    - &deepseek-r1-serving
+      benchmark: serving
+      model: deepseek-ai/DeepSeek-R1-0528
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1 8 32 128
+      extra_args:
+        async-scheduling: True
+        block-size: 1
+    ## gpt-oss requires AITER unified attention and performs best with block-size 64 and FULL_AND_PIECEWISE cudagraph mode
+    - &gpt-oss-120b-serving
+      benchmark: serving
+      model: openai/gpt-oss-120b
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1 8 32 128
+      env:
+        VLLM_ROCM_USE_AITER_MHA: 0
+        VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION: 1
+      extra_args:
+        async-scheduling: True
+        block-size: 64
+        compilation-config: '{\"cudagraph_mode\":\"FULL_AND_PIECEWISE\"}'
+    - &llama-3-serving
+      benchmark: serving
+      model:
+        meta-llama/Llama-3.1-405B-Instruct
+        amd/Llama-3.1-405B-Instruct-FP8-KV
+        meta-llama/Llama-3.3-70B-Instruct
+        amd/Llama-3.3-70B-Instruct-FP8-KV
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1 8 32 128
+      extra_args:
+        async-scheduling: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+    ## Llama 3.x MXFP4 (gfx950 only)
+    - &llama-3-mxfp4-serving
+      benchmark: serving
+      model:
+        amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1 8 32 128
+      extra_args:
+        async-scheduling: True
+    ## Llama 4 currently does not support full cudagraph or attn fusion
+    - &llama-4-fp8-serving
+      benchmark: serving
+      model:
+        meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1 8 32 128
+      extra_args:
+        async-scheduling: True
+        compilation-config: '{\"cudagraph_mode\":\"PIECEWISE\",\"pass_config\":{\"enable_attn_fusion\":false}}'
+      arch_overrides:
+        gfx942:
+          dtype: float16
+    - &mixtral-8x22b-serving
+      benchmark: serving
+      model:
+        mistralai/Mixtral-8x22B-Instruct-v0.1
+        amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1 8 32 128
+      extra_args:
+        async-scheduling: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+  extended:
+    ## gpt-oss requires AITER unified attention and performs best with block-size 64 and FULL_AND_PIECEWISE cudagraph mode
+    - &gpt-oss-20b-serving
+      benchmark: serving
+      model:
+        openai/gpt-oss-20b
+      tp: 1
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1
+      env:
+        VLLM_ROCM_USE_AITER_MHA: 0
+        VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION: 1
+      extra_args:
+        async-scheduling: True
+        block-size: 64
+        compilation-config: '{\"cudagraph_mode\":\"FULL_AND_PIECEWISE\"}'
+    - &llama-3-8b-phi-4-qwen3-serving
+      benchmark: serving
+      model:
+        meta-llama/Llama-3.1-8B-Instruct
+        amd/Llama-3.1-8B-Instruct-FP8-KV
+        microsoft/phi-4
+        Qwen/Qwen3-8B
+        Qwen/Qwen3-32B
+        Qwen/Qwen3-30B-A3B-Thinking-2507
+        Qwen/Qwen3-30B-A3B-Thinking-2507-FP8
+      tp: 1
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1
+      extra_args:
+        async-scheduling: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+
+    - &llama-2-70b-serving
+      benchmark: serving
+      model:
+        meta-llama/Llama-2-70b-chat-hf
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1
+      extra_args:
+        async-scheduling: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+    ## Llama 4 currently does not support full cudagraph or attn fusion
+    - &llama-4-serving
+      benchmark: serving
+      model:
+        meta-llama/Llama-4-Scout-17B-16E-Instruct
+        meta-llama/Llama-4-Maverick-17B-128E-Instruct
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1
+      extra_args:
+        async-scheduling: True
+        compilation-config: '{\"cudagraph_mode\":\"PIECEWISE\",\"pass_config\":{\"enable_attn_fusion\":false}}'
+      arch_overrides:
+        gfx942:
+          dtype: float16
+
+    - &mixtral-8x7b-serving
+      benchmark: serving
+      model:
+        mistralai/Mixtral-8x7B-Instruct-v0.1
+        amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1
+      extra_args:
+        async-scheduling: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+    ## Qwen 235B requires --enable-expert-parallel with tp 8
+    - &qwen3-235b-a22b-serving
+      benchmark: serving
+      model:
+        Qwen/Qwen3-235B-A22B-Thinking-2507
+        Qwen/Qwen3-235B-A22B-Thinking-2507-FP8
+      tp: 8
+      inp: 1024
+      out: 1024
+      dtype: auto
+      max_concurrency: 1
+      extra_args:
+        async-scheduling: True
+        enable-expert-parallel: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+  accuracy:
+    ## DeepSeek AITER MLA currently only supports --block-size 1
+    - &deepseek-r1-accuracy
+      benchmark: accuracy
+      model: deepseek-ai/DeepSeek-R1-0528
+      tp: 8
+      dtype: auto
+      extra_args:
+        async-scheduling: True
+        block-size: 1
+      bench_args:
+        apply_chat_template: True
+    ## gpt-oss requires AITER unified attention and performs best with block-size 64 and FULL_AND_PIECEWISE cudagraph mode
+    - &gpt-oss-120b-accuracy
+      benchmark: accuracy
+      model: openai/gpt-oss-120b
+      tp: 8
+      dtype: auto
+      env:
+        VLLM_ROCM_USE_AITER_MHA: 0
+        VLLM_USE_AITER_UNIFIED_ATTENTION: 1
+      extra_args:
+        async-scheduling: True
+        block-size: 64
+        compilation-config: '{\"cudagraph_mode\":\"FULL_AND_PIECEWISE\"}'
+      bench_args:
+        apply_chat_template: True
+    ## Llama 3.x bf16 and fp8 perform better with --dtype float16 on gfx942
+    - &llama-3-accuracy
+      benchmark: accuracy
+      model:
+        meta-llama/Llama-3.1-405B-Instruct
+        amd/Llama-3.1-405B-Instruct-FP8-KV
+        meta-llama/Llama-3.3-70B-Instruct
+        amd/Llama-3.3-70B-Instruct-FP8-KV
+      tp: 8
+      dtype: auto
+      extra_args:
+        async-scheduling: True
+      bench_args:
+        apply_chat_template: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+    ## Llama 3.x MXFP4 (gfx950 only)
+    - &llama-3-mxfp4-accuracy
+      benchmark: accuracy
+      model:
+        amd/Llama-3.1-405B-Instruct-MXFP4-Preview
+        amd/Llama-3.3-70B-Instruct-MXFP4-Preview
+      tp: 8
+      dtype: auto
+      extra_args:
+        async-scheduling: True
+      bench_args:
+        apply_chat_template: True
+    ## Llama 4 currently does not support full cudagraph or attn fusion
+    - &llama-4-fp8-accuracy
+      benchmark: accuracy
+      model:
+        meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+      tp: 8
+      dtype: auto
+      extra_args:
+        async-scheduling: True
+        compilation-config: '{\"cudagraph_mode\":\"PIECEWISE\",\"pass_config\":{\"enable_attn_fusion\":false}}'
+      bench_args:
+        apply_chat_template: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+    ## Mistral models require --tokenizer-mode mistral for correct decoding
+    - &mixtral-8x22b-accuracy
+      benchmark: accuracy
+      model:
+        mistralai/Mixtral-8x22B-Instruct-v0.1
+        amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+      tp: 8
+      dtype: auto
+      extra_args:
+        async-scheduling: True
+      bench_args:
+        apply_chat_template: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+    ## Qwen 235B requires --enable-expert-parallel with tp 8
+    - &qwen3-235b-a22b-accuracy
+      benchmark: accuracy
+      model:
+        Qwen/Qwen3-235B-A22B-Thinking-2507
+        Qwen/Qwen3-235B-A22B-Thinking-2507-FP8
+      dtype: auto
+      extra_args:
+        async-scheduling: True
+        enable-expert-parallel: True
+      bench_args:
+        apply_chat_template: True
+      arch_overrides:
+        gfx942:
+          dtype: float16
+
 model_groups:
  - group: Meta Llama
    tag: llama
@@ -18,132 +315,139 @@ model_groups:
        url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
        precision: float16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 4096
-          max_model_len: 4096
+          serving: *llama-2-70b-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 4096
+            max_model_len: 4096
      - model: Llama 3.1 8B
        mad_tag: pyt_vllm_llama-3.1-8b
        model_repo: meta-llama/Llama-3.1-8B-Instruct
        url: https://huggingface.co/meta-llama/Llama-3.1-8B
        precision: float16
        config:
-          tp: 1
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-3-8b-phi-4-qwen3-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
      - model: Llama 3.1 8B FP8
        mad_tag: pyt_vllm_llama-3.1-8b_fp8
        model_repo: amd/Llama-3.1-8B-Instruct-FP8-KV
        url: https://huggingface.co/amd/Llama-3.1-8B-Instruct-FP8-KV
        precision: float8
        config:
-          tp: 1
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-3-8b-phi-4-qwen3-serving
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
      - model: Llama 3.1 405B
        mad_tag: pyt_vllm_llama-3.1-405b
        model_repo: meta-llama/Llama-3.1-405B-Instruct
        url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
        precision: float16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-3-serving
+          accuracy: *llama-3-accuracy
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
      - model: Llama 3.1 405B FP8
        mad_tag: pyt_vllm_llama-3.1-405b_fp8
        model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
        precision: float8
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-3-serving
+          accuracy: *llama-3-accuracy
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
      - model: Llama 3.1 405B MXFP4
        mad_tag: pyt_vllm_llama-3.1-405b_fp4
        model_repo: amd/Llama-3.1-405B-Instruct-MXFP4-Preview
        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-MXFP4-Preview
        precision: float4
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-3-mxfp4-serving
+          accuracy: *llama-3-mxfp4-accuracy
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
      - model: Llama 3.3 70B
        mad_tag: pyt_vllm_llama-3.3-70b
        model_repo: meta-llama/Llama-3.3-70B-Instruct
        url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
        precision: float16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-3-serving
+          accuracy: *llama-3-accuracy
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
      - model: Llama 3.3 70B FP8
        mad_tag: pyt_vllm_llama-3.3-70b_fp8
        model_repo: amd/Llama-3.3-70B-Instruct-FP8-KV
        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-FP8-KV
        precision: float8
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-3-serving
+          accuracy: *llama-3-accuracy
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
      - model: Llama 3.3 70B MXFP4
        mad_tag: pyt_vllm_llama-3.3-70b_fp4
        model_repo: amd/Llama-3.3-70B-Instruct-MXFP4-Preview
        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-MXFP4-Preview
        precision: float4
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-3-mxfp4-serving
+          accuracy: *llama-3-mxfp4-accuracy
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
      - model: Llama 4 Scout 17Bx16E
        mad_tag: pyt_vllm_llama-4-scout-17b-16e
        model_repo: meta-llama/Llama-4-Scout-17B-16E-Instruct
        url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
        precision: float16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 32768
-          max_model_len: 8192
+          serving: *llama-4-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 32768
+            max_model_len: 8192
      - model: Llama 4 Maverick 17Bx128E
        mad_tag: pyt_vllm_llama-4-maverick-17b-128e
        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct
        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct
        precision: float16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 32768
-          max_model_len: 8192
+          serving: *llama-4-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 32768
+            max_model_len: 8192
      - model: Llama 4 Maverick 17Bx128E FP8
        mad_tag: pyt_vllm_llama-4-maverick-17b-128e_fp8
        model_repo: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
        url: https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
        precision: float8
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *llama-4-fp8-serving
+          accuracy: *llama-4-fp8-accuracy
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
  - group: DeepSeek
    tag: deepseek
    models:
@@ -153,12 +457,12 @@ model_groups:
        url: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528
        precision: float8
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_seqs: 1024
-          max_num_batched_tokens: 131072
-          max_model_len: 8192
+          serving: *deepseek-r1-serving
+          accuracy: *deepseek-r1-accuracy
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 131072
+            max_model_len: 8192
  - group: OpenAI GPT OSS
    tag: gpt-oss
    models:
@@ -168,22 +472,23 @@ model_groups:
        url: https://huggingface.co/openai/gpt-oss-20b
        precision: bfloat16
        config:
-          tp: 1
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 8192
-          max_model_len: 8192
+          serving: *gpt-oss-20b-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 8192
+            max_model_len: 8192
      - model: GPT OSS 120B
        mad_tag: pyt_vllm_gpt-oss-120b
        model_repo: openai/gpt-oss-120b
        url: https://huggingface.co/openai/gpt-oss-120b
        precision: bfloat16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 8192
-          max_model_len: 8192
+          serving: *gpt-oss-120b-serving
+          accuracy: *gpt-oss-120b-accuracy
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 8192
+            max_model_len: 8192
  - group: Mistral AI
    tag: mistral
    models:
@@ -193,44 +498,46 @@ model_groups:
        url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
        precision: float16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 32768
-          max_model_len: 8192
+          serving: *mixtral-8x7b-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 32768
+            max_model_len: 8192
      - model: Mixtral MoE 8x7B FP8
        mad_tag: pyt_vllm_mixtral-8x7b_fp8
        model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
        url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
        precision: float8
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 32768
-          max_model_len: 8192
+          serving: *mixtral-8x7b-serving
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 32768
+            max_model_len: 8192
      - model: Mixtral MoE 8x22B
        mad_tag: pyt_vllm_mixtral-8x22b
        model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
        url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
        precision: float16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 65536
-          max_model_len: 8192
+          serving: *mixtral-8x22b-serving
+          accuracy: *mixtral-8x22b-accuracy
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 65536
+            max_model_len: 8192
      - model: Mixtral MoE 8x22B FP8
        mad_tag: pyt_vllm_mixtral-8x22b_fp8
        model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
        url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
        precision: float8
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 65536
-          max_model_len: 8192
+          serving: *mixtral-8x22b-serving
+          accuracy: *mixtral-8x22b-accuracy
+          ex:
+            kv_cache_dtype: fp8
+            max_num_batched_tokens: 65536
+            max_model_len: 8192
  - group: Qwen
    tag: qwen
    models:
@@ -240,66 +547,68 @@ model_groups:
        url: https://huggingface.co/Qwen/Qwen3-8B
        precision: float16
        config:
-          tp: 1
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 40960
-          max_model_len: 8192
+          serving: *llama-3-8b-phi-4-qwen3-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 40960
+            max_model_len: 8192
      - model: Qwen3 32B
        mad_tag: pyt_vllm_qwen3-32b
-        model_repo: Qwen/Qwen3-32b
+        model_repo: Qwen/Qwen3-32B
        url: https://huggingface.co/Qwen/Qwen3-32B
        precision: float16
        config:
-          tp: 1
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 40960
-          max_model_len: 8192
-      - model: Qwen3 30B A3B
+          serving: *llama-3-8b-phi-4-qwen3-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 40960
+            max_model_len: 8192
+      - model: Qwen3 30B A3B Thinking
        mad_tag: pyt_vllm_qwen3-30b-a3b
-        model_repo: Qwen/Qwen3-30B-A3B
-        url: https://huggingface.co/Qwen/Qwen3-30B-A3B
+        model_repo: Qwen/Qwen3-30B-A3B-Thinking-2507
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507
        precision: float16
        config:
-          tp: 1
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 40960
-          max_model_len: 8192
-      - model: Qwen3 30B A3B FP8
+          serving: *llama-3-8b-phi-4-qwen3-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 40960
+            max_model_len: 8192
+      - model: Qwen3 30B A3B Thinking FP8
        mad_tag: pyt_vllm_qwen3-30b-a3b_fp8
-        model_repo: Qwen/Qwen3-30B-A3B-FP8
-        url: https://huggingface.co/Qwen/Qwen3-30B-A3B-FP8
+        model_repo: Qwen/Qwen3-30B-A3B-Thinking-2507-FP8
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507-FP8
        precision: float16
        config:
-          tp: 1
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 40960
-          max_model_len: 8192
-      - model: Qwen3 235B A22B
+          serving: *llama-3-8b-phi-4-qwen3-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 40960
+            max_model_len: 8192
+      - model: Qwen3 235B A22B Thinking
        mad_tag: pyt_vllm_qwen3-235b-a22b
-        model_repo: Qwen/Qwen3-235B-A22B
-        url: https://huggingface.co/Qwen/Qwen3-235B-A22B
+        model_repo: Qwen/Qwen3-235B-A22B-Thinking-2507
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507
        precision: float16
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 40960
-          max_model_len: 8192
-      - model: Qwen3 235B A22B FP8
+          serving: *qwen3-235b-a22b-serving
+          accuracy: *qwen3-235b-a22b-accuracy
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 40960
+            max_model_len: 8192
+      - model: Qwen3 235B A22B Thinking FP8
        mad_tag: pyt_vllm_qwen3-235b-a22b_fp8
-        model_repo: Qwen/Qwen3-235B-A22B-FP8
-        url: https://huggingface.co/Qwen/Qwen3-235B-A22B-FP8
+        model_repo: Qwen/Qwen3-235B-A22B-Thinking-2507-FP8
+        url: https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8
        precision: float8
        config:
-          tp: 8
-          dtype: auto
-          kv_cache_dtype: fp8
-          max_num_batched_tokens: 40960
-          max_model_len: 8192
+          serving: *qwen3-235b-a22b-serving
+          accuracy: *qwen3-235b-a22b-accuracy
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 40960
+            max_model_len: 8192
  - group: Microsoft Phi
    tag: phi
    models:
@@ -309,8 +618,8 @@ model_groups:
        url: https://huggingface.co/microsoft/phi-4
        precision: float16
        config:
-          tp: 1
-          dtype: auto
-          kv_cache_dtype: auto
-          max_num_batched_tokens: 16384
-          max_model_len: 8192
+          serving: *llama-3-8b-phi-4-qwen3-serving
+          ex:
+            kv_cache_dtype: auto
+            max_num_batched_tokens: 16384
+            max_model_len: 8192
--- a/docs/how-to/deep-learning-rocm.rst
+++ b/docs/how-to/deep-learning-rocm.rst
@@ -19,117 +19,95 @@ The table below summarizes information about ROCm-enabled deep learning framewor
    :widths: 5 3 6 3

    * - Framework
-      - Installation
+      - Installation guide
      - Installation options
      - GitHub

-    * - `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>
+    * - :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/pytorch-install>`
      - 
-        - `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
+        - Wheels package
+        - ROCm Base Docker image
+        - Upstream Docker file
      - .. 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>`__
-      - .. 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>
+    * - :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
      - 
-        - `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
+        - 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>`__
-      - .. 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>
+    * - :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/jax-install>`
      - 
-        - `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
      - .. 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>`__
-      - .. 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>
+    * - :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/verl-install>`
      - 
-        - `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
      - .. 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>`__
-      - .. 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>
+    * - :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
      - 
-        - `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
      - .. 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>`__
-      - .. 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>
+    * - :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/dgl-install>`
      - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/dgl-install.html#use-a-prebuilt-docker-image-with-dgl-pre-installed>`__
-        - `Wheels package <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/dgl-install.html#use-a-wheels-package>`__
-
+        - Docker image
      - .. 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>`__
-      - .. 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>
+    * - :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/megablocks-install>`
      - 
-        - `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
      - .. raw:: html

          <a href="https://github.com/ROCm/megablocks"><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>
+    * - :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/ray-install>`
      - 
-        - `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>`__
+        - Docker image
+        - Wheels package
+        - ROCm Base 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>
+    * - :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/llama-cpp-install>`
      - 
-        - `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>`__
-        - `ROCm Base Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/llama-cpp-install.html#build-your-own-docker-image>`__
+        - Docker image
+        - ROCm Base Docker image
      - .. raw:: html

          <a href="https://github.com/ROCm/llama.cpp"><i class="fab fa-github fa-lg"></i></a>

-    * - `FlashInfer <https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/flashinfer-compatibility.html>`__
-      - .. raw:: html
-
-          <a href="https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/flashinfer-install.html"><i class="fas fa-link fa-lg"></i></a>
+    * - :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/flashinfer-install>`
      - 
-        - `Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/flashinfer-install.html#use-a-prebuilt-docker-image-with-flashinfer-pre-installed>`__
-        - `ROCm Base Docker image <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/flashinfer-install.html#build-your-own-docker-image>`__
+        - Docker image
+        - ROCm Base Docker image
      - .. raw:: html

          <a href="https://github.com/ROCm/flashinfer"><i class="fab fa-github fa-lg"></i></a>
--- a/docs/how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference.rst
+++ b/docs/how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference.rst
@@ -44,7 +44,7 @@ Setting up the base implementation environment

   .. code-block:: shell

-      rocm-smi --showproductname
+      amd-smi static --board

 #. Check that your GPUs are available to PyTorch.

@@ -65,8 +65,8 @@ Setting up the base implementation environment

 .. tip::

-   During training and inference, you can check the memory usage by running the ``rocm-smi`` command in your terminal.
-   This tool helps you see shows which GPUs are involved.
+   During training and inference, you can check the memory usage by running the ``amd-smi`` command in your terminal.
+   This tool helps you see which GPUs are involved.


 .. _fine-tuning-llms-multi-gpu-hugging-face-accelerate:
@@ -91,10 +91,10 @@ Now, it's important to adjust how you load the model. Add the ``device_map`` par

   ...
   base_model_name = "meta-llama/Llama-2-7b-chat-hf"
-   
+
   # Load base model to GPU memory
   base_model = AutoModelForCausalLM.from_pretrained(
-           base_model_name, 
+           base_model_name,
           device_map = "auto",
           trust_remote_code = True)
   ...
@@ -130,7 +130,7 @@ After loading the model in this way, the model is fully ready to use the resourc
 torchtune for fine-tuning and inference
 =============================================

-`torchtune <https://meta-pytorch.org/torchtune/main/>`_ is a PyTorch-native library for easy single and multi-GPU 
+`torchtune <https://pytorch.org/torchtune/main/>`_ is a PyTorch-native library for easy single and multi-GPU
 model fine-tuning and inference with LLMs.

 #. Install torchtune using pip.
@@ -139,7 +139,7 @@ model fine-tuning and inference with LLMs.

      # Install torchtune with PyTorch release 2.2.2+
      pip install torchtune
-      
+
      # To confirm that the package is installed correctly
      tune --help

@@ -148,12 +148,12 @@ model fine-tuning and inference with LLMs.
   .. code-block:: shell

      usage: tune [-h] {download,ls,cp,run,validate} ...
-      
+
      Welcome to the TorchTune CLI!
-      
+
      options:
        -h, --help            show this help message and exit
-      
+
      subcommands:
        {download,ls,cp,run,validate}

@@ -194,11 +194,11 @@ model fine-tuning and inference with LLMs.
        apply_lora_to_output: False
        lora_rank: 8
        lora_alpha: 16
-      
+
      tokenizer:
        _component_: torchtune.models.llama2.llama2_tokenizer
        path: /tmp/Llama-2-7b-hf/tokenizer.model
-      
+
      # Dataset and sampler
      dataset:
        _component_: torchtune.datasets.alpaca_cleaned_dataset
--- a/docs/how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference.rst
+++ b/docs/how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference.rst
@@ -44,20 +44,19 @@ Setting up the base implementation environment

   .. code-block:: shell

-      rocm-smi --showproductname
+      amd-smi static --board

   Your output should look like this:

   .. code-block:: shell

-      ============================ ROCm System Management Interface ============================
-      ====================================== Product Info ======================================
-      GPU[0]          : Card Series:          AMD Instinct MI300X OAM
-      GPU[0]          : Card model:           0x74a1
-      GPU[0]          : Card vendor:          Advanced Micro Devices, Inc. [AMD/ATI]
-      GPU[0]          : Card SKU:             MI3SRIOV
-      ==========================================================================================
-      ================================== End of ROCm SMI Log ===================================
+      GPU: 0
+         BOARD:
+            MODEL_NUMBER: 102-G39203-0B
+            PRODUCT_SERIAL: PCB079220-1150
+            FRU_ID: 113-AMDG392030B04-100-300000097H
+            PRODUCT_NAME: AMD Instinct MI325 OAM
+            MANUFACTURER_NAME: AMD

 #. Check that your GPUs are available to PyTorch.

@@ -94,13 +93,13 @@ Setting up the base implementation environment
      pip install -r requirements-dev.txt
      cmake -DBNB_ROCM_ARCH="gfx942" -DCOMPUTE_BACKEND=hip -S .
      python setup.py install
-      
+
      # To leverage the SFTTrainer in TRL for model fine-tuning.
      pip install trl
-      
+
      # To leverage PEFT for efficiently adapting pre-trained language models .
      pip install peft
-      
+
      # Install the other dependencies.
      pip install transformers datasets huggingface-hub scipy

@@ -132,7 +131,7 @@ Download the base model and fine-tuning dataset

   .. note::

-      You can also use the `NousResearch Llama-2-7b-chat-hf <https://huggingface.co/NousResearch/Llama-2-7b-chat-hf>`_ 
+      You can also use the `NousResearch Llama-2-7b-chat-hf <https://huggingface.co/NousResearch/Llama-2-7b-chat-hf>`_
      as a substitute. It has the same model weights as the original.

 #. Run the following code to load the base model and tokenizer.
@@ -141,14 +140,14 @@ Download the base model and fine-tuning dataset

      # Base model and tokenizer names.
      base_model_name = "meta-llama/Llama-2-7b-chat-hf"
-      
+
      # Load base model to GPU memory.
      device = "cuda:0"
      base_model = AutoModelForCausalLM.from_pretrained(base_model_name, trust_remote_code = True).to(device)
-      
+
      # Load tokenizer.
      tokenizer = AutoTokenizer.from_pretrained(
-              base_model_name, 
+              base_model_name,
              trust_remote_code = True)
      tokenizer.pad_token = tokenizer.eos_token
      tokenizer.padding_side = "right"
@@ -162,10 +161,10 @@ Download the base model and fine-tuning dataset
      # Dataset for fine-tuning.
      training_dataset_name = "mlabonne/guanaco-llama2-1k"
      training_dataset = load_dataset(training_dataset_name, split = "train")
-      
+
      # Check the data.
      print(training_dataset)
-      
+
      # Dataset 11 is a QA sample in English.
      print(training_dataset[11])

@@ -252,8 +251,8 @@ Compare the number of trainable parameters and training time under the two diffe
                    dataset_text_field = "text",
                    tokenizer = tokenizer,
                    args = training_arguments
-            ) 
-            
+            )
+
            # Run the trainer.
            sft_trainer.train()

@@ -286,7 +285,7 @@ Compare the number of trainable parameters and training time under the two diffe
                    if param.requires_grad:
                        trainable_params += param.numel()
                print(f"trainable params: {trainable_params} || all params: {all_param} || trainable%: {100 * trainable_params / all_param:.2f}")
-            
+
            sft_trainer.peft_config = None
            print_trainable_parameters(sft_trainer.model)

@@ -309,8 +308,8 @@ Compare the number of trainable parameters and training time under the two diffe
                    dataset_text_field = "text",
                    tokenizer = tokenizer,
                    args = training_arguments
-            ) 
-            
+            )
+
            # Training.
            trainer_full.train()

@@ -349,7 +348,7 @@ store, and load.

         # PEFT adapter name.
         adapter_name = "llama-2-7b-enhanced-adapter"
-         
+
         # Save PEFT adapter.
         sft_trainer.model.save_pretrained(adapter_name)

@@ -359,21 +358,21 @@ store, and load.

         # Access adapter directory.
         cd llama-2-7b-enhanced-adapter
-         
+
         # List all adapter files.
         README.md  adapter_config.json  adapter_model.safetensors

   .. tab-item:: Saving a fully fine-tuned model
      :sync: without

-      If you're not using LoRA and PEFT so there is no PEFT LoRA configuration used for training, use the following code 
+      If you're not using LoRA and PEFT so there is no PEFT LoRA configuration used for training, use the following code
      to save your fine-tuned model to your system.

      .. code-block:: python

         # Fully fine-tuned model name.
         new_model_name = "llama-2-7b-enhanced"
-         
+
         # Save the fully fine-tuned model.
         full_trainer.model.save_pretrained(new_model_name)

@@ -383,7 +382,7 @@ store, and load.

         # Access new model directory.
         cd llama-2-7b-enhanced
-         
+
         # List all model files.
         config.json                       model-00002-of-00006.safetensors  model-00005-of-00006.safetensors
         generation_config.json            model-00003-of-00006.safetensors  model-00006-of-00006.safetensors
@@ -412,26 +411,26 @@ Let's look at achieving model inference using these types of models.

   .. tab-item:: Inference using PEFT adapters

-      To use PEFT adapters like a normal transformer model, you can run the generation by loading a base model along with PEFT 
+      To use PEFT adapters like a normal transformer model, you can run the generation by loading a base model along with PEFT
      adapters as follows.

      .. code-block:: python

         from peft import PeftModel
         from transformers import AutoModelForCausalLM
-         
+
         # Set the path of the model or the name on Hugging face hub
         base_model_name = "meta-llama/Llama-2-7b-chat-hf"
-         
+
         # Set the path of the adapter
         adapter_name = "Llama-2-7b-enhanced-adpater"
-         
-         # Load base model 
+
+         # Load base model
         base_model = AutoModelForCausalLM.from_pretrained(base_model_name)
-         
-         # Adapt the base model with the adapter 
+
+         # Adapt the base model with the adapter
         new_model = PeftModel.from_pretrained(base_model, adapter_name)
-         
+
         # Then, run generation as the same with a normal model outlined in 2.1

      The PEFT library provides a ``merge_and_unload`` method, which merges the adapter layers into the base model. This is
@@ -439,13 +438,13 @@ Let's look at achieving model inference using these types of models.

      .. code-block:: python

-         # Load base model 
+         # Load base model
         base_model = AutoModelForCausalLM.from_pretrained(base_model_name)
-         
-         # Adapt the base model with the adapter 
+
+         # Adapt the base model with the adapter
         new_model = PeftModel.from_pretrained(base_model, adapter_name)
-         
-         # Merge adapter 
+
+         # Merge adapter
         model = model.merge_and_unload()

         # Save the merged model into local
@@ -461,25 +460,25 @@ Let's look at achieving model inference using these types of models.

         # Import relevant class for loading model and tokenizer
         from transformers import AutoTokenizer, AutoModelForCausalLM
-         
+
         # Set the pre-trained model name on Hugging face hub
         model_name = "meta-llama/Llama-2-7b-chat-hf"
-         
-         # Set device type 
+
+         # Set device type
         device = "cuda:0"
-         
-         # Load model and tokenizer 
+
+         # Load model and tokenizer
         model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
         tokenizer = AutoTokenizer.from_pretrained(model_name)
-         
-         # Input prompt encoding 
+
+         # Input prompt encoding
         query = "What is a large language model?"
         inputs = tokenizer.encode(query, return_tensors="pt").to(device)
-         
-         # Token generation  
-         outputs = model.generate(inputs) 
-         
-         # Outputs decoding 
+
+         # Token generation
+         outputs = model.generate(inputs)
+
+         # Outputs decoding
         print(tokenizer.decode(outputs[0]))

      In addition, pipelines from Transformers offer simple APIs to use pre-trained models for different tasks, including
@@ -490,14 +489,14 @@ Let's look at achieving model inference using these types of models.

         # Import relevant class for loading model and tokenizer
         from transformers import pipeline
-         
+
         # Set the path of your model or the name on Hugging face hub
         model_name_or_path = "meta-llama/Llama-2-7b-chat-hf"
-         
-         # Set pipeline 
+
+         # Set pipeline
         # A positive device value will run the model on associated CUDA device id
         pipe = pipeline("text-generation", model=model_name_or_path, device=0)
-         
+
         # Token generation
         print(pipe("What is a large language model?")[0]["generated_text"])

--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
@@ -189,6 +189,10 @@ Benchmarking
   {% for model_group in model_groups %}
      {% for model in model_group.models %}

+      {% set serv_config = model.config.serving %}
+      {% set acc_config = model.config.accuracy %}
+      {% set ex_config = model.config.ex %}
+
   .. container:: model-doc {{model.mad_tag}}

      .. tab-set::
@@ -283,108 +287,173 @@ Benchmarking
                   --name test \
                   {{ docker.pull_tag }}

-            .. rubric:: Throughput command
+            .. rubric:: Run the inference benchmarks

-            Use the following command to start the throughput benchmark.
+            .. tab-set::

-            .. code-block:: shell
+               .. tab-item:: Latency command

-               model={{ model.model_repo }}
-               tp={{ model.config.tp }}
-               num_prompts={{ model.config.num_prompts | default(1024) }}
-               in={{ model.config.in | default(128) }}
-               out={{ model.config.in | default(128) }}
-               dtype={{ model.config.dtype | default("auto") }}
-               kv_cache_dtype={{ model.config.kv_cache_dtype }}
-               max_num_seqs={{ model.config.max_num_seqs | default(1024) }}
-               max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
-               max_model_len={{ model.config.max_model_len }}
+                  Use the following command to start the latency benchmark.

-               vllm bench throughput --model $model \
-                   -tp $tp \
-                   --num-prompts $num_prompts \
-                   --input-len $in \
-                   --output-len $out \
-                   --dtype $dtype \
-                   --kv-cache-dtype $kv_cache_dtype \
-                   --max-num-seqs $max_num_seqs \
-                   --max-num-batched-tokens $max_num_batched_tokens \
-                   --max-model-len $max_model_len \
-                   --trust-remote-code \
-                   --output-json ${model}_throughput.json \
-                   --gpu-memory-utilization {{ model.config.gpu_memory_utilization | default(0.9) }}
+                  .. code-block:: shell

-            .. rubric:: Serving command
+                     model={{ model.model_repo }}
+                     tp={{ serv_config.tp }}
+                     batch_size=16
+                     in={{ serv_config.inp | default(1024) }}
+                     out={{ serv_config.out | default(1024) }}
+                     dtype={{ serv_config.dtype | default("auto") }}
+                     kv_cache_dtype={{ ex_config.kv_cache_dtype | default("auto") }}
+                     max_num_seqs={{ ex_config.max_num_seqs | default(1024) }}
+                     max_num_batched_tokens={{ ex_config.max_num_batched_tokens }}
+                     max_model_len={{ ex_config.max_model_len }}

-            1. Start the server using the following command:
+                     vllm bench latency --model $model \
+                         -tp $tp \
+                         --batch-size $batch_size \
+                         --input-len $in \
+                         --output-len $out \
+                         --dtype $dtype \
+                         --kv-cache-dtype $kv_cache_dtype \
+                         --max-num-seqs $max_num_seqs \
+                         --max-num-batched-tokens $max_num_batched_tokens \
+                         --max-model-len $max_model_len \
+                         --output-json ${model}_throughput.json \

-               .. code-block:: shell
+               .. tab-item:: Throughput command

-                  model={{ model.model_repo }}
-                  tp={{ model.config.tp }}
-                  dtype={{ model.config.dtype }}
-                  kv_cache_dtype={{ model.config.kv_cache_dtype }}
-                  max_num_seqs=256
-                  max_num_batched_tokens={{ model.config.max_num_batched_tokens }}
-                  max_model_len={{ model.config.max_model_len }}
+                  Use the following command to start the throughput benchmark.

-                  vllm serve $model \
-                      -tp $tp \
-                      --dtype $dtype \
-                      --kv-cache-dtype $kv_cache_dtype \
-                      --max-num-seqs $max_num_seqs \
-                      --max-num-batched-tokens $max_num_batched_tokens \
-                      --max-model-len $max_model_len \
-                      --no-enable-prefix-caching \
-                      --swap-space 16 \
-                      --disable-log-requests \
-                      --trust-remote-code \
-                      --gpu-memory-utilization 0.9
+                  .. code-block:: shell

-               Wait until the model has loaded and the server is ready to accept requests.
+                     model={{ model.model_repo }}
+                     tp={{ serv_config.tp }}
+                     num_prompts={{ model.config.num_prompts | default(1024) }}
+                     in={{ serv_config.inp | default(1024) }}
+                     out={{ serv_config.out | default(1024) }}
+                     dtype={{ serv_config.dtype | default("auto") }}
+                     kv_cache_dtype={{ ex_config.kv_cache_dtype | default("auto") }}
+                     max_num_seqs={{ ex_config.max_num_seqs | default(1024) }}
+                     max_num_batched_tokens={{ ex_config.max_num_batched_tokens }}
+                     max_model_len={{ ex_config.max_model_len }}

-            2. On another terminal on the same machine, run the benchmark:
+                     vllm bench throughput --model $model \
+                         -tp $tp \
+                         --num-prompts $num_prompts \
+                         --input-len $in \
+                         --output-len $out \
+                         --dtype $dtype \
+                         --kv-cache-dtype $kv_cache_dtype \
+                         --max-num-seqs $max_num_seqs \
+                         --max-num-batched-tokens $max_num_batched_tokens \
+                         --max-model-len $max_model_len \
+                         --trust-remote-code \
+                         --output-json ${model}_throughput.json \
+                         --gpu-memory-utilization {{ model.config.gpu_memory_utilization | default(0.9) }}

-               .. code-block:: shell
+               .. tab-item:: Serving command

-                  # Connect to the container
-                  docker exec -it test bash
+                  1. Start the server using the following command:

-                  # Wait for the server to start
-                  until curl -s http://localhost:8000/v1/models; do sleep 30; done
+                     .. code-block:: shell

-                  # Run the benchmark
-                  model={{ model.model_repo }}
-                  max_concurrency=1
-                  num_prompts=10
-                  in=128
-                  out=128
-                  vllm bench serve --model $model \
-                      --percentile-metrics "ttft,tpot,itl,e2el" \
-                      --dataset-name random \
-                      --ignore-eos \
-                      --max-concurrency $max_concurrency \
-                      --num-prompts $num_prompts \
-                      --random-input-len $in \
-                      --random-output-len $out \
-                      --trust-remote-code \
-                      --save-result \
-                      --result-filename ${model}_serving.json
+                        model={{ model.model_repo }}
+                        tp={{ serv_config.tp }}
+                        dtype={{ serv_config.dtype }}
+                        kv_cache_dtype={{ ex_config.kv_cache_dtype }}
+                        max_num_seqs=1024
+                        max_num_batched_tokens={{ ex_config.max_num_batched_tokens }}
+                        max_model_len={{ ex_config.max_model_len }}

-            .. note::
+                        vllm serve $model \
+                            -tp $tp \
+                            --dtype $dtype \
+                            --kv-cache-dtype $kv_cache_dtype \
+                            --max-num-seqs $max_num_seqs \
+                            --max-num-batched-tokens $max_num_batched_tokens \
+                            --max-model-len $max_model_len \
+                            --no-enable-prefix-caching \
+                            --swap-space 16 \
+                            --disable-log-requests

-               For improved performance with certain Mixture of Experts models, such as Mixtral 8x22B,
-               try adding ``export VLLM_ROCM_USE_AITER=1`` to your commands.
+                     Wait until the model has loaded and the server is ready to accept requests.

-               If you encounter the following error, pass your access-authorized Hugging
-               Face token to the gated models.
+                  2. On another terminal on the same machine, run the benchmark:

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

-                  OSError: You are trying to access a gated repo.
+                        # Connect to the container
+                        docker exec -it test bash

-                  # pass your HF_TOKEN
-                  export HF_TOKEN=$your_personal_hf_token
+                        # Wait for the server to start
+                        until curl -s http://localhost:8000/v1/models; do sleep 30; done
+
+                        # Run the benchmark
+                        model={{ model.model_repo }}
+                        max_concurrency=1
+                        num_prompts=10
+                        in={{ serv_config.inp | default("1024") }}
+                        out={{ serv_config.out | default("1024") }}
+                        vllm bench serve --model $model \
+                            --percentile-metrics "ttft,tpot,itl,e2el" \
+                            --dataset-name random \
+                            --ignore-eos \
+                            --max-concurrency $max_concurrency \
+                            --num-prompts $num_prompts \
+                            --random-input-len $in \
+                            --random-output-len $out \
+                            --trust-remote-code \
+                            --save-result \
+                            --result-filename ${model}_serving.json
+
+               {% if acc_config %}
+               .. tab-item:: Accuracy command
+
+                  1. Start the server using the following command:
+
+                     .. code-block:: shell
+
+                        model={{ model.model_repo }}
+                        tp={{ acc_config.tp }}
+                        dtype={{ acc_config.dtype }}
+                        kv_cache_dtype={{ ex_config.kv_cache_dtype }}
+                        max_num_seqs=1024
+                        max_num_batched_tokens={{ ex_config.max_num_batched_tokens }}
+                        max_model_len={{ ex_config.max_model_len }}
+
+                        vllm serve $model \
+                            -tp $tp \
+                            --dtype $dtype \
+                            --kv-cache-dtype $kv_cache_dtype \
+                            --max-num-seqs $max_num_seqs \
+                            --max-num-batched-tokens $max_num_batched_tokens \
+                            --max-model-len $max_model_len \
+                            --no-enable-prefix-caching \
+                            --swap-space 16 \
+                            --disable-log-requests
+
+                     Wait until the model has loaded and the server is ready to accept requests.
+
+                  2. On another terminal on the same machine, run the benchmark:
+
+                     .. code-block:: shell
+
+                        # Connect to the container
+                        docker exec -it test bash
+
+                        # Wait for the server to start
+                        until curl -s http://localhost:8000/v1/models; do sleep 30; done
+
+                        # Install lm-eval
+                        pip install lm-eval[api]
+
+                        # Run the benchmark
+                        model={{ acc_config.model }}
+                        lm_eval --model local-completions \
+                            --model_args model=$model,max_gen_toks=2048,num_concurrent=256,max_retries=10,base_url=http://localhost:8000/v1/completions \
+                            --tasks gsm8k --limit 250 --output_path ./tmp
+
+               {% endif %}

            .. raw:: html

--- a/docs/how-to/rocm-for-ai/system-setup/prerequisite-system-validation.rst
+++ b/docs/how-to/rocm-for-ai/system-setup/prerequisite-system-validation.rst
@@ -31,16 +31,16 @@ in the Instinct documentation for more information.
 Hardware verification with ROCm
 -------------------------------

-Use the command ``rocm-smi --setperfdeterminism 1900`` to set the max clock speed up to 1900 MHz
+Use the command ``amd-smi set --perf-determinism 1900`` to set the max clock speed up to 1900 MHz
 instead of the default 2100 MHz. This can reduce the chance of a PCC event lowering the attainable
 GPU clocks. This setting will not be required for new IFWI releases with the production PRC feature.
-You can restore this setting to its default value with the ``rocm-smi -r`` command.
+You can restore this setting to its default value with the ``amd-smi reset --clocks`` command.

 Run the command:

 .. code-block:: shell

-   rocm-smi --setperfdeterminism 1900
+   amd-smi set --perf-determinism 1900

 See `Hardware verfication for ROCm <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html#hardware-verification-with-rocm>`_
 in the Instinct documentation for more information.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev.rst
@@ -108,16 +108,16 @@ for more information.
 Hardware verification with ROCm
 -------------------------------

-Use the command ``rocm-smi --setperfdeterminism 1900`` to set the max clock speed up to 1900 MHz
+Use the command ``amd-smi set --perf-determinism 1900`` to set the max clock speed up to 1900 MHz
 instead of the default 2100 MHz. This can reduce the chance of a PCC event lowering the attainable
 GPU clocks. This setting will not be required for new IFWI releases with the production PRC feature.
-You can restore this setting to its default value with the ``rocm-smi -r`` command.
+You can restore this setting to its default value with the ``amd-smi reset --clocks`` command.

 Run the command:

 .. code-block:: shell

-   rocm-smi --setperfdeterminism 1900
+   amd-smi set --perf-determinism 1900

 See `Hardware verification with ROCm <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html#hardware-verification-with-rocm>`_ for more information.

@@ -248,7 +248,7 @@ Download the Docker image and required packages
      Checking out this specific commit is recommended for a stable and reproducible environment.

      .. code-block:: shell
-         
+
         git checkout bb93ccbfeae6363c67b361a97a27c74ab86e7e92

 Prepare training datasets
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
@@ -285,7 +285,7 @@ tweak some configurations (such as batch sizes).

                     .. code-block:: shell

-                        EXP=examples/torchtitan/configs/MI355X/llama3.1_8B-BF16-pretrain.yaml \
+                        EXP=examples/torchtitan/configs/MI355X/llama3.1_8B-FP8-pretrain.yaml \
                        bash examples/run_pretrain.sh

                  .. tab-item:: MI325X
--- a/docs/reference/gpu-arch-specs.rst
+++ b/docs/reference/gpu-arch-specs.rst
@@ -5,7 +5,7 @@
 GPU hardware specifications
 ===========================================

-The following tables provide an overview of the hardware specifications for AMD Instinct™ GPUs, and AMD Radeon™ PRO and Radeon™ GPUs.
+The following tables provide an overview of the hardware specifications for AMD Instinct™ GPUs, AMD Radeon™ PRO and Radeon™ GPUs, and AMD Ryzen™ APUs.

 For more information about ROCm hardware compatibility, see the ROCm `Compatibility matrix <https://rocm.docs.amd.com/en/latest/compatibility/compatibility-matrix.html>`_.

@@ -18,7 +18,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
        :name: instinct-arch-spec-table

        *
-          - Model
+          - Name
          - Architecture
          - LLVM target name
          - VRAM (GiB)
@@ -297,7 +297,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
        :name: radeon-pro-arch-spec-table

        *
-          - Model
+          - Name
          - Architecture
          - LLVM target name

@@ -539,7 +539,7 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
        :name: radeon-arch-spec-table

        *
-          - Model
+          - Name
          - Architecture
          - LLVM target name
          - VRAM (GiB)
@@ -953,6 +953,127 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - 9
          - 0

+  .. tab-item:: AMD Ryzen APUs
+
+    .. list-table::
+        :header-rows: 1
+        :name: ryzen-arch-spec-table
+
+        *
+          - Name
+          - Graphics model
+          - Architecture
+          - LLVM target name
+          - VRAM (GiB)
+          - Compute Units
+          - Wavefront Size
+          - LDS (KiB)
+          - Infinity Cache (MiB)
+          - L2 Cache (MiB)
+          - Graphics L1 Cache (KiB)
+          - L0 Vector Cache (KiB)
+          - L0 Scalar Cache (KiB)
+          - L0 Instruction Cache (KiB)
+          - VGPR File (KiB)
+          - SGPR File (KiB)
+          - GFXIP Major version
+          - GFXIP Minor version
+        *
+          - AMD Ryzen 7 7840U
+          - Radeon 780M
+          - RDNA3
+          - gfx1103
+          - Dynamic + carveout
+          - 12
+          - 32 or 64
+          - 128
+          - N/A
+          - 2
+          - 256
+          - 32
+          - 16
+          - 32
+          - 512
+          - 32
+          - 11
+          - 0
+        *
+          - AMD Ryzen 9 270
+          - Radeon 780M
+          - RDNA3
+          - gfx1103
+          - Dynamic + carveout
+          - 12
+          - 32 or 64
+          - 128
+          - N/A
+          - 2
+          - 256
+          - 32
+          - 16
+          - 32
+          - 512
+          - 32
+          - 11
+          - 0
+        *
+          - AMD Ryzen AI 9 HX 375
+          - Radeon 890M
+          - RDNA3.5
+          - gfx1150
+          - Dynamic + carveout
+          - 16
+          - 32 or 64
+          - 128
+          - N/A
+          - 2
+          - 256
+          - 32
+          - 16
+          - 32
+          - 512
+          - 32
+          - 11
+          - 5
+        *
+          - AMD Ryzen AI Max+ PRO 395
+          - Radeon 8060S
+          - RDNA3.5
+          - gfx1151
+          - Dynamic + carveout
+          - 40
+          - 32 or 64
+          - 128
+          - 32
+          - 2
+          - 256
+          - 32
+          - 16
+          - 32
+          - 768
+          - 32
+          - 11
+          - 5
+        *
+          - AMD Ryzen Al 7 350
+          - Radeon 860M
+          - RDNA3.5
+          - gfx1152
+          - Dynamic + carveout
+          - 8
+          - 32 or 64
+          - 128
+          - N/A
+          - 1
+          - 256
+          - 32
+          - 16
+          - 32
+          - 512
+          - 32
+          - 11
+          - 5
+
 Glossary
 ========

--- a/docs/sphinx/_toc.yml.in
+++ b/docs/sphinx/_toc.yml.in
@@ -25,7 +25,7 @@ subtrees:
    title: HIP SDK on Windows
  - url: https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/index.html
    title: ROCm on Radeon and Ryzen
-  - file: how-to/deep-learning-rocm.md
+  - file: how-to/deep-learning-rocm
    title: Deep learning frameworks
    subtrees:
    - entries:
--- a/docs/sphinx/requirements.in
+++ b/docs/sphinx/requirements.in
@@ -1,4 +1,4 @@
-rocm-docs-core==1.31.1
+rocm-docs-core==1.31.2
 sphinx-reredirects
 sphinx-sitemap
 sphinxcontrib.datatemplates==0.11.0
--- a/docs/sphinx/requirements.txt
+++ b/docs/sphinx/requirements.txt
@@ -19,11 +19,11 @@ babel==2.17.0
    # via
    #   pydata-sphinx-theme
    #   sphinx
-beautifulsoup4==4.14.2
+beautifulsoup4==4.14.3
    # via pydata-sphinx-theme
 breathe==4.36.0
    # via rocm-docs-core
-certifi==2025.11.12
+certifi==2026.1.4
    # via requests
 cffi==2.0.0
    # via
@@ -39,7 +39,7 @@ comm==0.2.3
    # via ipykernel
 cryptography==46.0.3
    # via pyjwt
-debugpy==1.8.17
+debugpy==1.8.19
    # via ipykernel
 decorator==5.2.1
    # via ipython
@@ -60,21 +60,21 @@ fastjsonschema==2.21.2
    #   rocm-docs-core
 gitdb==4.0.12
    # via gitpython
-gitpython==3.1.45
+gitpython==3.1.46
    # via rocm-docs-core
-greenlet==3.2.4
+greenlet==3.3.0
    # via sqlalchemy
 idna==3.11
    # via requests
 imagesize==1.4.1
    # via sphinx
-importlib-metadata==8.7.0
+importlib-metadata==8.7.1
    # via
    #   jupyter-cache
    #   myst-nb
 ipykernel==7.1.0
    # via myst-nb
-ipython==8.37.0
+ipython==8.38.0
    # via
    #   ipykernel
    #   myst-nb
@@ -84,13 +84,13 @@ jinja2==3.1.6
    # via
    #   myst-parser
    #   sphinx
-jsonschema==4.25.1
+jsonschema==4.26.0
    # via nbformat
 jsonschema-specifications==2025.9.1
    # via jsonschema
 jupyter-cache==1.0.1
    # via myst-nb
-jupyter-client==8.6.3
+jupyter-client==8.8.0
    # via
    #   ipykernel
    #   nbclient
@@ -118,7 +118,7 @@ myst-nb==1.3.0
    # via rocm-docs-core
 myst-parser==4.0.1
    # via myst-nb
-nbclient==0.10.2
+nbclient==0.10.4
    # via
    #   jupyter-cache
    #   myst-nb
@@ -138,11 +138,11 @@ parso==0.8.5
    # via jedi
 pexpect==4.9.0
    # via ipython
-platformdirs==4.5.0
+platformdirs==4.5.1
    # via jupyter-core
 prompt-toolkit==3.0.52
    # via ipython
-psutil==7.1.3
+psutil==7.2.1
    # via ipykernel
 ptyprocess==0.7.0
    # via pexpect
@@ -188,9 +188,9 @@ requests==2.32.5
    # via
    #   pygithub
    #   sphinx
-rocm-docs-core==1.31.1
+rocm-docs-core==1.31.2
    # via -r requirements.in
-rpds-py==0.29.0
+rpds-py==0.30.0
    # via
    #   jsonschema
    #   referencing
@@ -200,7 +200,7 @@ smmap==5.0.2
    # via gitdb
 snowballstemmer==3.0.1
    # via sphinx
-soupsieve==2.8
+soupsieve==2.8.1
    # via beautifulsoup4
 sphinx==8.1.3
    # via
@@ -250,15 +250,15 @@ sphinxcontrib-runcmd==0.2.0
    # via sphinxcontrib-datatemplates
 sphinxcontrib-serializinghtml==2.0.0
    # via sphinx
-sqlalchemy==2.0.44
+sqlalchemy==2.0.45
    # via jupyter-cache
 stack-data==0.6.3
    # via ipython
 tabulate==0.9.0
    # via jupyter-cache
-tomli==2.3.0
+tomli==2.4.0
    # via sphinx
-tornado==6.5.2
+tornado==6.5.4
    # via
    #   ipykernel
    #   jupyter-client
@@ -282,7 +282,7 @@ typing-extensions==4.15.0
    #   pygithub
    #   referencing
    #   sqlalchemy
-urllib3==2.5.0
+urllib3==2.6.3
    # via
    #   pygithub
    #   requests
--- a/docs/what-is-rocm.rst
+++ b/docs/what-is-rocm.rst
@@ -123,7 +123,8 @@ Performance

 .. note::

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

 Development
 ^^^^^^^^^^^
Author	SHA1	Message	Date
randyh62	2b83a962a0	Use intersphinx links for deep learning (#5859 ) * Use intersphinx links for deep learning * Update deep-learning-rocm.rst remove Taichi * Update deep-learning-rocm.rst Change Install link to "link" * Apply suggestion from @randyh62 OK	2026-01-20 09:17:37 -08:00
Jeffrey Novotny	54bf4c0319	Add missing APU entries to GPU hardware specifications (#646 ) (#5862 ) (#5863 ) * Add missing APU entries to GPU hardware specifications * Move Ryzen APUs to new tab * Add new column to Ryzen table and rename column elsewhere --------- (cherry picked from commit `7ab402a3b3`) (cherry picked from commit `33fbde69db`) Co-authored-by: alexxu-amd <159800977+alexxu-amd@users.noreply.github.com>	2026-01-16 13:02:06 -05:00
peterjunpark	4347a11bc4	Doc update for vLLM refactor #5855 (#5856 ) (cherry picked from commit `a745e45dcb`)	2026-01-15 11:34:02 -05:00
ROCm Docs Automation	2b7fde505f	Update rocm-docs-core to 1.31.2	2026-01-14 11:26:11 -05:00
anisha-amd	a98d6a5777	Docs: Ray release 25.12 and compatibility version format standardization (#5845 ) (#5846 )	2026-01-08 12:29:00 -05:00
Swati Rawat	38b271df55	Merge pull request #5843 from SwRaw/sw_cherrypick Cherrypicking amd-smi updates from ROCm internal	2026-01-08 20:33:14 +05:30
Swati Rawat	4184d1ee1f	Update docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev.rst Co-authored-by: peterjunpark <git@peterjunpark.com>	2026-01-08 16:46:22 +05:30
Swati Rawat	0786c328c1	Update docs/how-to/rocm-for-ai/system-setup/prerequisite-system-validation.rst Co-authored-by: peterjunpark <git@peterjunpark.com>	2026-01-08 16:46:22 +05:30
Swati Rawat	88ea6072f5	Update docs/how-to/rocm-for-ai/system-setup/prerequisite-system-validation.rst Co-authored-by: peterjunpark <git@peterjunpark.com>	2026-01-08 16:46:22 +05:30
Swati Rawat	b32dcc8570	Update docs/how-to/rocm-for-ai/system-setup/prerequisite-system-validation.rst Co-authored-by: peterjunpark <git@peterjunpark.com>	2026-01-08 16:46:22 +05:30
Swati Rawat	0faa92e922	Update docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev.rst Co-authored-by: peterjunpark <git@peterjunpark.com>	2026-01-08 16:46:21 +05:30
Swati Rawat	26ae989602	Update docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev.rst Co-authored-by: peterjunpark <git@peterjunpark.com>	2026-01-08 16:46:21 +05:30
srawat	4402dc4147	Update single-gpu-fine-tuning-and-inference.rst	2026-01-08 16:46:21 +05:30
srawat	5eda438e0a	Update multi-gpu-fine-tuning-and-inference.rst	2026-01-08 16:46:20 +05:30
srawat	049784e1a7	Update prerequisite-system-validation.rst	2026-01-08 16:42:18 +05:30
srawat	f12169c5b7	replace rocm-smi reference with amd-smi	2026-01-08 16:42:18 +05:30
peterjunpark	b35d1a0627	fix(primus-pytorch.rst): FP8 config instead of BF16 (#5839 ) (cherry picked from commit `2dc22ca890`)	2026-01-07 13:51:50 -05:00
Pratik Basyal	912618cb08	ROCM-core version fixed (#5827 ) (#5828 )	2026-01-02 16:10:16 -05:00
peterjunpark	7d2feaa8b1	Fix inconsistency in xDiT doc (#5823 ) Fix inconsistency in xDiT doc (cherry picked from commit `172b0f7c08`)	2025-12-29 10:29:59 -05:00
peterjunpark	7d0d114994	Merge pull request #5821 from peterjunpark/docs/7.1.1 [docs/7.1.1] Add xDiT and Primus doc updates	2025-12-29 08:49:44 -05:00
peterjunpark	2a65394e32	Update docs for xDiT diffusion inference 25.13 Docker release (#5820 ) * archive previous version * add xdit 25.13 * update history index * add perf results section (cherry picked from commit `c67fac78bd`)	2025-12-29 08:45:29 -05:00
peterjunpark	268c1332c9	Update training docs for Primus/25.11 (#5819 ) * update conf and toc.yml.in * archive previous versions archive data files update anchors * primus pytorch: remove training batch size args * update primus megatron run cmds multi-node * update primus pytorch update * update update * update docker tag (cherry picked from commit `e0b8ec4dfb`)	2025-12-29 08:45:17 -05:00
Pratik Basyal	374e0944dc	OS table removed from compatibility table [develop] (#5810 ) (#5811 ) * OS table removed from compatibility table * Feedback added * Azure Linux 3.0 and compatibility version update * Version fix * Review feedback added * Minor change	2025-12-23 16:38:03 -05:00
peterjunpark	512e311041	Update xdit diffusion inference history (#5808 ) (#5809 ) * Update xdit diffusion inference history * fix (cherry picked from commit `3a43bacdda`)	2025-12-22 11:14:57 -05:00
peterjunpark	ad4f486635	fix link to ROCm PyT docker image (#5803 ) (#5804 ) (cherry picked from commit `48d8fe139b`)	2025-12-19 15:51:20 -05:00
peterjunpark	485886712b	clean up formatting in FA2 page (#5795 ) (#5796 ) (cherry picked from commit `7455fe57b8`)	2025-12-19 09:38:20 -05:00
peterjunpark	1cd6a14a22	Update Flash Attention guidance in "Model acceleration libraries" (#5793 ) * flash attention update Signed-off-by: seungrok.jung <seungrok.jung@amd.com> flash attention update Signed-off-by: seungrok.jung <seungrok.jung@amd.com> flash attention update Signed-off-by: seungrok.jung <seungrok.jung@amd.com> sentence-case heading * Update docs/how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries.rst Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com> * Apply suggestions from code review Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com> --------- Co-authored-by: seungrok.jung <seungrok.jung@amd.com> Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com> (cherry picked from commit `52c0a47e84`)	2025-12-19 09:00:40 -05:00
peterjunpark	a17f04a3b5	Update documentation for JAX training MaxText 25.11 release (#5789 ) (#5790 ) (cherry picked from commit `cbab9a465d`)	2025-12-18 11:26:42 -05:00
peterjunpark	94de66ef3f	[docs/7.1.1] Publish vLLM and xDiT doc updates (#5787 ) * vLLM inference benchmark 1210 (#5776) * Archive previous ver fix anchors * Update vllm.rst and data yaml for 20251210 (cherry picked from commit `1b4f25733d`) * xDiT diffusion inference v25.12 documentation update (#5786) * Add xdit-diffusion ROCm docs page. * Update template formatting and fix sphinx warnings * Add System Validation section. * Add sw component versions/commits. * Update to use latest v25.10 image instead of v25.9 * Update commands and add FLUX instructions. * Update Flux instructions. Change image tag. Describe as diffusion inference instead of specifically video. * git rm xdit-video-diffusion.rst * Docs for v25.12 * Add hyperlinks to components * Command fixes * -Diffusers suffix * Simplify yaml file and cleanup main rst page. * Spelling, added 'js' * fix merge conflict fix --------- Co-authored-by: Kristoffer <kristoffer.torp@amd.com> (cherry picked from commit `459283da3c`) --------- Co-authored-by: Kristoffer <kristoffer.torp@amd.com>	2025-12-17 10:28:30 -05:00
Pratik Basyal	e5cebe7b4e	Taichi removed from ROCm docs [Develop] (#5779 ) (#5781 ) * Taichi removed from ROCm docs * Warnings fixed	2025-12-16 13:24:12 -05:00
Pratik Basyal	7047cfa19c	Onnx and rocshmem version updated (#5760 ) (#5764 )	2025-12-11 17:11:05 -05:00
Matt Williams	de71bf5fa7	Merge pull request #5759 from ROCm/cherry-pick-701 Fixing link redirects (#5758)	2025-12-10 11:39:53 -05:00
Matt Williams	0d17c96f7f	Fixing link redirects (#5758 ) * Update multi-gpu-fine-tuning-and-inference.rst * Update pytorch-training-v25.6.rst * Update pytorch-compatibility.rst	2025-12-10 11:31:26 -05:00
anisha-amd	2f8c99f7f0	Docs: update verl compatibility - fix (#5755 )	2025-12-09 19:52:12 -05:00
anisha-amd	982927e866	Docs: verl framework - compatibility - 25.11 release (#5752 ) (#5753 )	2025-12-09 12:02:20 -05:00
peterjunpark	8f45b791fe	Fix Primus PyTorch doc: training.batch_size -> training.local_batch_size (#5748 ) (#5749 ) (cherry picked from commit `bf74351e5a`)	2025-12-08 13:59:00 -05:00
yugang-amd	f7c7587b10	xdit-diffusion v25.11 docs (#5743 )	2025-12-05 17:08:21 -05:00
Pratik Basyal	96b3c0d4f3	PyTorch 2.7 support added (#5740 ) (#5741 )	2025-12-04 17:00:34 -05:00
peterjunpark	d6d4d2ef92	fix docker hub links for primus:v25.10 (#5738 ) (cherry picked from commit `453751a86f`)	2025-12-04 09:21:53 -05:00
peterjunpark	8647ebcf76	Update training Docker docs for Primus 25.10 (#5737 ) (cherry picked from commit `fb644412d5`)	2025-12-04 09:21:53 -05:00
Pratik Basyal	48ca38b0dc	Conflict resolved (#5735 )	2025-12-03 09:02:57 -05:00
Istvan Kiss	acbd671e99	JAX key features and enhancements (#5708 ) Co-authored-by: Pratik Basyal <prbasyal@amd.com>	2025-12-01 19:52:07 +01:00
Pratik Basyal	133a97ec18	711 post GA known issue update [docs/711] (#5723 ) * 7.1.1 known issues post GA (#5721) * rocblas known issues added * Minor change * Update RELEASE.md Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> * Resolved * Update RELEASE.md Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com> --------- Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com> * GitHub Issue added --------- Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> Co-authored-by: Leo Paoletti <164940351+lpaoletti@users.noreply.github.com>	2025-11-30 00:16:26 -05:00
Pratik Basyal	2d40066f29	Merged cell removed for coloring issue (#5713 ) (#5714 )	2025-11-27 20:03:11 -05:00
ROCm Docs Automation	5d7fdace0e	Update rocm-docs-core to 1.30.0	2025-11-26 17:09:50 -05:00
Istvan Kiss	7dbcdc5deb	Update release notes links ROCm 7.1.1 (#5705 )	2025-11-26 20:02:33 +01:00
Pratik Basyal	a966db29ca	Known issue from 7.1.0 removed (#5702 ) (#5703 )	2025-11-26 12:30:28 -05:00
Pratik Basyal	9ea8a48b3a	Link and PyTorch version updated (#5700 ) (#5701 )	2025-11-26 12:01:12 -05:00
Alex Xu	9956d72614	fix dependency	2025-11-26 11:42:22 -05:00
Alex Xu	305d24f486	Merge branch 'roc-7.1.x' into docs/7.1.1	2025-11-26 11:37:06 -05:00
Alex Xu	26f6b6b3e1	Merge branch 'roc-7.1.x' into docs/7.1.1	2025-11-26 11:29:02 -05:00
Alex Xu	d4cdbd79a3	Merge branch 'develop' into docs/7.1.1	2025-11-26 08:47:19 -05:00
alexxu-amd	26d1ab7d27	Update documentation requirements	2025-11-25 16:30:46 -05:00
alexxu-amd	272c9f6be3	Update documentation requirements	2025-11-25 15:37:04 -05:00