Apply suggestion from @randyh62

OK
2026-01-15 15:53:46 -08:00 · 2026-01-15 15:53:00 -08:00 · 2026-01-15 15:52:14 -08:00 · 2026-01-15 15:48:31 -08:00 · 2026-01-15 11:21:38 -05:00 · 2026-01-14 16:55:26 -05:00
23 changed files with 1118 additions and 296 deletions
@@ -34,6 +34,7 @@ parameters:
  default:
    - cmake
    - libnuma-dev
+    - libsimde-dev
    - mesa-common-dev
    - ninja-build
    - ocl-icd-libopencl1
@@ -39,6 +39,7 @@ parameters:
    - python3
    - python3-dev
    - python3-pip
+    - python3-venv
    - libgtest-dev
    - libboost-filesystem-dev
    - libboost-program-options-dev
@@ -46,6 +47,8 @@ parameters:
  type: object
  default:
    - nanobind>=2.0.0
+    - pytest
+    - pytest-cov
 - name: rocmDependencies
  type: object
  default:
@@ -72,8 +75,10 @@ parameters:
      - { os: ubuntu2204, packageManager: apt }
      - { os: almalinux8, packageManager: dnf }
    testJobs:
-      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1151 }
+      # - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
 - name: downstreamComponentMatrix
  type: object
  default:
@@ -116,6 +121,11 @@ jobs:
      parameters:
        dependencyList:
          - gtest
+    - ${{ if ne(job.os, 'almalinux8') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+        parameters:
+          dependencyList:
+            - catch2
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
@@ -137,6 +147,7 @@ jobs:
          -DORIGAMI_BUILD_SHARED_LIBS=ON
          -DORIGAMI_ENABLE_PYTHON=ON
          -DORIGAMI_BUILD_TESTING=ON
+          -DORIGAMI_ENABLE_FETCH=ON
          -GNinja
    - ${{ if ne(job.os, 'almalinux8') }}:
      - task: PublishPipelineArtifact@1
@@ -169,7 +180,6 @@ jobs:
      dependsOn: origami_build_${{ job.os }}
      condition:
        and(succeeded(),
-          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
          eq(${{ parameters.aggregatePipeline }}, False)
        )
@@ -180,30 +190,30 @@ jobs:
      workspace:
        clean: all
      steps:
-      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-        parameters:
-          checkoutRepo: ${{ parameters.checkoutRepo }}
-          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
        parameters:
          aptPackages: ${{ parameters.aptPackages }}
          pipModules: ${{ parameters.pipModules }}
          packageManager: ${{ job.packageManager }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+        parameters:
+          dependencyList:
+            - gtest
+      - ${{ if ne(job.os, 'almalinux8') }}:
+        - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+          parameters:
+            dependencyList:
+              - catch2
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
        parameters:
          preTargetFilter: ${{ parameters.componentName }}
          os: ${{ job.os }}
-      - task: DownloadPipelineArtifact@2
-        displayName: 'Download Build Directory Artifact'
-        inputs:
-          artifact: '${{ parameters.componentName }}_${{ job.os }}_build_dir'
-          path: '$(Agent.BuildDirectory)/s/build'
-      - task: DownloadPipelineArtifact@2
-        displayName: 'Download Python Source Artifact'
-        inputs:
-          artifact: '${{ parameters.componentName }}_${{ job.os }}_python_src'
-          path: '$(Agent.BuildDirectory)/s/python'
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
        parameters:
          checkoutRef: ${{ parameters.checkoutRef }}
@@ -212,25 +222,72 @@ jobs:
          gpuTarget: ${{ job.target }}
          ${{ if parameters.triggerDownstreamJobs }}:
            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - task: CMake@1
+        displayName: 'Origami Test CMake Configuration'
+        inputs:
+          cmakeArgs: >-
+            -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
+            -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+            -DORIGAMI_BUILD_SHARED_LIBS=ON
+            -DORIGAMI_ENABLE_PYTHON=ON
+            -DORIGAMI_BUILD_TESTING=ON
+            -GNinja
+            $(Agent.BuildDirectory)/s
+      - task: Bash@3
+        displayName: 'Build Origami Tests and Python Bindings'
+        inputs:
+          targetType: inline
+          workingDirectory: build
+          script: |
+            cmake --build . --target origami-tests origami_python -- -j$(nproc)
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      # Run tests using CTest (discovers and runs both C++ and Python tests)
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
        parameters:
          componentName: ${{ parameters.componentName }}
          os: ${{ job.os }}
-          testDir: '$(Agent.BuildDirectory)/rocm/bin'
-          testExecutable: './origami-tests'
-          testParameters: '--yaml origami-tests.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
-      - script: |
-          set -e
-          export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH
-
-          echo "--- Running origami_test.py ---"
-          python3 $(Agent.BuildDirectory)/s/python/origami_test.py
-          
-          echo "--- Running origami_grid_test.py ---"
-          python3 $(Agent.BuildDirectory)/s/python/origami_grid_test.py
-        displayName: 'Run Python Binding Tests'
-        condition: succeeded()
+          testDir: 'build'
+          testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+      # Test pip install workflow
+      # - task: Bash@3
+      #   displayName: 'Test Pip Install'
+      #   inputs:
+      #     targetType: inline
+      #     script: |
+      #       set -e
+            
+      #       echo "==================================================================="
+      #       echo "Testing pip install workflow (pip install -e .)"
+      #       echo "==================================================================="
+            
+      #       # Set environment variables for pip install CMake build
+      #       export ROCM_PATH=$(Agent.BuildDirectory)/rocm
+      #       export CMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm:$(Agent.BuildDirectory)/vendor
+      #       export CMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+            
+      #       echo "ROCM_PATH: $ROCM_PATH"
+      #       echo "CMAKE_PREFIX_PATH: $CMAKE_PREFIX_PATH"
+      #       echo "CMAKE_CXX_COMPILER: $CMAKE_CXX_COMPILER"
+      #       echo ""
+            
+      #       # Install from source directory
+      #       cd "$(Agent.BuildDirectory)/s/python"
+      #       pip install -e .
+            
+      #       # Verify import works
+      #       echo ""
+      #       echo "Verifying origami can be imported..."
+      #       python3 -c "import origami; print('✓ Successfully imported origami')"
+            
+      #       # Run pytest on installed package
+      #       echo ""
+      #       echo "Running pytest tests..."
+      #       python3 -m pytest tests/ -v -m "not slow" --tb=short
+            
+      #       echo ""
+      #       echo "==================================================================="
+      #       echo "Pip install test completed successfully"
+      #       echo "==================================================================="
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
        parameters:
          aptPackages: ${{ parameters.aptPackages }}
@@ -30,6 +30,7 @@ parameters:
    - python3-pip
    - protobuf-compiler
    - libprotoc-dev
+    - libopencv-dev
 - name: pipModules
  type: object
  default:
@@ -64,6 +65,7 @@ parameters:
    - MIVisionX
    - rocm_smi_lib
    - rccl
+    - rocAL
    - rocALUTION
    - rocBLAS
    - rocDecode
@@ -103,6 +105,7 @@ parameters:
    - MIVisionX
    - rocm_smi_lib
    - rccl
+    - rocAL
    - rocALUTION
    - rocBLAS
    - rocDecode
@@ -36,7 +36,6 @@ Andrej
 Arb
 Autocast
 autograd
-Backported
 BARs
 BatchNorm
 BLAS
@@ -204,11 +203,9 @@ GenAI
 GenZ
 GitHub
 Gitpod
-hardcoded
 HBM
 HCA
 HGX
-HLO
 HIPCC
 hipDataType
 HIPExtension
@@ -336,7 +333,6 @@ MoEs
 Mooncake
 Mpops
 Multicore
-multihost
 Multithreaded
 mx
 MXFP
@@ -1031,7 +1027,6 @@ uncacheable
 uncorrectable
 underoptimized
 unhandled
-unfused
 uninstallation
 unmapped
 unsqueeze
@@ -239,6 +239,9 @@ ROCm 7.1.1 enables support for PyTorch 2.9. For more information, see [PyTorch c

 Deep Graph Library [(DGL)](https://www.dgl.ai/) is an easy-to-use, high-performance, and scalable Python package for deep learning on graphs. DGL is framework agnostic, meaning that if a deep graph model is a component in an end-to-end application, the rest of the logic is implemented using PyTorch. It's supported on ROCm 7.0.0, ROCm 6.4.3, and ROCm 6.4.0. For more information, see [DGL compatibility](https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/dgl-compatibility.html).

+#### llama.cpp
+
+llama.cpp is an open-source framework for Large Language Model (LLM) inference that runs on both central processing units (CPUs) and graphics processing units (GPUs). It is written in plain C/C++, providing a simple, dependency-free setup. It's supported on ROCm 7.0.0 and ROCm 6.4.x. For more information, see [llama.cpp compatibility](https://rocm.docs.amd.com/en/latest/compatibility/ml-compatibility/llama-cpp-compatibility.html).

 ### ROCm Offline Installer Creator updates
 
@@ -267,26 +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://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)
+* [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/)
 :::
 :::{grid}
 :margin: auto 0 auto auto
-* [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)
+* [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/)
 :::
 ::::

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

-* [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)
+* [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)

-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.
+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.

 ### ROCm documentation updates

@@ -33,7 +33,13 @@ 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:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.9, 2.8, 2.7","2.8, 2.7, 2.6","2.8, 2.7, 2.6","2.7, 2.6, 2.5","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.7.1,0.7.1,0.6.0,0.6.0,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
+      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat-past-60]_,N/A,N/A,N/A,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat-past-60]_,N/A,N/A,N/A,2.4.0,2.4.0,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,N/A,2.51.1,N/A,N/A,2.48.0.post0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat-past-60]_,N/A,N/A,N/A,b6652,b6356,b6356,b6356,b5997,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>` [#flashinfer_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,v0.2.5,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.1,1.22.0,1.22.0,1.22.0,1.20.0,1.20.0,1.20.0,1.20.0,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
      ,,,,,,,,,,,,,,,,,,,,,,
      ,,,,,,,,,,,,,,,,,,,,,,
@@ -58,6 +58,7 @@ compatibility and system requirements.
      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.18.1, 2.17.1, 2.16.2"
      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.7.1,0.7.1,0.4.35
      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,2.4.0
+      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat]_,N/A,N/A,b5997
      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.1,1.22.0,1.20.0
      ,,,
      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
@@ -157,6 +158,7 @@ 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 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>`_.
@@ -202,7 +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 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>`_.
@@ -0,0 +1,98 @@
+:orphan:
+
+.. meta::
+    :description: FlashInfer compatibility
+    :keywords: GPU, LLM, FlashInfer, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+FlashInfer compatibility
+********************************************************************************
+
+`FlashInfer <https://docs.flashinfer.ai/index.html>`__ is a library and kernel generator 
+for Large Language Models (LLMs) that provides a high-performance implementation of graphics 
+processing units (GPUs) kernels. FlashInfer focuses on LLM serving and inference, as well 
+as advanced performance across diverse scenarios.
+
+FlashInfer features highly efficient attention kernels, load-balanced scheduling, and memory-optimized 
+techniques, while supporting customized attention variants. It’s compatible with ``torch.compile``, and 
+offers high-performance LLM-specific operators, with easy integration through PyTorch, and C++ APIs.
+
+.. note::
+
+  The ROCm port of FlashInfer is under active development, and some features are not yet available. 
+  For the latest feature compatibility matrix, refer to the ``README`` of the 
+  `https://github.com/ROCm/flashinfer <https://github.com/ROCm/flashinfer>`__ repository.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of FlashInfer is maintained in the official `https://github.com/ROCm/flashinfer 
+  <https://github.com/ROCm/flashinfer>`__ repository, which differs from the 
+  `https://github.com/flashinfer-ai/flashinfer <https://github.com/flashinfer-ai/flashinfer>`__ 
+  upstream repository.
+
+- To get started and install FlashInfer on ROCm, use the prebuilt :ref:`Docker images <flashinfer-docker-compat>`, 
+  which include ROCm, FlashInfer, and all required dependencies.
+
+  - See the :doc:`ROCm FlashInfer installation guide <rocm-install-on-linux:install/3rd-party/flashinfer-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://docs.flashinfer.ai/installation.html>`__ 
+    for additional context.
+
+.. _flashinfer-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `FlashInfer images <https://hub.docker.com/r/rocm/flashinfer/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tag and associated
+inventories represent the latest available FlashInfer version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - FlashInfer
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/flashinfer/flashinfer-0.2.5_rocm6.4_ubuntu24.04_py3.12_pytorch2.7/images/sha256-558914838821c88c557fb6d42cfbc1bdb67d79d19759f37c764a9ee801f93313"><i class="fab fa-docker fa-lg"></i> rocm/flashinfer</a>
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - `v0.2.5 <https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.2.5>`__
+      - `2.7.1 <https://github.com/ROCm/pytorch/releases/tag/v2.7.1>`__
+      - 24.04
+      - `3.12 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X
+
+.. _flashinfer-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+The release of FlashInfer on ROCm provides the decode functionality for LLM inferencing.
+In the decode phase, tokens are generated sequentially, with the model predicting each new 
+token based on the previously generated tokens and the input context.
+
+FlashInfer on ROCm brings over upstream features such as load balancing, sparse and dense 
+attention optimizations, and batching support, enabling efficient execution on AMD Instinct™ MI300X GPUs.
+
+Because large LLMs often require substantial KV caches or long context windows, FlashInfer on ROCm 
+also implements cascade attention from upstream to reduce memory usage. 
+
+For currently supported use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for examples and best practices to optimize your workloads on AMD GPUs.
+
@@ -269,33 +269,6 @@ 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
 ===============================================================================

@@ -0,0 +1,275 @@
+:orphan:
+
+.. meta::
+    :description: llama.cpp compatibility
+    :keywords: GPU, GGML, llama.cpp, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+llama.cpp compatibility
+********************************************************************************
+
+`llama.cpp <https://github.com/ggml-org/llama.cpp>`__ is an open-source framework 
+for Large Language Model (LLM) inference that runs on both central processing units 
+(CPUs) and graphics processing units (GPUs). It is written in plain C/C++, providing 
+a simple, dependency-free setup. 
+
+The framework supports multiple quantization options, from 1.5-bit to 8-bit integers, 
+to accelerate inference and reduce memory usage. Originally built as a CPU-first library, 
+llama.cpp is easy to integrate with other programming environments and is widely 
+adopted across diverse platforms, including consumer devices. 
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of llama.cpp is maintained in the official `https://github.com/ROCm/llama.cpp 
+  <https://github.com/ROCm/llama.cpp>`__ repository, which differs from the 
+  `https://github.com/ggml-org/llama.cpp <https://github.com/ggml-org/llama.cpp>`__ upstream repository.
+
+- To get started and install llama.cpp on ROCm, use the prebuilt :ref:`Docker images <llama-cpp-docker-compat>`, 
+  which include ROCm, llama.cpp, and all required dependencies.
+
+  - See the :doc:`ROCm llama.cpp installation guide <rocm-install-on-linux:install/3rd-party/llama-cpp-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md>`__ 
+    for additional context.
+
+.. _llama-cpp-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `llama.cpp images <https://hub.docker.com/r/rocm/llama.cpp/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest available llama.cpp versions from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. important::
+
+   Tag endings of ``_full``, ``_server``, and ``_light`` serve different purposes for entrypoints as follows:
+
+   - Full: This image includes both the main executable file and the tools to convert ``LLaMA`` models into ``ggml`` and convert into 4-bit quantization.
+   - Server: This image only includes the server executable file.
+   - Light: This image only includes the main executable file.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Full Docker
+      - Server Docker
+      - Light Docker
+      - llama.cpp
+      - ROCm
+      - Ubuntu
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_full/images/sha256-a94f0c7a598cc6504ff9e8371c016d7a2f93e69bf54a36c870f9522567201f10g"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_server/images/sha256-be175932c3c96e882dfbc7e20e0e834f58c89c2925f48b222837ee929dfc47ee"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_light/images/sha256-d8ba0c70603da502c879b1f8010b439c8e7fa9f6cbdac8bbbbbba97cb41ebc9e"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6652 <https://github.com/ROCm/llama.cpp/tree/release/b6652>`__
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_full/images/sha256-37582168984f25dce636cc7288298e06d94472ea35f65346b3541e6422b678ee"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_server/images/sha256-7e70578e6c3530c6591cc2c26da24a9ee68a20d318e12241de93c83224f83720"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_light/images/sha256-9a5231acf88b4a229677bc2c636ea3fe78a7a80f558bd80910b919855de93ad5"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6652 <https://github.com/ROCm/llama.cpp/tree/release/b6652>`__
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_full/images/sha256-5960fc850024a8a76451f9eaadd89b7e59981ae9f393b407310c1ddf18892577"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_server/images/sha256-1b79775d9f546065a6aaf9ca426e1dd4ed4de0b8f6ee83687758cc05af6538e6"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_light/images/sha256-8f863c4c2857ae42bebd64e4f1a0a1e7cc3ec4503f243e32b4a4dcad070ec361"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_full/images/sha256-888879b3ee208f9247076d7984524b8d1701ac72611689e89854a1588bec9867"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_server/images/sha256-90e4ff99a66743e33fd00728cd71a768588e5f5ef355aaa196669fe65ac70672"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_light/images/sha256-bd447a049939cb99054f8fbf3f2352870fe906a75e2dc3339c845c08b9c53f9b"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_full/images/sha256-5b3a1bc4889c1fcade434b937fbf9cc1c22ff7dc0317c130339b0c9238bc88c4"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_server/images/sha256-5228ff99d0f627a9032d668f4381b2e80dc1e301adc3e0821f26d8354b175271"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_light/images/sha256-b12723b332a826a89b7252dddf868cbe4d1a869562fc4aa4032f59e1a683b968"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_full/images/sha256-cd6e21a6a73f59b35dd5309b09dd77654a94d783bf13a55c14eb8dbf8e9c2615"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_server/images/sha256-c2b4689ab2c47e6626e8fea22d7a63eb03d47c0fde9f5ef8c9f158d15c423e58"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_light/images/sha256-1acc28f29ed87db9cbda629cb29e1989b8219884afe05f9105522be929e94da4"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_full/images/sha256-2f8ae8a44510d96d52dea6cb398b224f7edeb7802df7ec488c6f63d206b3cdc9"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_server/images/sha256-fece497ff9f4a28b12f645de52766941da8ead8471aa1ea84b61d4b4568e51f2"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_light/images/sha256-3e14352fa6f8c6128b23cf9342531c20dbfb522550b626e09d83b260a1947022"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_full/images/sha256-80763062ef0bec15038c35fd01267f1fc99a5dd171d4b48583cc668b15efad69"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_server/images/sha256-db2a6c957555ed83b819bbc54aea884a93192da0fb512dae63d32e0dc4e8ab8f"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_light/images/sha256-c6dbb07cc655fb079d5216e4b77451cb64a9daa0585d23b6fb8b32cb22021197"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_full/images/sha256-f78f6c81ab2f8e957469415fe2370a1334fe969c381d1fe46050c85effaee9d5"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_server/images/sha256-275ad9e18f292c26a00a2de840c37917e98737a88a3520bdc35fd3fc5c9a6a9b"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_light/images/sha256-cc324e6faeedf0e400011f07b49d2dc41a16bae257b2b7befa0f4e2e97231320"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b5997 <https://github.com/ROCm/llama.cpp/tree/release/b5997>`__
+      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__
+      - 24.04
+      - MI300X, MI210
+
+.. _llama-cpp-key-rocm-libraries:
+
+Key ROCm libraries for llama.cpp
+================================================================================
+
+llama.cpp functionality on ROCm is determined by its underlying library
+dependencies. These ROCm components affect the capabilities, performance, and
+feature set available to developers. Ensure you have the required libraries for 
+your corresponding ROCm version.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - ROCm 7.0.0 version
+      - ROCm 6.4.x version
+      - Purpose
+      - Usage
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`__
+      - 3.0.0
+      - 2.4.0
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Supports operations such as matrix multiplication, matrix-vector
+        products, and tensor contractions. Utilized in both dense and batched
+        linear algebra operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`__
+      - 1.0.0
+      - 0.12.0
+      - hipBLASLt is an extension of the hipBLAS library, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+      - By setting the flag ``ROCBLAS_USE_HIPBLASLT``, you can dispatch hipblasLt
+        kernels where possible.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`__
+      - 2.0.0
+      - 1.7.0
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+      - Can be used to enhance the flash attention performance on AMD compute, by enabling
+        the flag during compile time.
+
+.. _llama-cpp-uses-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+llama.cpp can be applied in a variety of scenarios, particularly when you need to meet one or more of the following requirements:
+
+- Plain C/C++ implementation with no external dependencies
+- Support for 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory usage
+- Custom HIP (Heterogeneous-compute Interface for Portability) kernels for running large language models (LLMs) on AMD GPUs (graphics processing units)
+- CPU (central processing unit) + GPU (graphics processing unit) hybrid inference for partially accelerating models larger than the total available VRAM (video random-access memory)
+
+llama.cpp is also used in a range of real-world applications, including:
+
+- Games such as `Lucy's Labyrinth <https://github.com/MorganRO8/Lucys_Labyrinth>`__:
+  A simple maze game where AI-controlled agents attempt to trick the player.
+- Tools such as `Styled Lines <https://marketplace.unity.com/packages/tools/ai-ml-integration/style-text-webgl-ios-stand-alone-llm-llama-cpp-wrapper-292902>`__:
+  A proprietary, asynchronous inference wrapper for Unity3D game development, including pre-built mobile and web platform wrappers and a model example.
+- Various other AI applications use llama.cpp as their inference engine;  
+  for a detailed list, see the `user interfaces (UIs) section <https://github.com/ggml-org/llama.cpp?tab=readme-ov-file#description>`__.
+
+For more use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for llama.cpp examples and best practices to optimize your workloads on AMD GPUs.
+
+- The `Llama.cpp Meets Instinct: A New Era of Open-Source AI Acceleration <https://rocm.blogs.amd.com/ecosystems-and-partners/llama-cpp/README.html>`__ 
+  blog post outlines how the open-source llama.cpp framework enables efficient LLM inference—including interactive inference with ``llama-cli``, 
+  server deployment with ``llama-server``, GGUF model preparation and quantization, performance benchmarking, and optimizations tailored for 
+  AMD Instinct GPUs within the ROCm ecosystem. 
+
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/llama-cpp-history` to find documentation for previous releases
+of the ``ROCm/llama.cpp`` Docker image.
@@ -0,0 +1,104 @@
+:orphan:
+
+.. meta::
+    :description: Megablocks compatibility
+    :keywords: GPU, megablocks, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+Megablocks compatibility
+********************************************************************************
+
+`Megablocks <https://github.com/databricks/megablocks>`__ is a lightweight library 
+for mixture-of-experts `(MoE) <https://huggingface.co/blog/moe>`__ training. 
+The core of the system is efficient "dropless-MoE" and standard MoE layers. 
+Megablocks is integrated with `https://github.com/stanford-futuredata/Megatron-LM 
+<https://github.com/stanford-futuredata/Megatron-LM>`__, 
+where data and pipeline parallel training of MoEs is supported.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Megablocks is maintained in the official `https://github.com/ROCm/megablocks 
+  <https://github.com/ROCm/megablocks>`__ repository, which differs from the 
+  `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`__ upstream repository.
+
+- To get started and install Megablocks on ROCm, use the prebuilt :ref:`Docker image <megablocks-docker-compat>`, 
+  which includes ROCm, Megablocks, and all required dependencies.
+
+  - See the :doc:`ROCm Megablocks installation guide <rocm-install-on-linux:install/3rd-party/megablocks-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/databricks/megablocks>`__ 
+    for additional context.
+
+.. _megablocks-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `Megablocks images <https://hub.docker.com/r/rocm/megablocks/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tag and associated
+inventories represent the latest available Megablocks version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Megablocks
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/megablocks/megablocks-0.7.0_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-372ff89b96599019b8f5f9db469c84add2529b713456781fa62eb9a148659ab4"><i class="fab fa-docker fa-lg"></i> rocm/megablocks</a>
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `0.7.0 <https://github.com/databricks/megablocks/releases/tag/v0.7.0>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - MI300X
+
+Supported models and features with ROCm 6.3.0
+================================================================================
+
+This section summarizes the Megablocks features supported by ROCm.
+
+* Distributed Pre-training
+* Activation Checkpointing and Recomputation
+* Distributed Optimizer
+* Mixture-of-Experts
+* dropless-Mixture-of-Experts
+
+.. _megablocks-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+* The `Efficient MoE training on AMD ROCm: How-to use Megablocks on AMD GPUs 
+  <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`__ 
+  blog post guides how to leverage the ROCm platform for pre-training using the 
+  Megablocks framework. It introduces a streamlined approach for training Mixture-of-Experts 
+  (MoE) models using the Megablocks library on AMD hardware. Focusing on GPT-2, it 
+  demonstrates how block-sparse computations can enhance scalability and efficiency in MoE 
+  training. The guide provides step-by-step instructions for setting up the environment, 
+  including cloning the repository, building the Docker image, and running the training container. 
+  Additionally, it offers insights into utilizing the ``oscar-1GB.json`` dataset for pre-training 
+  language models. By leveraging Megablocks and the ROCm platform, you can optimize your MoE 
+  training workflows for large-scale transformer models.
+
+It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
+
+* Single-GPU pre-training
+* Multi-GPU pre-training
+
@@ -0,0 +1,114 @@
+:orphan:
+
+.. meta::
+    :description: Ray compatibility
+    :keywords: GPU, Ray, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+Ray compatibility
+*******************************************************************************
+
+Ray is a unified framework for scaling AI and Python applications from your laptop 
+to a full cluster, without changing your code. Ray consists of `a core distributed 
+runtime  <https://docs.ray.io/en/latest/ray-core/walkthrough.html>`__ and a set of 
+`AI libraries <https://docs.ray.io/en/latest/ray-air/getting-started.html>`__ for 
+simplifying machine learning computations.
+
+Ray is a general-purpose framework that runs many types of workloads efficiently. 
+Any Python application can be scaled with Ray, without extra infrastructure.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Ray is maintained in the official `https://github.com/ROCm/ray 
+  <https://github.com/ROCm/ray>`__ repository, which differs from the 
+  `https://github.com/ray-project/ray <https://github.com/ray-project/ray>`__ upstream repository.
+
+- To get started and install Ray on ROCm, use the prebuilt :ref:`Docker image <ray-docker-compat>`, 
+  which includes ROCm, Ray, and all required dependencies.
+
+  - See the :doc:`ROCm Ray installation guide <rocm-install-on-linux:install/3rd-party/ray-install>`
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://docs.ray.io/en/latest/ray-overview/installation.html>`__ 
+    for additional context.
+
+.. _ray-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `ROCm Ray Docker images <https://hub.docker.com/r/rocm/ray/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and
+associated inventories represent the latest Ray version from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Ray
+      - Pytorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.51.1_rocm7.0.0_ubuntu22.04_py3.12_pytorch2.9.0/images/sha256-a02f6766b4ba406f88fd7e85707ec86c04b569834d869a08043ec9bcbd672168"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - `2.51.1 <https://github.com/ROCm/ray/tree/release/2.51.1>`__
+      - 2.9.0a0+git1c57644
+      - 22.04
+      - `3.12.12 <https://www.python.org/downloads/release/python-31212/>`__
+      - MI300X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.48.0.post0_rocm6.4.1_ubuntu24.04_py3.12_pytorch2.6.0/images/sha256-0d166fe6bdced38338c78eedfb96eff92655fb797da3478a62dd636365133cc0"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - `2.48.0.post0 <https://github.com/ROCm/ray/tree/release/2.48.0.post0>`__
+      - 2.6.0+git684f6f2
+      - 24.04
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - MI300X, MI210
+
+Use cases and recommendations
+================================================================================
+
+* The `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm 
+  Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__  
+  blog provides an overview of Volcano Engine Reinforcement Learning (verl) 
+  for large language models (LLMs) and discusses its benefits in large-scale 
+  reinforcement learning from human feedback (RLHF). It uses Ray as part of a 
+  hybrid orchestration engine to schedule and coordinate training and inference 
+  tasks in parallel, enabling optimized resource utilization and potential overlap 
+  between these phases. This dynamic resource allocation strategy significantly 
+  improves overall system efficiency. The blog presents verl’s performance results, 
+  focusing on throughput and convergence accuracy achieved on AMD Instinct™ MI300X 
+  GPUs. Follow this guide to get started with verl on AMD Instinct GPUs and 
+  accelerate your RLHF training with ROCm-optimized performance.
+
+* The `Exploring Use Cases for Scalable AI: Implementing Ray with ROCm Support for Efficient ML Workflows 
+  <https://rocm.blogs.amd.com/artificial-intelligence/rocm-ray/README.html>`__
+  blog post describes key use cases such as training and inference for large language models (LLMs), 
+  model serving, hyperparameter tuning, reinforcement learning, and the orchestration of large-scale 
+  workloads using Ray in the ROCm environment.
+
+For more use cases and recommendations, see the AMD GPU tabs in the `Accelerator Support 
+topic <https://docs.ray.io/en/latest/ray-core/scheduling/accelerators.html#accelerator-support>`__ 
+of the Ray core documentation and refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for Ray examples and best practices to optimize your workloads on AMD GPUs.
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/ray-history` to find documentation for previous releases
+of the ``ROCm/ray`` Docker image.
@@ -0,0 +1,116 @@
+:orphan:
+
+.. meta::
+    :description: Stanford Megatron-LM compatibility
+    :keywords: Stanford, Megatron-LM, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+Stanford Megatron-LM compatibility
+********************************************************************************
+
+Stanford Megatron-LM is a large-scale language model training framework developed 
+by NVIDIA at `https://github.com/NVIDIA/Megatron-LM <https://github.com/NVIDIA/Megatron-LM>`_. 
+It is designed to train massive transformer-based language models efficiently by model 
+and data parallelism. 
+
+It provides efficient tensor, pipeline, and sequence-based model parallelism for 
+pre-training transformer-based language models such as GPT (Decoder Only), BERT 
+(Encoder Only), and T5 (Encoder-Decoder). 
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Stanford Megatron-LM is maintained in the official `https://github.com/ROCm/Stanford-Megatron-LM 
+  <https://github.com/ROCm/Stanford-Megatron-LM>`__ repository, which differs from the 
+  `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`__ upstream repository.
+
+- To get started and install Stanford Megatron-LM on ROCm, use the prebuilt :ref:`Docker image <megatron-lm-docker-compat>`, 
+  which includes ROCm, Stanford Megatron-LM, and all required dependencies.
+
+  - See the :doc:`ROCm Stanford Megatron-LM installation guide <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/NVIDIA/Megatron-LM>`__ 
+    for additional context.
+
+.. _megatron-lm-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `Stanford Megatron-LM images <https://hub.docker.com/r/rocm/stanford-megatron-lm/tags>`_
+with ROCm and Pytorch backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest Stanford Megatron-LM version from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Stanford Megatron-LM
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/stanford-megatron-lm/stanford-megatron-lm85f95ae_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-070556f078be10888a1421a2cb4f48c29f28b02bfeddae02588d1f7fc02a96a6"><i class="fab fa-docker fa-lg"></i> rocm/stanford-megatron-lm</a>
+
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `85f95ae <https://github.com/stanford-futuredata/Megatron-LM/commit/85f95aef3b648075fe6f291c86714fdcbd9cd1f5>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - MI300X
+
+Supported models and features with ROCm 6.3.0
+================================================================================
+
+This section details models & features that are supported by the ROCm version on Stanford Megatron-LM.
+
+Models:
+
+* BERT
+* GPT
+* T5
+* ICT
+
+Features:
+
+* Distributed Pre-training
+* Activation Checkpointing and Recomputation
+* Distributed Optimizer
+* Mixture-of-Experts
+
+.. _megatron-lm-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+The following blog post mentions Megablocks, but you can run Stanford Megatron-LM with the same steps to pre-process datasets on AMD GPUs:
+
+* The `Efficient MoE training on AMD ROCm: How-to use Megablocks on AMD GPUs 
+  <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`__ 
+  blog post guides how to leverage the ROCm platform for pre-training using the 
+  Megablocks framework. It introduces a streamlined approach for training Mixture-of-Experts 
+  (MoE) models using the Megablocks library on AMD hardware. Focusing on GPT-2, it 
+  demonstrates how block-sparse computations can enhance scalability and efficiency in MoE 
+  training. The guide provides step-by-step instructions for setting up the environment, 
+  including cloning the repository, building the Docker image, and running the training container. 
+  Additionally, it offers insights into utilizing the ``oscar-1GB.json`` dataset for pre-training 
+  language models. By leveraging Megablocks and the ROCm platform, you can optimize your MoE 
+  training workflows for large-scale transformer models.
+
+It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
+
+* Single-GPU pre-training
+* Multi-GPU pre-training
@@ -0,0 +1,118 @@
+:orphan:
+
+.. meta::
+   :description: verl compatibility
+   :keywords: GPU, verl, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+verl compatibility
+*******************************************************************************
+
+Volcano Engine Reinforcement Learning for LLMs (`verl <https://verl.readthedocs.io/en/latest/>`__)  
+is a reinforcement learning framework designed for large language models (LLMs). 
+verl offers a scalable, open-source fine-tuning solution by using a hybrid programming model 
+that makes it easy to define and run complex post-training dataflows efficiently. 
+
+Its modular APIs separate computation from data, allowing smooth integration with other frameworks. 
+It also supports flexible model placement across GPUs for efficient scaling on different cluster sizes.
+verl achieves high training and generation throughput by building on existing LLM frameworks. 
+Its 3D-HybridEngine reduces memory use and communication overhead when switching between training 
+and inference, improving overall performance.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of verl is maintained in the official `https://github.com/ROCm/verl 
+  <https://github.com/ROCm/verl>`__ repository, which differs from the 
+  `https://github.com/volcengine/verl <https://github.com/volcengine/verl>`__ upstream repository.
+
+- To get started and install verl on ROCm, use the prebuilt :ref:`Docker image <verl-docker-compat>`, 
+  which includes ROCm, verl, and all required dependencies.
+
+  - See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>`
+    for installation and setup instructions.
+
+  - You can also consult the upstream `verl documentation <https://verl.readthedocs.io/en/latest/>`__ 
+    for additional context.
+
+.. _verl-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `verl Docker images <https://hub.docker.com/r/rocm/verl/tags>`_
+with ROCm backends on Docker Hub. The following Docker image tag and associated inventories 
+represent the latest verl version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table::
+   :header-rows: 1
+   :class: docker-image-compatibility
+
+   * - Docker image
+     - ROCm
+     - verl
+     - Ubuntu
+     - PyTorch
+     - Python
+     - vllm
+     - GPU
+
+   * - .. raw:: html
+
+        <a href="https://hub.docker.com/layers/rocm/verl/verl-0.6.0.amd0_rocm7.0_vllm0.11.0.dev/images/sha256-f70a3ebc94c1f66de42a2fcc3f8a6a8d6d0881eb0e65b6958d7d6d24b3eecb0d"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+     - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+     - `0.6.0 <https://github.com/volcengine/verl/releases/tag/v0.6.0>`__
+     - 22.04
+     - `2.9.0 <https://github.com/ROCm/pytorch/tree/release/2.9-rocm7.x-gfx115x>`__
+     - `3.12.11 <https://www.python.org/downloads/release/python-31211/>`__
+     - `0.11.0 <https://github.com/vllm-project/vllm/releases/tag/v0.11.0>`__
+     - MI300X
+
+   * - .. raw:: html
+
+        <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+     - `6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`__
+     - `0.3.0.post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`__
+     - 20.04
+     - `2.5.0 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
+     - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`__
+     - `0.6.3 <https://github.com/vllm-project/vllm/releases/tag/v0.6.3>`__
+     - MI300X
+
+.. _verl-supported_features:
+
+Supported modules with verl on ROCm
+===============================================================================
+
+The following GPU-accelerated modules are supported with verl on ROCm:
+
+- ``FSDP``: Training engine
+- ``vllm``: Inference engine
+
+.. _verl-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+* The benefits of verl in large-scale reinforcement learning from human feedback 
+  (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD 
+  GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__ 
+  blog. The blog post outlines how the Volcano Engine Reinforcement Learning 
+  (verl) framework integrates with the AMD ROCm platform to optimize training on 
+  AMD Instinct™ GPUs. The guide details the process of building a Docker image, 
+  setting up single-node and multi-node training environments, and highlights 
+  performance benchmarks demonstrating improved throughput and convergence accuracy. 
+  This resource serves as a comprehensive starting point for deploying verl on AMD GPUs, 
+  facilitating efficient RLHF training workflows.
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/verl-history` to find documentation for previous releases
+of the ``ROCm/verl`` Docker image.
@@ -107,7 +107,13 @@ article_pages = [
    {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
    {"file": "compatibility/ml-compatibility/tensorflow-compatibility", "os": ["linux"]},
    {"file": "compatibility/ml-compatibility/jax-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/verl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/stanford-megatron-lm-compatibility", "os": ["linux"]},
    {"file": "compatibility/ml-compatibility/dgl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/megablocks-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/ray-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/llama-cpp-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/flashinfer-compatibility", "os": ["linux"]},
    {"file": "how-to/deep-learning-rocm", "os": ["linux"]},

    {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},
@@ -262,3 +268,6 @@ html_context = {
    "granularity_type" : [('Coarse-grained', 'coarse-grained'), ('Fine-grained', 'fine-grained')],
    "scope_type" : [('Device', 'device'), ('System', 'system')]
 }
+
+# Disable figure and table numbering
+numfig = False
@@ -24,7 +24,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
      - GitHub

    * - :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`
-      - :doc:`link <rocm-install-on-linux:install/3rd-party/pytorch-install>`
+      - :doc:`Pytorch install <rocm-install-on-linux:install/3rd-party/pytorch-install>`
      - 
        - Docker image
        - Wheels package
@@ -35,7 +35,7 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/pytorch"><i class="fab fa-github fa-lg"></i></a>

    * - :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`
-      - :doc:`link <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
+      - :doc:`TensorFlow install <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
      - 
        - Docker image
        - Wheels package
@@ -45,21 +45,82 @@ The table below summarizes information about ROCm-enabled deep learning framewor
          <a href="https://github.com/ROCm/tensorflow-upstream"><i class="fab fa-github fa-lg"></i></a> 

    * - :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`
-      - :doc:`link <rocm-install-on-linux:install/3rd-party/jax-install>`
+      - :doc:`JAX install <rocm-install-on-linux:install/3rd-party/jax-install>`
      - 
        - Docker image
      - .. raw:: html

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

+    * - :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>`
+      - :doc:`verl install <rocm-install-on-linux:install/3rd-party/verl-install>`
+      - 
+        - Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/verl"><i class="fab fa-github fa-lg"></i></a>
+
+    * - :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
+      - :doc:`Stanford Megatron-LM install <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
+      - 
+        - Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/Stanford-Megatron-LM"><i class="fab fa-github fa-lg"></i></a>
+
    * - :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`
-      - :doc:`link <rocm-install-on-linux:install/3rd-party/dgl-install>`
+      - :doc:`DGL install <rocm-install-on-linux:install/3rd-party/dgl-install>`
      - 
        - Docker image
      - .. raw:: html

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

+    * - :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`
+      - :doc:`Megablocks install <rocm-install-on-linux:install/3rd-party/megablocks-install>`
+      - 
+        - Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/megablocks"><i class="fab fa-github fa-lg"></i></a>
+
+    * - :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>`
+      - `Taichi install <https://rocm.docs.amd.com/projects/taichi/en/latest/install/taichi-install.html>`__
+      - 
+        - Docker image
+        - Wheels package
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/taichi"><i class="fab fa-github fa-lg"></i></a>
+
+    * - :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>`
+      - :doc:`Ray install <rocm-install-on-linux:install/3rd-party/ray-install>`
+      - 
+        - 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>
+
+    * - :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>`
+      - :doc:`llama.cpp install <rocm-install-on-linux:install/3rd-party/llama-cpp-install>`
+      - 
+        - 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>
+
+    * - :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>`
+      - :doc:`FlashInfer install <rocm-install-on-linux:install/3rd-party/flashinfer-install>`
+      - 
+        - Docker image
+        - ROCm Base Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/flashinfer"><i class="fab fa-github fa-lg"></i></a>
+
 Learn how to use your ROCm deep learning environment for training, fine-tuning, inference, and performance optimization
 through the following guides.

@@ -44,7 +44,7 @@ Setting up the base implementation environment

   .. code-block:: shell

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

 #. 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 ``amd-smi`` command in your terminal.
-   This tool helps you see which GPUs are involved.
+   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.


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

 #. Install torchtune using pip.
@@ -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
@@ -44,19 +44,20 @@ Setting up the base implementation environment

   .. code-block:: shell

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

   Your output should look like this:

   .. code-block:: shell

-      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
+      ============================ 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 ===================================

 #. Check that your GPUs are available to PyTorch.

@@ -93,13 +94,13 @@ 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

@@ -131,7 +132,7 @@ 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.
@@ -140,14 +141,14 @@ 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"
@@ -161,10 +162,10 @@ 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])

@@ -251,8 +252,8 @@ 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()

@@ -285,7 +286,7 @@ 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)

@@ -308,8 +309,8 @@ 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()

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

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

@@ -358,21 +359,21 @@ 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)

@@ -382,7 +383,7 @@ 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
@@ -411,26 +412,26 @@ 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
@@ -438,13 +439,13 @@ 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
@@ -460,25 +461,25 @@ 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
@@ -489,14 +490,14 @@ 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"])

@@ -31,16 +31,16 @@ in the Instinct documentation for more information.
 Hardware verification with ROCm
 -------------------------------

-Use the command ``amd-smi set --perf-determinism 1900`` to set the max clock speed up to 1900 MHz
+Use the command ``rocm-smi --setperfdeterminism 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 ``amd-smi reset --clocks`` command.
+You can restore this setting to its default value with the ``rocm-smi -r`` command.

 Run the command:

 .. code-block:: shell

-   amd-smi set --perf-determinism 1900
+   rocm-smi --setperfdeterminism 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.
@@ -108,16 +108,16 @@ for more information.
 Hardware verification with ROCm
 -------------------------------

-Use the command ``amd-smi set --perf-determinism 1900`` to set the max clock speed up to 1900 MHz
+Use the command ``rocm-smi --setperfdeterminism 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 ``amd-smi reset --clocks`` command.
+You can restore this setting to its default value with the ``rocm-smi -r`` command.

 Run the command:

 .. code-block:: shell

-   amd-smi set --perf-determinism 1900
+   rocm-smi --setperfdeterminism 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
@@ -5,7 +5,7 @@
 GPU hardware specifications
 ===========================================

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

 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

        *
-          - Name
+          - Model
          - 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

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

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

        *
-          - Name
+          - Model
          - Architecture
          - LLVM target name
          - VRAM (GiB)
@@ -953,127 +953,6 @@ 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
 ========

@@ -29,14 +29,28 @@ subtrees:
    title: Deep learning frameworks
    subtrees:
    - entries:
-      - file: compatibility/ml-compatibility/pytorch-compatibility.rst
+      - file: compatibility/ml-compatibility/pytorch-compatibility
        title: PyTorch compatibility
-      - file: compatibility/ml-compatibility/tensorflow-compatibility.rst
+      - file: compatibility/ml-compatibility/tensorflow-compatibility
        title: TensorFlow compatibility
-      - file: compatibility/ml-compatibility/jax-compatibility.rst
+      - file: compatibility/ml-compatibility/jax-compatibility
        title: JAX compatibility
-      - file: compatibility/ml-compatibility/dgl-compatibility.rst
+      - file: compatibility/ml-compatibility/verl-compatibility
+        title: verl compatibility
+      - file: compatibility/ml-compatibility/stanford-megatron-lm-compatibility
+        title: Stanford Megatron-LM compatibility
+      - file: compatibility/ml-compatibility/dgl-compatibility
        title: DGL compatibility
+      - file: compatibility/ml-compatibility/megablocks-compatibility
+        title: Megablocks compatibility
+      - file: compatibility/ml-compatibility/taichi-compatibility
+        title: Taichi compatibility
+      - file: compatibility/ml-compatibility/ray-compatibility
+        title: Ray compatibility
+      - file: compatibility/ml-compatibility/llama-cpp-compatibility
+        title: llama.cpp compatibility
+      - file: compatibility/ml-compatibility/flashinfer-compatibility
+        title: FlashInfer compatibility
  - file: how-to/build-rocm.rst
    title: Build ROCm from source

@@ -63,14 +77,8 @@ subtrees:
        - entries:
          - file: how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
            title: Train a model with Primus and Megatron-LM
-            entries:
-            - file: how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst
-              title: Train a model with Megatron-LM
          - file: how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
            title: Train a model with Primus and PyTorch
-            entries:
-            - file: how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
-              title: Train a model with PyTorch
          - file: how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
            title: Train a model with JAX MaxText
          - file: how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry
@@ -109,8 +117,6 @@ subtrees:
            title: SGLang inference performance testing
          - file: how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
            title: SGLang distributed inference with Mooncake
-          - file: how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst
-            title: xDiT diffusion inference
          - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
            title: Deploy your model

@@ -128,8 +134,6 @@ subtrees:
            title: Profile and debug
          - file: how-to/rocm-for-ai/inference-optimization/workload.rst
            title: Workload optimization
-          - file: how-to/rocm-for-ai/inference-optimization/vllm-optimization.rst
-            title: vLLM V1 performance optimization

      - url: https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/
        title: AI tutorials
@@ -176,7 +180,7 @@ subtrees:
          - file: conceptual/gpu-arch/mi300-mi200-performance-counters.rst
            title: MI300 and MI200 performance counters
          - file: conceptual/gpu-arch/mi350-performance-counters.rst
-            title: MI350 Series performance counters
+            title: MI350 series performance counters
      - file: conceptual/gpu-arch/mi250.md
        title: MI250 microarchitecture
        subtrees:
@@ -210,8 +214,6 @@ subtrees:
    title: ROCm tools, compilers, and runtimes
  - file: reference/gpu-arch-specs.rst
  - file: reference/gpu-atomics-operation.rst
-  - file: reference/env-variables.rst
-    title: Environment variables
  - file: reference/precision-support.rst
    title: Data types and precision support
  - file: reference/graph-safe-support.rst
@@ -123,8 +123,7 @@ Performance

 .. note::

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

 Development
 ^^^^^^^^^^^
Author	SHA1	Message	Date
randyh62andGitHub	8d183c2e95	Apply suggestion from @randyh62 OK	2026-01-15 15:53:46 -08:00
randyh62andGitHub	3a7cfd3958	Apply suggestion from @randyh62 OK	2026-01-15 15:53:00 -08:00
randyh62andGitHub	833fdf4c95	Apply suggestion from @randyh62 OK	2026-01-15 15:52:14 -08:00
randyh62	28f028d304	Update Deep Frameworks to use intersphinx links where possible	2026-01-15 15:48:31 -08:00
peterjunparkandGitHub	a745e45dcb	Doc update for vLLM refactor #5855	2026-01-15 11:21:38 -05:00
alexxu-amdandGitHub	8beac1891f	update requirements.txt (#5851 )	2026-01-14 16:55:26 -05:00
anisha-amdandGitHub	773f5de407	Docs: Ray release 25.12 and compatibility version format standardization (#5845 )	2026-01-08 12:09:11 -05:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	b297ced032	Bump urllib3 from 2.5.0 to 2.6.3 in /docs/sphinx (#5842 ) Bumps [urllib3](https://github.com/urllib3/urllib3) from 2.5.0 to 2.6.3. - [Release notes](https://github.com/urllib3/urllib3/releases) - [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst) - [Commits](https://github.com/urllib3/urllib3/compare/2.5.0...2.6.3) --- updated-dependencies: - dependency-name: urllib3 dependency-version: 2.6.3 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2026-01-08 08:22:01 -05:00
peterjunparkandGitHub	2dc22ca890	fix(primus-pytorch.rst): FP8 config instead of BF16 (#5839 )	2026-01-07 13:49:31 -05:00
Joseph MacaranasandGitHub	85102079ed	[External CI] Add SIMDe dev package to HIP runtime pipeline (#5838 )	2026-01-07 11:00:38 -05:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	ba95e0e689	Bump pynacl from 1.6.1 to 1.6.2 in /docs/sphinx (#5836 ) Bumps [pynacl](https://github.com/pyca/pynacl) from 1.6.1 to 1.6.2. - [Changelog](https://github.com/pyca/pynacl/blob/main/CHANGELOG.rst) - [Commits](https://github.com/pyca/pynacl/compare/1.6.1...1.6.2) --- updated-dependencies: - dependency-name: pynacl dependency-version: 1.6.2 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2026-01-06 14:10:42 -05:00
Pratik BasyalandGitHub	1691d369e9	ROCM-core version fixed (#5827 )	2026-01-02 16:06:27 -05:00
peterjunparkandGitHub	172b0f7c08	Fix inconsistency in xDiT doc Fix inconsistency in xDiT doc	2025-12-29 10:26:25 -05:00
peterjunparkandGitHub	c67fac78bd	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	2025-12-29 08:44:45 -05:00
peterjunparkandGitHub	e0b8ec4dfb	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	2025-12-29 08:05:47 -05:00
Pratik BasyalandGitHub	38f2d043dc	OS table removed from compatibility table [develop] (#5810 ) * 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 16:28:19 -05:00
peterjunparkandGitHub	3a43bacdda	Update xdit diffusion inference history (#5808 ) * Update xdit diffusion inference history * fix	2025-12-22 11:05:32 -05:00
peterjunparkandGitHub	48d8fe139b	fix link to ROCm PyT docker image (#5803 )	2025-12-19 15:47:55 -05:00
peterjunparkandGitHub	7455fe57b8	clean up formatting in FA2 page (#5795 )	2025-12-19 09:21:41 -05:00
peterjunpark GitHub seungrok.jung Leo Paoletti	52c0a47e84	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>	2025-12-19 08:48:52 -05:00
peterjunparkandGitHub	cbab9a465d	Update documentation for JAX training MaxText 25.11 release (#5789 )	2025-12-18 11:23:58 -05:00
peterjunpark GitHub Kristoffer	459283da3c	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>	2025-12-17 10:20:10 -05:00
peterjunparkandGitHub	1b4f25733d	vLLM inference benchmark 1210 (#5776 ) * Archive previous ver fix anchors * Update vllm.rst and data yaml for 20251210	2025-12-17 09:21:57 -05:00
Ibrahim WaniandGitHub	b287372be5	[origami] Test update (#5768 ) * Fix the skipping of origami tests * Update dependencies for origami refactor * test * Unsupress test output. * Ctest implementation * Test ctest * Test ctest 2 * Add pip install test * Fix python version * Add python dep * test * test 2 * Debug for readme * Fix pip install * Fix pip install 2 * Clean up * Run tests on 950 * Replace 950 with 1201 * 1101 * Add more archs * Add more archs 2 * Comment out archs * Move pip install script to ./azuredevops/scripts * Fix path * Fix path 2 * Fix path 3 * Fix path 4 * Remove pip install testing: * Use inline script * Add old deps	2025-12-16 15:37:41 -07:00
Pratik BasyalandGitHub	78e8baf147	Taichi removed from ROCm docs [Develop] (#5779 ) * Taichi removed from ROCm docs * Warnings fixed	2025-12-16 13:12:40 -05:00
Matt WilliamsandGitHub	3e0c8b47e3	Merge pull request #5771 from ROCm/mattwill-amd-patch-4 Reverting Optiq note	2025-12-12 17:53:41 -05:00
Matt WilliamsandGitHub	c3f0b99cc0	Reverting Optiq note	2025-12-12 17:47:33 -05:00
dependabot[bot]andpeterjunpark	c9d1679486	Bump rocm-docs-core from 1.31.0 to 1.31.1 in /docs/sphinx Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.31.0 to 1.31.1. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.31.0...v1.31.1) --- updated-dependencies: - dependency-name: rocm-docs-core dependency-version: 1.31.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com>	2025-12-12 16:15:26 -05:00
Pratik BasyalandGitHub	fdbef17d7b	Onnx and rocshmem version updated (#5760 )	2025-12-11 17:05:25 -05:00
Matt WilliamsandGitHub	6592a41a7f	Adding ROCm-Optiq note to What is ROCm page (#5709 ) * Adding ROCm-Optiq note to What is ROCm page Adding a note for a link to the Optiq docs * Apply suggestion from @mattwill-amd * Apply suggestion from @mattwill-amd * Apply suggestion from @mattwill-amd * Update what-is-rocm.rst * Update what-is-rocm.rst * Apply suggestion from @mattwill-amd * Apply suggestion from @mattwill-amd * Apply suggestion from @mattwill-amd * Apply suggestion from @mattwill-amd	2025-12-10 12:56:33 -08:00
Matt WilliamsandGitHub	65a936023b	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 11:17:59 -05:00
anisha-amdandGitHub	2a64949081	Docs: update verl compatibility - fix (#5756 )	2025-12-09 19:51:37 -05:00
anisha-amdandGitHub	0a17434517	Docs: update verl compatibility - fix (#5754 )	2025-12-09 18:36:16 -05:00
anisha-amdandGitHub	2be7e5ac1e	Docs: verl framework - compatibility - 25.11 release (#5752 )	2025-12-09 11:41:43 -05:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	ae80c4a31c	Bump rocm-docs-core from 1.30.1 to 1.31.0 in /docs/sphinx (#5751 ) Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.30.1 to 1.31.0. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/v1.31.0/CHANGELOG.md) - [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.30.1...v1.31.0) --- updated-dependencies: - dependency-name: rocm-docs-core dependency-version: 1.31.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-12-09 08:25:16 -05:00
Adel Johar	dd89a692e1	[Ex CI] Add rocAL dependencies	2025-12-09 10:56:23 +01:00
peterjunparkandGitHub	bf74351e5a	Fix Primus PyTorch doc: training.batch_size -> training.local_batch_size (#5748 )	2025-12-08 13:35:22 -05:00
yugang-amdandGitHub	f2067767e0	xdit-diffusion v25.11 docs (#5744 )	2025-12-05 17:09:48 -05:00
Pratik BasyalandGitHub	effd4174fb	PyTorch 2.7 support added (#5740 )	2025-12-04 15:49:23 -05:00
peterjunparkandGitHub	453751a86f	fix docker hub links for primus:v25.10 (#5738 )	2025-12-04 09:17:33 -05:00
peterjunparkandGitHub	fb644412d5	Update training Docker docs for Primus 25.10 (#5737 )	2025-12-04 09:08:00 -05:00
Pratik Basyal GitHub Jeffrey Novotny	e8fdc34b71	711 hipBLASLT performance decline known issue added (#5730 ) * hipBLASLT performance decline known issue added * Update RELEASE.md Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> * GitHub Issue added * Ram's feedback incorporated * GitHub Issue added * Update RELEASE.md Co-authored-by: Jeffrey Novotny <jnovotny@amd.com> --------- Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>	2025-12-03 08:50:25 -05:00
Pratik Basyal GitHub Jeffrey Novotny Leo Paoletti	b4031ef23c	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>	2025-11-28 16:34:47 -05:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	d0bd4e6f03	Bump rocm-docs-core from 1.29.0 to 1.30.1 in /docs/sphinx (#5712 ) Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.29.0 to 1.30.1. - [Release notes](https://github.com/ROCm/rocm-docs-core/releases) - [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md) - [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.29.0...v1.30.1) --- updated-dependencies: - dependency-name: rocm-docs-core dependency-version: 1.30.1 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-11-28 08:18:23 -05:00
Jan Stephan	0056b9453e	Remove continuous numbering of tables and figures Signed-off-by: Jan Stephan <jan.stephan@amd.com>	2025-11-28 10:29:01 +01:00
Pratik BasyalandGitHub	3d1ad79766	Merged cell removed for coloring issue (#5713 )	2025-11-27 19:52:36 -05:00
Pratik BasyalandGitHub	8683bed11b	Known issue from 7.1.0 removed (#5702 )	2025-11-26 12:27:22 -05:00
Pratik BasyalandGitHub	847cd7c423	Link and PyTorch version updated (#5700 )	2025-11-26 11:52:47 -05:00