Merge branch 'james/build-instr-fix' of https://github.com/ROCm/ROCm into james/build-instr-fix

These were encountered while debugging
https://github.com/ROCm/ROCm/issues/4190

- There is no manifest (-m) for ROCm 6.3.1 in the tools/rocm-build folder
-- Changed the rocm version to 6.3.0 to avoid immediate build failure
- The manifest is not specified in the first instance of "Downloading the ROCm source code", but it is in "Build ROCm from source".
-- Without the correct manifest, subsequent build instructions will fail as the ROCm/ROCm directory doesn't get pulled. It's unclear why these two otherwise identical commands are duplicated and have this discrepancy

.azuredevops/components/omniperf.yml

@@ -1,166 +0,0 @@
-parameters:
-- name: checkoutRepo
-  type: string
-  default: 'self'
-- name: checkoutRef
-  type: string
-  default: ''
-- name: aptPackages
-  type: object
-  default:
-    - cmake
-    - python3-pip
-- name: pipModules
-  type: object
-  default:
-    - astunparse==1.6.2
-    - colorlover
-    - dash>=1.12.0
-    - matplotlib
-    - numpy>=1.17.5
-    - pandas>=1.4.3
-    - pymongo
-    - pyyaml
-    - tabulate
-    - tqdm
-    - dash-svg
-    - dash-bootstrap-components
-    - kaleido
-    - setuptools
-    - plotille
-    - mock
-    - pytest
-    - pytest-cov
-    - pytest-xdist
-- name: rocmDependencies
-  type: object
-  default:
-    - clr
-    - llvm-project
-    - rocm-cmake
-    - rocm-core
-    - rocminfo
-    - ROCR-Runtime
-    - rocprofiler
-    - rocprofiler-register
-    - roctracer
-
-jobs:
-- job: omniperf
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  pool:
-    vmImage: ${{ variables.BASE_BUILD_POOL }}
-  workspace:
-    clean: all
-  strategy:
-    matrix:
-      gfx942:
-        JOB_GPU_TARGET: gfx942
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    parameters:
-      ${{ if eq(parameters.checkoutRef, '') }}:
-        dependencySource: staging
-      ${{ elseif ne(parameters.checkoutRef, '') }}:
-        dependencySource: tag-builds
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      dependencyList: ${{ parameters.rocmDependencies }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      # CI case: download latest default branch build
-      ${{ if eq(parameters.checkoutRef, '') }}:
-        dependencySource: staging
-      # manual build case: triggered by ROCm/ROCm repo
-      ${{ elseif ne(parameters.checkoutRef, '') }}:
-        dependencySource: tag-builds
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
-    parameters:
-      gpuTarget: $(JOB_GPU_TARGET)
-
-- job: omniperf_testing
-  dependsOn: omniperf
-  condition: and(succeeded(), eq(variables.ENABLE_GFX942_TESTS, 'true'), not(containsValue(split(variables.DISABLED_GFX942_TESTS, ','), variables['Build.DefinitionName'])))
-  variables:
-  - group: common
-  - template: /.azuredevops/variables-global.yml
-  - name: PYTHON_VERSION
-    value: 3.10
-  pool: $(JOB_TEST_POOL)
-  workspace:
-    clean: all
-  strategy:
-    matrix:
-      gfx942:
-        JOB_GPU_TARGET: gfx942
-        JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
-  steps:
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
-    parameters:
-      checkoutRepo: ${{ parameters.checkoutRepo }}
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    parameters:
-      ${{ if eq(parameters.checkoutRef, '') }}:
-        dependencySource: staging
-      ${{ elseif ne(parameters.checkoutRef, '') }}:
-        dependencySource: tag-builds
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-    parameters:
-      dependencyList: ${{ parameters.rocmDependencies }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      ${{ if eq(parameters.checkoutRef, '') }}:
-        dependencySource: staging
-      ${{ elseif ne(parameters.checkoutRef, '') }}:
-        dependencySource: tag-builds
-  - task: Bash@3
-    displayName: Add ROCm binaries to PATH
-    inputs:
-      targetType: inline
-      script: echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
-  - task: Bash@3
-    displayName: Add ROCm compilers to PATH
-    inputs:
-      targetType: inline
-      script: echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
-    parameters:
-      extraBuildFlags: >-
-        -DCMAKE_HIP_ARCHITECTURES=$(JOB_GPU_TARGET)
-        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-        -DCMAKE_MODULE_PATH=$(Agent.BuildDirectory)/rocm/lib/cmake/hip
-        -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
-        -DCMAKE_BUILD_TYPE=Release
-        -DENABLE_TESTS=ON
-        -DINSTALL_TESTS=ON
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-    parameters:
-      componentName: omniperf
-      testDir: $(Build.BinariesDirectory)/libexec/omniperf
-      testExecutable: export OMNIPERF_ARCH_OVERRIDE="MI300X"; ctest
-  - task: Bash@3
-    displayName: Remove ROCm binaries from PATH
-    inputs:
-      targetType: inline
-      script: echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$(Agent.BuildDirectory)/rocm/bin;;' -e 's;^/;;' -e 's;/$;;')"
-  - task: Bash@3
-    displayName: Remove ROCm compilers from PATH
-    inputs:
-      targetType: inline
-      script: echo "##vso[task.setvariable variable=PATH]$(echo $PATH | sed -e 's;:$(Agent.BuildDirectory)/rocm/llvm/bin;;' -e 's;^/;;' -e 's;/$;;')"

.azuredevops/nightly/rocm-nightly.yml

@@ -26,7 +26,6 @@ parameters:
     - llvm-project
     - MIOpen
     - MIVisionX
-    - omniperf
     - rccl
     - rdc
     - rocAL

.azuredevops/tag-builds/omniperf.yml

@@ -1,29 +0,0 @@
-variables:
-- group: common
-- template: /.azuredevops/variables-global.yml
-
-parameters:
-- name: checkoutRef
-  type: string
-  default: refs/tags/$(LATEST_RELEASE_TAG)
-
-resources:
-  repositories:
-  - repository: pipelines_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/ROCm
-  - repository: release_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/omniperf
-    ref: ${{ parameters.checkoutRef }}
-
-trigger: none
-pr: none
-
-jobs:
-  - template: ${{ variables.CI_COMPONENT_PATH }}/omniperf.yml
-    parameters:
-      checkoutRepo: release_repo
-      checkoutRef: ${{ parameters.checkoutRef }}

.azuredevops/templates/steps/artifact-download.yml

@@ -62,7 +62,7 @@ parameters:
     ROCgdb: amd-staging
     rocJPEG: develop
     rocm-cmake: develop
-    rocm-core: amd-staging
+    rocm-core: master
     rocm-examples: develop
     rocminfo: amd-staging
     rocMLIR: develop

.wordlist.txt

@@ -107,6 +107,7 @@ FFT
 FFTs
 FFmpeg
 FHS
+FIXME
 FMA
 FP
 FX
@@ -131,6 +132,7 @@ GiB
 GIM
 GL
 GLXT
+Gloo
 GMI
 GPG
 GPR
@@ -148,6 +150,7 @@ HCA
 HGX
 HIPCC
 HIPExtension
+HIPification
 HIPIFY
 HPC
 HPCG
@@ -243,6 +246,7 @@ MyEnvironment
 MyST
 NBIO
 NBIOs
+NCCL
 NIC
 NICs
 NLI
@@ -401,9 +405,14 @@ TensorFlow
 TensorParallel
 ToC
 TorchAudio
+torchaudio
+TorchElastic
 TorchMIGraphX
+torchrec
 TorchScript
 TorchServe
+torchserve
+torchtext
 TorchVision
 TransferBench
 TrapStatus
@@ -510,6 +519,9 @@ copyable
 cpp
 csn
 cuBLAS
+cuda
+cuDNN
+cudnn
 cuFFT
 cuLIB
 cuRAND
@@ -674,6 +686,7 @@ prebuilt
 precompiled
 preconditioner
 preconfigured
+preemptible
 prefetch
 prefetchable
 prefill
@@ -690,6 +703,7 @@ profilers
 protobuf
 pseudorandom
 py
+recommender
 quantile
 quantizer
 quasirandom

README.md

@@ -50,7 +50,8 @@ The following example shows how to use the repo tool to download the ROCm source
 ```bash
 mkdir -p ~/ROCm/
 cd ~/ROCm/
-~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.3.x
+export ROCM_VERSION=6.3.1
+~/bin/repo init -u http://github.com/ROCm/ROCm.git -b roc-6.3.x -m tools/rocm-build/rocm-${ROCM_VERSION}.xml
 ~/bin/repo sync
 ```
 
@@ -87,11 +88,11 @@ export ROCM_VERSION=6.3.1
 # Option 1: Start a docker container
 # Pulling required base docker images:
 # Ubuntu20.04 built from ROCm/tools/rocm-build/docker/ubuntu20/Dockerfile
-docker pull rocm/rocm-build-ubuntu-20.04:6.2
+docker pull rocm/rocm-build-ubuntu-20.04:6.3
 # Ubuntu22.04 built from ROCm/tools/rocm-build/docker/ubuntu22/Dockerfile
-docker pull rocm/rocm-build-ubuntu-22.04:6.2
+docker pull rocm/rocm-build-ubuntu-22.04:6.3
 # Ubuntu24.04 built from ROCm/tools/rocm-build/docker/ubuntu24/Dockerfile
-docker pull rocm/rocm-build-ubuntu-24.04:6.2
+docker pull rocm/rocm-build-ubuntu-24.04:6.3
 
 # Start docker container and mount the source code folder:
 docker run -ti \

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

@@ -22,7 +22,7 @@ ROCm Version,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.
       ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
       ,,,,,,,,,,,
       FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,,,
-      :doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"2.4, 2.3, 2.2, 2.1, 2.0, 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"
+      :doc:`PyTorch <../compatibility/pytorch-compatibility>`,"2.4, 2.3, 2.2, 2.1, 2.0, 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"
       :doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"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","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
       :doc:`JAX <rocm-install-on-linux:install/3rd-party/jax-install>`,0.4.35,0.4.35,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1

docs/compatibility/compatibility-matrix.rst

@@ -47,7 +47,7 @@ compatibility and system requirements.
       ,gfx908,gfx908,gfx908
       ,,,
       FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix:,,
-      :doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"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"
+      :doc:`PyTorch <../compatibility/pytorch-compatibility>`,"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"
       :doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"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"
       :doc:`JAX <rocm-install-on-linux:install/3rd-party/jax-install>`,0.4.35,0.4.35,0.4.26
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.17.3

docs/compatibility/pytorch-compatibility.rst

@@ -0,0 +1,916 @@
+.. meta::
+    :description: PyTorch compatibility
+    :keywords: GPU, PyTorch compatibility
+
+********************************************************************************
+PyTorch compatibility
+********************************************************************************
+
+`PyTorch <https://pytorch.org/>`_ is an open-source tensor library designed for
+deep learning. PyTorch on ROCm provides mixed-precision and large-scale training
+using `MIOpen <https://github.com/ROCm/MIOpen>`_ and
+`RCCL <https://github.com/ROCm/rccl>`_ libraries.
+
+ROCm support for PyTorch is upstreamed into the official PyTorch repository. Due to independent
+compatibility considerations, this results in two distinct release cycles for PyTorch on ROCm:
+
+- ROCm PyTorch release:
+
+  - Provides the latest version of ROCm but doesn't immediately support the latest stable PyTorch
+    version.
+
+  - Offers :ref:`Docker images <pytorch-docker-compat>` with ROCm and PyTorch
+    pre-installed.
+
+  - ROCm PyTorch repository: `<https://github.com/rocm/pytorch>`__
+
+  - See the :doc:`ROCm PyTorch installation guide <rocm-install-on-linux:install/3rd-party/pytorch-install>` to get started.
+
+- Official PyTorch release:
+
+  - Provides the latest stable version of PyTorch but doesn't immediately support the latest ROCm version.
+
+  - Official PyTorch repository: `<https://github.com/pytorch/pytorch>`__
+
+  - See the `Nightly and latest stable version installation guide <https://pytorch.org/get-started/locally/>`_
+    or `Previous versions <https://pytorch.org/get-started/previous-versions/>`_ to get started.
+
+The upstream PyTorch includes an automatic HIPification solution that automatically generates HIP
+source code from the CUDA backend. This approach allows PyTorch to support ROCm without requiring
+manual code modifications.
+
+ROCm's development is aligned with the stable release of PyTorch while upstream PyTorch testing uses
+the stable release of ROCm to maintain consistency.
+
+.. _pytorch-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+AMD validates and publishes ready-made `PyTorch <https://hub.docker.com/r/rocm/pytorch>`_
+images with ROCm backends on Docker Hub. The following Docker image tags and
+associated inventories are validated for `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_.
+
+.. list-table:: PyTorch Docker image components
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker
+      - PyTorch
+      - Ubuntu
+      - Python
+      - Apex
+      - torchvision
+      - TensorBoard
+      - MAGMA
+      - UCX
+      - OMPI
+      - OFED
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu24.04_py3.12_pytorch_release_2.4.0/images/sha256-98ddf20333bd01ff749b8092b1190ee369a75d3b8c71c2fac80ffdcb1a98d529?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12 <https://www.python.org/downloads/release/python-3128/>`_
+      - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`_
+      - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.4.0/images/sha256-402c9b4f1a6b5a81c634a1932b56cbe01abb699cfcc7463d226276997c6cf8ea?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 22.04
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
+      - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`_
+      - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.9_pytorch_release_2.4.0/images/sha256-e0608b55d408c3bfe5c19fdd57a4ced3e0eb3a495b74c309980b60b156c526dd?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 22.04
+      - `3.9 <https://www.python.org/downloads/release/python-3918/>`_
+      - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`_
+      - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.7 <https://github.com/open-mpi/ompi/tree/v4.0.7>`_
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-652cf25263d05b1de548222970aeb76e60b12de101de66751264709c0d0ff9d8?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`_
+      - 22.04
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
+      - `1.3.0 <https://github.com/ROCm/apex/tree/release/1.3.0>`_
+      - `0.18.0 <https://github.com/pytorch/vision/tree/v0.18.0>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.10_pytorch_release_2.2.1/images/sha256-051976f26beab8f9aa65d999e3ad546c027b39240a0cc3ee81b114a9024f2912?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.2.1 <https://github.com/ROCm/pytorch/tree/release/2.2>`_
+      - 22.04
+      - `3.10 <https://www.python.org/downloads/release/python-31016/>`_
+      - `1.2.0 <https://github.com/ROCm/apex/tree/release/1.2.0>`_
+      - `0.17.1 <https://github.com/pytorch/vision/tree/v0.17.1>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu20.04_py3.9_pytorch_release_2.2.1/images/sha256-88c839a364d109d3748c100385bfa100d28090d25118cc723fd0406390ab2f7e?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `2.2.1 <https://github.com/ROCm/pytorch/tree/release/2.2>`_
+      - 20.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.2.0 <https://github.com/ROCm/apex/tree/release/1.2.0>`_
+      - `0.17.1 <https://github.com/pytorch/vision/tree/v0.17.1>`_
+      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu22.04_py3.9_pytorch_release_1.13.1/images/sha256-994424ed07a63113f79dd9aa72159124c00f5fbfe18127151e6658f7d0b6f821?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `1.13.1 <https://github.com/ROCm/pytorch/tree/release/1.13>`_
+      - 22.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.0.0 <https://github.com/ROCm/apex/tree/release/1.0.0>`_
+      - `0.14.0 <https://github.com/pytorch/vision/tree/v0.14.0>`_
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.14.1 <https://github.com/openucx/ucx/tree/v1.14.1>`_
+      - `4.1.5 <https://github.com/open-mpi/ompi/tree/v4.1.5>`_
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.3_ubuntu20.04_py3.9_pytorch_release_1.13.1/images/sha256-7b8139fe40a9aeb4bca3aecd15c22c1fa96e867d93479fa3a24fdeeeeafa1219?context=explore"><i class="fab fa-docker fa-lg"></i></a>
+
+      - `1.13.1 <https://github.com/ROCm/pytorch/tree/release/1.13>`_
+      - 20.04
+      - `3.9 <https://www.python.org/downloads/release/python-3921/>`_
+      - `1.0.0 <https://github.com/ROCm/apex/tree/release/1.0.0>`_
+      - `0.14.0 <https://github.com/pytorch/vision/tree/v0.14.0>`_
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18>`_
+      - `master <https://bitbucket.org/icl/magma/src/master/>`_
+      - `1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
+      - `4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
+      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`_
+
+Critical ROCm libraries for PyTorch
+================================================================================
+
+The functionality of PyTorch with ROCm is shaped by its underlying library
+dependencies. These critical ROCm components affect the capabilities,
+performance, and feature set available to developers.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - Version
+      - Purpose
+      - Used in
+    * - `Composable Kernel <https://github.com/ROCm/composable_kernel>`_
+      - 1.1.0
+      - Enables faster execution of core operations like matrix multiplication
+        (GEMM), convolutions and transformations.
+      - Speeds up ``torch.permute``, ``torch.view``, ``torch.matmul``,
+        ``torch.mm``, ``torch.bmm``, ``torch.nn.Conv2d``, ``torch.nn.Conv3d``
+        and ``torch.nn.MultiheadAttention``. 
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
+      - 2.3.0
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Supports operations like matrix multiplication, matrix-vector products,
+        and tensor contractions. Utilized in both dense and batched linear
+        algebra operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
+      - 0.10.0
+      - 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.
+      - It accelerates operations like ``torch.matmul``, ``torch.mm``, and the
+        matrix multiplications used in convolutional and linear layers.
+    * - `hipCUB <https://github.com/ROCm/hipCUB>`_
+      - 3.3.0
+      - Provides a C++ template library for parallel algorithms for reduction,
+        scan, sort and select.
+      - Supports operations like ``torch.sum``, ``torch.cumsum``, ``torch.sort``
+        and ``torch.topk``. Operations on sparse tensors or tensors with
+        irregular shapes often involve scanning, sorting, and filtering, which
+        hipCUB handles efficiently.
+    * - `hipFFT <https://github.com/ROCm/hipFFT>`_
+      - 1.0.17
+      - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
+      - Used in functions like the ``torch.fft`` module.
+    * - `hipRAND <https://github.com/ROCm/hipRAND>`_
+      - 2.11.0
+      - Provides fast random number generation for GPUs.
+      - The ``torch.rand``, ``torch.randn`` and stochastic layers like 
+        ``torch.nn.Dropout``.
+    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
+      - 2.3.0
+      - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
+        singular value decompositions (SVD).
+      - Supports functions like ``torch.linalg.solve``,
+        ``torch.linalg.eig``, and ``torch.linalg.svd``.
+    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
+      - 3.1.2
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+      - Sparse tensor operations ``torch.sparse``.
+    * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
+      - 0.2.2
+      - Accelerates operations on sparse matrices, such as sparse matrix-vector
+        or matrix-matrix products.
+      - Sparse tensor operations ``torch.sparse``.
+    * - `hipTensor <https://github.com/ROCm/hipTensor>`_
+      - 1.4.0
+      - Optimizes for high-performance tensor operations, such as contractions.
+      - Accelerates tensor algebra, especially in deep learning and scientific
+        computing.
+    * - `MIOpen <https://github.com/ROCm/MIOpen>`_
+      - 3.3.0
+      - Optimizes deep learning primitives such as convolutions, pooling,
+        normalization, and activation functions.
+      - Speeds up convolutional neural networks (CNNs), recurrent neural
+        networks (RNNs), and other layers. Used in operations like
+        ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
+    * - `MIGraphX <https://github.com/ROCm/AMDMIGraphX>`_
+      - 2.11.0
+      - Add graph-level optimizations, ONNX models and mixed precision support
+        and enable Ahead-of-Time (AOT) Compilation.
+      - Speeds up inference models and executes ONNX models for
+        compatibility with other frameworks.
+        ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
+    * - `MIVisionX <https://github.com/ROCm/MIVisionX>`_
+      - 3.1.0
+      - Optimizes acceleration for computer vision and AI workloads like
+        preprocessing, augmentation, and inferencing.
+      - Faster data preprocessing and augmentation pipelines for datasets like
+        ImageNet or COCO and easy to integrate into PyTorch's ``torch.utils.data``
+        and ``torchvision`` workflows.
+    * - `rocAL <https://github.com/ROCm/rocAL>`_
+      - 2.1.0
+      - Accelerates the data pipeline by offloading intensive preprocessing and
+        augmentation tasks. rocAL is part of MIVisionX.
+      - Easy to integrate into PyTorch's ``torch.utils.data`` and
+        ``torchvision`` data load workloads.
+    * - `RCCL <https://github.com/ROCm/rccl>`_
+      - 2.21.5
+      - Optimizes for multi-GPU communication for operations like AllReduce and
+        Broadcast.
+      - Distributed data parallel training (``torch.nn.parallel.DistributedDataParallel``).
+        Handles communication in multi-GPU setups.
+    * - `rocDecode <https://github.com/ROCm/rocDecode>`_
+      - 0.8.0
+      - Provide hardware-accelerated data decoding capabilities, particularly
+        for image, video, and other dataset formats.
+      - Can be integrated in ``torch.utils.data``, ``torchvision.transforms``
+        and ``torch.distributed``.
+    * - `rocJPEG <https://github.com/ROCm/rocJPEG>`_
+      - 0.6.0
+      - Provide hardware-accelerated JPEG image decoding and encoding.
+      - GPU accelerated ``torchvision.io.decode_jpeg`` and
+        ``torchvision.io.encode_jpeg`` and can be integrated in
+        ``torch.utils.data`` and ``torchvision``.
+    * - `RPP <https://github.com/ROCm/RPP>`_
+      - 1.9.1
+      - Speed up data augmentation, transformation, and other preprocessing step.
+      - Easy to integrate into PyTorch's ``torch.utils.data`` and
+        ``torchvision`` data load workloads.
+    * - `rocThrust <https://github.com/ROCm/rocThrust>`_
+      - 3.3.0
+      - Provides a C++ template library for parallel algorithms like sorting,
+        reduction, and scanning.
+      - Utilized in backend operations for tensor computations requiring
+        parallel processing.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
+      - 1.6.0
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+      - Linear layers (``torch.nn.Linear``), convolutional layers
+        (``torch.nn.Conv2d``), attention layers, general tensor operations that
+        involve matrix products, such as ``torch.matmul``, ``torch.bmm``, and
+        more.
+
+Supported and unsupported features
+================================================================================
+
+The following section maps GPU-accelerated PyTorch features to their supported
+ROCm and PyTorch versions.
+
+torch
+--------------------------------------------------------------------------------
+
+`torch <https://pytorch.org/docs/stable/index.html>`_ is the central module of
+PyTorch, providing data structures for multi-dimensional tensors and
+implementing mathematical operations on them. It also includes utilities for
+efficient serialization of tensors and arbitrary data types, along with various
+other tools.
+
+Tensor data types
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The data type of a tensor is specified using the ``dtype`` attribute or argument, and PyTorch supports a wide range of data types for different use cases.
+
+The following table lists `torch.Tensor <https://pytorch.org/docs/stable/tensors.html>`_'s single data types:
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``torch.float8_e4m3fn``
+      - 8-bit floating point, e4m3
+      - 2.3
+      - 5.5
+    * - ``torch.float8_e5m2``
+      - 8-bit floating point, e5m2
+      - 2.3
+      - 5.5
+    * - ``torch.float16`` or ``torch.half``
+      - 16-bit floating point
+      - 0.1.6
+      - 2.0
+    * - ``torch.bfloat16``
+      - 16-bit floating point
+      - 1.6
+      - 2.6
+    * - ``torch.float32`` or ``torch.float``
+      - 32-bit floating point
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.float64`` or ``torch.double``
+      - 64-bit floating point
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.complex32`` or ``torch.chalf``
+      - PyTorch provides native support for 32-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.complex64`` or ``torch.cfloat``
+      - PyTorch provides native support for 64-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.complex128`` or ``torch.cdouble``
+      - PyTorch provides native support for 128-bit complex numbers
+      - 1.6
+      - 2.0
+    * - ``torch.uint8``
+      - 8-bit integer (unsigned)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.uint16``
+      - 16-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.uint32``
+      - 32-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.uint64``
+      - 32-bit integer (unsigned)
+      - 2.3
+      - Not natively supported
+    * - ``torch.int8``
+      - 8-bit integer (signed)
+      - 1.12
+      - 5.0
+    * - ``torch.int16`` or ``torch.short``
+      - 16-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.int32`` or ``torch.int``
+      - 32-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.int64`` or ``torch.long``
+      - 64-bit integer (signed)
+      - 0.1.12_2
+      - 2.0
+    * - ``torch.bool``
+      - Boolean
+      - 1.2
+      - 2.0
+    * - ``torch.quint8``
+      - Quantized 8-bit integer (unsigned)
+      - 1.8
+      - 5.0
+    * - ``torch.qint8``
+      - Quantized 8-bit integer (signed)
+      - 1.8
+      - 5.0
+    * - ``torch.qint32``
+      - Quantized 32-bit integer (signed)
+      - 1.8
+      - 5.0
+    * - ``torch.quint4x2``
+      - Quantized 4-bit integer (unsigned)
+      - 1.8
+      - 5.0
+
+.. note::
+
+  Unsigned types aside from ``uint8`` are currently only have limited support in
+  eager mode (they primarily exist to assist usage with ``torch.compile``).
+
+  The :doc:`ROCm precision support page <rocm:reference/precision-support>`
+  collected the native HW support of different data types.
+
+torch.cuda
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+``torch.cuda`` in PyTorch is a module that provides utilities and functions for
+managing and utilizing AMD and NVIDIA GPUs. It enables GPU-accelerated
+computations, memory management, and efficient execution of tensor operations,
+leveraging ROCm and CUDA as the underlying frameworks.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - Device management
+      - Utilities for managing and interacting with GPUs.
+      - 0.4.0
+      - 3.8
+    * - Tensor operations on GPU
+      - Perform tensor operations such as addition and matrix multiplications on
+        the GPU.
+      - 0.4.0
+      - 3.8
+    * - Streams and events
+      - Streams allow overlapping computation and communication for optimized
+        performance, events enable synchronization.
+      - 1.6.0
+      - 3.8
+    * - Memory management
+      - Functions to manage and inspect memory usage like
+        ``torch.cuda.memory_allocated()``, ``torch.cuda.max_memory_allocated()``,
+        ``torch.cuda.memory_reserved()`` and ``torch.cuda.empty_cache()``.
+      - 0.3.0
+      - 1.9.2
+    * - Running process lists of memory management
+      - Return a human-readable printout of the running processes and their GPU
+        memory use for a given device with functions like 
+        ``torch.cuda.memory_stats()`` and ``torch.cuda.memory_summary()``.
+      - 1.8.0
+      - 4.0
+    * - Communication collectives
+      - A set of APIs that enable efficient communication between multiple GPUs,
+        allowing for distributed computing and data parallelism.
+      - 1.9.0
+      - 5.0
+    * - ``torch.cuda.CUDAGraph``
+      - Graphs capture sequences of GPU operations to minimize kernel launch
+        overhead and improve performance.
+      - 1.10.0
+      - 5.3
+    * - TunableOp
+      - A mechanism that allows certain operations to be more flexible and
+        optimized for performance. It enables automatic tuning of kernel
+        configurations and other settings to achieve the best possible
+        performance based on the specific hardware (GPU) and workload.
+      - 2.0
+      - 5.4
+    * - NVIDIA Tools Extension (NVTX)
+      - Integration with NVTX for profiling and debugging GPU performance using
+        NVIDIA's Nsight tools.
+      - 1.8.0
+      - ❌
+    * - Lazy loading NVRTC
+      - Delays JIT compilation with NVRTC until the code is explicitly needed.
+      - 1.13.0
+      - ❌
+    * - Jiterator (beta)
+      - Jiterator allows asynchronous data streaming into computation streams
+        during training loops.
+      - 1.13.0
+      - 5.2
+
+.. Need to validate and extend.
+
+torch.backends.cuda
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+``torch.backends.cuda`` is a PyTorch module that provides configuration options
+and flags to control the behavior of CUDA or ROCm operations. It is part of the
+PyTorch backend configuration system, which allows users to fine-tune how
+PyTorch interacts with the CUDA or ROCm environment.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``cufft_plan_cache``
+      - Manages caching of GPU FFT plans to optimize repeated FFT computations.
+      - 1.7.0
+      - 5.0
+    * - ``matmul.allow_tf32``
+      - Enables or disables the use of TensorFloat-32 (TF32) precision for
+        faster matrix multiplications on GPUs with Tensor Cores.
+      - 1.10.0
+      - ❌
+    * - ``matmul.allow_fp16_reduced_precision_reduction``
+      - Reduced precision reductions (e.g., with fp16 accumulation type) are
+        allowed with fp16 GEMMs.
+      - 2.0
+      - ❌
+    * - ``matmul.allow_bf16_reduced_precision_reduction``
+      - Reduced precision reductions are allowed with bf16 GEMMs.
+      - 2.0
+      - ❌
+    * - ``enable_cudnn_sdp``
+      - Globally enables cuDNN SDPA's kernels within SDPA.
+      - 2.0
+      - ❌
+    * - ``enable_flash_sdp``
+      - Globally enables or disables FlashAttention for SDPA.
+      - 2.1
+      - ❌
+    * - ``enable_mem_efficient_sdp``
+      - Globally enables or disables Memory-Efficient Attention for SDPA.
+      - 2.1
+      - ❌
+    * - ``enable_math_sdp``
+      - Globally enables or disables the PyTorch C++ implementation within SDPA.
+      - 2.1
+      - ❌
+
+.. Need to validate and extend.
+
+torch.backends.cudnn
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Supported ``torch`` options:
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``allow_tf32``
+      - TensorFloat-32 tensor cores may be used in cuDNN convolutions on NVIDIA
+        Ampere or newer GPUs.
+      - 1.12.0
+      - ❌
+    * - ``deterministic``
+      - A bool that, if True, causes cuDNN to only use deterministic
+        convolution algorithms.
+      - 1.12.0
+      - 6.0
+
+Automatic mixed precision: torch.amp
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+PyTorch that automates the process of using both 16-bit (half-precision,
+float16) and 32-bit (single-precision, float32) floating-point types in model
+training and inference.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - Autocasting
+      - Instances of autocast serve as context managers or decorators that allow
+        regions of your script to run in mixed precision.
+      - 1.9
+      - 2.5
+    * - Gradient scaling
+      - To prevent underflow, “gradient scaling” multiplies the network’s
+        loss(es) by a scale factor and invokes a backward pass on the scaled
+        loss(es). Gradients flowing backward through the network are then
+        scaled by the same factor. In other words, gradient values have a
+        larger magnitude, so they don’t flush to zero.
+      - 1.9
+      - 2.5
+    * - CUDA op-specific behavior
+      - These ops always go through autocasting whether they are invoked as part
+        of a ``torch.nn.Module``, as a function, or as a ``torch.Tensor`` method. If
+        functions are exposed in multiple namespaces, they go through
+        autocasting regardless of the namespace.
+      - 1.9
+      - 2.5
+
+Distributed library features
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The PyTorch distributed library includes a collective of parallelism modules, a
+communications layer, and infrastructure for launching and debugging large
+training jobs. See :ref:`rocm-for-ai-pytorch-distributed` for more information.
+
+The Distributed Library feature in PyTorch provides tools and APIs for building
+and running distributed machine learning workflows. It allows training models
+across multiple processes, GPUs, or nodes in a cluster, enabling efficient use
+of computational resources and scalability for large-scale tasks.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - TensorPipe
+      - TensorPipe is a point-to-point communication library integrated into
+        PyTorch for distributed training. It is designed to handle tensor data
+        transfers efficiently between different processes or devices, including
+        those on separate machines.
+      - 1.8
+      - 5.4
+    * - Gloo
+      - Gloo is designed for multi-machine and multi-GPU setups, enabling
+        efficient communication and synchronization between processes. Gloo is
+        one of the default backends for PyTorch's Distributed Data Parallel
+        (DDP) and RPC frameworks, alongside other backends like NCCL and MPI.
+      - 1.0
+      - 2.0
+
+torch.compiler
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since PyTorch
+      - Since ROCm
+    * - ``torch.compiler`` (AOT Autograd)
+      - Autograd captures not only the user-level code, but also backpropagation,
+        which results in capturing the backwards pass “ahead-of-time”. This
+        enables acceleration of both forwards and backwards pass using
+        ``TorchInductor``.
+      - 2.0
+      - 5.3
+    * - ``torch.compiler`` (TorchInductor)
+      - The default ``torch.compile`` deep learning compiler that generates fast
+        code for multiple accelerators and backends. You need to use a backend
+        compiler to make speedups through ``torch.compile`` possible. For AMD,
+        NVIDIA, and Intel GPUs, it leverages OpenAI Triton as the key building block.
+      - 2.0
+      - 5.3
+
+torchaudio
+--------------------------------------------------------------------------------
+
+The `torchaudio <https://pytorch.org/audio/stable/index.html>`_ library provides
+utilities for processing audio data in PyTorch, such as audio loading,
+transformations, and feature extraction.
+
+To ensure GPU-acceleration with ``torchaudio.transforms``, you need to move audio
+data (waveform tensor) explicitly to GPU using ``.to('cuda')``.
+
+The following ``torchaudio`` features are GPU-accelerated.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since torchaudio version
+      - Since ROCm
+    * - ``torchaudio.transforms.Spectrogram``
+      - Generate spectrogram of an input waveform using STFT.
+      - 0.6.0
+      - 4.5
+    * - ``torchaudio.transforms.MelSpectrogram``
+      - Generate the mel-scale spectrogram of raw audio signals.
+      - 0.9.0
+      - 4.5
+    * - ``torchaudio.transforms.MFCC``
+      - Extract of MFCC features.
+      - 0.9.0
+      - 4.5
+    * - ``torchaudio.transforms.Resample``
+      - Resample a signal from one frequency to another
+      - 0.9.0
+      - 4.5
+
+torchvision
+--------------------------------------------------------------------------------
+
+The `torchvision <https://pytorch.org/vision/stable/index.html>`_ library
+provide datasets, model architectures, and common image transformations for
+computer vision.
+
+The following ``torchvision`` features are GPU-accelerated.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Features
+      - Description
+      - Since torchvision version
+      - Since ROCm
+    * - ``torchvision.transforms.functional``
+      - Provides GPU-compatible transformations for image preprocessing like
+        resize, normalize, rotate and crop.
+      - 0.2.0
+      - 4.0
+    * - ``torchvision.ops``
+      - GPU-accelerated operations for object detection and segmentation tasks.
+        ``torchvision.ops.roi_align``, ``torchvision.ops.nms`` and
+        ``box_convert``.
+      - 0.6.0
+      - 3.3
+    * - ``torchvision.models`` with ``.to('cuda')``
+      - ``torchvision`` provides several pre-trained models (ResNet, Faster
+        R-CNN, Mask R-CNN, ...) that can run on CUDA for faster inference and
+        training.
+      - 0.1.6
+      - 2.x
+    * - ``torchvision.io``
+      - Video decoding and frame extraction using GPU acceleration with NVIDIA’s
+        NVDEC and nvJPEG (rocJPEG) on CUDA-enabled GPUs.
+      - 0.4.0
+      - 6.3
+
+torchtext
+--------------------------------------------------------------------------------
+
+The `torchtext <https://pytorch.org/text/stable/index.html>`_ library provides
+utilities for processing and working with text data in PyTorch, including
+tokenization, vocabulary management, and text embeddings. torchtext supports
+preprocessing pipelines and integration with PyTorch models, simplifying the
+implementation of natural language processing (NLP) tasks.
+
+To leverage GPU acceleration in torchtext, you need to move tensors
+explicitly to the GPU using ``.to('cuda')``.
+
+* torchtext does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+torchtune
+--------------------------------------------------------------------------------
+
+The `torchtune <https://pytorch.org/torchtune/stable/index.html>`_ library for
+authoring, fine-tuning and experimenting with LLMs.
+
+* Usage: It works out-of-the-box, enabling developers to fine-tune ROCm PyTorch solutions.
+
+* Only official release exists.
+
+torchserve
+--------------------------------------------------------------------------------
+
+The `torchserve <https://pytorch.org/torchserve/>`_ is a PyTorch domain library
+for common sparsity and parallelism primitives needed for large-scale recommender
+systems.
+
+* torchtext does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+torchrec
+--------------------------------------------------------------------------------
+
+The `torchrec <https://pytorch.org/torchrec/>`_ is a PyTorch domain library for
+common sparsity and parallelism primitives needed for large-scale recommender
+systems.
+
+* torchrec does not implement its own kernels. ROCm support is enabled by linking against ROCm libraries.
+
+* Only official release exists.
+
+Unsupported PyTorch features
+----------------------------
+
+The following are GPU-accelerated PyTorch features not currently supported by ROCm.
+
+.. list-table::
+    :widths: 30, 60, 10
+    :header-rows: 1
+
+    * - Data type
+      - Description
+      - Since PyTorch
+    * - APEX batch norm
+      - Use APEX batch norm instead of PyTorch batch norm.
+      - 1.6.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_tf32``
+      - A bool that controls whether TensorFloat-32 tensor cores may be used in
+        matrix multiplications.
+      - 1.7
+    * - ``torch.cuda`` / NVIDIA Tools Extension (NVTX)
+      - Integration with NVTX for profiling and debugging GPU performance using
+        NVIDIA's Nsight tools.
+      - 1.7.0
+    * - ``torch.cuda`` / Lazy loading NVRTC
+      - Delays JIT compilation with NVRTC until the code is explicitly needed.
+      - 1.8.0
+    * - ``torch-tensorrt``
+      - Integrate TensorRT library for optimizing and deploying PyTorch models.
+        ROCm does not have equialent library for TensorRT.
+      - 1.9.0
+    * - ``torch.backends`` / ``cudnn.allow_tf32``
+      - TensorFloat-32 tensor cores may be used in cuDNN convolutions.
+      - 1.10.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_fp16_reduced_precision_reduction``
+      - Reduced precision reductions with fp16 accumulation type are
+        allowed with fp16 GEMMs.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``matmul.allow_bf16_reduced_precision_reduction``
+      - Reduced precision reductions are allowed with bf16 GEMMs.
+      - 2.0
+    * - ``torch.nn.functional`` / ``scaled_dot_product_attention`` 
+      - Flash attention backend for SDPA to accelerate attention computation in
+        transformer-based models.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``enable_cudnn_sdp``
+      - Globally enables cuDNN SDPA's kernels within SDPA.
+      - 2.0
+    * - ``torch.backends.cuda`` / ``enable_flash_sdp``
+      - Globally enables or disables FlashAttention for SDPA.
+      - 2.1
+    * - ``torch.backends.cuda`` / ``enable_mem_efficient_sdp``
+      - Globally enables or disables Memory-Efficient Attention for SDPA.
+      - 2.1
+    * - ``torch.backends.cuda`` / ``enable_math_sdp``
+      - Globally enables or disables the PyTorch C++ implementation within SDPA.
+      - 2.1
+    * - Dynamic parallelism
+      - PyTorch itself does not directly expose dynamic parallelism as a core
+        feature. Dynamic parallelism allow GPU threads to launch additional
+        threads which can be reached using custom operations via the
+        ``torch.utils.cpp_extension`` module.
+      - Not a core feature
+    * - Unified memory support in PyTorch
+      - Unified Memory is not directly exposed in PyTorch's core API, it can be
+        utilized effectively through custom CUDA extensions or advanced
+        workflows.
+      - Not a core feature
+
+Use cases and recommendations
+================================================================================
+
+* :doc:`Using ROCm for AI: training a model </how-to/rocm-for-ai/train-a-model>` provides
+  guidance on how to leverage the ROCm platform for training AI models. It covers the steps, tools, and best practices
+  for optimizing training workflows on AMD GPUs using PyTorch features.
+
+* :doc:`Single-GPU fine-tuning and inference </how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference>`
+  describes and demonstrates how to use the ROCm platform for the fine-tuning and inference of
+  machine learning models, particularly large language models (LLMs), on systems with a single AMD
+  Instinct MI300X accelerator. This page provides a detailed guide for setting up, optimizing, and
+  executing fine-tuning and inference workflows in such environments.
+
+* :doc:`Multi-GPU fine-tuning and inference optimization </how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference>`
+  describes and demonstrates the fine-tuning and inference of machine learning models on systems
+  with multi MI300X accelerators.
+
+* The :doc:`Instinct MI300X workload optimization guide </how-to/tuning-guides/mi300x/workload>` provides detailed
+  guidance on optimizing workloads for the AMD Instinct MI300X accelerator using ROCm. This guide is aimed at helping
+  users achieve optimal performance for deep learning and other high-performance computing tasks on the MI300X
+  accelerator.
+
+* The :doc:`Inception with PyTorch documentation </conceptual/ai-pytorch-inception>`
+  describes how PyTorch integrates with ROCm for AI workloads It outlines the use of PyTorch on the ROCm platform and
+  focuses on how to efficiently leverage AMD GPU hardware for training and inference tasks in AI applications.
+
+For more use cases and recommendations, see `ROCm PyTorch blog posts <https://rocm.blogs.amd.com/blog/tag/pytorch.html>`_

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

@@ -11,20 +11,24 @@ ROCm provides a comprehensive ecosystem for deep learning development, including
 deep learning frameworks and libraries such as PyTorch, TensorFlow, and JAX. ROCm works closely with these
 frameworks to ensure that framework-specific optimizations take advantage of AMD accelerator and GPU architectures.
 
-The following guides cover installation processes for ROCm-aware deep learning frameworks.
+The following guides provide information on compatibility and supported
+features for these ROCm-enabled deep learning frameworks.
 
-* :doc:`PyTorch for ROCm <rocm-install-on-linux:install/3rd-party/pytorch-install>`
-* :doc:`TensorFlow for ROCm <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
-* :doc:`JAX for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`
+* :doc:`PyTorch compatibility <../compatibility/pytorch-compatibility>`
+.. * :doc:`TensorFlow compatibility <../compatibility/tensorflow-compatibility>`
+.. * :doc:`JAX compatibility <../compatibility/jax-compatibility>`
 
-The following chart steps through typical installation workflows for installing deep learning frameworks for ROCm.
+This chart steps through typical installation workflows for installing deep learning frameworks for ROCm.
 
 .. image:: ../data/how-to/framework_install_2024_07_04.png
    :alt: Flowchart for installing ROCm-aware machine learning frameworks
    :align: center
 
-Find information on version compatibility and framework release notes in :doc:`Third-party support matrix
-<rocm-install-on-linux:reference/3rd-party-support-matrix>`.
+See the installation instructions to get started.
+
+* :doc:`PyTorch for ROCm <rocm-install-on-linux:install/3rd-party/pytorch-install>`
+* :doc:`TensorFlow for ROCm <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
+* :doc:`JAX for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`
 
 .. note::
 
@@ -36,3 +40,4 @@ through the following guides.
 * :doc:`rocm-for-ai/index`
 
 * :doc:`llm-fine-tuning-optimization/index`
+

docs/how-to/gpu-enabled-mpi.rst

@@ -1,264 +0,0 @@
-.. meta::
-   :description: GPU-enabled Message Passing Interface
-   :keywords: Message Passing Interface, MPI, AMD, ROCm
-
-***************************************************************************************************
-GPU-enabled Message Passing Interface
-***************************************************************************************************
-
-The Message Passing Interface (`MPI <https://www.mpi-forum.org>`_) is a standard API for distributed
-and parallel application development that can scale to multi-node clusters. To facilitate the porting of
-applications to clusters with GPUs, ROCm enables various technologies. You can use these
-technologies add GPU pointers to MPI calls and enable ROCm-aware MPI libraries to deliver optimal
-performance for both intra-node and inter-node GPU-to-GPU communication.
-
-The AMD kernel driver exposes remote direct memory access (RDMA) through *PeerDirect* interfaces.
-This allows network interface cards (NICs) to directly read and write to RDMA-capable GPU device
-memory, resulting in high-speed direct memory access (DMA) transfers between GPU and NIC. These
-interfaces are used to optimize inter-node MPI message communication.
-
-The Open MPI project is an open source implementation of the MPI. It's developed and maintained by
-a consortium of academic, research, and industry partners. To compile Open MPI with ROCm support,
-refer to the following sections:
-
-* :ref:`open-mpi-ucx`
-* :ref:`open-mpi-libfabric`
-
-.. _open-mpi-ucx:
-
-ROCm-aware Open MPI on InfiniBand and RoCE networks using UCX
-================================================================
-
-The `Unified Communication Framework <https://www.openucx.org/documentation>`_ (UCX), is an
-open source, cross-platform framework designed to provide a common set of communication
-interfaces for various network programming models and interfaces. UCX uses ROCm technologies to
-implement various network operation primitives. UCX is the standard communication library for
-InfiniBand and RDMA over Converged Ethernet (RoCE) network interconnect. To optimize data
-transfer operations, many MPI libraries, including Open MPI, can leverage UCX internally.
-
-UCX and Open MPI have a compile option to enable ROCm support. To install and configure UCX to compile Open MPI for ROCm, use the following instructions.
-
-1. Set environment variables to install all software components in the same base directory. We use the
-home directory in our example, but you can specify a different location if you want.
-
-    .. code-block:: shell
-
-        export INSTALL_DIR=$HOME/ompi_for_gpu
-        export BUILD_DIR=/tmp/ompi_for_gpu_build
-        mkdir -p $BUILD_DIR
-
-2. Install UCX. To view UCX and ROCm version compatibility, refer to the
-`communication libraries tables <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/3rd-party-support-matrix.html>`_
-
-    .. code-block:: shell
-
-        export UCX_DIR=$INSTALL_DIR/ucx
-        cd $BUILD_DIR
-        git clone https://github.com/openucx/ucx.git -b v1.15.x
-        cd ucx
-        ./autogen.sh
-        mkdir build
-        cd build
-        ../configure -prefix=$UCX_DIR \
-            --with-rocm=/opt/rocm
-        make -j $(nproc)
-        make -j $(nproc) install
-
-3. Install Open MPI.
-
-    .. code-block:: shell
-
-        export OMPI_DIR=$INSTALL_DIR/ompi
-        cd $BUILD_DIR
-        git clone --recursive https://github.com/open-mpi/ompi.git \
-            -b v5.0.x
-        cd ompi
-        ./autogen.pl
-        mkdir build
-        cd build
-        ../configure --prefix=$OMPI_DIR --with-ucx=$UCX_DIR \
-            --with-rocm=/opt/rocm
-        make -j $(nproc)
-        make install
-
-.. _rocm-enabled-osu:
-
-ROCm-enabled OSU benchmarks
----------------------------------------------------------------------------------------------------------------
-
-You can use OSU Micro Benchmarks (OMB) to evaluate the performance of various primitives on
-ROCm-supported AMD GPUs. The ``--enable-rocm`` option exposes this functionality.
-
-.. code-block:: shell
-
-    export OSU_DIR=$INSTALL_DIR/osu
-    cd $BUILD_DIR
-    wget http://mvapich.cse.ohio-state.edu/download/mvapich/osu-micro-benchmarks-7.2.tar.gz
-    tar xfz osu-micro-benchmarks-7.2.tar.gz
-    cd osu-micro-benchmarks-7.2
-    ./configure --enable-rocm \
-        --with-rocm=/opt/rocm \
-        CC=$OMPI_DIR/bin/mpicc CXX=$OMPI_DIR/bin/mpicxx \
-        LDFLAGS="-L$OMPI_DIR/lib/ -lmpi -L/opt/rocm/lib/ \
-        $(hipconfig -C) -lamdhip64" CXXFLAGS="-std=c++11"
-    make -j $(nproc)
-
-Intra-node run
-----------------------------------------------------------------------------------------------------------------
-
-Before running an Open MPI job, you must set the following environment variables to ensure that
-you're using the correct versions of Open MPI and UCX.
-
-.. code-block:: shell
-
-    export LD_LIBRARY_PATH=$OMPI_DIR/lib:$UCX_DIR/lib:/opt/rocm/lib
-    export PATH=$OMPI_DIR/bin:$PATH
-
-To run the OSU bandwidth benchmark between the first two GPU devices (``GPU 0`` and ``GPU 1``)
-inside the same node, use the following code.
-
-.. code-block:: shell
-
-    $OMPI_DIR/bin/mpirun -np 2 \
-    -x UCX_TLS=sm,self,rocm \
-    --mca pml ucx \
-    ./c/mpi/pt2pt/standard/osu_bw D D
-
-This measures the unidirectional bandwidth from the first device (``GPU 0``) to the second device
-(``GPU 1``). To select specific devices, for example ``GPU 2`` and ``GPU 3``, include the following
-command:
-
-.. code-block:: shell
-
-    export HIP_VISIBLE_DEVICES=2,3
-
-To force using a copy kernel instead of a DMA engine for the data transfer, use the following
-command:
-
-.. code-block:: shell
-
-    export HSA_ENABLE_SDMA=0
-
-The following output shows the effective transfer bandwidth measured for inter-die data transfer
-between ``GPU 2`` and ``GPU 3`` on a system with MI250 GPUs. For messages larger than 67 MB, an effective
-utilization of about 150 GB/sec is achieved:
-
-.. image:: ../data/how-to/gpu-enabled-mpi-1.png
-  :width: 400
-  :alt: Inter-GPU bandwidth for various payload sizes
-
-Collective operations
-----------------------------------------------------------------------------------------------------------------
-
-Collective operations on GPU buffers are best handled through the Unified Collective Communication
-(UCC) library component in Open MPI. To accomplish this, you must configure and compile the UCC
-library with ROCm support.
-
-.. note::
-
-    You can verify UCC and ROCm version compatibility using the
-    `communication libraries tables <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/3rd-party-support-matrix.html>`_
-
-.. code-block:: shell
-
-    export UCC_DIR=$INSTALL_DIR/ucc
-    git clone https://github.com/openucx/ucc.git -b v1.2.x
-    cd ucc
-    ./autogen.sh
-    ./configure --with-rocm=/opt/rocm \
-                --with-ucx=$UCX_DIR   \
-                --prefix=$UCC_DIR
-    make -j && make install
-
-    # Configure and compile Open MPI with UCX, UCC, and ROCm support
-    cd ompi
-    ./configure --with-rocm=/opt/rocm  \
-                --with-ucx=$UCX_DIR    \
-                --with-ucc=$UCC_DIR
-                --prefix=$OMPI_DIR
-
-To use the UCC component with an MPI application, you must set additional parameters:
-
-.. code-block:: shell
-
-    mpirun --mca pml ucx --mca osc ucx \
-       --mca coll_ucc_enable 1     \
-       --mca coll_ucc_priority 100 -np 64 ./my_mpi_app
-
-.. _open-mpi-libfabric:
-
-ROCm-aware Open MPI using libfabric
-================================================================
-
-For network interconnects that are not covered in the previous category, such as HPE Slingshot,
-ROCm-aware communication can often be achieved through the libfabric library. For more information,
-refer to the `libfabric documentation <https://github.com/ofiwg/libfabric/wiki>`_.
-
-.. note::
-
-    When using Open MPI v5.0.x with libfabric support, shared memory communication between
-    processes on the same node goes through the *ob1/sm* component. This component has
-    fundamental support for GPU memory that is, accomplished by using a staging host buffer
-    Consequently, the performance of device-to-device shared memory communication is lower than
-    the theoretical peak performance allowed by the GPU-to-GPU interconnect.
-
-1.	Install libfabric. Note that libfabric is often pre-installed. To determine if it's already installed, run:
-
-    .. code-block:: shell
-
-        module avail libfabric
-
-    Alternatively, you can download and compile libfabric with ROCm support. Note that not all
-    components required to support some networks (e.g., HPE Slingshot) are available in the open source
-    repository. Therefore, using a pre-installed libfabric library is strongly recommended over compiling
-    libfabric manually.
-
-    If a pre-compiled libfabric library is available on your system, you can skip the following step.
-
-2.	Compile libfabric with ROCm support.
-
-    .. code-block:: shell
-
-        export OFI_DIR=$INSTALL_DIR/ofi
-        cd $BUILD_DIR
-        git clone https://github.com/ofiwg/libfabric.git -b v1.19.x
-        cd libfabric
-        ./autogen.sh
-        ./configure --prefix=$OFI_DIR   \
-                    --with-rocr=/opt/rocm
-        make -j $(nproc)
-        make install
-
-Installing Open MPI with libfabric support
-----------------------------------------------------------------------------------------------------------------
-
-To build Open MPI with libfabric, use the following code:
-
-.. code-block:: shell
-
-    export OMPI_DIR=$INSTALL_DIR/ompi
-    cd $BUILD_DIR
-    git clone --recursive https://github.com/open-mpi/ompi.git \
-        -b v5.0.x
-    cd ompi
-    ./autogen.pl
-    mkdir build
-    cd build
-    ../configure --prefix=$OMPI_DIR --with-ofi=$OFI_DIR \
-                    --with-rocm=/opt/rocm
-    make -j $(nproc)
-    make install
-
-ROCm-aware OSU with Open MPI and libfabric
-----------------------------------------------------------------------------------------------------------------
-
-Compiling a ROCm-aware version of OSU benchmarks with Open MPI and libfabric uses the same
-process described in :ref:`rocm-enabled-osu`.
-
-To run an OSU benchmark using multiple nodes, use the following code:
-
-.. code-block:: shell
-
-    export LD_LIBRARY_PATH=$OMPI_DIR/lib:$OFI_DIR/lib64:/opt/rocm/lib
-    $OMPI_DIR/bin/mpirun --mca pml ob1 --mca btl_ofi_mode 2 -np 2 \
-    ./c/mpi/pt2pt/standard/osu_bw D D

docs/how-to/performance-validation/mi300x/vllm-benchmark.rst

@@ -399,9 +399,6 @@ Further reading
 - To learn how to optimize inference on LLMs, see
   :doc:`Fine-tuning LLMs and inference optimization </how-to/llm-fine-tuning-optimization/index>`.
 
-- For a list of other ready-made Docker images for ROCm, see the
-  :doc:`Docker image support matrix <rocm-install-on-linux:reference/docker-image-support-matrix>`.
-
 - To compare with the previous version of the ROCm vLLM Docker image for performance validation, refer to
   `LLM inference performance validation on AMD Instinct MI300X (ROCm 6.2.0) <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_.
 

docs/how-to/tuning-guides/mi300x/workload.rst

@@ -92,7 +92,7 @@ involves configuring tensor parallelism, leveraging advanced features, and
 ensuring efficient execution. Here’s how to optimize vLLM performance:
 
 * Tensor parallelism: Configure the
-  :ref:`tensor-parallel-size parameter <mi300x-vllm-optimize-tp-gemm>` to distribute
+  :ref:`tensor-parallel-size parameter <mi300x-vllm-multiple-gpus>` to distribute
   tensor computations across multiple GPUs. Adjust parameters such as
   ``batch-size``, ``input-len``, and ``output-len`` based on your workload.
 

docs/index.md

@@ -42,7 +42,6 @@ ROCm documentation is organized into the following categories:
 * [Fine-tune LLMs and inference optimization](./how-to/llm-fine-tuning-optimization/index.rst)
 * [System optimization](./how-to/system-optimization/index.rst)
 * [AMD Instinct MI300X performance validation and tuning](./how-to/tuning-guides/mi300x/index.rst)
-* [GPU cluster networking](https://rocm.docs.amd.com/projects/gpu-cluster-networking/en/latest/index.html)
 * [System debugging](./how-to/system-debugging.md)
 * [Use MPI](./how-to/gpu-enabled-mpi.rst)
 * [Use advanced compiler features](./conceptual/compiler-topics.md)

docs/sphinx/_toc.yml.in

@@ -94,10 +94,6 @@ subtrees:
         title: System tuning
       - file: how-to/tuning-guides/mi300x/workload.rst
         title: Workload tuning
-  - url: https://rocm.docs.amd.com/projects/gpu-cluster-networking/en/${branch}/index.html
-    title: GPU cluster networking
-  - file: how-to/gpu-enabled-mpi.rst
-    title: Use MPI
   - file: how-to/system-debugging.md
   - file: conceptual/compiler-topics.md
     title: Use advanced compiler features

docs/sphinx/requirements.in

@@ -1,3 +1,3 @@
-rocm-docs-core==1.11.0
+rocm-docs-core==1.12.0
 sphinx-reredirects
 sphinx-sitemap

docs/sphinx/requirements.txt

@@ -90,7 +90,7 @@ requests==2.32.3
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.11.0
+rocm-docs-core==1.12.0
     # via -r requirements.in
 smmap==5.0.1
     # via gitdb