improve title

wording
words words
2026-01-10 23:28:03 -05:00 · 2024-12-16 12:57:17 -05:00 · 2024-12-16 12:45:53 -05:00 · 2024-12-13 22:19:52 -05:00
159 changed files with 4802 additions and 6163 deletions
--- a/.azuredevops/components/omniperf.yml
+++ b/.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;/$;;')"
--- a/.azuredevops/components/rocprofiler-systems.yml
+++ b/.azuredevops/components/rocprofiler-systems.yml
@@ -51,7 +51,6 @@ parameters:
    - rocprofiler
    - rocprofiler-register
    - roctracer
-    - rocprofiler-sdk

 jobs:
 - job: rocprofiler_systems
@@ -74,12 +73,6 @@ jobs:
  - 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 }}
@@ -116,7 +109,6 @@ jobs:
        -DROCPROFSYS_BUILD_TESTING=ON
        -DROCPROFSYS_BUILD_DYNINST=ON
        -DROCPROFSYS_BUILD_LIBUNWIND=ON
-        -DROCPROFSYS_DISABLE_EXAMPLES="openmp-target"
        -DDYNINST_BUILD_TBB=ON
        -DDYNINST_BUILD_ELFUTILS=ON
        -DDYNINST_BUILD_LIBIBERTY=ON
--- a/.azuredevops/nightly/pytorch.yml
+++ b/.azuredevops/nightly/pytorch.yml
@@ -142,10 +142,6 @@ parameters:
    - binary_ufuncs
    - autograd
 #    - inductor/torchinductor takes too long
-# set to false to disable torchvision build and test
- name: includeVision
-  type: boolean
-  default: false

 trigger: none
 pr: none
@@ -241,12 +237,6 @@ jobs:
        git clone https://github.com/pytorch/builder.git --depth=1 --recurse-submodules
        sudo ln -s $(Build.SourcesDirectory)/builder /builder
      workingDirectory: $(Build.SourcesDirectory)
-  - task: Bash@3
-    displayName: Temporarily Patch CK Submodule
-    inputs:
-      targetType: inline
-      script: git pull origin develop
-      workingDirectory: $(Build.SourcesDirectory)/pytorch/third_party/composable_kernel
  - task: Bash@3
    displayName: Install patchelf
    inputs:
@@ -306,60 +296,59 @@ jobs:
      sourceDir: /remote/wheelhouserocm$(ROCM_VERSION)
      contentsString: '*.whl'
 # common helper source for pytorch vision and audio
-  - ${{ if eq(parameters.includeVision, true) }}:
-    - task: Bash@3
-      displayName: git clone pytorch test-infra
-      inputs:
-        targetType: inline
-        script: git clone https://github.com/pytorch/test-infra.git --depth=1 --recurse-submodules
-        workingDirectory: $(Build.SourcesDirectory)
-    - task: Bash@3
-      displayName: install package helper
-      inputs:
-        targetType: inline
-        script: python3 -m pip install test-infra/tools/pkg-helpers
-        workingDirectory: $(Build.SourcesDirectory)
-    - task: Bash@3
-      displayName: pytorch pkg helpers
-      inputs:
-        targetType: inline
-        script: CU_VERSION=${CU_VERSION} CHANNEL=${CHANNEL} python -m pytorch_pkg_helpers
-  # get torch vision source and build
-    - task: Bash@3
-      displayName: git clone pytorch vision
-      inputs:
-        targetType: inline
-        script: git clone https://github.com/pytorch/vision.git --depth=1 --recurse-submodules
-        workingDirectory: $(Build.SourcesDirectory)
-    - task: Bash@3
-      displayName: Build vision
-      inputs:
-        targetType: inline
-        script: >-
-          TORCH_PACKAGE_NAME=torch.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
-          TORCHVISION_PACKAGE_NAME=torchvision.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
-          PYTORCH_VERSION=$(cat $(Build.SourcesDirectory)/pytorch/version.txt | cut -da -f1)post$(date -u +%Y%m%d)
-          BUILD_VERSION=$(cat $(Build.SourcesDirectory)/vision/version.txt | cut -da -f1)post$(date -u +%Y%m%d)
-          python3 setup.py bdist_wheel
-        workingDirectory: $(Build.SourcesDirectory)/vision
-    - task: Bash@3
-      displayName: Relocate vision
-      inputs:
-        targetType: inline
-        script: python3 packaging/wheel/relocate.py
-        workingDirectory: $(Build.SourcesDirectory)/vision
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
-      parameters:
-        sourceDir: $(Build.SourcesDirectory)/vision/dist
-        contentsString: '*.whl'
-        clean: false
+  - task: Bash@3
+    displayName: git clone pytorch test-infra
+    inputs:
+      targetType: inline
+      script: git clone https://github.com/pytorch/test-infra.git --depth=1 --recurse-submodules
+      workingDirectory: $(Build.SourcesDirectory)
+  - task: Bash@3
+    displayName: install package helper
+    inputs:
+      targetType: inline
+      script: python3 -m pip install test-infra/tools/pkg-helpers
+      workingDirectory: $(Build.SourcesDirectory)
+  - task: Bash@3
+    displayName: pytorch pkg helpers
+    inputs:
+      targetType: inline
+      script: CU_VERSION=${CU_VERSION} CHANNEL=${CHANNEL} python -m pytorch_pkg_helpers
+# get torch vision source and build
+  - task: Bash@3
+    displayName: git clone pytorch vision
+    inputs:
+      targetType: inline
+      script: git clone https://github.com/pytorch/vision.git --depth=1 --recurse-submodules
+      workingDirectory: $(Build.SourcesDirectory)
+  - task: Bash@3
+    displayName: Build vision
+    inputs:
+      targetType: inline
+      script: >-
+        TORCH_PACKAGE_NAME=torch.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
+        TORCHVISION_PACKAGE_NAME=torchvision.$(ROCM_BRANCH).$(JOB_GPU_TARGET)
+        PYTORCH_VERSION=$(cat $(Build.SourcesDirectory)/pytorch/version.txt | cut -da -f1)post$(date -u +%Y%m%d)
+        BUILD_VERSION=$(cat $(Build.SourcesDirectory)/vision/version.txt | cut -da -f1)post$(date -u +%Y%m%d)
+        python3 setup.py bdist_wheel
+      workingDirectory: $(Build.SourcesDirectory)/vision
+  - task: Bash@3
+    displayName: Relocate vision
+    inputs:
+      targetType: inline
+      script: python3 packaging/wheel/relocate.py
+      workingDirectory: $(Build.SourcesDirectory)/vision
+  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-prepare-package.yml
+    parameters:
+      sourceDir: $(Build.SourcesDirectory)/vision/dist
+      contentsString: '*.whl'
+      clean: false
  - task: PublishPipelineArtifact@1
    displayName: 'wheel file Publish'
    retryCountOnTaskFailure: 3
    inputs:
      targetPath: $(Build.BinariesDirectory)

- job: pytorch_testing
+- job: torchvision_testing
  dependsOn: pytorch
  condition: and(succeeded(), eq(variables.ENABLE_GFX942_TESTS, 'true'), not(containsValue(split(variables.DISABLED_GFX942_TESTS, ','), variables['Build.DefinitionName'])))
  variables:
@@ -412,13 +401,12 @@ jobs:
      targetType: inline
      script: git clone https://github.com/pytorch/pytorch.git --depth=1 --recurse-submodules
      workingDirectory: $(Build.SourcesDirectory)
-  - ${{ if eq(parameters.includeVision, true) }}:
-    - task: Bash@3
-      displayName: git clone pytorch vision
-      inputs:
-        targetType: inline
-        script: git clone https://github.com/pytorch/vision.git --depth=1 --recurse-submodules
-        workingDirectory: $(Build.SourcesDirectory)
+  - task: Bash@3
+    displayName: git clone pytorch vision
+    inputs:
+      targetType: inline
+      script: git clone https://github.com/pytorch/vision.git --depth=1 --recurse-submodules
+      workingDirectory: $(Build.SourcesDirectory)
  - task: Bash@3
    displayName: Install Wheel Files
    inputs:
@@ -522,14 +510,13 @@ jobs:
          script: pytest test/test_${{ torchTest }}.py
 # Reference on what tests to run for torchvision found in private repo:
 # https://github.com/ROCm/rocAutomation/blob/jenkins-pipelines/pytorch/pytorch_ci/test_torchvision.sh#L51
-  - ${{ if eq(parameters.includeVision, true) }}:
-    - task: Bash@3
-      displayName: Test vision/transforms
-      continueOnError: true
-      inputs:
-        targetType: inline
-        script: pytest test/test_transforms.py
-        workingDirectory: $(Build.SourcesDirectory)/vision
+  - task: Bash@3
+    displayName: Test vision/transforms
+    continueOnError: true
+    inputs:
+      targetType: inline
+      script: pytest test/test_transforms.py
+      workingDirectory: $(Build.SourcesDirectory)/vision
  - task: Bash@3
    displayName: Uninstall Wheel Files
    inputs:
--- a/.azuredevops/nightly/rocm-nightly.yml
+++ b/.azuredevops/nightly/rocm-nightly.yml
@@ -26,7 +26,6 @@ parameters:
    - llvm-project
    - MIOpen
    - MIVisionX
-    - omniperf
    - rccl
    - rdc
    - rocAL
--- a/.azuredevops/tag-builds/omniperf.yml
+++ b/.azuredevops/tag-builds/omniperf.yml
@@ -1,29 +0,0 @@
-variables:
- group: common
- template: /.azuredevops/variables-global.yml
-
-parameters:
- name: checkoutRef
-  type: string
-  default: refs/tags/$(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 }}
--- a/.azuredevops/templates/steps/artifact-download.yml
+++ b/.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
--- a/.wordlist.txt
+++ b/.wordlist.txt
@@ -26,7 +26,6 @@ ASm
 ATI
 AddressSanitizer
 AlexNet
-Andrej
 Arb
 Autocast
 BARs
@@ -74,7 +73,6 @@ Conda
 ConnectX
 CuPy
 Dashboarding
-DBRX
 DDR
 DF
 DGEMM
@@ -92,8 +90,6 @@ Dask
 DataFrame
 DataLoader
 DataParallel
-Debian
-DeepSeek
 DeepSpeed
 Dependabot
 Deprecations
@@ -110,7 +106,6 @@ FFT
 FFTs
 FFmpeg
 FHS
-FIXME
 FMA
 FP
 FX
@@ -131,12 +126,10 @@ GDS
 GEMM
 GEMMs
 GFortran
-Gemma
 GiB
 GIM
 GL
 GLXT
-Gloo
 GMI
 GPG
 GPR
@@ -155,8 +148,6 @@ HGX
 HIPCC
 HIPExtension
 HIPIFY
-HIPification
-HIPify
 HPC
 HPCG
 HPE
@@ -192,17 +183,15 @@ Interop
 Intersphinx
 Intra
 Ioffe
-JAX's
 Jinja
 JSON
 Jupyter
 KFD
 KFDTest
+KiB
 KMD
 KV
 KVM
-Karpathy's
-KiB
 Keras
 Khronos
 LAPACK
@@ -223,7 +212,6 @@ MiB
 MIGraphX
 MIOpen
 MIOpenGEMM
-MIOpen's
 MIVisionX
 MLM
 MMA
@@ -253,8 +241,6 @@ MyEnvironment
 MyST
 NBIO
 NBIOs
-NCCL
-NCF
 NIC
 NICs
 NLI
@@ -296,12 +282,10 @@ OpenVX
 OpenXLA
 Oversubscription
 PagedAttention
-Pallas
 PCC
 PCI
 PCIe
 PEFT
-PEQT
 PIL
 PILImage
 POR
@@ -331,7 +315,6 @@ RDMA
 RDNA
 README
 RHEL
-RMW
 RNN
 RNNs
 ROC
@@ -348,7 +331,6 @@ ROCmSoftwarePlatform
 ROCmValidationSuite
 ROCprofiler
 ROCr
-RPP
 RST
 RW
 Radeon
@@ -356,7 +338,6 @@ RelWithDebInfo
 Req
 Rickle
 RoCE
-Runfile
 Ryzen
 SALU
 SBIOS
@@ -369,7 +350,6 @@ SENDMSG
 SGPR
 SGPRs
 SHA
-SHARK's
 SIGQUIT
 SIMD
 SIMDs
@@ -414,14 +394,9 @@ TensorFlow
 TensorParallel
 ToC
 TorchAudio
-torchaudio
-TorchElastic
 TorchMIGraphX
-torchrec
 TorchScript
 TorchServe
-torchserve
-torchtext
 TorchVision
 TransferBench
 TrapStatus
@@ -528,9 +503,6 @@ copyable
 cpp
 csn
 cuBLAS
-cuda
-cuDNN
-cudnn
 cuFFT
 cuLIB
 cuRAND
@@ -547,7 +519,6 @@ dbgapi
 de
 deallocation
 debuggability
-debian
 denoise
 denoised
 denoises
@@ -585,7 +556,6 @@ gRPC
 galb
 gcc
 gdb
-gemm
 gfortran
 gfx
 githooks
@@ -601,7 +571,6 @@ hipBLASLt's
 hipblaslt
 hipCUB
 hipFFT
-hipFORT
 hipLIB
 hipRAND
 hipSOLVER
@@ -650,7 +619,6 @@ len
 libfabric
 libjpeg
 libs
-linalg
 linearized
 linter
 linux
@@ -673,7 +641,6 @@ mutex
 mvffr
 namespace
 namespaces
-nanoGPT
 num
 numref
 ocl
@@ -685,9 +652,7 @@ optimizers
 os
 oversubscription
 pageable
-pallas
 parallelization
-parallelizing
 parameterization
 passthrough
 perfcounter
@@ -700,7 +665,6 @@ prebuilt
 precompiled
 preconditioner
 preconfigured
-preemptible
 prefetch
 prefetchable
 prefill
@@ -717,13 +681,10 @@ profilers
 protobuf
 pseudorandom
 py
-recommender
-recommenders
 quantile
 quantizer
 quasirandom
 queueing
-radeon
 rccl
 rdc
 rdma
@@ -745,7 +706,6 @@ rocALUTION
 rocBLAS
 rocDecode
 rocFFT
-rocHPCG
 rocJPEG
 rocLIB
 rocMLIR
@@ -777,7 +737,6 @@ runtimes
 sL
 scalability
 scalable
-scipy
 seealso
 sendmsg
 seqs
@@ -785,7 +744,6 @@ serializers
 shader
 sharding
 sigmoid
-single-node
 sm
 smi
 softmax
--- a/2
+++ b/2
@@ -1,6 +1,6 @@
 MIT License

-Copyright (c) 2023 - 2025 Advanced Micro Devices, Inc. All rights reserved.
+Copyright (c) 2023 - 2024 Advanced Micro Devices, Inc. All rights reserved.

 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
--- a/README.md
+++ b/README.md
@@ -76,7 +76,7 @@ The Build time will reduce significantly if we limit the GPU Architecture/s agai

 mkdir -p ~/WORKSPACE/      # Or any folder name other than WORKSPACE
 cd ~/WORKSPACE/
-export ROCM_VERSION=6.3.1
+export ROCM_VERSION=6.3.0
 ~/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

--- a/RELEASE.md
+++ b/RELEASE.md
--- a/default.xml
+++ b/default.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.3.1"
+    <default revision="refs/tags/rocm-6.3.0"
     remote="rocm-org"
     sync-c="true"
     sync-j="4" />
--- a/docs/about/license.md
+++ b/docs/about/license.md
@@ -25,15 +25,15 @@ additional licenses. Please review individual repositories for more information.
 <!-- spellcheck-disable -->
 | Component | License |
 |:---------------------|:-------------------------|
-| [AMD Compute Language Runtime (CLR)](https://github.com/ROCm/clr) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/LICENCE) |
-| [AMD SMI](https://github.com/ROCm/amdsmi) | [MIT](https://github.com/ROCm/amdsmi/blob/amd-staging/LICENSE) |
+| [AMD Compute Language Runtime (CLR)](https://github.com/ROCm/clr) | [MIT](https://github.com/ROCm/clr/blob/develop/LICENCE) |
+| [AMD SMI](https://github.com/ROCm/amdsmi) | [MIT](https://github.com/ROCm/amdsmi/blob/develop/LICENSE) |
 | [aomp](https://github.com/ROCm/aomp/) | [Apache 2.0](https://github.com/ROCm/aomp/blob/aomp-dev/LICENSE) |
 | [aomp-extras](https://github.com/ROCm/aomp-extras/) | [MIT](https://github.com/ROCm/aomp-extras/blob/aomp-dev/LICENSE) |
 | [Code Object Manager (Comgr)](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/comgr) | [The University of Illinois/NCSA](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/comgr/LICENSE.txt) |
 | [Composable Kernel](https://github.com/ROCm/composable_kernel) | [MIT](https://github.com/ROCm/composable_kernel/blob/develop/LICENSE) |
 | [half](https://github.com/ROCm/half/) | [MIT](https://github.com/ROCm/half/blob/rocm/LICENSE.txt) |
-| [HIP](https://github.com/ROCm/HIP/) | [MIT](https://github.com/ROCm/HIP/blob/amd-staging/LICENSE.txt) |
-| [hipamd](https://github.com/ROCm/clr/tree/amd-staging/hipamd) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/hipamd/LICENSE.txt) |
+| [HIP](https://github.com/ROCm/HIP/) | [MIT](https://github.com/ROCm/HIP/blob/develop/LICENSE.txt) |
+| [hipamd](https://github.com/ROCm/clr/tree/develop/hipamd) | [MIT](https://github.com/ROCm/clr/blob/develop/hipamd/LICENSE.txt) |
 | [hipBLAS](https://github.com/ROCm/hipBLAS/) | [MIT](https://github.com/ROCm/hipBLAS/blob/develop/LICENSE.md) |
 | [hipBLASLt](https://github.com/ROCm/hipBLASLt/) | [MIT](https://github.com/ROCm/hipBLASLt/blob/develop/LICENSE.md) |
 | [HIPCC](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/hipcc) | [MIT](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/hipcc/LICENSE.txt) |
@@ -58,29 +58,29 @@ additional licenses. Please review individual repositories for more information.
 | [ROCdbgapi](https://github.com/ROCm/ROCdbgapi/) | [MIT](https://github.com/ROCm/ROCdbgapi/blob/amd-staging/LICENSE.txt) |
 | [rocDecode](https://github.com/ROCm/rocDecode) | [MIT](https://github.com/ROCm/rocDecode/blob/develop/LICENSE) |
 | [rocFFT](https://github.com/ROCm/rocFFT/) | [MIT](https://github.com/ROCm/rocFFT/blob/develop/LICENSE.md) |
-| [ROCgdb](https://github.com/ROCm/ROCgdb/) | [GNU General Public License v3.0](https://github.com/ROCm/ROCgdb/blob/amd-staging/COPYING3) |
+| [ROCgdb](https://github.com/ROCm/ROCgdb/) | [GNU General Public License v3.0](https://github.com/ROCm/ROCgdb/blob/amd-master/COPYING3) |
 | [rocJPEG](https://github.com/ROCm/rocJPEG/) | [MIT](https://github.com/ROCm/rocJPEG/blob/develop/LICENSE) |
 | [ROCK-Kernel-Driver](https://github.com/ROCm/ROCK-Kernel-Driver/) | [GPL 2.0 WITH Linux-syscall-note](https://github.com/ROCm/ROCK-Kernel-Driver/blob/master/COPYING) |
 | [rocminfo](https://github.com/ROCm/rocminfo/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocminfo/blob/amd-staging/License.txt) |
-| [ROCm Bandwidth Test](https://github.com/ROCm/rocm_bandwidth_test/) | [MIT](https://github.com/ROCm/rocm_bandwidth_test/blob/master/LICENSE.txt) |
+| [ROCm Bandwidth Test](https://github.com/ROCm/rocm_bandwidth_test/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocm_bandwidth_test/blob/master/LICENSE.txt) |
 | [ROCm CMake](https://github.com/ROCm/rocm-cmake/) | [MIT](https://github.com/ROCm/rocm-cmake/blob/develop/LICENSE) |
 | [ROCm Communication Collectives Library (RCCL)](https://github.com/ROCm/rccl/) | [Custom](https://github.com/ROCm/rccl/blob/develop/LICENSE.txt) |
 | [ROCm-Core](https://github.com/ROCm/rocm-core) | [MIT](https://github.com/ROCm/rocm-core/blob/master/copyright) |
 | [ROCm Compute Profiler](https://github.com/ROCm/rocprofiler-compute) | [MIT](https://github.com/ROCm/rocprofiler-compute/blob/amd-staging/LICENSE) |
-| [ROCm Data Center (RDC)](https://github.com/ROCm/rdc/) | [MIT](https://github.com/ROCm/rdc/blob/amd-staging/LICENSE) |
+| [ROCm Data Center (RDC)](https://github.com/ROCm/rdc/) | [MIT](https://github.com/ROCm/rdc/blob/develop/LICENSE) |
 | [ROCm-Device-Libs](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/device-libs) | [The University of Illinois/NCSA](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/device-libs/LICENSE.TXT) |
-| [ROCm-OpenCL-Runtime](https://github.com/ROCm/clr/tree/amd-staging/opencl) | [MIT](https://github.com/ROCm/clr/blob/amd-staging/opencl/LICENSE.txt) |
+| [ROCm-OpenCL-Runtime](https://github.com/ROCm/clr/tree/develop/opencl) | [MIT](https://github.com/ROCm/clr/blob/develop/opencl/LICENSE.txt) |
 | [ROCm Performance Primitives (RPP)](https://github.com/ROCm/rpp) | [MIT](https://github.com/ROCm/rpp/blob/develop/LICENSE) |
-| [ROCm SMI Lib](https://github.com/ROCm/rocm_smi_lib/) | [MIT](https://github.com/ROCm/rocm_smi_lib/blob/amd-staging/License.txt) |
+| [ROCm SMI Lib](https://github.com/ROCm/rocm_smi_lib/) | [MIT](https://github.com/ROCm/rocm_smi_lib/blob/develop/License.txt) |
 | [ROCm Systems Profiler](https://github.com/ROCm/rocprofiler-systems) | [MIT](https://github.com/ROCm/rocprofiler-systems/blob/amd-staging/LICENSE) |
 | [ROCm Validation Suite](https://github.com/ROCm/ROCmValidationSuite/) | [MIT](https://github.com/ROCm/ROCmValidationSuite/blob/master/LICENSE) |
 | [rocPRIM](https://github.com/ROCm/rocPRIM/) | [MIT](https://github.com/ROCm/rocPRIM/blob/develop/LICENSE.txt) |
-| [ROCProfiler](https://github.com/ROCm/rocprofiler/) | [MIT](https://github.com/ROCm/rocprofiler/blob/amd-staging/LICENSE) |
+| [ROCProfiler](https://github.com/ROCm/rocprofiler/) | [MIT](https://github.com/ROCm/rocprofiler/blob/amd-master/LICENSE) |
 | [ROCprofiler-SDK](https://github.com/ROCm/rocprofiler-sdk) | [MIT](https://github.com/ROCm/rocprofiler-sdk/blob/amd-mainline/LICENSE) |
 | [rocPyDecode](https://github.com/ROCm/rocPyDecode) | [MIT](https://github.com/ROCm/rocPyDecode/blob/develop/LICENSE) |
 | [rocRAND](https://github.com/ROCm/rocRAND/) | [MIT](https://github.com/ROCm/rocRAND/blob/develop/LICENSE.txt) |
 | [ROCr Debug Agent](https://github.com/ROCm/rocr_debug_agent/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocr_debug_agent/blob/amd-staging/LICENSE.txt) |
-| [ROCR-Runtime](https://github.com/ROCm/ROCR-Runtime/) | [The University of Illinois/NCSA](https://github.com/ROCm/ROCR-Runtime/blob/amd-staging/LICENSE.txt) |
+| [ROCR-Runtime](https://github.com/ROCm/ROCR-Runtime/) | [The University of Illinois/NCSA](https://github.com/ROCm/ROCR-Runtime/blob/master/LICENSE.txt) |
 | [rocSOLVER](https://github.com/ROCm/rocSOLVER/) | [BSD-2-Clause](https://github.com/ROCm/rocSOLVER/blob/develop/LICENSE.md) |
 | [rocSPARSE](https://github.com/ROCm/rocSPARSE/) | [MIT](https://github.com/ROCm/rocSPARSE/blob/develop/LICENSE.md) |
 | [rocThrust](https://github.com/ROCm/rocThrust/) | [Apache 2.0](https://github.com/ROCm/rocThrust/blob/develop/LICENSE) |
@@ -99,7 +99,7 @@ repositories to distinguish from open sourced packages.
 The following additional terms and conditions apply to your use of ROCm technical documentation.
 ```

-©2023 - 2025 Advanced Micro Devices, Inc. All rights reserved.
+©2023 - 2024 Advanced Micro Devices, Inc. All rights reserved.

 The information presented in this document is for informational purposes only
 and may contain technical inaccuracies, omissions, and typographical errors. The
--- a/docs/compatibility/compatibility-matrix-historical-6.0.csv
+++ b/docs/compatibility/compatibility-matrix-historical-6.0.csv
@@ -1,129 +1,118 @@
-ROCm Version,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
-      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,Ubuntu 24.04.2,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,,
-      ,Ubuntu 22.04.5,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
-      ,,,,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
-      ,"RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
-      ,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
-      ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
-      ,,,,,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
-      ,Oracle Linux 8.10 [#mic300x-past-60]_,Oracle Linux 8.10 [#mic300x-past-60]_,Oracle Linux 8.9 [#mic300x-past-60]_,Oracle Linux 8.9 [#mic300x-past-60]_,Oracle Linux 8.9 [#mic300x-past-60]_,Oracle Linux 8.9 [#mic300x-past-60]_,Oracle Linux 8.9 [#mic300x-past-60]_,Oracle Linux 8.9 [#mic300x-past-60]_,Oracle Linux 8.9 [#mic300x-past-60]_,,,
-,Debian 12 [#single-node-past-60]_,,,,,,,,,,,
-,Azure Linux 3.0 [#mic300x-past-60]_,,,,,,,,,,,
-      ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
-      ,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
-      ,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
-      ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
-      ,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
-      ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
-      ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
-      ,gfx942,gfx942,gfx942 [#mi300_624-past-60]_,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
-      ,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
-      ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
-      ,,,,,,,,,,,,
-      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.4, 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","2.1, 2.0, 1.13"
-      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"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>`,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
-      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
-      ,,,,,,,,,,,,
-      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      `UCC <https://github.com/ROCm/ucc>`_,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
-      `UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
-      ,,,,,,,,,,,,
-      THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      Thrust,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      CUB,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-,,,,,,,,,,,,
-      ,,,,,,,,,,,,
-      KMD & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      Tested user space versions,"6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
-      ,,,,,,,,,,,,
-      ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
-      :doc:`MIGraphX <amdmigraphx:index>`,2.11.0,2.11.0,2.10.0,2.10.0,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
-      :doc:`MIOpen <miopen:index>`,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`MIVisionX <mivisionx:index>`,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
-      :doc:`rocAL <rocal:index>`,2.1.0,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`rocDecode <rocdecode:index>`,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
-      :doc:`rocJPEG <rocjpeg:index>`,0.6.0,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`rocPyDecode <rocpydecode:index>`,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`RPP <rpp:index>`,1.9.1,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
-      ,,,,,,,,,,,,
-      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      :doc:`RCCL <rccl:index>`,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
-      ,,,,,,,,,,,,
-      MATH LIBS,.. _mathlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
-      :doc:`hipBLAS <hipblas:index>`,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
-      :doc:`hipBLASLt <hipblaslt:index>`,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
-      :doc:`hipFFT <hipfft:index>`,1.0.17,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
-      :doc:`hipfort <hipfort:index>`,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
-      :doc:`hipRAND <hiprand:index>`,2.11.1,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
-,,,,,,,,,,,,
-      :doc:`hipSOLVER <hipsolver:index>`,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
-      :doc:`hipSPARSE <hipsparse:index>`,3.1.2,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.2,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
-      :doc:`rocALUTION <rocalution:index>`,3.2.1,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
-      :doc:`rocBLAS <rocblas:index>`,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
-      :doc:`rocFFT <rocfft:index>`,1.0.31,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
-      :doc:`rocRAND <rocrand:index>`,3.2.0,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
-      :doc:`rocSOLVER <rocsolver:index>`,3.27.0,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
-      :doc:`rocSPARSE <rocsparse:index>`,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
-      :doc:`rocWMMA <rocwmma:index>`,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
-      :doc:`Tensile <tensile:src/index>`,4.42.0,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
-      ,,,,,,,,,,,,
-      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      :doc:`hipCUB <hipcub:index>`,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`hipTensor <hiptensor:index>`,1.4.0,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
-      :doc:`rocPRIM <rocprim:index>`,3.3.0,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`rocThrust <rocthrust:index>`,3.3.0,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      ,,,,,,,,,,,,
-      SUPPORT LIBS,,,,,,,,,,,,
-      `hipother <https://github.com/ROCm/hipother>`_,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-,,,,,,,,,,,,
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
-      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,20240607.5.7,20240607.5.7,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
-      ,,,,,,,,,,,,
-      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      :doc:`AMD SMI <amdsmi:index>`,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
-      :doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
-      :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.4.0,7.4.0,7.3.0,7.3.0,7.3.0,7.3.0,7.2.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
-      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60105,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
-      ,,,,,,,,,,,,
-      PERFORMANCE TOOLS,,,,,,,,,,,,
-      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
-      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60301,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
-,,,,,,,,,,,,
-      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCTracer <roctracer:index>`,4.1.60301,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
-,,,,,,,,,,,,
-      ,,,,,,,,,,,,
-      DEVELOPMENT TOOLS,,,,,,,,,,,,
-      :doc:`HIPIFY <hipify:index>`,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-,,,,,,,,,,,,
-      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
-      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.0,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,15.2.0,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
-      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
-      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
-      ,,,,,,,,,,,,
-      COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A,N/A,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
-      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      `Flang <https://github.com/ROCm/flang>`_,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`llvm-project <llvm-project:index>`,18.0.0.24455,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24455,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-,,,,,,,,,,,,
-      ,,,,,,,,,,,,
-      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,,,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-,,,,,,,,,,,,
-      :doc:`HIP <hip:index>`,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-,,,,,,,,,,,,
-      `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
-      :doc:`ROCr Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
+ROCm Version,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, 6.0.0
+      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,
+      ,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
+      ,,,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
+      ,"RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.4 [#red-hat94-past-60]_, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
+      ,"RHEL 8.10","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
+      ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
+      ,,,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
+      ,Oracle Linux 8.10 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,Oracle Linux 8.9 [#oracle89-past-60]_,,,
+      ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,
+      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
+      ,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
+      ,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
+      ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
+      ,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
+      ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
+      ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
+      ,gfx942,gfx942 [#mi300_624-past-60]_,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
+      ,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
+      ,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","2.3, 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","2.16.1, 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>`,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
+      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
+      ,,,,,,,,,,
+      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,,,
+      `UCC <https://github.com/ROCm/ucc>`_,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
+      `UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
+      ,,,,,,,,,,
+      THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix-past-60:,,,,,,,,,
+      Thrust,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      CUB,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      ,,,,,,,,,,
+      KMD & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,
+      Tested user space versions,"6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
+      ,,,,,,,,,,
+      ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,,,,
+      :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
+      :doc:`MIGraphX <amdmigraphx:index>`,2.11.0,2.10.0,2.10.0,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
+      :doc:`MIOpen <miopen:index>`,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`MIVisionX <mivisionx:index>`,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
+      :doc:`rocAL <rocal:index>`,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      :doc:`rocDecode <rocdecode:index>`,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
+      :doc:`rocJPEG <rocjpeg:index>`,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`rocPyDecode <rocpydecode:index>`,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A
+      :doc:`RPP <rpp:index>`,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
+      ,,,,,,,,,,
+      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,
+      :doc:`RCCL <rccl:index>`,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
+      ,,,,,,,,,,
+      MATH LIBS,.. _mathlibs-support-compatibility-matrix-past-60:,,,,,,,,,
+      `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
+      :doc:`hipBLAS <hipblas:index>`,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
+      :doc:`hipBLASLt <hipblaslt:index>`,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
+      :doc:`hipFFT <hipfft:index>`,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
+      :doc:`hipfort <hipfort:index>`,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
+      :doc:`hipRAND <hiprand:index>`,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
+      :doc:`hipSOLVER <hipsolver:index>`,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
+      :doc:`hipSPARSE <hipsparse:index>`,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
+      :doc:`rocALUTION <rocalution:index>`,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
+      :doc:`rocBLAS <rocblas:index>`,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
+      :doc:`rocFFT <rocfft:index>`,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
+      :doc:`rocRAND <rocrand:index>`,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
+      :doc:`rocSOLVER <rocsolver:index>`,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
+      :doc:`rocSPARSE <rocsparse:index>`,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
+      :doc:`rocWMMA <rocwmma:index>`,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
+      :doc:`Tensile <tensile:index>`,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
+      ,,,,,,,,,,
+      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,,
+      :doc:`hipCUB <hipcub:index>`,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`hipTensor <hiptensor:index>`,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
+      :doc:`rocPRIM <rocprim:index>`,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`rocThrust <rocthrust:index>`,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      ,,,,,,,,,,
+      SUPPORT LIBS,,,,,,,,,,
+      `hipother <https://github.com/ROCm/hipother>`_,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
+      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr-past-60]_,20240607.5.7,20240607.5.7,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
+      ,,,,,,,,,,
+      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,,,
+      :doc:`AMD SMI <amdsmi:index>`,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
+      :doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
+      :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.4.0,7.3.0,7.3.0,7.3.0,7.3.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
+      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
+      ,,,,,,,,,,
+      PERFORMANCE TOOLS,,,,,,,,,,
+      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
+      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
+      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCTracer <roctracer:index>`,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
+      ,,,,,,,,,,
+      DEVELOPMENT TOOLS,,,,,,,,,,
+      :doc:`HIPIFY <hipify:index>`,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
+      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,N/A,N/A
+      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
+      ,,,,,,,,,,
+      COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,,,
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
+      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      `Flang <https://github.com/ROCm/flang>`_,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`llvm-project <llvm-project:index>`,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      ,,,,,,,,,,
+      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,,
+      :doc:`AMD CLR <hip:understand/amd_clr>`,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      :doc:`HIP <hip:index>`,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
+      :doc:`ROCr Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
--- a/docs/compatibility/compatibility-matrix.rst
+++ b/docs/compatibility/compatibility-matrix.rst
@@ -23,17 +23,17 @@ compatibility and system requirements.
 .. container:: format-big-table

  .. csv-table::
-      :header: "ROCm Version", "6.3.1", "6.3.0", "6.2.0"
+      :header: "ROCm Version", "6.3.0", "6.2.4", "6.1.0"
      :stub-columns: 1

-      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04
-      ,Ubuntu 22.04.5,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4"
-      ,"RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3"
-      ,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9"
-      ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5"
-      ,Oracle Linux 8.10 [#mi300x]_,Oracle Linux 8.10 [#mi300x]_,Oracle Linux 8.9 [#mi300x]_
-      ,Debian 12 [#single-node]_,,
-      ,Azure Linux 3.0 [#mi300x]_,,
+      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.2,"Ubuntu 24.04.1, 24.04",
+      ,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.4, 22.04.3"
+      ,,,"Ubuntu 20.04.6, 20.04.5"
+      ,"RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4 [#red-hat94]_, 9.3, 9.2"
+      ,"RHEL 8.10","RHEL 8.10, 8.9","RHEL 8.9, 8.8"
+      ,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4"
+      ,,,CentOS 7.9
+      ,Oracle Linux 8.10 [#oracle89]_,Oracle Linux 8.9 [#oracle89]_,
      ,.. _architecture-support-compatibility-matrix:,,
      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA3,CDNA3,CDNA3
      ,CDNA2,CDNA2,CDNA2
@@ -43,115 +43,115 @@ compatibility and system requirements.
      ,.. _gpu-support-compatibility-matrix:,,
      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx1100,gfx1100,gfx1100
      ,gfx1030,gfx1030,gfx1030
-      ,gfx942,gfx942,gfx942 [#mi300_620]_
+      ,gfx942,gfx942 [#mi300_624]_, gfx942 [#mi300_610]_
      ,gfx90a,gfx90a,gfx90a
      ,gfx908,gfx908,gfx908
      ,,,
      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix:,,
-      :doc:`PyTorch <../compatibility/ml-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 <../compatibility/ml-compatibility/tensorflow-compatibility>`,"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 <../compatibility/ml-compatibility/jax-compatibility>`,0.4.31,0.4.31,0.4.26
+      :doc:`PyTorch <rocm-install-on-linux:install/3rd-party/pytorch-install>`,"2.4, 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"
+      :doc:`TensorFlow <rocm-install-on-linux:install/3rd-party/tensorflow-install>`,"2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1"
+      :doc:`JAX <rocm-install-on-linux:install/3rd-party/jax-install>`,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
      ,,,
      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
      `UCC <https://github.com/ROCm/ucc>`_,>=1.3.0,>=1.3.0,>=1.3.0
-      `UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.15.0
+      `UCX <https://github.com/ROCm/ucx>`_,>=1.15.0,>=1.15.0,>=1.14.1
      ,,,
      THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix:,,
-      Thrust,2.3.2,2.3.2,2.2.0
-      CUB,2.3.2,2.3.2,2.2.0
+      Thrust,2.3.2,2.2.0,2.1.0
+      CUB,2.3.2,2.2.0,2.1.0
      ,,,
      KMD & USER SPACE [#kfd_support]_,.. _kfd-userspace-support-compatibility-matrix:,,
-      Tested user space versions,"6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x, 6.0.x"
+      Tested user space versions,"6.3.x, 6.2.x, 6.1.x","6.3.x, 6.2.x, 6.1.x, 6.0.x","6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x"
      ,,,
      ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix:,,
      :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0
-      :doc:`MIGraphX <amdmigraphx:index>`,2.11.0,2.11.0,2.10.0
-      :doc:`MIOpen <miopen:index>`,3.3.0,3.3.0,3.2.0
-      :doc:`MIVisionX <mivisionx:index>`,3.1.0,3.1.0,3.0.0
-      :doc:`rocAL <rocal:index>`,2.1.0,2.1.0,1.0.0
-      :doc:`rocDecode <rocdecode:index>`,0.8.0,0.8.0,0.6.0
-      :doc:`rocJPEG <rocjpeg:index>`,0.6.0,0.6.0,N/A
-      :doc:`rocPyDecode <rocpydecode:index>`,0.2.0,0.2.0,0.1.0
-      :doc:`RPP <rpp:index>`,1.9.1,1.9.1,1.8.0
+      :doc:`MIGraphX <amdmigraphx:index>`,2.11.0,2.10.0,2.9.0
+      :doc:`MIOpen <miopen:index>`,3.3.0,3.2.0,3.1.0
+      :doc:`MIVisionX <mivisionx:index>`,3.1.0,3.0.0,2.5.0
+      :doc:`rocAL <rocal:index>`,2.1.0,2.0.0,1.0.0
+      :doc:`rocDecode <rocdecode:index>`,0.8.0,0.6.0,0.5.0
+      :doc:`rocJPEG <rocjpeg:index>`,0.6.0,N/A,N/A
+      :doc:`rocPyDecode <rocpydecode:index>`,0.2.0,0.1.0,N/A
+      :doc:`RPP <rpp:index>`,1.9.1,1.8.0,1.5.0
      ,,,
      COMMUNICATION,.. _commlibs-support-compatibility-matrix:,,
-      :doc:`RCCL <rccl:index>`,2.21.5,2.21.5,2.20.5
+      :doc:`RCCL <rccl:index>`,2.21.5,2.20.5,2.18.6
      ,,,
      MATH LIBS,.. _mathlibs-support-compatibility-matrix:,,
      `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0
-      :doc:`hipBLAS <hipblas:index>`,2.3.0,2.3.0,2.2.0
-      :doc:`hipBLASLt <hipblaslt:index>`,0.10.0,0.10.0,0.8.0
-      :doc:`hipFFT <hipfft:index>`,1.0.17,1.0.17,1.0.14
-      :doc:`hipfort <hipfort:index>`,0.5.0,0.5.0,0.4.0
-      :doc:`hipRAND <hiprand:index>`,2.11.1,2.11.0,2.11.0
-      :doc:`hipSOLVER <hipsolver:index>`,2.3.0,2.3.0,2.2.0
-      :doc:`hipSPARSE <hipsparse:index>`,3.1.2,3.1.2,3.1.1
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.2,0.2.2,0.2.1
-      :doc:`rocALUTION <rocalution:index>`,3.2.1,3.2.1,3.2.0
-      :doc:`rocBLAS <rocblas:index>`,4.3.0,4.3.0,4.2.0
-      :doc:`rocFFT <rocfft:index>`,1.0.31,1.0.31,1.0.28
-      :doc:`rocRAND <rocrand:index>`,3.2.0,3.2.0,3.1.0
-      :doc:`rocSOLVER <rocsolver:index>`,3.27.0,3.27.0,3.26.0
-      :doc:`rocSPARSE <rocsparse:index>`,3.3.0,3.3.0,3.2.0
-      :doc:`rocWMMA <rocwmma:index>`,1.6.0,1.6.0,1.5.0
-      :doc:`Tensile <tensile:src/index>`,4.42.0,4.42.0,4.41.0
+      :doc:`hipBLAS <hipblas:index>`,2.3.0,2.2.0,2.1.0
+      :doc:`hipBLASLt <hipblaslt:index>`,0.10.0,0.8.0,0.7.0
+      :doc:`hipFFT <hipfft:index>`,1.0.17,1.0.16,1.0.14
+      :doc:`hipfort <hipfort:index>`,0.5.0,0.4.0,0.4.0
+      :doc:`hipRAND <hiprand:index>`,2.11.0,2.11.1,2.10.16
+      :doc:`hipSOLVER <hipsolver:index>`,2.3.0,2.2.0,2.1.0
+      :doc:`hipSPARSE <hipsparse:index>`,3.1.2,3.1.1,3.0.1
+      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.2,0.2.1,0.1.0
+      :doc:`rocALUTION <rocalution:index>`,3.2.1,3.2.1,3.1.1
+      :doc:`rocBLAS <rocblas:index>`,4.3.0,4.2.4,4.1.0
+      :doc:`rocFFT <rocfft:index>`,1.0.31,1.0.30,1.0.26
+      :doc:`rocRAND <rocrand:index>`,3.2.0,3.1.1,3.0.1
+      :doc:`rocSOLVER <rocsolver:index>`,3.27.0,3.26.2,3.25.0
+      :doc:`rocSPARSE <rocsparse:index>`,3.3.0,3.2.1,3.1.2
+      :doc:`rocWMMA <rocwmma:index>`,1.6.0,1.5.0,1.4.0
+      :doc:`Tensile <tensile:index>`,4.42.0,4.41.0,4.40.0
      ,,,
      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix:,,
-      :doc:`hipCUB <hipcub:index>`,3.3.0,3.3.0,3.2.0
-      :doc:`hipTensor <hiptensor:index>`,1.4.0,1.4.0,1.3.0
-      :doc:`rocPRIM <rocprim:index>`,3.3.0,3.3.0,3.2.0
-      :doc:`rocThrust <rocthrust:index>`,3.3.0,3.3.0,3.0.1
+      :doc:`hipCUB <hipcub:index>`,3.3.0,3.2.1,3.1.0
+      :doc:`hipTensor <hiptensor:index>`,1.4.0,1.3.0,1.2.0
+      :doc:`rocPRIM <rocprim:index>`,3.3.0,3.2.2,3.1.0
+      :doc:`rocThrust <rocthrust:index>`,3.3.0,3.1.1,3.0.1
      ,,,
      SUPPORT LIBS,,,
-      `hipother <https://github.com/ROCm/hipother>`_,6.3.42133,6.3.42131,6.2.41133
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.3.1,6.3.0,6.2.0
-      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr]_,N/A [#ROCT-rocr]_,20240607.1.4246
+      `hipother <https://github.com/ROCm/hipother>`_,6.3.42131,6.2.41134,6.1.40091
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,6.3.0,6.2.4,6.1.0
+      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr]_,20240607.5.7,20240125.3.30
      ,,,
      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix:,,
-      :doc:`AMD SMI <amdsmi:index>`,24.7.1,24.7.1,24.6.2
+      :doc:`AMD SMI <amdsmi:index>`,24.7.1,24.6.3,24.4.1
      :doc:`ROCm Data Center Tool <rdc:index>`,0.3.0,0.3.0,0.3.0
      :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.4.0,7.4.0,7.3.0
-      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.1.0,1.1.0,1.0.60200
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.4.0,7.3.0,7.0.0
+      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.1.0,1.0.60204,1.0.60100
      ,,,
      PERFORMANCE TOOLS,,,
      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,1.4.0,1.4.0,1.4.0
-      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.0.0,3.0.0,2.0.1
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,0.1.0,0.1.0,1.11.2
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60301,2.0.60300,2.0.60200
-      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.5.0,0.5.0,0.4.0
-      :doc:`ROCTracer <roctracer:index>`,4.1.60301,4.1.60300,4.1.60200
+      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.0.0,2.0.1,N/A
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,0.1.0,1.11.2,N/A
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.60300,2.0.60204,2.0.60100
+      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,0.5.0,0.4.0,N/A
+      :doc:`ROCTracer <roctracer:index>`,4.1.60300,4.1.60204,4.1.60100
      ,,,
      DEVELOPMENT TOOLS,,,
-      :doc:`HIPIFY <hipify:index>`,18.0.0.24491,18.0.0.24455,18.0.0.24232
-      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.13.0
-      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.0,0.77.0,0.76.0
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,15.2.0,15.2.0,14.2.0
-      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.4.0
+      :doc:`HIPIFY <hipify:index>`,18.0.0.24455,18.0.0.24392,17.0.0.24103
+      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.13.0,0.12.0
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.0,0.76.0,0.71.0
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,15.2.0,14.2.0,14.1.0
+      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.4.0,0.4.0,0.3.0
      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.0.3,2.0.3,2.0.3
      ,,,
      COMPILERS,.. _compilers-support-compatibility-matrix:,,
-      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A
-      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1
-      `Flang <https://github.com/ROCm/flang>`_,18.0.0.24491,18.0.0.24455,18.0.0.24232
-      :doc:`llvm-project <llvm-project:index>`,18.0.0.24491,18.0.0.24455,18.0.0.24232
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24491,18.0.0.24455,18.0.0.24232
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,0.5.0
+      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.0.0
+      `Flang <https://github.com/ROCm/flang>`_,18.0.0.24455,18.0.0.24392,17.0.0.24103
+      :doc:`llvm-project <llvm-project:index>`,18.0.0.24455,18.0.0.24392,17.0.0.24103
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,18.0.0.24455,18.0.0.24392,17.0.0.24103
      ,,,
      RUNTIMES,.. _runtime-support-compatibility-matrix:,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,6.3.42133,6.3.42131,6.2.41133
-      :doc:`HIP <hip:index>`,6.3.42133,6.3.42131,6.2.41133
+      :doc:`AMD CLR <hip:understand/amd_clr>`,6.3.42131,6.2.41134,6.1.40091
+      :doc:`HIP <hip:index>`,6.3.42131,6.2.41134,6.1.40091
      `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0
      :doc:`ROCr Runtime <rocr-runtime:index>`,1.14.0,1.14.0,1.13.0

-
 .. rubric:: Footnotes

-.. [#mi300x] Oracle Linux and Azure Linux are supported only on AMD Instinct MI300X.
-.. [#single-node] Debian 12 is supported only on AMD Instinct MI300X for single-node functionality. 
-.. [#mi300_620] **For ROCm 6.2.0** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
-.. [#kfd_support] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
-.. [#ROCT-rocr] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
+.. [#red-hat94] RHEL 9.4 is supported only on AMD Instinct MI300A.
+.. [#oracle89] Oracle Linux is supported only on AMD Instinct MI300X.
+.. [#mi300_624] **For ROCm 6.2.4** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
+.. [#mi300_610] **For ROCm 6.1.0** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
+.. [#kfd_support] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software for +/- 2 releases. These are the compatibility combinations that are currently supported.
+.. [#ROCT-rocr] As of ROCm 6.3.0, the ROCT Thunk Interface is now included as part of the ROCr runtime package.

 .. _OS-kernel-versions:

@@ -166,26 +166,35 @@ Use this lookup table to confirm which operating system and kernel versions are
   :stub-columns: 1

   `Ubuntu <https://ubuntu.com/about/release-cycle#ubuntu-kernel-release-cycle>`_, 24.04.2, "6.8 GA, 6.11 HWE"
+   , 24.04.1, "6.8 GA"
   , 24.04, "6.8 GA"
   ,,
   `Ubuntu <https://ubuntu.com/about/release-cycle#ubuntu-kernel-release-cycle>`_, 22.04.5, "5.15 GA, 6.8 HWE"
   , 22.04.4, "5.15 GA, 6.5 HWE"
+   , 22.04.3, "5.15 GA, 6.2 HWE"
+   , 22.04.2, "5.15 GA, 5.19 HWE"
+   ,,
+   `Ubuntu <https://ubuntu.com/about/release-cycle#ubuntu-kernel-release-cycle>`_, 20.04.06, "5.15 HWE"
+   , 20.04.5, "5.15 HWE"
   ,,
   `Red Hat Enterprise Linux (RHEL) <https://access.redhat.com/articles/3078#RHEL9>`_, 9.5, 5.14.0
   ,9.4, 5.14.0
   ,9.3, 5.14.0
+   ,9.2, 5.14.0
   ,,
   `Red Hat Enterprise Linux (RHEL) <https://access.redhat.com/articles/3078#RHEL8>`_, 8.10, 4.18.0
   ,8.9, 4.18.0
+   ,8.8, 4.18.0
+   ,,
+   `CentOS <https://access.redhat.com/articles/3078#RHEL7>`_, 7.9, 3.10
   ,,
   `SUSE Linux Enterprise Server (SLES) <https://www.suse.com/support/kb/doc/?id=000019587#SLE15SP4>`_, 15 SP6, 6.4.0
   ,15 SP5, 5.14.21
+   ,15 SP4, 5.14.21
   ,,
   `Oracle Linux <https://blogs.oracle.com/scoter/post/oracle-linux-and-unbreakable-enterprise-kernel-uek-releases>`_, 8.10, 5.15.0
   ,8.9, 5.15.0
-   ,,
-   `Debian <https://www.debian.org/download>`_,12, 6.1
-   `Azure Linux <https://techcommunity.microsoft.com/blog/linuxandopensourceblog/azure-linux-3-0-now-in-preview-on-azure-kubernetes-service-v1-31/4287229>`_,3.0, 6.6
+   `Azure Linux <https://github.com/microsoft/azurelinux/releases>`_, 3.0, 6.6.60

 ..
   Footnotes and ref anchors in below historical tables should be appended with "-past-60", to differentiate from the 
@@ -213,8 +222,7 @@ Expand for full historical view of:

   .. rubric:: Footnotes

-   .. [#mic300x-past-60] Oracle Linux and Azure Linux are supported only on AMD Instinct MI300X.
-   .. [#single-node-past-60] Debian 12 is supported only on AMD Instinct MI300X for single-node functionality. 
+   .. [#oracle89-past-60] Oracle Linux is supported only on AMD Instinct MI300X.
   .. [#mi300_624-past-60] **For ROCm 6.2.4** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
   .. [#mi300_622-past-60] **For ROCm 6.2.2** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
   .. [#mi300_621-past-60] **For ROCm 6.2.1** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
@@ -224,5 +232,5 @@ Expand for full historical view of:
   .. [#mi300_610-past-60] **For ROCm 6.1.0** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
   .. [#mi300_602-past-60] **For ROCm 6.0.2** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
   .. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
-   .. [#kfd_support-past-60] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software for +/- 2 releases. The tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
-   .. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
+   .. [#kfd_support-past-60] ROCm provides forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software for +/- 2 releases. These are the compatibility combinations that are currently supported.
+   .. [#ROCT-rocr-past-60] As of ROCm 6.3.0, the ROCT Thunk Interface is now included as part of the ROCr runtime package.
--- a/docs/compatibility/ml-compatibility/jax-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/jax-compatibility.rst
@@ -1,663 +0,0 @@
-.. meta::
-   :description: JAX compatibility
-   :keywords: GPU, JAX compatibility
-
-*******************************************************************************
-JAX compatibility
-*******************************************************************************
-
-JAX provides a NumPy-like API, which combines automatic differentiation and the
-Accelerated Linear Algebra (XLA) compiler to achieve high-performance machine
-learning at scale.
-
-JAX uses composable transformations of Python and NumPy through just-in-time (JIT) compilation,
-automatic vectorization, and parallelization. To learn about JAX, including profiling and
-optimizations, see the official `JAX documentation
-<https://jax.readthedocs.io/en/latest/notebooks/quickstart.html>`_.
-
-ROCm support for JAX is upstreamed and users can build the official source code with ROCm
-support:
-
- ROCm JAX release:
-
-  - Offers AMD-validated and community :ref:`Docker images <jax-docker-compat>` with ROCm and JAX pre-installed.
-
-  - ROCm JAX repository: `<https://github.com/ROCm/jax>`__
-
-  - See the :doc:`ROCm JAX installation guide <rocm-install-on-linux:install/3rd-party/jax-install>`
-    to get started.
-
- Official JAX release:
-
-  - Official JAX repository: `<https://github.com/jax-ml/jax>`__
-
-  - See the `AMD GPU (Linux) installation section
-    <https://jax.readthedocs.io/en/latest/installation.html#amd-gpu-linux>`_ in the JAX
-    documentation.
-
-.. note::
-
-   AMD releases official `ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax>`_
-   quarterly alongside new ROCm releases. These images undergo full AMD testing.
-   `Community ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax-community>`_
-   follow upstream JAX releases and use the latest available ROCm version.
-
-.. _jax-docker-compat:
-
-Docker image compatibility
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes ready-made `JAX <https://hub.docker.com/r/rocm/jax/>`_
-images with ROCm backends on Docker Hub. The following Docker image tags and
-associated inventories are validated for
-`ROCm 6.3.1 <https://repo.radeon.com/rocm/apt/6.3.1/>`_. Click the |docker-icon|
-icon to view the image on Docker Hub.
-
-.. list-table:: JAX Docker image components
-    :header-rows: 1
-
-    * - Docker image
-      - JAX
-      - Linux
-      - Python
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.3.1-jax0.4.31-py3.12/images/sha256-085a0cd5207110922f1fca684933a9359c66d42db6c5aba4760ed5214fdabde0"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
-
-      - `0.4.31 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.31>`_
-      - Ubuntu 24.04
-      - `3.12.7 <https://www.python.org/downloads/release/python-3127/>`_
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.3.1-jax0.4.31-py3.10/images/sha256-f88eddad8f47856d8640b694da4da347ffc1750d7363175ab7dc872e82b43324"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
-
-      - `0.4.31 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.31>`_
-      - Ubuntu 22.04
-      - `3.10.14 <https://www.python.org/downloads/release/python-31014/>`_
-
-AMD publishes community `JAX <https://hub.docker.com/r/rocm/jax-community>`_
-images with ROCm backends on Docker Hub. The following Docker image tags and
-associated inventories are tested for `ROCm 6.2.4 <https://repo.radeon.com/rocm/apt/6.2.4/>`_.
-
-.. list-table:: JAX community Docker image components
-    :header-rows: 1
-
-    * - Docker image
-      - JAX
-      - Linux
-      - Python
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.2.4-jax0.4.35-py3.12.7/images/sha256-a6032d89c07573b84c44e42c637bf9752b1b7cd2a222d39344e603d8f4c63beb?context=explore"><i class="fab fa-docker fa-lg"></i> rocm/jax-community</a>
-
-      - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
-      - Ubuntu 22.04
-      - `3.12.7 <https://www.python.org/downloads/release/python-3127/>`_
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.2.4-jax0.4.35-py3.11.10/images/sha256-d462f7e445545fba2f3b92234a21beaa52fe6c5f550faabcfdcd1bf53486d991?context=explore"><i class="fab fa-docker fa-lg"></i> rocm/jax-community</a>
-
-      - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
-      - Ubuntu 22.04
-      - `3.11.10 <https://www.python.org/downloads/release/python-31110/>`_
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.2.4-jax0.4.35-py3.10.15/images/sha256-6f2d4d0f529378d9572f0e8cfdcbc101d1e1d335bd626bb3336fff87814e9d60?context=explore"><i class="fab fa-docker fa-lg"></i> rocm/jax-community</a>
-
-      - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
-      - Ubuntu 22.04
-      - `3.10.15 <https://www.python.org/downloads/release/python-31015/>`_
-
-Critical ROCm libraries for JAX
-================================================================================
-
-The functionality of JAX with ROCm is determined 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
-    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - 2.3.0
-      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
-        matrix and vector operations.
-      - Matrix multiplication in ``jax.numpy.matmul``, ``jax.lax.dot`` and
-        ``jax.lax.dot_general``, operations like ``jax.numpy.dot``, which
-        involve vector and matrix computations and batch matrix multiplications
-        ``jax.numpy.einsum`` with matrix-multiplication patterns algebra
-        operations.
-    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - 0.10.0
-      - hipBLASLt is an extension of hipBLAS, providing additional
-        features like epilogues fused into the matrix multiplication kernel or
-        use of integer tensor cores.
-      - Matrix multiplication in ``jax.numpy.matmul`` or ``jax.lax.dot``, and
-        the XLA (Accelerated Linear Algebra) use hipBLASLt for optimized matrix
-        operations, mixed-precision support, and hardware-specific
-        optimizations.
-    * - `hipCUB <https://github.com/ROCm/hipCUB>`_
-      - 3.3.0
-      - Provides a C++ template library for parallel algorithms for reduction,
-        scan, sort and select.
-      - Reduction functions (``jax.numpy.sum``, ``jax.numpy.mean``, 
-        ``jax.numpy.prod``, ``jax.numpy.max`` and ``jax.numpy.min``), prefix sum
-        (``jax.numpy.cumsum``, ``jax.numpy.cumprod``) and sorting
-        (``jax.numpy.sort``, ``jax.numpy.argsort``).
-    * - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - 1.0.17
-      - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
-      - Used in functions like ``jax.numpy.fft``.
-    * - `hipRAND <https://github.com/ROCm/hipRAND>`_
-      - 2.11.0
-      - Provides fast random number generation for GPUs.
-      - The ``jax.random.uniform``, ``jax.random.normal``,
-        ``jax.random.randint`` and ``jax.random.split``.
-    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - 2.3.0
-      - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
-        singular value decompositions (SVD).
-      - Solving linear systems (``jax.numpy.linalg.solve``), matrix
-        factorizations, SVD (``jax.numpy.linalg.svd``) and eigenvalue problems 
-        (``jax.numpy.linalg.eig``).
-    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - 3.1.2
-      - Accelerates operations on sparse matrices, such as sparse matrix-vector
-        or matrix-matrix products.
-      - Sparse matrix multiplication (``jax.numpy.matmul``), sparse
-        matrix-vector and matrix-matrix products
-        (``jax.experimental.sparse.dot``), sparse linear system solvers and
-        sparse data handling.
-    * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
-      - 0.2.2
-      - Accelerates operations on sparse matrices, such as sparse matrix-vector
-        or matrix-matrix products.
-      - Sparse matrix multiplication (``jax.numpy.matmul``), sparse
-        matrix-vector and matrix-matrix products
-        (``jax.experimental.sparse.dot``) and sparse linear system solvers.
-    * - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - 3.3.0
-      - Optimized for 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
-        ``jax.nn.conv``, ``jax.nn.relu``, and ``jax.nn.batch_norm``.
-    * - `RCCL <https://github.com/ROCm/rccl>`_
-      - 2.21.5
-      - Optimized for multi-GPU communication for operations like  all-reduce,
-        broadcast, and scatter.
-      - Distribute computations across multiple GPU with ``pmap`` and
-        ``jax.distributed``. XLA automatically uses rccl when executing
-        operations across multiple GPUs on AMD hardware.
-    * - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - 3.3.0
-      - Provides a C++ template library for parallel algorithms like sorting,
-        reduction, and scanning.
-      - Reduction operations like ``jax.numpy.sum``, ``jax.pmap`` for
-        distributed training, which involves parallel reductions or
-        operations like ``jax.numpy.cumsum`` can use rocThrust.
-
-Supported and unsupported features
-===============================================================================
-
-The following table maps GPU-accelerated JAX modules to their supported
-ROCm and JAX versions.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Module
-      - Description
-      - Since JAX
-      - Since ROCm
-    * - ``jax.numpy``
-      - Implements the NumPy API, using the primitives in ``jax.lax``.
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.scipy``
-      - Provides GPU-accelerated and differentiable implementations of many
-        functions from the SciPy library, leveraging JAX's transformations
-        (e.g., ``grad``, ``jit``, ``vmap``).
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.lax``
-      - A library of primitives operations that underpins libraries such as
-        ``jax.numpy.`` Transformation rules, such as Jacobian-vector product
-        (JVP) and batching rules, are typically defined as transformations on
-        ``jax.lax`` primitives.
-      - 0.1.57
-      - 5.0.0
-    * - ``jax.random``
-      - Provides a number of routines for deterministic generation of sequences
-        of pseudorandom numbers.
-      - 0.1.58
-      - 5.0.0
-    * - ``jax.sharding``
-      - Allows to define partitioning and distributing arrays across multiple
-        devices.
-      - 0.3.20
-      - 5.1.0
-    * - ``jax.dlpack``
-      - For exchanging tensor data between JAX and other libraries that support the
-        DLPack standard.
-      - 0.1.57
-      - 5.0.0
-    * - ``jax.distributed``
-      - Enables the scaling of computations across multiple devices on a single
-        machine or across multiple machines.
-      - 0.1.74
-      - 5.0.0
-    * - ``jax.dtypes``
-      - Provides utilities for working with and managing data types in JAX
-        arrays and computations.
-      - 0.1.66
-      - 5.0.0 
-    * - ``jax.image``
-      - Contains image manipulation functions like resize, scale and translation.
-      - 0.1.57
-      - 5.0.0
-    * - ``jax.nn``
-      - Contains common functions for neural network libraries.
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.ops``
-      - Computes the minimum, maximum, sum or product within segments of an
-        array.
-      - 0.1.57
-      - 5.0.0
-    * - ``jax.profiler``
-      - Contains JAX’s tracing and time profiling features.
-      - 0.1.57
-      - 5.0.0
-    * - ``jax.stages``
-      - Contains interfaces to stages of the compiled execution process.
-      - 0.3.4
-      - 5.0.0
-    * - ``jax.tree``
-      - Provides utilities for working with tree-like container data structures.
-      - 0.4.26
-      - 5.6.0
-    * - ``jax.tree_util``
-      - Provides utilities for working with nested data structures, or
-        ``pytrees``.
-      - 0.1.65
-      - 5.0.0
-    * - ``jax.typing``
-      - Provides JAX-specific static type annotations.
-      - 0.3.18
-      - 5.1.0
-    * - ``jax.extend``
-      - Provides modules for access to JAX internal machinery module. The
-        ``jax.extend`` module defines a library view of some of JAX’s internal
-        components.
-      - 0.4.15
-      - 5.5.0
-    * - ``jax.example_libraries``
-      - Serves as a collection of example code and libraries that demonstrate
-        various capabilities of JAX.
-      - 0.1.74
-      - 5.0.0
-    * - ``jax.experimental``
-      - Namespace for experimental features and APIs that are in development or
-        are not yet fully stable for production use.
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.lib``
-      - Set of internal tools and types for bridging between JAX’s Python
-        frontend and its XLA backend.
-      - 0.4.6
-      - 5.3.0
-    * - ``jax_triton``
-      - Library that integrates the Triton deep learning compiler with JAX.
-      - jax_triton 0.2.0 
-      - 6.2.4
-
-jax.scipy module
-------------------------------------------------------------------------------
-
-A SciPy-like API for scientific computing.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Module
-      - Since JAX
-      - Since ROCm
-    * - ``jax.scipy.cluster``
-      - 0.3.11
-      - 5.1.0
-    * - ``jax.scipy.fft``
-      - 0.1.71
-      - 5.0.0
-    * - ``jax.scipy.integrate``
-      - 0.4.15
-      - 5.5.0
-    * - ``jax.scipy.interpolate``
-      - 0.1.76
-      - 5.0.0
-    * - ``jax.scipy.linalg``
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.scipy.ndimage``
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.scipy.optimize``
-      - 0.1.57
-      - 5.0.0
-    * - ``jax.scipy.signal``
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.scipy.spatial.transform``
-      - 0.4.12
-      - 5.4.0
-    * - ``jax.scipy.sparse.linalg``
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.scipy.special``
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.scipy.stats``
-      - 0.1.56
-      - 5.0.0
-
-jax.scipy.stats module
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-.. list-table::
-   :header-rows: 1
-
-   * - Module
-     - Since JAX
-     - Since ROCm
-   * - ``jax.scipy.stats.bernouli``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.beta``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.betabinom``
-     - 0.1.61
-     - 5.0.0
-   * - ``jax.scipy.stats.binom``
-     - 0.4.14
-     - 5.4.0
-   * - ``jax.scipy.stats.cauchy``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.chi2``
-     - 0.1.61
-     - 5.0.0
-   * - ``jax.scipy.stats.dirichlet``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.expon``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.gamma``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.gennorm``
-     - 0.3.15
-     - 5.2.0
-   * - ``jax.scipy.stats.geom``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.laplace``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.logistic``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.multinomial``
-     - 0.3.18
-     - 5.1.0
-   * - ``jax.scipy.stats.multivariate_normal``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.nbinom``
-     - 0.1.72
-     - 5.0.0
-   * - ``jax.scipy.stats.norm``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.pareto``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.poisson``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.t``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.truncnorm``
-     - 0.4.0
-     - 5.3.0
-   * - ``jax.scipy.stats.uniform``
-     - 0.1.56
-     - 5.0.0
-   * - ``jax.scipy.stats.vonmises``
-     - 0.4.2
-     - 5.3.0
-   * - ``jax.scipy.stats.wrapcauchy``
-     - 0.4.20
-     - 5.6.0
-
-jax.extend module
-------------------------------------------------------------------------------
-
-Modules for JAX extensions.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Module
-      - Since JAX
-      - Since ROCm
-    * - ``jax.extend.ffi``
-      - 0.4.30
-      - 6.0.0
-    * - ``jax.extend.linear_util``
-      - 0.4.17
-      - 5.6.0
-    * - ``jax.extend.mlir``
-      - 0.4.26
-      - 5.6.0
-    * - ``jax.extend.random``
-      - 0.4.15
-      - 5.5.0
-
-jax.experimental module
-------------------------------------------------------------------------------
-
-Experimental modules and APIs.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Module
-      - Since JAX
-      - Since ROCm
-    * - ``jax.experimental.checkify``
-      - 0.1.75
-      - 5.0.0
-    * - ``jax.experimental.compilation_cache.compilation_cache``
-      - 0.1.68
-      - 5.0.0
-    * - ``jax.experimental.custom_partitioning``
-      - 0.4.0
-      - 5.3.0
-    * - ``jax.experimental.jet``
-      - 0.1.56
-      - 5.0.0
-    * - ``jax.experimental.key_reuse``
-      - 0.4.26
-      - 5.6.0
-    * - ``jax.experimental.mesh_utils``
-      - 0.1.76
-      - 5.0.0
-    * - ``jax.experimental.multihost_utils``
-      - 0.3.2
-      - 5.0.0
-    * - ``jax.experimental.pallas``
-      - 0.4.15
-      - 5.5.0
-    * - ``jax.experimental.pjit``
-      - 0.1.61
-      - 5.0.0
-    * - ``jax.experimental.serialize_executable``
-      - 0.4.0
-      - 5.3.0
-    * - ``jax.experimental.shard_map``
-      - 0.4.3
-      - 5.3.0
-    * - ``jax.experimental.sparse``
-      - 0.1.75
-      - 5.0.0
-
-.. list-table::
-    :header-rows: 1
-
-    * - API
-      - Since JAX
-      - Since ROCm
-    * - ``jax.experimental.enable_x64``
-      - 0.1.60
-      - 5.0.0
-    * - ``jax.experimental.disable_x64``
-      - 0.1.60
-      - 5.0.0
-
-jax.experimental.pallas module
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Module for Pallas, a JAX extension for custom kernels.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Module
-      - Since JAX
-      - Since ROCm
-    * - ``jax.experimental.pallas.mosaic_gpu``
-      - 0.4.31
-      - 6.1.3
-    * - ``jax.experimental.pallas.tpu``
-      - 0.4.15
-      - 5.5.0
-    * - ``jax.experimental.pallas.triton``
-      - 0.4.32
-      - 6.1.3
-
-jax.experimental.sparse module
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Experimental support for sparse matrix operations.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Module
-      - Since JAX
-      - Since ROCm
-    * - ``jax.experimental.sparse.linalg``
-      - 0.3.15
-      - 5.2.0
-    * - ``jax.experimental.sparse.sparsify``
-      - 0.3.25
-      - ❌
-
-.. list-table::
-    :header-rows: 1
-
-    * - ``sparse`` data structure API
-      - Since JAX
-      - Since ROCm
-    * - ``jax.experimental.sparse.BCOO``
-      - 0.1.72
-      - 5.0.0
-    * - ``jax.experimental.sparse.BCSR``
-      - 0.3.20
-      - 5.1.0
-    * - ``jax.experimental.sparse.CSR``
-      - 0.1.75
-      - 5.0.0
-    * - ``jax.experimental.sparse.NM``
-      - 0.4.27
-      - 5.6.0
-    * - ``jax.experimental.sparse.COO``
-      - 0.1.75
-      - 5.0.0
-
-Unsupported JAX features
------------------------
-
-The following are GPU-accelerated JAX features not currently supported by
-ROCm.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Feature
-      - Description
-      - Since JAX
-    * - Mixed Precision with TF32
-      - Mixed precision with TF32 is used for matrix multiplications,
-        convolutions, and other linear algebra operations, particularly in
-        deep learning workloads like CNNs and transformers.
-      - 0.2.25
-    * - RNN support
-      - Currently only LSTM with double bias is supported with float32 input
-        and weight.
-      - 0.3.25
-    * - XLA int4 support
-      - 4-bit integer (int4) precision in the XLA compiler.
-      - 0.4.0
-    * - ``jax.experimental.sparsify``
-      - Converts a dense matrix to a sparse matrix representation.
-      - Experimental
-
-Use cases and recommendations
-================================================================================
-
-* The `nanoGPT in JAX <https://rocm.blogs.amd.com/artificial-intelligence/nanoGPT-JAX/README.html>`_
-  blog explores the implementation and training of a Generative Pre-trained
-  Transformer (GPT) model in JAX, inspired by Andrej Karpathy’s PyTorch-based
-  nanoGPT. By comparing how essential GPT components—such as self-attention
-  mechanisms and optimizers—are realized in PyTorch and JAX, also highlight
-  JAX’s unique features.
-
-* The `Optimize GPT Training: Enabling Mixed Precision Training in JAX using
-  ROCm on AMD GPUs <https://rocm.blogs.amd.com/artificial-intelligence/jax-mixed-precision/README.html>`_
-  blog post provides a comprehensive guide on enhancing the training efficiency
-  of GPT models by implementing mixed precision techniques in JAX, specifically
-  tailored for AMD GPUs utilizing the ROCm platform.
-
-* The `Supercharging JAX with Triton Kernels on AMD GPUs <https://rocm.blogs.amd.com/artificial-intelligence/jax-triton/README.html>`_
-  blog demonstrates how to develop a custom fused dropout-activation kernel for
-  matrices using Triton, integrate it with JAX, and benchmark its performance
-  using ROCm.
-
-* The `Distributed fine-tuning with JAX on AMD GPUs <https://rocm.blogs.amd.com/artificial-intelligence/distributed-sft-jax/README.html>`_
-  outlines the process of fine-tuning a Bidirectional Encoder Representations
-  from Transformers (BERT)-based large language model (LLM) using JAX for a text
-  classification task. The blog post discuss techniques for parallelizing the
-  fine-tuning across multiple AMD GPUs and assess the model's performance on a
-  holdout dataset. During the fine-tuning, a BERT-base-cased transformer model
-  and the General Language Understanding Evaluation (GLUE) benchmark dataset was
-  used on a multi-GPU setup.
-
-* The `MI300X workload optimization guide <https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/workload.html>`_
-  provides detailed guidance on optimizing workloads for the AMD Instinct MI300X
-  accelerator using ROCm. The page is aimed at helping users achieve optimal
-  performance for deep learning and other high-performance computing tasks on
-  the MI300X GPU.
-
-For more use cases and recommendations, see `ROCm JAX blog posts <https://rocm.blogs.amd.com/blog/tag/jax.html>`_.
--- a/docs/compatibility/ml-compatibility/pytorch-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/pytorch-compatibility.rst
@@ -1,922 +0,0 @@
-.. 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.
-
-Development of ROCm 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
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-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/>`_.
-Click the |docker-icon| icon to view the image on Docker Hub.
-
-.. 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 determined 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
-      - Adds 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
-      - Provides 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
-      - Provides 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
-      - Speeds up data augmentation, transformation, and other preprocessing steps.
-      - 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
-
-    * - Feature
-      - Description
-      - Since PyTorch
-      - Since ROCm
-    * - Device management
-      - Utilities for managing and interacting with GPUs.
-      - 0.4.0
-      - 3.8
-    * - Tensor operations on GPU
-      - Performs 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
-      - Returns 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
-      - 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 ROCm or CUDA operations. It is part of the
-PyTorch backend configuration system, which allows users to fine-tune how
-PyTorch interacts with the ROCm or CUDA environment.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Feature
-      - 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 include:
-
-.. list-table::
-    :header-rows: 1
-
-    * - Option
-      - 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
-
-    * - Feature
-      - 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
-
-    * - Feature
-      - Description
-      - Since PyTorch
-      - Since ROCm
-    * - TensorPipe
-      - 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
-      - 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
-
-    * - Feature
-      - 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
-
-    * - Feature
-      - Description
-      - Since torchaudio version
-      - Since ROCm
-    * - ``torchaudio.transforms.Spectrogram``
-      - Generates spectrogram of an input waveform using STFT.
-      - 0.6.0
-      - 4.5
-    * - ``torchaudio.transforms.MelSpectrogram``
-      - Generates 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``
-      - Resamples 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
-
-    * - Feature
-      - 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``
-      - Enables 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
-
-    * - Feature
-      - 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/training/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/rocm-for-ai/fine-tuning/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/rocm-for-ai/fine-tuning/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/rocm-for-ai/inference-optimization/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>`_.
--- a/docs/compatibility/ml-compatibility/tensorflow-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/tensorflow-compatibility.rst
@@ -1,489 +0,0 @@
-.. meta::
-    :description: TensorFlow compatibility
-    :keywords: GPU, TensorFlow compatibility
-
-*******************************************************************************
-TensorFlow compatibility
-*******************************************************************************
-
-`TensorFlow <https://www.tensorflow.org/>`_ is an open-source library for
-solving machine learning, deep learning, and AI problems. It can solve many
-problems across different sectors and industries but primarily focuses on
-neural network training and inference. It is one of the most popular and
-in-demand frameworks and is very active in open-source contribution and
-development.
-
-The `official TensorFlow repository <http://github.com/tensorflow/tensorflow>`_
-includes full ROCm support. AMD maintains a TensorFlow `ROCm repository
-<http://github.com/rocm/tensorflow-upstream>`_ in order to quickly add bug
-fixes, updates, and support for the latest ROCM versions.
-
- ROCm TensorFlow release:
-
-  - Offers :ref:`Docker images <tensorflow-docker-compat>` with
-    ROCm and TensorFlow pre-installed.
-
-  - ROCm TensorFlow repository: `<https://github.com/ROCm/tensorflow-upstream>`_
-
-  - See the :doc:`ROCm TensorFlow installation guide <rocm-install-on-linux:install/3rd-party/tensorflow-install>`
-    to get started.
-
- Official TensorFlow release:
-
-  - Official TensorFlow repository: `<https://github.com/tensorflow/tensorflow>`_
-
-  - See the `TensorFlow API versions <https://www.tensorflow.org/versions>`_ list.
-
-  .. note::
-
-     The official TensorFlow documentation does not cover ROCm support. Use the
-     ROCm documentation for installation instructions for Tensorflow on ROCm.
-     See :doc:`rocm-install-on-linux:install/3rd-party/tensorflow-install`.
-
-.. _tensorflow-docker-compat:
-
-Docker image compatibility
-===============================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes ready-made `TensorFlow
-<https://hub.docker.com/r/rocm/tensorflow>`_ images with ROCm backends on
-Docker Hub. The following Docker image tags and associated inventories are
-validated for `ROCm 6.3.1 <https://repo.radeon.com/rocm/apt/6.3.1/>`_. Click
-the |docker-icon| icon to view the image on Docker Hub.
-
-.. list-table:: TensorFlow Docker image components
-    :header-rows: 1
-
-    * - Docker image
-      - TensorFlow
-      - Dev
-      - Python
-      - TensorBoard 
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.12-tf2.17.0-dev/images/sha256-804121ee4985718277ba7dcec53c57bdade130a1ef42f544b6c48090ad379c17"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.17.0 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.17.0-cp312-cp312-manylinux_2_28_x86_64.whl>`_
-      - dev
-      - `Python 3.12 <https://www.python.org/downloads/release/python-3124/>`_
-      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`_
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.10-tf2.17.0-dev/images/sha256-776837ffa945913f6c466bfe477810a11453d21d5b6afb200be1c36e48fbc08e"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.17.0 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.17.0-cp310-cp310-manylinux_2_28_x86_64.whl>`_
-      - dev
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31012/>`_
-      - `TensorBoard 2.17.0 <https://github.com/tensorflow/tensorboard/tree/2.17.0>`_
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.12-tf2.16.2-dev/images/sha256-c793e1483e30809c3c28fc5d7805bedc033c73da224f839fff370717cb100944"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`_
-      - dev
-      - `Python 3.12 <https://www.python.org/downloads/release/python-3124/>`_
-      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`_
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.10-tf2.16.0-dev/images/sha256-263e78414ae85d7bcd52a025a94131d0a279872a45ed632b9165336dfdcd4443"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.16.2-cp310-cp310-manylinux_2_28_x86_64.whl>`_
-      - dev
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31012/>`_
-      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`_
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.3.1-py3.10-tf2.15.0-dev/images/sha256-479046a8477ca701a9494a813ab17e8ab4f6baa54641e65dc8d07629f1e6a880"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.15.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3/tensorflow_rocm-2.15.1-cp310-cp310-manylinux_2_28_x86_64.whl>`_
-      - dev
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31012/>`_
-      - `TensorBoard 2.15.2 <https://github.com/tensorflow/tensorboard/tree/2.15.2>`_
-
-Critical ROCm libraries for TensorFlow
-===============================================================================
-
-TensorFlow depends on multiple components and the supported features of those
-components can affect the TensorFlow ROCm supported feature set. The versions
-in the following table refer to the first TensorFlow version where the ROCm
-library was introduced as a dependency.
-
-.. list-table::
-    :widths: 25, 10, 35, 30
-    :header-rows: 1
-
-    * - ROCm library
-      - Version
-      - Purpose
-      - Used in
-    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - 2.3.0
-      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
-        matrix and vector operations.
-      - Accelerates operations like ``tf.matmul``, ``tf.linalg.matmul``, and
-        other matrix multiplications commonly used in neural network layers.
-    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - 0.10.0
-      - Extends hipBLAS with additional optimizations like fused kernels and
-        integer tensor cores.
-      - Optimizes matrix multiplications and linear algebra operations used in
-        layers like dense, convolutional, and RNNs in TensorFlow.
-    * - `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 ``tf.reduce_sum``, ``tf.cumsum``, ``tf.sort``
-        and other tensor operations in TensorFlow, especially those involving
-        scanning, sorting, and filtering.
-    * - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - 1.0.17
-      - Accelerates Fast Fourier Transforms (FFT) for signal processing tasks.
-      - Used for operations like signal processing, image filtering, and
-        certain types of neural networks requiring FFT-based transformations.
-    * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - 2.3.0
-      - Provides GPU-accelerated direct linear solvers for dense and sparse
-        systems.
-      - Optimizes linear algebra functions such as solving systems of linear
-        equations, often used in optimization and training tasks.
-    * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - 3.1.2
-      - Optimizes sparse matrix operations for efficient computations on sparse
-        data.
-      - Accelerates sparse matrix operations in models with sparse weight
-        matrices or activations, commonly used in neural networks.
-    * - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - 3.3.0
-      - Provides optimized deep learning primitives such as convolutions,
-        pooling,
-        normalization, and activation functions.
-      - Speeds up convolutional neural networks (CNNs) and other layers. Used
-        in TensorFlow for layers like ``tf.nn.conv2d``, ``tf.nn.relu``, and
-        ``tf.nn.lstm_cell``.
-    * - `RCCL <https://github.com/ROCm/rccl>`_
-      - 2.21.5
-      - Optimizes for multi-GPU communication for operations like AllReduce and
-        Broadcast.
-      - Distributed data parallel training (``tf.distribute.MirroredStrategy``).
-        Handles communication in multi-GPU setups.
-    * - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - 3.3.0
-      - Provides a C++ template library for parallel algorithms like sorting,
-        reduction, and scanning.
-      - Reduction operations like ``tf.reduce_sum``, ``tf.cumsum`` for computing
-        the cumulative sum of elements along a given axis or ``tf.unique`` to
-        finds unique elements in a tensor can use rocThrust.
-
-Supported and unsupported features
-===============================================================================
-
-The following section maps supported data types and GPU-accelerated TensorFlow
-features to their minimum supported ROCm and TensorFlow versions.
-
-Data types
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-The data type of a tensor is specified using the ``dtype`` attribute or
-argument, and TensorFlow supports a wide range of data types for different use
-cases.
-
-The basic, single data types of `tf.dtypes <https://www.tensorflow.org/api_docs/python/tf/dtypes>`_
-are as follows:
-
-.. list-table::
-    :header-rows: 1
-
-    * - Data type
-      - Description
-      - Since TensorFlow
-      - Since ROCm
-    * - ``bfloat16``
-      - 16-bit bfloat (brain floating point).
-      - 1.0.0
-      - 1.7
-    * - ``bool``
-      - Boolean.
-      - 1.0.0
-      - 1.7
-    * - ``complex128``
-      - 128-bit complex.
-      - 1.0.0
-      - 1.7
-    * - ``complex64``
-      - 64-bit complex.
-      - 1.0.0
-      - 1.7
-    * - ``double``
-      - 64-bit (double precision) floating-point.
-      - 1.0.0
-      - 1.7
-    * - ``float16``
-      - 16-bit (half precision) floating-point.
-      - 1.0.0
-      - 1.7
-    * - ``float32``
-      - 32-bit (single precision) floating-point.
-      - 1.0.0
-      - 1.7
-    * - ``float64``
-      - 64-bit (double precision) floating-point.
-      - 1.0.0
-      - 1.7
-    * - ``half``
-      - 16-bit (half precision) floating-point.
-      - 2.0.0
-      - 2.0
-    * - ``int16``
-      - Signed 16-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``int32``
-      - Signed 32-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``int64``
-      - Signed 64-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``int8``
-      - Signed 8-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``qint16``
-      - Signed quantized 16-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``qint32``
-      - Signed quantized 32-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``qint8``
-      - Signed quantized 8-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``quint16``
-      - Unsigned quantized 16-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``quint8``
-      - Unsigned quantized 8-bit integer.
-      - 1.0.0
-      - 1.7
-    * - ``resource``
-      - Handle to a mutable, dynamically allocated resource.
-      - 1.0.0
-      - 1.7
-    * - ``string``
-      - Variable-length string, represented as byte array.
-      - 1.0.0
-      - 1.7
-    * - ``uint16``
-      - Unsigned 16-bit (word) integer.
-      - 1.0.0
-      - 1.7
-    * - ``uint32``
-      - Unsigned 32-bit (dword) integer.
-      - 1.5.0
-      - 1.7
-    * - ``uint64``
-      - Unsigned 64-bit (qword) integer.
-      - 1.5.0
-      - 1.7
-    * - ``uint8``
-      - Unsigned 8-bit (byte) integer.
-      - 1.0.0
-      - 1.7
-    * - ``variant``
-      - Data of arbitrary type (known at runtime).
-      - 1.4.0
-      - 1.7
-
-Features
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-This table provides an overview of key features in TensorFlow and their
-availability in ROCm.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Module
-      - Description
-      - Since TensorFlow
-      - Since ROCm
-    * - ``tf.linalg`` (Linear Algebra)
-      - Operations for matrix and tensor computations, such as
-        ``tf.linalg.matmul`` (matrix multiplication), ``tf.linalg.inv``
-        (matrix inversion) and ``tf.linalg.cholesky`` (Cholesky decomposition).
-        These leverage GPUs for high-performance linear algebra operations.
-      - 1.4
-      - 1.8.2
-    * - ``tf.nn`` (Neural Network Operations)
-      - GPU-accelerated building blocks for deep learning models, such as 2D
-        convolutions with ``tf.nn.conv2d``, max pooling operations with
-        ``tf.nn.max_pool``, activation functions like ``tf.nn.relu`` or softmax
-        for output layers with ``tf.nn.softmax``.
-      - 1.0
-      - 1.8.2
-    * - ``tf.image`` (Image Processing)
-      - GPU-accelerated functions for image preprocessing and augmentations,
-        such as resize images with ``tf.image.resize``, flip images horizontally
-        with ``tf.image.flip_left_right`` and adjust image brightness randomly
-        with ``tf.image.random_brightness``.
-      - 1.1
-      - 1.8.2
-    * - ``tf.keras`` (High-Level API)
-      - GPU acceleration for Keras layers and models, including dense layers
-        (``tf.keras.layers.Dense``), convolutional layers
-        (``tf.keras.layers.Conv2D``) and recurrent layers
-        (``tf.keras.layers.LSTM``).
-      - 1.4
-      - 1.8.2
-    * - ``tf.math`` (Mathematical Operations)
-      - GPU-accelerated mathematical operations, such as sum across dimensions
-        with ``tf.math.reduce_sum``, elementwise exponentiation with
-        ``tf.math.exp`` and sigmoid activation (``tf.math.sigmoid``).
-      - 1.5
-      - 1.8.2
-    * - ``tf.signal`` (Signal Processing)
-      - Functions for spectral analysis and signal transformations.
-      - 1.13
-      - 2.1
-    * - ``tf.data`` (Data Input Pipeline)
-      - GPU-accelerated data preprocessing for efficient input pipelines, 
-        Prefetching with ``tf.data.experimental.AUTOTUNE``. GPU-enabled
-        transformations like map and batch. 
-      - 1.4
-      - 1.8.2
-    * - ``tf.distribute`` (Distributed Training)
-      - Enabling to scale computations across multiple devices on a single
-        machine or across multiple machines.
-      - 1.13
-      - 2.1
-    * - ``tf.random`` (Random Number Generation)
-      - GPU-accelerated random number generation
-      - 1.12
-      - 1.9.2
-    * - ``tf.TensorArray`` (Dynamic Array Operations)
-      - Enables dynamic tensor manipulation on GPUs.
-      - 1.0
-      - 1.8.2
-    * - ``tf.sparse`` (Sparse Tensor Operations)
-      - GPU-accelerated sparse matrix manipulations.
-      - 1.9
-      - 1.9.0
-    * - ``tf.experimental.numpy``
-      - GPU-accelerated NumPy-like API for numerical computations.
-      - 2.4
-      - 4.1.1
-    * - ``tf.RaggedTensor``
-      - Handling of variable-length sequences and ragged tensors with GPU
-        support.
-      - 1.13
-      - 2.1
-    * - ``tf.function`` with XLA (Accelerated Linear Algebra)
-      - Enable GPU-accelerated functions in optimization.
-      - 1.14
-      - 2.4
-    * - ``tf.quantization``
-      - Quantized operations for inference, accelerated on GPUs.
-      - 1.12 
-      - 1.9.2
-
-Distributed library features
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Enables developers to scale computations across multiple devices on a single machine or
-across multiple machines.
-
-.. list-table::
-   :header-rows: 1
-
-   * - Feature
-     - Description
-     - Since TensorFlow
-     - Since ROCm
-   * - ``MultiWorkerMirroredStrategy``
-     - Synchronous training across multiple workers using mirrored variables.
-     - 2.0
-     - 3.0
-   * - ``MirroredStrategy``
-     - Synchronous training across multiple GPUs on one machine.
-     - 1.5
-     - 2.5
-   * - ``TPUStrategy``
-     - Efficiently trains models on Google TPUs.
-     - 1.9
-     - ❌
-   * - ``ParameterServerStrategy``
-     - Asynchronous training using parameter servers for variable management.
-     - 2.1
-     - 4.0
-   * - ``CentralStorageStrategy``
-     - Keeps variables on a single device and performs computation on multiple
-       devices.
-     - 2.3
-     - 4.1
-   * - ``CollectiveAllReduceStrategy``
-     - Synchronous training across multiple devices and hosts.
-     - 1.14
-     - 3.5
-   * - Distribution Strategies API
-     - High-level API to simplify distributed training configuration and
-       execution.
-     - 1.10
-     - 3.0
-
-Unsupported TensorFlow features
-===============================================================================
-
-The following are GPU-accelerated TensorFlow features not currently supported by
-ROCm.
-
-.. list-table::
-    :header-rows: 1
-
-    * - Feature
-      - Description
-      - Since TensorFlow
-    * - Mixed Precision with TF32
-      - Mixed precision with TF32 is used for matrix multiplications,
-        convolutions, and other linear algebra operations, particularly in
-        deep learning workloads like CNNs and transformers.
-      - 2.4
-    * - ``tf.distribute.TPUStrategy``
-      - Efficiently trains models on Google TPUs.
-      - 1.9
-
-Use cases and recommendations
-===============================================================================
-
-* The `Training a Neural Collaborative Filtering (NCF) Recommender on an AMD
-  GPU <https://rocm.blogs.amd.com/artificial-intelligence/ncf/README.html>`_
-  blog post discusses training an NCF recommender system using TensorFlow. It
-  explains how NCF improves traditional collaborative filtering methods by
-  leveraging neural networks to model non-linear user-item interactions. The
-  post outlines the implementation using the recommenders library, focusing on
-  the use of implicit data (for example, user interactions like viewing or
-  purchasing) and how it addresses challenges like the lack of negative values.
-
-* The `Creating a PyTorch/TensorFlow code environment on AMD GPUs
-  <https://rocm.blogs.amd.com/software-tools-optimization/pytorch-tensorflow-env/README.html>`_
-  blog post provides instructions for creating a machine learning environment
-  for PyTorch and TensorFlow on AMD GPUs using ROCm. It covers steps like
-  installing the libraries, cloning code repositories, installing dependencies,
-  and troubleshooting potential issues with CUDA-based code. Additionally, it
-  explains how to HIPify code (port CUDA code to HIP) and manage Docker images
-  for a better experience on AMD GPUs. This guide aims to help data scientists
-  and ML practitioners adapt their code for AMD GPUs.
-
-For more use cases and recommendations, see the `ROCm Tensorflow blog posts <https://rocm.blogs.amd.com/blog/tag/tensorflow.html>`_.
--- a/docs/conceptual/More-about-how-ROCm-uses-PCIe-Atomics.rst
+++ b/docs/conceptual/More-about-how-ROCm-uses-PCIe-Atomics.rst
@@ -0,0 +1,156 @@
+.. meta::
+   :description: How ROCm uses PCIe atomics
+   :keywords: PCIe, PCIe atomics, atomics, BAR memory, AMD, ROCm
+
+*****************************************************************************
+How ROCm uses PCIe atomics
+*****************************************************************************
+
+ROCm PCIe feature and overview of BAR memory
+================================================================
+
+ROCm is an extension of HSA platform architecture, so it shares the queuing model, memory model,
+signaling and synchronization protocols. Platform atomics are integral to perform queuing and
+signaling memory operations where there may be multiple-writers across CPU and GPU agents.
+
+The full list of HSA system architecture platform requirements are here:
+`HSA Sys Arch Features <http://hsafoundation.com/wp-content/uploads/2021/02/HSA-SysArch-1.2.pdf>`_.
+
+AMD ROCm Software uses the new PCI Express 3.0 (Peripheral Component Interconnect Express [PCIe]
+3.0) features for atomic read-modify-write transactions which extends inter-processor synchronization
+mechanisms to IO to support the defined set of HSA capabilities needed for queuing and signaling
+memory operations.
+
+The new PCIe atomic operations operate as completers for ``CAS`` (Compare and Swap), ``FetchADD``,
+``SWAP`` atomics. The atomic operations are initiated by the I/O device which support 32-bit, 64-bit and
+128-bit operand which target address have to be naturally aligned to operation sizes.
+
+For ROCm the Platform atomics are used in ROCm in the following ways:
+
+  * Update HSA queue's read_dispatch_id: 64 bit atomic add used by the command processor on the
+    GPU agent to update the packet ID it processed.
+  * Update HSA queue's write_dispatch_id: 64 bit atomic add used by the CPU and GPU agent to
+    support multi-writer queue insertions.
+  * Update HSA Signals -- 64bit atomic ops are used for CPU & GPU synchronization.
+
+The PCIe 3.0 atomic operations feature allows atomic transactions to be requested by, routed through
+and completed by PCIe components. Routing and completion does not require software support.
+Component support for each is detectable via the Device Capabilities 2 (DevCap2) register. Upstream
+bridges need to have atomic operations routing enabled or the atomic operations will fail even though
+PCIe endpoint and PCIe I/O devices has the capability to atomic operations.
+
+To do atomic operations routing capability between two or more Root Ports, each associated Root Port
+must indicate that capability via the atomic operations routing supported bit in the DevCap2 register.
+
+If your system has a PCIe Express Switch it needs to support atomic operations routing. Atomic
+operations requests are permitted only if a component's ``DEVCTL2.ATOMICOP_REQUESTER_ENABLE``
+field is set. These requests can only be serviced if the upstream components support atomic operation
+completion and/or routing to a component which does. Atomic operations routing support=1, routing
+is supported; atomic operations routing support=0, routing is not supported.
+
+An atomic operation is a non-posted transaction supporting 32-bit and 64-bit address formats, there
+must be a response for Completion containing the result of the operation. Errors associated with the
+operation (uncorrectable error accessing the target location or carrying out the atomic operation) are
+signaled to the requester by setting the Completion Status field in the completion descriptor, they are
+set to to Completer Abort (CA) or Unsupported Request (UR).
+
+To understand more about how PCIe atomic operations work, see
+`PCIe atomics <https://pcisig.com/specifications/pciexpress/specifications/ECN_Atomic_Ops_080417.pdf>`_
+
+`Linux Kernel Patch to pci_enable_atomic_request <https://patchwork.kernel.org/project/linux-pci/patch/1443110390-4080-1-git-send-email-jay@jcornwall.me/>`_
+
+There are also a number of papers which talk about these new capabilities:
+
+  * `Atomic Read Modify Write Primitives by Intel <https://www.intel.es/content/dam/doc/white-paper/atomic-read-modify-write-primitives-i-o-devices-paper.pdf>`_
+  * `PCI express 3 Accelerator White paper by Intel <https://www.intel.sg/content/dam/doc/white-paper/pci-express3-accelerator-white-paper.pdf>`_
+  * `PCIe Generation 4 Base Specification includes atomic operations <https://astralvx.com/storage/2020/11/PCI_Express_Base_4.0_Rev0.3_February19-2014.pdf>`_
+  * `Xilinx PCIe Ultrascale White paper <https://docs.xilinx.com/v/u/8OZSA2V1b1LLU2rRCDVGQw>`_
+
+Other I/O devices with PCIe atomics support:
+
+  * Mellanox ConnectX-5 InfiniBand Card
+  * Cray Aries Interconnect
+  * Xilinx 7 Series Devices
+
+Future bus technology with richer I/O atomics operation Support
+
+  * GenZ
+
+New PCIe Endpoints with support beyond AMD Ryzen and EPYC CPU; Intel Haswell or newer CPUs
+with PCIe Generation 3.0 support.
+
+  * Mellanox Bluefield SOC
+  * Cavium Thunder X2
+
+In ROCm, we also take advantage of PCIe ID based ordering technology for P2P when the GPU
+originates two writes to two different targets:
+
+* Write to another GPU memory
+* Write to system memory to indicate transfer complete
+
+They are routed off to different ends of the computer but we want to make sure the write to system
+memory to indicate transfer complete occurs AFTER P2P write to GPU has complete.
+
+BAR memory overview
+----------------------------------------------------------------------------------------------------
+On a Xeon E5 based system in the BIOS we can turn on above 4GB PCIe addressing, if so he need to set
+memory-mapped input/output (MMIO) base address (MMIOH base) and range (MMIO high size) in the BIOS.
+
+In the Supermicro system in the system bios you need to see the following
+
+  * Advanced->PCIe/PCI/PnP configuration-\> Above 4G Decoding = Enabled
+  * Advanced->PCIe/PCI/PnP Configuration-\>MMIOH Base = 512G
+  * Advanced->PCIe/PCI/PnP Configuration-\>MMIO High Size = 256G
+
+When we support Large Bar Capability there is a Large Bar VBIOS which also disable the IO bar.
+
+For GFX9 and Vega10 which have Physical Address up 44 bit and 48 bit Virtual address.
+
+  * BAR0-1 registers: 64bit, prefetchable, GPU memory. 8GB or 16GB depending on Vega10 SKU. Must
+    be placed < 2^44 to support P2P  	access from other Vega10.
+  * BAR2-3 registers: 64bit, prefetchable, Doorbell. Must be placed \< 2^44 to support P2P access from
+    other Vega10.
+  * BAR4 register: Optional, not a boot device.
+  * BAR5 register: 32bit, non-prefetchable, MMIO. Must be placed \< 4GB.
+
+Here is how our base address register (BAR) works on GFX 8 GPUs with 40 bit Physical Address Limit ::
+
+  11:00.0 Display controller: Advanced Micro Devices, Inc. [AMD/ATI] Fiji [Radeon R9 FURY / NANO
+  Series] (rev c1)
+
+  Subsystem: Advanced Micro Devices, Inc. [AMD/ATI] Device 0b35
+
+  Flags: bus master, fast devsel, latency 0, IRQ 119
+
+  Memory at bf40000000 (64-bit, prefetchable) [size=256M]
+
+  Memory at bf50000000 (64-bit, prefetchable) [size=2M]
+
+  I/O ports at 3000 [size=256]
+
+  Memory at c7400000 (32-bit, non-prefetchable) [size=256K]
+
+  Expansion ROM at c7440000 [disabled] [size=128K]
+
+Legend:
+
+1 : GPU Frame Buffer BAR -- In this example it happens to be 256M, but typically this will be size of the
+GPU memory (typically 4GB+). This BAR has to be placed \< 2^40 to allow peer-to-peer access from
+other GFX8 AMD GPUs. For GFX9 (Vega GPU) the BAR has to be placed \< 2^44 to allow peer-to-peer
+access from other GFX9 AMD GPUs.
+
+2 : Doorbell BAR -- The size of the BAR is typically will be \< 10MB (currently fixed at 2MB) for this
+generation GPUs. This BAR has to be placed \< 2^40 to allow peer-to-peer access from other current
+generation AMD GPUs.
+
+3 : IO BAR -- This is for legacy VGA and boot device support, but since this the GPUs in this project are
+not VGA devices (headless), this is not a concern even if the SBIOS does not setup.
+
+4 : MMIO BAR -- This is required for the AMD Driver SW to access the configuration registers. Since the
+reminder of the BAR available is only 1 DWORD (32bit), this is placed \< 4GB. This is fixed at 256KB.
+
+5 : Expansion ROM -- This is required for the AMD Driver SW to access the GPU video-bios. This is
+currently fixed at 128KB.
+
+For more information, you can review
+`Overview of Changes to PCI Express 3.0 <https://www.mindshare.com/files/resources/PCIe%203-0.pdf>`_.
--- a/docs/conceptual/gpu-arch/mi300-mi200-performance-counters.rst
+++ b/docs/conceptual/gpu-arch/mi300-mi200-performance-counters.rst
@@ -615,6 +615,7 @@ The following table shows the hardware counters *by* all texture addressing unit
  "``TA_FLAT_READ_WAVEFRONTS_sum``", "Sum of flat opcode reads processed"
  "``TA_FLAT_WRITE_WAVEFRONTS_sum``", "Sum of flat opcode writes processed"
  "``TA_FLAT_WAVEFRONTS_sum``", "Total number of flat opcode wavefronts processed"
+  "``TA_FLAT_READ_WAVEFRONTS_sum``", "Total number of flat opcode read wavefronts processed"
  "``TA_FLAT_ATOMIC_WAVEFRONTS_sum``", "Total number of flat opcode atomic wavefronts processed"
  "``TA_TOTAL_WAVEFRONTS_sum``", "Total number of wavefronts processed"

--- a/docs/conceptual/pcie-atomics.rst
+++ b/docs/conceptual/pcie-atomics.rst
@@ -1,57 +0,0 @@
-.. meta::
-   :description: How ROCm uses PCIe atomics
-   :keywords: PCIe, PCIe atomics, atomics, Atomic operations, AMD, ROCm
-
-*****************************************************************************
-How ROCm uses PCIe atomics
-*****************************************************************************
-AMD ROCm is an extension of the Heterogeneous System Architecture (HSA). To meet the requirements of an HSA-compliant system, ROCm supports queuing models, memory models, and signaling and synchronization protocols. ROCm can perform atomic Read-Modify-Write (RMW) transactions that extend inter-processor synchronization mechanisms to Input/Output (I/O) devices starting from Peripheral Component Interconnect Express 3.0 (PCIe™ 3.0). It supports the defined HSA capabilities for queuing and signaling memory operations. To learn more about the requirements of an HSA-compliant system, see the 
-`HSA Platform System Architecture Specification <http://hsafoundation.com/wp-content/uploads/2021/02/HSA-SysArch-1.2.pdf>`_.
-
-ROCm uses platform atomics to perform memory operations like queuing, signaling, and synchronization across multiple CPU, GPU agents, and I/O devices. Platform atomics ensure that atomic operations run synchronously, without interruptions or conflicts, across multiple shared resources.
-
-Platform atomics in ROCm
-==============================
-Platform atomics enable the set of atomic operations that perform RMW actions across multiple processors, devices, and memory locations so that they run synchronously without interruption. An atomic operation is a sequence of computing instructions run as a single, indivisible unit. These instructions are completed in their entirety without any interruptions. If the instructions can't be completed as a unit without interruption, none of the instructions are run. These operations support 32-bit and 64-bit address formats.
-
-Some of the operations for which ROCm uses platform atomics are:
-
-* Update the HSA queue's ``read_dispatch_id``. The command processor on the GPU agent uses a 64-bit atomic add operation. It updates the packet ID it processed.
-* Update the HSA queue's ``write_dispatch_id``. The CPU and GPU agents use a 64-bit atomic add operation. It supports multi-writer queue insertions.
-* Update HSA Signals. A 64-bit atomic operation is used for CPU & GPU synchronization.
-
-
-PCIe for atomic operations
----------------------------
-ROCm requires CPUs that support PCIe atomics. Similarly, all connected I/O devices should also support PCIe atomics for optimum compatibility. PCIe supports the ``CAS`` (Compare and Swap), ``FetchADD``, and ``SWAP`` atomic operations across multiple resources. These atomic operations are initiated by the I/O devices that support 32-bit, 64-bit, and 128-bit operands. Likewise, the target memory address where these atomic operations are performed should also be aligned to the size of the operand. This alignment ensures that the operations are performed efficiently and correctly without failure. 
-
-When an atomic operation is successful, the requester receives a response of completion along with the operation result. However, any errors associated with the operation are signaled to the requester by updating the Completion Status field. Issues accessing the target location or running the atomic operation are common errors. Depending upon the error, the Completion Status field is updated to Completer Abort (CA) or Unsupported Request (UR). The field is present in the Completion Descriptor.
-
-To learn more about the industry standards and specifications of PCIe, see `PCI-SIG Specification <https://pcisig.com/specifications>`_.
-
-To learn more about PCIe and its capabilities, consult the following white papers:
-
-* `Atomic Read Modify Write Primitives by Intel <https://www.intel.es/content/dam/doc/white-paper/atomic-read-modify-write-primitives-i-o-devices-paper.pdf>`_
-* `PCI Express 3 Accelerator White paper by Intel <https://www.intel.sg/content/dam/doc/white-paper/pci-express3-accelerator-white-paper.pdf>`_
-* `PCIe Generation 4 Base Specification includes atomic operations <https://astralvx.com/storage/2020/11/PCI_Express_Base_4.0_Rev0.3_February19-2014.pdf>`_
-* `Xilinx PCIe Ultrascale White paper <https://docs.xilinx.com/v/u/8OZSA2V1b1LLU2rRCDVGQw>`_
-
-Working with PCIe 3.0 in ROCm
-------------------------------
-Starting with PCIe 3.0, atomic operations can be requested, routed through, and completed by PCIe components. Routing and completion do not require software support. Component support for each can be identified by the Device Capabilities 2 (DevCap2) register. Upstream
-bridges need to have atomic operations routing enabled. If not enabled, the atomic operations will fail even if the 
-PCIe endpoint and PCIe I/O devices can perform atomic operations. 
-
-If your system uses PCIe switches to connect and enable communication between multiple PCIe components, the switches must also support atomic operations routing.
-
-To enable atomic operations routing between multiple root ports, each root port must support atomic operation routing. This capability can be identified from the atomic operations routing support bit in the DevCap2 register. If the bit has value of 1, routing is supported. Atomic operation requests are permitted only if a component's ``DEVCTL2.ATOMICOP_REQUESTER_ENABLE``
-field is set. These requests can only be serviced if the upstream components also support atomic operation completion or if the requests can be routed to a component that supports atomic operation completion.
-
-ROCm uses the PCIe-ID-based ordering technology for peer-to-peer (P2P) data transmission. PCIe-ID-based ordering technology is used when the GPU initiates multiple write operations to different memory locations.
-
-For more information on changes implemented in PCIe 3.0, see `Overview of Changes to PCI Express 3.0 <https://www.mindshare.com/files/resources/PCIe%203-0.pdf>`_.
-
-
-
-
-
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -29,48 +29,60 @@ if os.environ.get("READTHEDOCS", "") == "True":
 # configurations for PDF output by Read the Docs
 project = "ROCm Documentation"
 author = "Advanced Micro Devices, Inc."
-copyright = "Copyright (c) 2025 Advanced Micro Devices, Inc. All rights reserved."
-version = "6.3.1"
-release = "6.3.1"
+copyright = "Copyright (c) 2024 Advanced Micro Devices, Inc. All rights reserved."
+version = "6.3.0"
+release = "6.3.0"
 setting_all_article_info = True
 all_article_info_os = ["linux", "windows"]
 all_article_info_author = ""

 # pages with specific settings
 article_pages = [
-    {"file": "about/release-notes", "os": ["linux", "windows"], "date": "2024-12-20"},
-    {"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": "about/release-notes", "os": ["linux", "windows"], "date": "2024-12-03"},
    {"file": "how-to/deep-learning-rocm", "os": ["linux"]},
-
    {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},
-
-    {"file": "how-to/rocm-for-ai/training/index", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/training/train-a-model", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/training/scale-model-training", "os": ["linux"]},
-
-    {"file": "how-to/rocm-for-ai/fine-tuning/index", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/fine-tuning/overview", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/fine-tuning/fine-tuning-and-inference", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference", "os": ["linux"]},
-
-    {"file": "how-to/rocm-for-ai/inference/index", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/install", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/hugging-face-models", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/llm-inference-frameworks", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/vllm-benchmark", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/deploy-your-model", "os": ["linux"]},
-    
-    {"file": "how-to/rocm-for-ai/inference-optimization/index", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference-optimization/model-quantization", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference-optimization/optimizing-with-composable-kernel", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference-optimization/optimizing-triton-kernel", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference-optimization/profiling-and-debugging", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference-optimization/workload", "os": ["linux"]},
-
+    {"file": "how-to/rocm-for-ai/install", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/train-a-model", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/accelerate-training", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/deploy-your-model", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/hugging-face-models", "os": ["linux"]},
+    {"file": "how-to/rocm-for-hpc/index", "os": ["linux"]},
+    {"file": "how-to/llm-fine-tuning-optimization/index", "os": ["linux"]},
+    {"file": "how-to/llm-fine-tuning-optimization/overview", "os": ["linux"]},
+    {
+        "file": "how-to/llm-fine-tuning-optimization/fine-tuning-and-inference",
+        "os": ["linux"],
+    },
+    {
+        "file": "how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference",
+        "os": ["linux"],
+    },
+    {
+        "file": "how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference",
+        "os": ["linux"],
+    },
+    {
+        "file": "how-to/llm-fine-tuning-optimization/llm-inference-frameworks",
+        "os": ["linux"],
+    },
+    {
+        "file": "how-to/llm-fine-tuning-optimization/model-acceleration-libraries",
+        "os": ["linux"],
+    },
+    {"file": "how-to/llm-fine-tuning-optimization/model-quantization", "os": ["linux"]},
+    {
+        "file": "how-to/llm-fine-tuning-optimization/optimizing-with-composable-kernel",
+        "os": ["linux"],
+    },
+    {
+        "file": "how-to/llm-fine-tuning-optimization/optimizing-triton-kernel",
+        "os": ["linux"],
+    },
+    {
+        "file": "how-to/llm-fine-tuning-optimization/profiling-and-debugging",
+        "os": ["linux"],
+    },
+    {"file": "how-to/performance-validation/mi300x/vllm-benchmark", "os": ["linux"]},
    {"file": "how-to/system-optimization/index", "os": ["linux"]},
    {"file": "how-to/system-optimization/mi300x", "os": ["linux"]},
    {"file": "how-to/system-optimization/mi200", "os": ["linux"]},
@@ -89,9 +101,6 @@ extensions = ["rocm_docs", "sphinx_reredirects", "sphinx_sitemap"]

 external_projects_current_project = "rocm"

-# Uncomment if facing rate limit exceed issue with local build 
-# external_projects_remote_repository = ""
-
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "https://rocm-stg.amd.com/")
 html_context = {}
 if os.environ.get("READTHEDOCS", "") == "True":
--- a/docs/contribute/building.md
+++ b/docs/contribute/building.md
@@ -1,150 +0,0 @@
-<head>
-  <meta charset="UTF-8">
-  <meta name="description" content="Building ROCm documentation">
-  <meta name="keywords" content="documentation, Visual Studio Code, GitHub, command line,
-  AMD, ROCm">
-</head>
-
-# Building documentation
-
-## GitHub
-
-If you open a pull request and scroll down to the summary panel,
-there is a commit status section. Next to the line
-`docs/readthedocs.com:advanced-micro-devices-demo`, there is a `Details` link.
-If you click this, it takes you to the Read the Docs build for your pull request.
-
-![GitHub PR commit status](../data/contribute/commit-status.png)
-
-If you don't see this line, click `Show all checks` to get an itemized view.
-
-## Command line
-
-You can build our documentation via the command line using Python.
-
-See the `build.tools.python` setting in the [Read the Docs configuration file](https://github.com/ROCm/ROCm/blob/develop/.readthedocs.yaml) for the Python version used by Read the Docs to build documentation.
-
-See the [Python requirements file](https://github.com/ROCm/ROCm/blob/develop/docs/sphinx/requirements.txt) for Python packages needed to build the documentation.
-
-Use the Python Virtual Environment (`venv`) and run the following commands from the project root:
-
-```sh
-python3 -mvenv .venv
-
-.venv/bin/python     -m pip install -r docs/sphinx/requirements.txt
-.venv/bin/python     -m sphinx -T -E -b html -d _build/doctrees -D language=en docs _build/html
-```
-
-Navigate to `_build/html/index.html` and open this file in a web browser.
-
-## Visual Studio Code
-
-With the help of a few extensions, you can create a productive environment to author and test
-documentation locally using Visual Studio (VS) Code. Follow these steps to configure VS Code:
-
-1. Install the required extensions:
-
-   * Python: `(ms-python.python)`
-   * Live Server: `(ritwickdey.LiveServer)`
-
-2. Add the following entries to `.vscode/settings.json`.
-
-    ```json
-      {
-        "liveServer.settings.root": "/.vscode/build/html",
-        "liveServer.settings.wait": 1000,
-        "python.terminal.activateEnvInCurrentTerminal": true
-      }
-    ```
-
-    * `liveServer.settings.root`: Sets the root of the output website for live previews. Must be changed
-      alongside the `tasks.json` command.
-    * `liveServer.settings.wait`: Tells the live server to wait with the update in order to give Sphinx time to
-      regenerate the site contents and not refresh before the build is complete.
-    * `python.terminal.activateEnvInCurrentTerminal`: Activates the automatic virtual environment, so you
-      can build the site from the integrated terminal.
-
-3. Add the following tasks to `.vscode/tasks.json`.
-
-    ```json
-      {
-        "version": "2.0.0",
-        "tasks": [
-          {
-            "label": "Build Docs",
-            "type": "process",
-            "windows": {
-              "command": "${workspaceFolder}/.venv/Scripts/python.exe"
-            },
-            "command": "${workspaceFolder}/.venv/bin/python3",
-            "args": [
-              "-m",
-              "sphinx",
-              "-j",
-              "auto",
-              "-T",
-              "-b",
-              "html",
-              "-d",
-              "${workspaceFolder}/.vscode/build/doctrees",
-              "-D",
-              "language=en",
-              "${workspaceFolder}/docs",
-              "${workspaceFolder}/.vscode/build/html"
-            ],
-            "problemMatcher": [
-              {
-                "owner": "sphinx",
-                "fileLocation": "absolute",
-                "pattern": {
-                  "regexp": "^(?:.*\\.{3}\\s+)?(\\/[^:]*|[a-zA-Z]:\\\\[^:]*):(\\d+):\\s+(WARNING|ERROR):\\s+(.*)$",
-                  "file": 1,
-                  "line": 2,
-                  "severity": 3,
-                  "message": 4
-                }
-              },
-              {
-              "owner": "sphinx",
-                "fileLocation": "absolute",
-                "pattern": {
-                  "regexp": "^(?:.*\\.{3}\\s+)?(\\/[^:]*|[a-zA-Z]:\\\\[^:]*):{1,2}\\s+(WARNING|ERROR):\\s+(.*)$",
-                  "file": 1,
-                  "severity": 2,
-                  "message": 3
-                }
-              }
-            ],
-            "group": {
-              "kind": "build",
-              "isDefault": true
-            }
-          }
-        ]
-      }
-    ```
-
-    > Implementation detail: two problem matchers were needed to be defined,
-    > because VS Code doesn't tolerate some problem information being potentially
-    > absent. While a single regex could match all types of errors, if a capture
-    > group remains empty (the line number doesn't show up in all warning/error
-    > messages) but the `pattern` references said empty capture group, VS Code
-    > discards the message completely.
-
-4. Configure the Python virtual environment (`venv`).
-
-    From the Command Palette, run `Python: Create Environment`. Select `venv` environment and
-    `docs/sphinx/requirements.txt`.
-
-5. Build the docs.
-
-    Launch the default build task using one of the following options:
-
-    * A hotkey (the default is `Ctrl+Shift+B`)
-    * Issuing the `Tasks: Run Build Task` from the Command Palette
-
-6. Open the live preview.
-
-    Navigate to the site output within VS Code: right-click on `.vscode/build/html/index.html` and
-    select `Open with Live Server`. The contents should update on every rebuild without having to
-    refresh the browser.
--- a/docs/data/how-to/gpu-enabled-mpi-1.png
+++ b/docs/data/how-to/gpu-enabled-mpi-1.png
--- a/docs/data/rocm-software-stack-6_3_0.jpg
+++ b/docs/data/rocm-software-stack-6_3_0.jpg
--- a/docs/data/rocm-software-stack-6_3_1.jpg
+++ b/docs/data/rocm-software-stack-6_3_1.jpg
--- a/docs/data/rocm-software-stack-6_3_2.jpg
+++ b/docs/data/rocm-software-stack-6_3_2.jpg
--- a/docs/how-to/Bar-Memory.rst
+++ b/docs/how-to/Bar-Memory.rst
@@ -1,99 +0,0 @@
-.. meta::
-   :description: Learn about BAR configuration in AMD GPUs and ways to troubleshoot physical addressing limit
-   :keywords: BAR memory, MMIO, GPU memory, Physical Addressing Limit, AMD, ROCm
-
-**************************************
-Troubleshoot BAR access limitation
-**************************************
-Direct Memory Access (DMA) to PCIe devices using Base Address Registers (BARs) can be restricted due to physical addressing limits. These restrictions can result in data access failures between the system components. Peer-to-peer (P2P) DMA is used to access resources such as registers and memory between devices. PCIe devices need memory-mapped input/output (MMIO) space for DMA, and these MMIO spaces are defined in the PCIe BARs.
-
-These BARs are a set of 32-bit or 64-bit registers that are used to define the resources that PCIe devices provide. The CPU and other system devices also use these to access the resources of the PCIe devices. P2P DMA only works when one device can directly access the local BAR memory of another. If the memory address of a BAR memory exceeds the physical addressing limit of a device, the device will not be able to access that BAR. This could be the device's own BAR or the BAR of another device in the system.
-
-If the BAR memory exceeds than the physical addressing limit of the device, the device will not be able to access the remote BAR. 
-
-To handle any BAR access issues that might occur, you need to be aware of the physical address limitations of the devices and understand the :ref:`BAR configuration of AMD GPUs <bar-configuration>`. This information is important when setting up additional MMIO apertures for PCIe devices in the system's physical address space.
-
-Handling physical address limitation
-=============================================
-When a system boots, the system BIOS allocates the physical address space for the components in the system, including system memory and MMIO apertures. On modern 64-bit platforms, there are generally two or more MMIO apertures: one located below 4 GB of physical address space for 32-bit compatibility, and one or more above 4 GB for devices needing more space.
-
-You can control the memory address of the high MMIO aperture from the system BIOS configuration options. This lets you configure the additional MMIO space to align with the physical addressing limit and allows P2P DMA between the devices. For example, if a PCIe device is limited to 44-bit of physical addressing, you should ensure that the MMIO aperture is set below 44-bit in the system physical address space.
-
-There are two ways to handle this:
-
-* Ensure that the high MMIO aperture is within the physical addressing limits of the devices in the system. For example, if the devices have a 44-bit physical addressing limit, set the ``MMIO High Base`` and ``MMIO High size`` options in the BIOS such that the aperture is within the 44-bit address range, and ensure that the ``Above 4G Decoding`` option is Enabled.  
-
-* Enable the Input-Output Memory Management Unit (IOMMU). When the IOMMU is enabled in non-passthrough mode, it will create a virtual I/O address space for each device on the system. It also ensures that all virtual addresses created in that space are within the physical addressing limits of the device. For more information on IOMMU, see :doc:`../conceptual/iommu`. 
-
-.. _bar-configuration:
-
-BAR configuration for AMD GPUs
-================================================
-
-The following table shows how the BARs are configured for AMD GPUs.
-
-
-.. list-table:: 
-  :widths: 25 25 50
-  :header-rows: 1
-
-  * - BAR Type
-    - Value
-    - Description
-  * - BAR0-1 registers
-    - 64-bit, Prefetchable, GPU memory
-    - 8 GB or 16 GB depending on GPU. Set to less than 2^44 to support P2P access from other GPUs with a 44-bit physical address limit. Prefetchable memory enables faster read operation for high-performance computing (HPC) by fetching the contiguous data from the same data source even before requested as an anticipation of a future request.
-  * - BAR2-3 registers
-    - 64-bit, Prefetchable, Doorbell
-    - Set to less than 2^44 to support P2P access from other GPUs with a 44-bit physical address limit. As a Doorbell BAR, it indicates to the GPU that a new operation is in its queue to be processed. 
-  * - BAR4 register
-    - Optional
-    - Not a boot device
-  * - BAR5 register
-    - 32-bit, Non-prefetchable, MMIO
-    - Is set to less than 4 GB.
-
-Example of BAR usage on AMD GPUs
-------------------------------------
-Following is an example configuration of BARs set by the system BIOS on GFX8 GPUs with the 40-bit physical addressing limit: 
-
-.. code:: shell 
-
-  11:00.0 Display controller: Advanced Micro Devices, Inc. [AMD/ATI] Fiji [Radeon R9 FURY / NANO
-  Series] (rev c1)
-
-  Subsystem: Advanced Micro Devices, Inc. [AMD/ATI] Device 0b35
-
-  Flags: bus master, fast devsel, latency 0, IRQ 119
-
-  Memory at bf40000000 (64-bit, prefetchable) [size=256M]
-
-  Memory at bf50000000 (64-bit, prefetchable) [size=2M]
-
-  I/O ports at 3000 [size=256]
-
-  Memory at c7400000 (32-bit, non-prefetchable) [size=256K]
-
-  Expansion ROM at c7440000 [disabled] [size=128K]
-
-Details of the BARs configured in the example are: 
-
-**GPU Frame Buffer BAR:** ``Memory at bf40000000 (64-bit, prefetchable) [size=256M]``
-
-The size of the BAR in the example is 256 MB. Generally, it will be the size of the GPU memory (typically 4 GB+). Depending upon the physical address limit and generation of AMD GPUs, the BAR can be set below 2^40, 2^44, or 2^48. 
-
-**Doorbell BAR:** ``Memory at bf50000000 (64-bit, prefetchable) [size=2M]``
-
-The size of the BAR should typically be less than 10 MB for this generation of GPUs and has been set to 2 MB in the example. This BAR is placed less than 2^40 to allow peer-to-peer access from other generations of AMD GPUs.
-
-**I/O BAR:** ``I/O ports at 3000 [size=256]``
-
-This is for legacy VGA and boot device support. Because the GPUs used are not connected to a display (VGA devices), this is not a concern, even if it isn't set up in the system BIOS.
-
-**MMIO BAR:** ``Memory at c7400000 (32-bit, non-prefetchable) [size=256K]``
-
-The AMD Driver requires this to access the configuration registers. Since the reminder of the BAR available is only 1 DWORD (32-bit), this is set less than 4 GB. In the example, it is fixed at 256 KB.
-
-**Expansion ROM:** ``Expansion ROM at c7440000 [disabled] [size=128K]``
-
-This is required by the AMD Driver to access the GPU video-BIOS. In the example, it is fixed at 128 KB.
--- a/docs/how-to/deep-learning-rocm.rst
+++ b/docs/how-to/deep-learning-rocm.rst
@@ -11,24 +11,20 @@ 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 provide information on compatibility and supported
-features for these ROCm-enabled deep learning frameworks.
+The following guides cover installation processes for ROCm-aware deep learning frameworks.

-* :doc:`PyTorch compatibility <../compatibility/ml-compatibility/pytorch-compatibility>`
-* :doc:`TensorFlow compatibility <../compatibility/ml-compatibility/tensorflow-compatibility>`
-* :doc:`JAX compatibility <../compatibility/ml-compatibility/jax-compatibility>`
+* :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>`

-This chart steps through typical installation workflows for installing deep learning frameworks for ROCm.
+The following 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

-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>`
+Find information on version compatibility and framework release notes in :doc:`Third-party support matrix
+<rocm-install-on-linux:reference/3rd-party-support-matrix>`.

 .. note::

@@ -39,11 +35,4 @@ through the following guides.

 * :doc:`rocm-for-ai/index`

-* :doc:`Training <rocm-for-ai/training/index>`
-
-* :doc:`Fine-tuning LLMs <rocm-for-ai/fine-tuning/index>`
-
-* :doc:`Inference <rocm-for-ai/inference/index>`
-
-* :doc:`Inference optimization <rocm-for-ai/inference-optimization/index>`
-
+* :doc:`llm-fine-tuning-optimization/index`
--- a/docs/how-to/gpu-enabled-mpi.rst
+++ b/docs/how-to/gpu-enabled-mpi.rst
@@ -0,0 +1,264 @@
+.. 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
--- a/docs/how-to/llm-fine-tuning-optimization/fine-tuning-and-inference.rst
+++ b/docs/how-to/llm-fine-tuning-optimization/fine-tuning-and-inference.rst
@@ -1,6 +1,6 @@
 .. meta::
-   :description: How to fine-tune models with ROCm
-   :keywords: ROCm, LLM, fine-tuning, inference, usage, tutorial, deep learning, PyTorch, TensorFlow, JAX
+   :description: How to fine-tune LLMs with ROCm
+   :keywords: ROCm, LLM, fine-tuning, inference, usage, tutorial

 *************************
 Fine-tuning and inference
@@ -9,7 +9,7 @@ Fine-tuning and inference
 Fine-tuning using ROCm involves leveraging AMD's GPU-accelerated :doc:`libraries <rocm:reference/api-libraries>` and
 :doc:`tools <rocm:reference/rocm-tools>` to optimize and train deep learning models. ROCm provides a comprehensive
 ecosystem for deep learning development, including open-source libraries for optimized deep learning operations and
-ROCm-aware versions of :doc:`deep learning frameworks <../../deep-learning-rocm>` such as PyTorch, TensorFlow, and JAX.
+ROCm-aware versions of :doc:`deep learning frameworks <../deep-learning-rocm>` such as PyTorch, TensorFlow, and JAX.

 Single-accelerator systems, such as a machine equipped with a single accelerator or GPU, are commonly used for
 smaller-scale deep learning tasks, including fine-tuning pre-trained models and running inference on moderately
--- a/docs/how-to/llm-fine-tuning-optimization/index.rst
+++ b/docs/how-to/llm-fine-tuning-optimization/index.rst
@@ -0,0 +1,37 @@
+.. meta::
+   :description: How to fine-tune LLMs with ROCm
+   :keywords: ROCm, LLM, fine-tuning, usage, tutorial
+
+*******************************************
+Fine-tuning LLMs and inference optimization
+*******************************************
+
+ROCm empowers the fine-tuning and optimization of large language models, making them accessible and efficient for
+specialized tasks. ROCm supports the broader AI ecosystem to ensure seamless integration with open frameworks,
+models, and tools.
+
+For more information, see `What is ROCm? <https://rocm.docs.amd.com/en/latest/what-is-rocm.html>`_
+
+Throughout the following topics, this guide discusses the goals and :ref:`challenges of fine-tuning a large language
+model <fine-tuning-llms-concept-challenge>` like Llama 2. Then, it introduces :ref:`common methods of optimizing your
+fine-tuning <fine-tuning-llms-concept-optimizations>` using techniques like LoRA with libraries like PEFT. In the
+sections that follow, you'll find practical guides on libraries and tools to accelerate your fine-tuning.
+
+- :doc:`Conceptual overview of fine-tuning LLMs <overview>`
+
+- :doc:`Fine-tuning and inference <fine-tuning-and-inference>` using a
+  :doc:`single-accelerator <single-gpu-fine-tuning-and-inference>` or
+  :doc:`multi-accelerator <multi-gpu-fine-tuning-and-inference>` system.
+
+- :doc:`Model quantization <model-quantization>`
+
+- :doc:`Model acceleration libraries <model-acceleration-libraries>`
+
+- :doc:`LLM inference frameworks <llm-inference-frameworks>`
+
+- :doc:`Optimizing with Composable Kernel <optimizing-with-composable-kernel>`
+
+- :doc:`Optimizing Triton kernels <optimizing-triton-kernel>`
+
+- :doc:`Profiling and debugging <profiling-and-debugging>`
+
--- a/docs/how-to/llm-fine-tuning-optimization/llm-inference-frameworks.rst
+++ b/docs/how-to/llm-fine-tuning-optimization/llm-inference-frameworks.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: How to implement the LLM inference frameworks with ROCm acceleration.
+   :description: How to fine-tune LLMs with ROCm
   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, inference, vLLM, TGI, text generation inference

 ************************
@@ -8,8 +8,8 @@ LLM inference frameworks

 This section discusses how to implement `vLLM <https://docs.vllm.ai/en/latest>`_ and `Hugging Face TGI
 <https://huggingface.co/docs/text-generation-inference/en/index>`_ using
-:doc:`single-accelerator <../fine-tuning/single-gpu-fine-tuning-and-inference>` and
-:doc:`multi-accelerator <../fine-tuning/multi-gpu-fine-tuning-and-inference>` systems.
+:doc:`single-accelerator <single-gpu-fine-tuning-and-inference>` and
+:doc:`multi-accelerator <multi-gpu-fine-tuning-and-inference>` systems.

 .. _fine-tuning-llms-vllm:

@@ -68,7 +68,7 @@ Installing vLLM

         The following log message is displayed in your command line indicates that the server is listening for requests.

-         .. image:: ../../../data/how-to/llm-fine-tuning-optimization/vllm-single-gpu-log.png
+         .. image:: ../../data/how-to/llm-fine-tuning-optimization/vllm-single-gpu-log.png
            :alt: vLLM API server log message
            :align: center

@@ -141,7 +141,7 @@ Installing vLLM

   ROCm provides a prebuilt optimized Docker image for validating the performance of LLM inference with vLLM
   on the MI300X accelerator. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in CSV
-   format. For more information, see :doc:`vllm-benchmark`.
+   format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.

 .. _fine-tuning-llms-tgi:

--- a/docs/how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries.rst
+++ b/docs/how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: How to use model acceleration techniques and libraries to improve memory efficiency and performance.
+   :description: How to fine-tune LLMs with ROCm
   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, Flash Attention, Hugging Face, xFormers, vLLM, PyTorch

 ****************************
@@ -20,7 +20,7 @@ Attention (GQA), and Multi-Query Attention (MQA). This reduction in memory movem
 time-to-first-token (TTFT) latency for large batch sizes and long prompt sequences, thereby enhancing overall
 performance.

-.. image:: ../../../data/how-to/llm-fine-tuning-optimization/attention-module.png
+.. image:: ../../data/how-to/llm-fine-tuning-optimization/attention-module.png
   :alt: Attention module of a large language module utilizing tiling
   :align: center

@@ -245,7 +245,7 @@ page describes the options.
   Validator,ROCBLAS_VERSION,4.1.0-cefa4a9b-dirty
   GemmTunableOp_float_TN,tn_200_100_20,Gemm_Rocblas_32323,0.00669595

-.. image:: ../../../data/how-to/llm-fine-tuning-optimization/tunableop.png
+.. image:: ../../data/how-to/llm-fine-tuning-optimization/tunableop.png
   :alt: GEMM and TunableOp
   :align: center

@@ -277,7 +277,7 @@ Installing FBGEMM_GPU
 Installing FBGEMM_GPU consists of the following steps:

 *  Set up an isolated Miniconda environment
-*  Install ROCm using Docker or the :doc:`package manager <rocm-install-on-linux:install/install-methods/package-manager-index>`
+*  Install ROCm using Docker or the :doc:`package manager <rocm-install-on-linux:install/native-install/index>`
 *  Install the nightly `PyTorch <https://pytorch.org/>`_ build
 *  Complete the pre-build and build tasks
  
--- a/docs/how-to/rocm-for-ai/inference-optimization/model-quantization.rst
+++ b/docs/how-to/rocm-for-ai/inference-optimization/model-quantization.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: How to use model quantization techniques to speed up inference.
+   :description: How to fine-tune LLMs with ROCm
   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, quantization, GPTQ, transformers, bitsandbytes

 *****************************
--- a/docs/how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference.rst
+++ b/docs/how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference.rst
@@ -1,6 +1,6 @@
 .. meta::
   :description: Model fine-tuning and inference on a multi-GPU system
-   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, multi-GPU, distributed, inference, accelerators, PyTorch, HuggingFace, torchtune
+   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, multi-GPU, distributed, inference

 *****************************************************
 Fine-tuning and inference using multiple accelerators
@@ -233,4 +233,4 @@ GPU model fine-tuning and inference with LLMs.
      INFO:torchtune.utils.logging:Learning rate scheduler is initialized.
      1|111|Loss: 1.5790324211120605:   7%|█                                          | 114/1618

-Read more about inference frameworks in :doc:`LLM inference frameworks <../inference/llm-inference-frameworks>`.
+Read more about inference frameworks in :doc:`LLM inference frameworks <llm-inference-frameworks>`.
--- a/docs/how-to/rocm-for-ai/inference-optimization/optimizing-triton-kernel.rst
+++ b/docs/how-to/rocm-for-ai/inference-optimization/optimizing-triton-kernel.rst
@@ -1,6 +1,6 @@
 .. meta::
-   :description: How to optimize Triton kernels for ROCm.
-   :keywords: ROCm, LLM, fine-tuning, usage, MI300X, tutorial, Triton, kernel, performance, optimization
+   :description: How to fine-tune LLMs with ROCm
+   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, Triton, kernel, performance, optimization

 *************************
 Optimizing Triton kernels
@@ -13,7 +13,7 @@ and CUDA kernel optimization.

 Refer to the
 :ref:`Triton kernel performance optimization <mi300x-triton-kernel-performance-optimization>`
-section of the :doc:`workload` guide
+section of the :doc:`/how-to/tuning-guides/mi300x/workload` guide
 for detailed information.

 Triton kernel performance optimization includes the following topics.
--- a/docs/how-to/rocm-for-ai/inference-optimization/optimizing-with-composable-kernel.md
+++ b/docs/how-to/rocm-for-ai/inference-optimization/optimizing-with-composable-kernel.md
@@ -1,9 +1,8 @@
---
-myst:
-  html_meta:
-    "description": "How to optimize machine learning workloads with Composable Kernel (CK)."
-    "keywords": "mixed, precision, kernel, inference, linear, algebra, ck, GEMM"
---
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="SmoothQuant model inference on AMD Instinct MI300X using Composable Kernel">
+  <meta name="keywords" content="Mixed Precision, Kernel, Inference, Linear Algebra">
+</head>

 # Optimizing with Composable Kernel

@@ -33,7 +32,7 @@ The template parameters of the instance are grouped into four parameter types:
 ================
 ### Figure 2
 ================ -->
-```{figure} ../../../data/how-to/llm-fine-tuning-optimization/ck-template_parameters.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-template_parameters.jpg
 The template parameters of the selected GEMM kernel are classified into four groups. These template parameter groups should be defined properly before running the instance.
 ```

@@ -127,7 +126,7 @@ The row and column, and stride information of input matrices are also passed to
 ================
 ### Figure 3
 ================ -->
-```{figure} ../../../data/how-to/llm-fine-tuning-optimization/ck-kernel_launch.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-kernel_launch.jpg
 Templated kernel launching consists of kernel instantiation, making arguments by passing in actual application parameters, creating an invoker, and running the instance through the invoker.
 ```

@@ -156,7 +155,7 @@ The first operation in the process is to perform the multiplication of input mat
 ================
 ### Figure 4
 ================ -->
-```{figure} ../../../data/how-to/llm-fine-tuning-optimization/ck-operation_flow.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-operation_flow.jpg
 Operation flow.
 ```

@@ -172,7 +171,7 @@ Here, we use [DeviceBatchedGemmMultiD_Xdl](https://github.com/ROCm/composable_ke
 ================
 ### Figure 5
 ================ -->
-```{figure} ../../../data/how-to/llm-fine-tuning-optimization/ck-root_instance.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-root_instance.jpg
 Use the ‘DeviceBatchedGemmMultiD_Xdl’ instance as a root.
 ```

@@ -422,7 +421,7 @@ Run `python setup.py install` to build and install the extension. It should look
 ================
 ### Figure 6
 ================ -->
-```{figure} ../../../data/how-to/llm-fine-tuning-optimization/ck-compilation.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-compilation.jpg
 Compilation and installation of the INT8 kernels.
 ```

@@ -434,7 +433,7 @@ The implementation architecture of running SmoothQuant models on MI300X GPUs is
 ================
 ### Figure 7
 ================ -->
-```{figure} ../../../data/how-to/llm-fine-tuning-optimization/ck-inference_flow.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-inference_flow.jpg
 The implementation architecture of running SmoothQuant models on AMD MI300X accelerators.
 ```

@@ -460,7 +459,7 @@ Figure 8 shows the performance comparisons between the original FP16 and the Smo
 ================
 ### Figure 8
 ================ -->
-```{figure} ../../../data/how-to/llm-fine-tuning-optimization/ck-comparisons.jpg
+```{figure} ../../data/how-to/llm-fine-tuning-optimization/ck-comparisons.jpg
 Performance comparisons between the original FP16 and the SmoothQuant-quantized INT8 models on a single MI300X accelerator.
 ```

--- a/docs/how-to/llm-fine-tuning-optimization/overview.rst
+++ b/docs/how-to/llm-fine-tuning-optimization/overview.rst
@@ -1,6 +1,6 @@
 .. meta::
-   :description: Conceptual overview of fine-tuning LLMs
-   :keywords: ROCm, LLM, Llama, fine-tuning, usage, tutorial, optimzation, LoRA, walkthrough, PEFT, Reinforcement
+   :description: How to fine-tune LLMs with ROCm
+   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, optimzation, LoRA, walkthrough

 ***************************************
 Conceptual overview of fine-tuning LLMs
@@ -41,7 +41,7 @@ The weight update is as follows: :math:`W_{updated} = W + ΔW`.
 If the weight matrix :math:`W` contains 7B parameters, then the weight update matrix :math:`ΔW` should also
 contain 7B parameters. Therefore, the :math:`ΔW` calculation is computationally and memory intensive.

-.. figure:: ../../../data/how-to/llm-fine-tuning-optimization/weight-update.png
+.. figure:: ../../data/how-to/llm-fine-tuning-optimization/weight-update.png
   :alt: Weight update diagram

   (a) Weight update in regular fine-tuning. (b) Weight update in LoRA where the product of matrix A (:math:`M\times K`)
--- a/docs/how-to/rocm-for-ai/inference-optimization/profiling-and-debugging.rst
+++ b/docs/how-to/rocm-for-ai/inference-optimization/profiling-and-debugging.rst
@@ -1,12 +1,12 @@
 .. meta::
-   :description: How to use ROCm profiling and debugging tools.
-   :keywords: ROCm, LLM, fine-tuning, usage, MI300X, tutorial, profiling, debugging, performance, Triton
+   :description: How to fine-tune LLMs with ROCm
+   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, profiling, debugging, performance, Triton

 ***********************
 Profiling and debugging
 ***********************

-This section provides an index for further documentation on profiling and
+This section provides an index for further documentation on  profiling and
 debugging tools and their common usage patterns.

 See :ref:`AMD Instinct MI300X™ workload optimization <mi300x-profiling-start>`
--- a/docs/how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference.rst
+++ b/docs/how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference.rst
@@ -1,6 +1,6 @@
 .. meta::
   :description: Model fine-tuning and inference on a single-GPU system
-   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, single-GPU, LoRA, PEFT, inference, SFTTrainer
+   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, single-GPU, LoRA, PEFT, inference

 ****************************************************
 Fine-tuning and inference using a single accelerator
@@ -80,7 +80,7 @@ Setting up the base implementation environment
 #. Install the required dependencies.

   bitsandbytes is a library that facilitates quantization to improve the efficiency of deep learning models. Learn more
-   about its use in :doc:`../inference-optimization/model-quantization`.
+   about its use in :doc:`model-quantization`.

   See the :ref:`Optimizations for model fine-tuning <fine-tuning-llms-concept-optimizations>` for a brief discussion on
   PEFT and TRL.
@@ -507,4 +507,4 @@ If using multiple accelerators, see
 popular libraries that simplify fine-tuning and inference in a multi-accelerator system.

 Read more about inference frameworks like vLLM and Hugging Face TGI in
-:doc:`LLM inference frameworks <../inference/llm-inference-frameworks>`.
+:doc:`LLM inference frameworks <llm-inference-frameworks>`.
--- a/docs/how-to/performance-validation/mi300x/vllm-benchmark.rst
+++ b/docs/how-to/performance-validation/mi300x/vllm-benchmark.rst
@@ -0,0 +1,407 @@
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the unified
+                 ROCm Docker image.
+   :keywords: model, MAD, automation, dashboarding, validate
+
+***********************************************************
+LLM inference performance validation on AMD Instinct MI300X
+***********************************************************
+
+.. _vllm-benchmark-unified-docker:
+
+The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
+a prebuilt, optimized environment designed for validating large language model
+(LLM) inference performance on the AMD Instinct™ MI300X accelerator. This
+ROCm vLLM Docker image integrates vLLM and PyTorch tailored specifically for the
+MI300X accelerator and includes the following components:
+
+* `ROCm 6.2.1 <https://github.com/ROCm/ROCm>`_
+
+* `vLLM 0.6.4 <https://docs.vllm.ai/en/latest>`_
+
+* `PyTorch 2.5.0 <https://github.com/pytorch/pytorch>`_
+
+* Tuning files (in CSV format)
+
+With this Docker image, you can quickly validate the expected inference
+performance numbers on the MI300X accelerator. This topic also provides tips on
+optimizing performance with popular AI models.
+
+.. hlist::
+   :columns: 6
+
+   * Llama 3.1 8B
+
+   * Llama 3.1 70B
+
+   * Llama 3.1 405B
+
+   * Llama 2 7B
+
+   * Llama 2 70B
+
+   * Mixtral 8x7B
+
+   * Mixtral 8x22B
+
+   * Mixtral 7B
+
+   * Qwen2 7B
+
+   * Qwen2 72B
+
+   * JAIS 13B
+
+   * JAIS 30B
+
+.. _vllm-benchmark-vllm:
+
+.. note::
+
+   vLLM is a toolkit and library for LLM inference and serving. AMD implements
+   high-performance custom kernels and modules in vLLM to enhance performance.
+   See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+   more information.
+
+Getting started
+===============
+
+Use the following procedures to reproduce the benchmark results on an
+MI300X accelerator with the prebuilt vLLM Docker image.
+
+.. _vllm-benchmark-get-started:
+
+1. Disable NUMA auto-balancing.
+
+   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+   might hang until the periodic balancing is finalized. For more information,
+   see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
+
+   .. code-block:: shell
+
+      # disable automatic NUMA balancing
+      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+      # check if NUMA balancing is disabled (returns 0 if disabled)
+      cat /proc/sys/kernel/numa_balancing
+      0
+
+2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
+
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+
+Once setup is complete, you can choose between two options to reproduce the
+benchmark results:
+
+-  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
+
+-  :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
+
+.. _vllm-benchmark-mad:
+
+MAD-integrated benchmarking
+===========================
+
+Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+directory and install the required packages on the host machine.
+
+.. code-block:: shell
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD
+   pip install -r requirements.txt
+
+Use this command to run a performance benchmark test of the Llama 3.1 8B model
+on one GPU with ``float16`` data type in the host machine.
+
+.. code-block:: shell
+
+   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+   python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
+
+ROCm MAD launches a Docker container with the name
+``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
+model are collected in the following path: ``~/MAD/reports_float16/``.
+
+Although the following models are preconfigured to collect latency and
+throughput performance data, you can also change the benchmarking parameters.
+Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
+
+Available models
+----------------
+
+.. hlist::
+   :columns: 3
+
+   * ``pyt_vllm_llama-3.1-8b``
+
+   * ``pyt_vllm_llama-3.1-70b``
+
+   * ``pyt_vllm_llama-3.1-405b``
+
+   * ``pyt_vllm_llama-2-7b``
+
+   * ``pyt_vllm_llama-2-70b``
+
+   * ``pyt_vllm_mixtral-8x7b``
+
+   * ``pyt_vllm_mixtral-8x22b``
+
+   * ``pyt_vllm_mistral-7b``
+
+   * ``pyt_vllm_qwen2-7b``
+
+   * ``pyt_vllm_qwen2-72b``
+
+   * ``pyt_vllm_jais-13b``
+
+   * ``pyt_vllm_jais-30b``
+
+   * ``pyt_vllm_llama-3.1-8b_fp8``
+
+   * ``pyt_vllm_llama-3.1-70b_fp8``
+
+   * ``pyt_vllm_llama-3.1-405b_fp8``
+
+   * ``pyt_vllm_mixtral-8x7b_fp8``
+
+   * ``pyt_vllm_mixtral-8x22b_fp8``
+
+.. _vllm-benchmark-standalone:
+
+Standalone benchmarking
+=======================
+
+You can run the vLLM benchmark tool independently by starting the
+:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
+snippet.
+
+.. code-block::
+
+   docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.4 rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+
+In the Docker container, clone the ROCm MAD repository and navigate to the
+benchmark scripts directory at ``~/MAD/scripts/vllm``.
+
+.. code-block::
+
+   git clone https://github.com/ROCm/MAD
+   cd MAD/scripts/vllm
+
+Command
+-------
+
+To start the benchmark, use the following command with the appropriate options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
+
+See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
+
+.. note::
+
+   The input sequence length, output sequence length, and tensor parallel (TP) are
+   already configured. You don't need to specify them with this script.
+
+.. note::
+
+   If you encounter the following error, pass your access-authorized Hugging
+   Face token to the gated models.
+
+   .. code-block:: shell
+
+      OSError: You are trying to access a gated repo.
+
+      # pass your HF_TOKEN
+      export HF_TOKEN=$your_personal_hf_token
+
+.. _vllm-benchmark-standalone-options:
+
+Options
+-------
+
+.. list-table::
+   :header-rows: 1
+   :align: center
+
+   * - Name
+     - Options
+     - Description
+
+   * - ``$test_option``
+     - latency
+     - Measure decoding token latency
+
+   * -
+     - throughput
+     - Measure token generation throughput
+
+   * -
+     - all
+     - Measure both throughput and latency
+
+   * - ``$model_repo``
+     - ``meta-llama/Meta-Llama-3.1-8B-Instruct``
+     - Llama 3.1 8B
+
+   * - (``float16``)
+     - ``meta-llama/Meta-Llama-3.1-70B-Instruct``
+     - Llama 3.1 70B
+
+   * -
+     - ``meta-llama/Meta-Llama-3.1-405B-Instruct``
+     - Llama 3.1 405B
+
+   * -
+     - ``meta-llama/Llama-2-7b-chat-hf``
+     - Llama 2 7B
+
+   * -
+     - ``meta-llama/Llama-2-70b-chat-hf``
+     - Llama 2 70B
+
+   * -
+     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
+     - Mixtral 8x7B
+
+   * -
+     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
+     - Mixtral 8x22B
+
+   * -
+     - ``mistralai/Mistral-7B-Instruct-v0.3``
+     - Mixtral 7B
+
+   * -
+     - ``Qwen/Qwen2-7B-Instruct``
+     - Qwen2 7B
+
+   * -
+     - ``Qwen/Qwen2-72B-Instruct``
+     - Qwen2 72B
+
+   * -
+     - ``core42/jais-13b-chat``
+     - JAIS 13B
+
+   * -
+     - ``core42/jais-30b-chat-v3``
+     - JAIS 30B
+
+   * - ``$model_repo``
+     - ``amd/Meta-Llama-3.1-8B-Instruct-FP8-KV``
+     - Llama 3.1 8B
+
+   * - (``float8``)
+     - ``amd/Meta-Llama-3.1-70B-Instruct-FP8-KV``
+     - Llama 3.1 70B
+
+   * -
+     - ``amd/Meta-Llama-3.1-405B-Instruct-FP8-KV``
+     - Llama 3.1 405B
+
+   * -
+     - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
+     - Mixtral 8x7B
+
+   * -
+     - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
+     - Mixtral 8x22B
+
+   * - ``$num_gpu``
+     - 1 or 8
+     - Number of GPUs
+
+   * - ``$datatype``
+     - ``float16`` or ``float8``
+     - Data type
+
+.. _vllm-benchmark-run-benchmark:
+
+Running the benchmark on the MI300X accelerator
+-----------------------------------------------
+
+Here are some examples of running the benchmark with various options.
+See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
+options and their descriptions.
+
+Example 1: latency benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+ 
+Use this command to benchmark the latency of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
+
+.. code-block::
+
+   ./vllm_benchmark_report.sh -s latency -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
+   ./vllm_benchmark_report.sh -s latency -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
+
+Find the latency reports at:
+
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_latency_report.csv``
+
+- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_latency_report.csv``
+
+Example 2: throughput benchmark
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Use this command to benchmark the throughput of the Llama 3.1 8B model on one GPU with the ``float16`` and ``float8`` data types.
+
+.. code-block:: shell
+
+   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Meta-Llama-3.1-8B-Instruct -g 1 -d float16
+   ./vllm_benchmark_report.sh -s throughput -m amd/Meta-Llama-3.1-8B-Instruct-FP8-KV -g 1 -d float8
+
+Find the throughput reports at:
+
+- ``./reports_float16/summary/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``
+
+- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_throughput_report.csv``
+
+.. raw:: html
+
+   <style>
+   mjx-container[jax="CHTML"][display="true"] {
+       text-align: left;
+       margin: 0;
+   }
+   </style>
+
+.. note::
+
+   Throughput is calculated as:
+
+   - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+   - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+
+Further reading
+===============
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/tuning-guides/mi300x/workload`.
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X accelerators, see :doc:`/how-to/system-optimization/mi300x`.
+
+- To learn how to run LLM models from Hugging Face or your own model, see
+  :doc:`Using ROCm for AI </how-to/rocm-for-ai/index>`.
+
+- 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>`_.
+
--- a/docs/how-to/rocm-for-ai/inference/deploy-your-model.rst
+++ b/docs/how-to/rocm-for-ai/inference/deploy-your-model.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: How to deploy your model for AI inference using vLLM and Hugging Face TGI.
+   :description: How to use ROCm for AI
   :keywords: ROCm, AI, LLM, train, fine-tune, deploy, FSDP, DeepSpeed, LLaMA, tutorial

 ********************
@@ -119,4 +119,4 @@ TGI walkthrough
 vLLM and Hugging Face TGI are robust solutions for anyone looking to deploy LLMs for applications that demand high
 performance, low latency, and scalability.

-Visit the topics in :doc:`Using ROCm for AI <../index>` to learn about other ROCm-aware solutions for AI development.
+Visit the topics in :doc:`Using ROCm for AI <index>` to learn about other ROCm-aware solutions for AI development.
--- a/docs/how-to/rocm-for-ai/fine-tuning/index.rst
+++ b/docs/how-to/rocm-for-ai/fine-tuning/index.rst
@@ -1,25 +0,0 @@
-.. meta::
-   :description: How to fine-tune LLMs with ROCm
-   :keywords: ROCm, LLM, fine-tuning, usage, tutorial, GPUs, Llama, accelerators
-
-*******************************************
-Use ROCm for fine-tuning LLMs
-*******************************************
-
-Fine-tuning is an essential technique in machine learning, where a pre-trained model, typically trained on a large-scale dataset, is further refined to achieve better performance and adapt to a particular task or dataset of interest.
-
-With AMD GPUs, the fine-tuning process benefits from the parallel processing capabilities and efficient resource management, ultimately leading to improved performance and faster model adaptation to the target domain.
-
-The ROCm™ software platform helps you optimize this fine-tuning process by supporting various optimization techniques tailored for AMD GPUs. It empowers the fine-tuning of large language models, making them accessible and efficient for specialized tasks. ROCm supports the broader AI ecosystem to ensure seamless integration with open frameworks, models, and tools. 
-
-Throughout the following topics, this guide discusses the goals and :ref:`challenges of fine-tuning a large language
-model <fine-tuning-llms-concept-challenge>` like Llama 2. In the
-sections that follow, you'll find practical guides on libraries and tools to accelerate your fine-tuning.
-
- :doc:`Conceptual overview of fine-tuning LLMs <overview>`
-
- :doc:`Fine-tuning and inference <fine-tuning-and-inference>` using a
-  :doc:`single-accelerator <single-gpu-fine-tuning-and-inference>` or
-  :doc:`multi-accelerator <multi-gpu-fine-tuning-and-inference>` system.
-
-
--- a/docs/how-to/rocm-for-ai/inference/hugging-face-models.rst
+++ b/docs/how-to/rocm-for-ai/inference/hugging-face-models.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: How to run models from Hugging Face on AMD GPUs.
+   :description: How to use ROCm for AI
   :keywords: ROCm, AI, LLM, Hugging Face, Optimum, Flash Attention, GPTQ, ONNX, tutorial

 ********************************
--- a/docs/how-to/rocm-for-ai/index.rst
+++ b/docs/how-to/rocm-for-ai/index.rst
@@ -1,27 +1,28 @@
 .. meta::
-   :description: Learn how to use ROCm for AI.
+   :description: How to use ROCm for AI
   :keywords: ROCm, AI, machine learning, LLM, usage, tutorial

-**************************
-Use ROCm for AI
-**************************
+*****************
+Using ROCm for AI
+*****************

-ROCm™ is an open-source software platform that enables high-performance computing and machine learning applications. It features the ability to accelerate training, fine-tuning, and inference for AI application development. With ROCm, you can access the full power of AMD GPUs, which can significantly improve the performance and efficiency of AI workloads.
+ROCm offers a suite of optimizations for AI workloads from large language models (LLMs) to image and video detection and
+recognition, life sciences and drug discovery, autonomous driving, robotics, and more. ROCm proudly supports the broader
+AI software ecosystem, including open frameworks, models, and tools.

-You can use ROCm to perform distributed training, which enables you to train models across multiple GPUs or nodes simultaneously. Additionally, ROCm supports mixed-precision training, which can help reduce the memory and compute requirements of training workloads. For fine-tuning, ROCm provides access to various algorithms and optimization techniques. In terms of inference, ROCm provides several techniques that can help you optimize your models for deployment, such as quantization, GEMM tuning, and optimization with composable kernel.
- 
-Overall, ROCm can be used to improve the performance and efficiency of your AI applications. With its training, fine-tuning, and inference support, ROCm provides a complete solution for optimizing AI workflows and achieving the optimum results possible on AMD GPUs. 
+For more information, see `What is ROCm? <https://rocm.docs.amd.com/en/latest/what-is-rocm.html>`_

-In this guide, you'll learn how to use ROCm for AI:
+In this guide, you'll learn about:

- :doc:`Training <training/index>`
+- :doc:`Installing ROCm and machine learning frameworks <install>`

- :doc:`Fine-tuning LLMs <fine-tuning/index>`
+- :doc:`Scaling model training <scale-model-training>`

- :doc:`Inference <inference/index>`
+- :doc:`Training a model <train-a-model>`

- :doc:`Inference optimization <inference-optimization/index>`
+- :doc:`Running models from Hugging Face <hugging-face-models>`

+- :doc:`Deploying your model <deploy-your-model>`

 To learn about ROCm for HPC applications and scientific computing, see
 :doc:`../rocm-for-hpc/index`.
--- a/docs/how-to/rocm-for-ai/inference-optimization/index.rst
+++ b/docs/how-to/rocm-for-ai/inference-optimization/index.rst
@@ -1,36 +0,0 @@
-.. meta::
-   :description: How to Use ROCm for AI inference optimization
-   :keywords: ROCm, LLM, AI inference, Optimization, GPUs, usage, tutorial
-
-*******************************************
-Use ROCm for AI inference optimization
-*******************************************
-
-AI inference optimization is the process of improving the performance of machine learning models and speeding up the inference process. It includes:
-
- **Quantization**: This involves reducing the precision of model weights and activations while maintaining acceptable accuracy levels. Reduced precision improves inference efficiency because lower precision data requires less storage and better utilizes the hardware's computation power.  
-
- **Kernel optimization**: This technique involves optimizing computation kernels to exploit the underlying hardware capabilities. For example, the kernels can be optimized to use multiple GPU cores or utilize specialized hardware like tensor cores to accelerate the computations. 
-
- **Libraries**: Libraries such as Flash Attention, xFormers, and PyTorch TunableOp are used to accelerate deep learning models and improve the performance of inference workloads. 
-
- **Hardware acceleration**: Hardware acceleration techniques, like GPUs for AI inference, can significantly improve performance due to their parallel processing capabilities. 
-
- **Pruning**: This involves removing unnecessary connections, layers, or weights from a pre-trained model while maintaining acceptable accuracy levels, resulting in a smaller model that requires fewer computational resources to run inference. 
-
-Utilizing these optimization techniques with the ROCm™ software platform can significantly reduce inference time, improve performance, and reduce the cost of your AI applications. 
-
-Throughout the following topics, this guide discusses optimization techniques for inference workloads.
-
- :doc:`Model quantization <model-quantization>`
-
- :doc:`Model acceleration libraries <model-acceleration-libraries>`
-
- :doc:`Optimizing with Composable Kernel <optimizing-with-composable-kernel>`
-
- :doc:`Optimizing Triton kernels <optimizing-triton-kernel>`
-
- :doc:`Profiling and debugging <profiling-and-debugging>`
-
- :doc:`Workload tuning <workload>`
-
--- a/docs/how-to/rocm-for-ai/inference/index.rst
+++ b/docs/how-to/rocm-for-ai/inference/index.rst
@@ -1,22 +0,0 @@
-.. meta::
-   :description: How to use ROCm for AI inference workloads.
-   :keywords: ROCm, AI, machine learning, LLM, AI inference, NLP, GPUs, usage, tutorial
-
-****************************
-Use ROCm for AI inference
-****************************
-AI inference is a process of deploying a trained machine learning model to make predictions or classifications on new data. This commonly involves using the model with real-time data and making quick decisions based on the predictions made by the model.  
-
-Understanding the ROCm™ software platform’s architecture and capabilities is vital for running AI inference. By leveraging the ROCm platform's capabilities, you can harness the power of high-performance computing and efficient resource management to run inference workloads, leading to faster predictions and classifications on real-time data.
-
-Throughout the following topics, this section provides a comprehensive guide to setting up and deploying AI inference on AMD GPUs. This includes instructions on how to install ROCm, how to use Hugging Face Transformers to manage pre-trained models for natural language processing (NLP) tasks, how to validate vLLM on AMD Instinct™ MI300X accelerators and illustrate how to deploy trained models in production environments. 
-
- :doc:`Installing ROCm and machine learning frameworks <install>`
-
- :doc:`Running models from Hugging Face <hugging-face-models>`
-
- :doc:`LLM inference frameworks <llm-inference-frameworks>`
-
- :doc:`Performance validation <vllm-benchmark>`
-
- :doc:`Deploying your model <deploy-your-model>`
--- a/docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst
+++ b/docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst
@@ -1,478 +0,0 @@
-.. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
-                 ROCm vLLM Docker image.
-   :keywords: model, MAD, automation, dashboarding, validate
-
-***********************************************************
-LLM inference performance validation on AMD Instinct MI300X
-***********************************************************
-
-.. _vllm-benchmark-unified-docker:
-
-The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
-a prebuilt, optimized environment for validating large language model (LLM)
-inference performance on the AMD Instinct™ MI300X accelerator. This ROCm vLLM
-Docker image integrates vLLM and PyTorch tailored specifically for the MI300X
-accelerator and includes the following components:
-
-* `ROCm 6.3.1 <https://github.com/ROCm/ROCm>`_
-
-* `vLLM 0.6.6 <https://docs.vllm.ai/en/latest>`_
-
-* `PyTorch 2.7.0 (2.7.0a0+git3a58512) <https://github.com/pytorch/pytorch>`_
-
-With this Docker image, you can quickly validate the expected inference
-performance numbers for the MI300X accelerator. This topic also provides tips on
-optimizing performance with popular AI models. For more information, see the lists of
-:ref:`available models for MAD-integrated benchmarking <vllm-benchmark-mad-models>`
-and :ref:`standalone benchmarking <vllm-benchmark-standalone-options>`.
-
-.. _vllm-benchmark-vllm:
-
-.. note::
-
-   vLLM is a toolkit and library for LLM inference and serving. AMD implements
-   high-performance custom kernels and modules in vLLM to enhance performance.
-   See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
-   more information.
-
-Getting started
-===============
-
-Use the following procedures to reproduce the benchmark results on an
-MI300X accelerator with the prebuilt vLLM Docker image.
-
-.. _vllm-benchmark-get-started:
-
-1. Disable NUMA auto-balancing.
-
-   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
-   might hang until the periodic balancing is finalized. For more information,
-   see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
-
-   .. code-block:: shell
-
-      # disable automatic NUMA balancing
-      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
-      # check if NUMA balancing is disabled (returns 0 if disabled)
-      cat /proc/sys/kernel/numa_balancing
-      0
-
-2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
-
-   Use the following command to pull the Docker image from Docker Hub.
-
-   .. code-block:: shell
-
-      docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
-
-Once the setup is complete, choose between two options to reproduce the
-benchmark results:
-
-  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
-
-  :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
-
-.. _vllm-benchmark-mad:
-
-MAD-integrated benchmarking
-===========================
-
-Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
-directory and install the required packages on the host machine.
-
-.. code-block:: shell
-
-   git clone https://github.com/ROCm/MAD
-   cd MAD
-   pip install -r requirements.txt
-
-Use this command to run a performance benchmark test of the Llama 3.1 8B model
-on one GPU with ``float16`` data type in the host machine.
-
-.. code-block:: shell
-
-   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-   python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
-
-ROCm MAD launches a Docker container with the name
-``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
-model are collected in the following path: ``~/MAD/reports_float16/``.
-
-Although the following models are preconfigured to collect latency and
-throughput performance data, you can also change the benchmarking parameters.
-Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
-
-.. _vllm-benchmark-mad-models:
-
-Available models
----------------
-
-.. list-table::
-   :header-rows: 1
-   :widths: 2, 3
-
-   * - Model name
-     - Tag
-
-   * - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
-     - ``pyt_vllm_llama-3.1-8b``
-
-   * - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
-     - ``pyt_vllm_llama-3.1-70b``
-
-   * - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
-     - ``pyt_vllm_llama-3.1-405b``
-
-   * - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
-     - ``pyt_vllm_llama-3.2-11b-vision-instruct``
-
-   * - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
-     - ``pyt_vllm_llama-2-7b``
-
-   * - `Llama 2 70B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
-     - ``pyt_vllm_llama-2-70b``
-
-   * - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
-     - ``pyt_vllm_mixtral-8x7b``
-
-   * - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
-     - ``pyt_vllm_mixtral-8x22b``
-
-   * - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
-     - ``pyt_vllm_mistral-7b``
-
-   * - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
-     - ``pyt_vllm_qwen2-7b``
-
-   * - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
-     - ``pyt_vllm_qwen2-72b``
-
-   * - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
-     - ``pyt_vllm_jais-13b``
-
-   * - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
-     - ``pyt_vllm_jais-30b``
-
-   * - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
-     - ``pyt_vllm_dbrx-instruct``
-
-   * - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
-     - ``pyt_vllm_gemma-2-27b``
-
-   * - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
-     - ``pyt_vllm_c4ai-command-r-plus-08-2024``
-
-   * - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
-     - ``pyt_vllm_deepseek-moe-16b-chat``
-
-   * - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
-     - ``pyt_vllm_llama-3.1-70b_fp8``
-
-   * - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
-     - ``pyt_vllm_llama-3.1-405b_fp8``
-
-   * - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
-     - ``pyt_vllm_mixtral-8x7b_fp8``
-
-   * - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
-     - ``pyt_vllm_mixtral-8x22b_fp8``
-
-   * - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
-     - ``pyt_vllm_mistral-7b_fp8``
-
-   * - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
-     - ``pyt_vllm_dbrx_fp8``
-
-   * - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
-     - ``pyt_vllm_command-r-plus_fp8``
-
-.. _vllm-benchmark-standalone:
-
-Standalone benchmarking
-=======================
-
-You can run the vLLM benchmark tool independently by starting the
-:ref:`Docker container <vllm-benchmark-get-started>` as shown in the following
-snippet.
-
-.. code-block::
-
-   docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
-   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.6 rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
-
-In the Docker container, clone the ROCm MAD repository and navigate to the
-benchmark scripts directory at ``~/MAD/scripts/vllm``.
-
-.. code-block::
-
-   git clone https://github.com/ROCm/MAD
-   cd MAD/scripts/vllm
-
-Command
-------
-
-To start the benchmark, use the following command with the appropriate options.
-See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
-options and their descriptions.
-
-.. code-block:: shell
-
-   ./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
-
-See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
-
-.. note::
-
-   The input sequence length, output sequence length, and tensor parallel (TP) are
-   already configured. You don't need to specify them with this script.
-
-.. note::
-
-   If you encounter the following error, pass your access-authorized Hugging
-   Face token to the gated models.
-
-   .. code-block:: shell
-
-      OSError: You are trying to access a gated repo.
-
-      # pass your HF_TOKEN
-      export HF_TOKEN=$your_personal_hf_token
-
-.. _vllm-benchmark-standalone-options:
-
-Options and available models
----------------------------
-
-.. list-table::
-   :header-rows: 1
-   :align: center
-
-   * - Name
-     - Options
-     - Description
-
-   * - ``$test_option``
-     - latency
-     - Measure decoding token latency
-
-   * -
-     - throughput
-     - Measure token generation throughput
-
-   * -
-     - all
-     - Measure both throughput and latency
-
-   * - ``$model_repo``
-     - ``meta-llama/Llama-3.1-8B-Instruct``
-     - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
-
-   * - (``float16``)
-     - ``meta-llama/Llama-3.1-70B-Instruct``
-     - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
-
-   * -
-     - ``meta-llama/Llama-3.1-405B-Instruct``
-     - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
-
-   * -
-     - ``meta-llama/Llama-3.2-11B-Vision-Instruct``
-     - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
-
-   * -
-     - ``meta-llama/Llama-2-7b-chat-hf``
-     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
-
-   * -
-     - ``meta-llama/Llama-2-70b-chat-hf``
-     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
-
-   * -
-     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
-     - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
-
-   * -
-     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
-     - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
-
-   * -
-     - ``mistralai/Mistral-7B-Instruct-v0.3``
-     - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
-
-   * -
-     - ``Qwen/Qwen2-7B-Instruct``
-     - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
-
-   * -
-     - ``Qwen/Qwen2-72B-Instruct``
-     - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
-
-   * -
-     - ``core42/jais-13b-chat``
-     - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
-
-   * -
-     - ``core42/jais-30b-chat-v3``
-     - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
-
-   * -
-     - ``databricks/dbrx-instruct``
-     - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
-
-   * -
-     - ``google/gemma-2-27b``
-     - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
-
-   * -
-     - ``CohereForAI/c4ai-command-r-plus-08-2024``
-     - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
-
-   * -
-     - ``deepseek-ai/deepseek-moe-16b-chat``
-     - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
-
-   * - ``$model_repo``
-     - ``amd/Llama-3.1-70B-Instruct-FP8-KV``
-     - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
-
-   * - (``float8``)
-     - ``amd/Llama-3.1-405B-Instruct-FP8-KV``
-     - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
-
-   * -
-     - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
-     - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
-
-   * -
-     - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
-     - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
-
-   * -
-     - ``amd/Mistral-7B-v0.1-FP8-KV``
-     - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
-
-   * -
-     - ``amd/dbrx-instruct-FP8-KV``
-     - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
-
-   * -
-     - ``amd/c4ai-command-r-plus-FP8-KV``
-     - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
-
-   * - ``$num_gpu``
-     - 1 or 8
-     - Number of GPUs
-
-   * - ``$datatype``
-     - ``float16`` or ``float8``
-     - Data type
-
-.. _vllm-benchmark-run-benchmark:
-
-Running the benchmark on the MI300X accelerator
-----------------------------------------------
-
-Here are some examples of running the benchmark with various options.
-See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
-options and their descriptions.
-
-Example 1: latency benchmark
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- 
-Use this command to benchmark the latency of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
-
-.. code-block::
-
-   ./vllm_benchmark_report.sh -s latency -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
-   ./vllm_benchmark_report.sh -s latency -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
-
-Find the latency reports at:
-
- ``./reports_float16/summary/Llama-3.1-70B-Instruct_latency_report.csv``
-
- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_latency_report.csv``
-
-Example 2: throughput benchmark
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Use this command to benchmark the throughput of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
-
-.. code-block:: shell
-
-   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
-   ./vllm_benchmark_report.sh -s throughput -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
-
-Find the throughput reports at:
-
- ``./reports_float16/summary/Llama-3.1-70B-Instruct_throughput_report.csv``
-
- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_throughput_report.csv``
-
-.. raw:: html
-
-   <style>
-   mjx-container[jax="CHTML"][display="true"] {
-       text-align: left;
-       margin: 0;
-   }
-   </style>
-
-.. note::
-
-   Throughput is calculated as:
-
-   - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
-
-   - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
-
-Further reading
-===============
-
- For application performance optimization strategies for HPC and AI workloads,
-  including inference with vLLM, see :doc:`../inference-optimization/workload`.
-
- To learn more about the options for latency and throughput benchmark scripts,
-  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
-
- To learn more about system settings and management practices to configure your system for
-  MI300X accelerators, see :doc:`../../system-optimization/mi300x`.
-
- To learn how to run LLM models from Hugging Face or your own model, see
-  :doc:`Running models from Hugging Face <hugging-face-models>`.
-
- To learn how to optimize inference on LLMs, see
-  :doc:`Inference optimization <../inference-optimization/index>`.
-
- To learn how to fine-tune LLMs, see
-  :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
-
-Previous versions
-=================
-
-This table lists previous versions of the ROCm vLLM Docker image for inference
-performance validation. For detailed information about available models for
-benchmarking, see the version-specific documentation.
-
-.. list-table::
-   :header-rows: 1
-   :stub-columns: 1
-
-   * - ROCm version
-     - vLLM version
-     - PyTorch version
-     - Resources
-
-   * - 6.2.1
-     - 0.6.4
-     - 2.5.0
-     - 
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4/images/sha256-ccbb74cc9e7adecb8f7bdab9555f7ac6fc73adb580836c2a35ca96ff471890d8>`_
-
-   * - 6.2.0
-     - 0.4.3
-     - 2.4.0
-     -
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50/images/sha256-9e4dd4788a794c3d346d7d0ba452ae5e92d39b8dfac438b2af8efdc7f15d22c0>`_
--- a/docs/how-to/rocm-for-ai/inference/install.rst
+++ b/docs/how-to/rocm-for-ai/inference/install.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: How to install ROCm and popular machine learning frameworks.
+   :description: How to use ROCm for AI
   :keywords: ROCm, AI, LLM, train, fine-tune, FSDP, DeepSpeed, LLaMA, tutorial

 .. _rocm-for-ai-install:
@@ -26,9 +26,9 @@ If you’re using a Radeon GPU for graphics-accelerated applications, refer to t

 ROCm supports multiple :doc:`installation methods <rocm-install-on-linux:install/install-overview>`:

-* :doc:`Using your Linux distribution's package manager <rocm-install-on-linux:install/install-methods/package-manager-index>`
+* :doc:`Using your Linux distribution's package manager <rocm-install-on-linux:install/native-install/index>`

-* :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/install-methods/amdgpu-installer-index>`
+* :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/amdgpu-install>`

 * :ref:`Multi-version installation <rocm-install-on-linux:installation-types>`.

@@ -59,4 +59,4 @@ images with the framework pre-installed.

 * :doc:`JAX for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`

-The sections that follow in :doc:`Training a model <../training/train-a-model>` are geared for a ROCm with PyTorch installation.
+The sections that follow in :doc:`Training a model <train-a-model>` are geared for a ROCm with PyTorch installation.
--- a/docs/how-to/rocm-for-ai/training/scale-model-training.rst
+++ b/docs/how-to/rocm-for-ai/training/scale-model-training.rst
@@ -105,7 +105,7 @@ Fine-tuning your model
 ROCm supports multiple techniques for :ref:`optimizing fine-tuning <fine-tuning-llms-concept-optimizations>`, for
 example, LoRA, QLoRA, PEFT, and FSDP.

-Learn more about challenges and solutions for model fine-tuning in :doc:`../fine-tuning/index`.
+Learn more about challenges and solutions for model fine-tuning in :doc:`../llm-fine-tuning-optimization/index`.

 The following developer blogs showcase examples of fine-tuning a model on an AMD accelerator or GPU.

@@ -132,4 +132,4 @@ The following developer blogs showcase examples of fine-tuning a model on an AMD
 * Recipes for fine-tuning Llama2 and 3 with ``llama-recipes``

  * `meta-llama/llama-recipes: Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover
-    single/multi-node GPUs <https://github.com/meta-llama/llama-cookbook/tree/main/getting-started/finetuning>`_
+    single/multi-node GPUs <https://github.com/meta-llama/llama-recipes/tree/main/recipes/quickstart/finetuning>`_
--- a/docs/how-to/rocm-for-ai/training/train-a-model.rst
+++ b/docs/how-to/rocm-for-ai/training/train-a-model.rst
@@ -164,7 +164,7 @@ Run on 8 GPUs (``-g 8``), scanning from 8 bytes to 10 GB:

   ./build/all_reduce_perf -b 8 -e 10G -f 2 -g 8

-.. image:: ../../../data/how-to/rocm-for-ai/rccl-tests-8-gpu.png
+.. image:: ../../data/how-to/rocm-for-ai/rccl-tests-8-gpu.png
   :width: 800

 Using one MPI process per GPU and ``-g 1`` for performance-oriented runs on both single-node and multi-node is
@@ -174,7 +174,7 @@ recommended. So, a run on 8 GPUs looks something like:

   mpirun -np 8 --bind-to numa ./build/all_reduce_perf -b 8 -e 10G -f 2 -g 1

-.. image:: ../../../data/how-to/rocm-for-ai/rccl-tests-1-mpi-process-per-gpu.png
+.. image:: ../../data/how-to/rocm-for-ai/rccl-tests-1-mpi-process-per-gpu.png
   :width: 800

 Running with one MPI process per GPU ensures a one-to-one mapping for CPUs and GPUs, which can be beneficial
@@ -195,7 +195,7 @@ Use the following script to run the RCCL test for four MI300X GPU nodes. Modify
   -x NCCL_DEBUG=version \
   $HOME/rccl-tests/build/all_reduce_perf -b 8 -e 8g -f 2 -g 1

-.. image:: ../../../data/how-to/rocm-for-ai/rccl-tests-4-mi300x-gpu-nodes.png
+.. image:: ../../data/how-to/rocm-for-ai/rccl-tests-4-mi300x-gpu-nodes.png
   :width: 800

 .. _mi300x-amd-megatron-lm-training:
@@ -264,7 +264,7 @@ end-of-document token, remove sentence splitting, and use the tokenizer type.
 In this case, the automatically generated output files are named ``my-gpt2_text_document.bin`` and
 ``my-gpt2_text_document.idx``.

-.. image:: ../../../data/how-to/rocm-for-ai/prep-training-datasets-my-gpt2-text-document.png
+.. image:: ../../data/how-to/rocm-for-ai/prep-training-datasets-my-gpt2-text-document.png
   :width: 800

 .. _amd-megatron-lm-environment-setup:
@@ -462,7 +462,7 @@ Benchmarking examples

      See the sample output:

-      .. image:: ../../../data/how-to/rocm-for-ai/llama2-7b-training-log-sample.png
+      .. image:: ../../data/how-to/rocm-for-ai/llama2-7b-training-log-sample.png
         :width: 800

   .. tab-item:: Multi node training
@@ -493,11 +493,11 @@ Benchmarking examples

      Master node:

-      .. image:: ../../../data/how-to/rocm-for-ai/2-node-training-master.png
+      .. image:: ../../data/how-to/rocm-for-ai/2-node-training-master.png
         :width: 800

      Worker node:

-      .. image:: ../../../data/how-to/rocm-for-ai/2-node-training-worker.png
+      .. image:: ../../data/how-to/rocm-for-ai/2-node-training-worker.png
         :width: 800

--- a/docs/how-to/rocm-for-ai/training/index.rst
+++ b/docs/how-to/rocm-for-ai/training/index.rst
@@ -1,21 +0,0 @@
-.. meta::
-   :description: How to use ROCm for training models
-   :keywords: ROCm, LLM, training, GPUs, training model, scaling model, usage, tutorial
-
-=======================
-Use ROCm for training
-=======================
-
-Training models is the process of teaching a computer program to recognize patterns in data. This involves providing the computer with large amounts of labeled data and allowing it to learn from that data, adjusting the model's parameters. 
-
-The process of training models is computationally intensive, requiring specialized hardware like GPUs to accelerate computations and reduce training time. Training models on AMD GPUs involves leveraging the parallel processing capabilities of these GPUs to significantly speed up the model training process in machine learning and deep learning tasks.  
-
-Training models on AMD GPUs with the ROCm™ software platform allows you to use the powerful parallel processing capabilities and efficient compute resource management, significantly improving training time and overall performance in machine learning applications.
- 
-The ROCm software platform makes it easier to train models on AMD GPUs while maintaining compatibility with existing code and tools. The platform also provides features like multi-GPU support, allowing for scaling and parallelization of model training across multiple GPUs to enhance performance. 
-
-In this guide, you'll learn about:
-
- :doc:`Training a model <train-a-model>`
-
- :doc:`Scale model training <scale-model-training>`
--- a/docs/how-to/rocm-for-hpc/index.rst
+++ b/docs/how-to/rocm-for-hpc/index.rst
@@ -1,6 +1,6 @@
 .. meta::
-   :description: How to use ROCm for high-performance computing (HPC).
-   :keywords: ROCm, AI, high performance computing, HPC, science, scientific
+   :description: How to use ROCm for HPC
+   :keywords: ROCm, AI, high performance computing, HPC

 ******************
 Using ROCm for HPC
@@ -115,12 +115,6 @@ Ubuntu versions.
          for non-destructive testing or for ocean acoustics.

      * - Molecular dynamics
-        - `Amber <https://github.com/amd/InfinityHub-CI/tree/main/amber>`_
-        - Amber is a suite of biomolecular simulation programs. It is a set of molecular mechanical force fields for 
-          simulating biomolecules. Amber is also a package of molecular simulation 
-          programs which includes source code and demos.
-
-      * - 
        - `GROMACS with HIP (AMD implementation) <https://github.com/amd/InfinityHub-CI/tree/main/gromacs>`_
        - GROMACS is a versatile package to perform molecular dynamics, i.e.
          simulate the Newtonian equations of motion for systems with hundreds
@@ -135,13 +129,6 @@ Ubuntu versions.
          Parallel Simulator.

      * - Computational fluid dynamics
-        - `Ansys Fluent <https://github.com/amd/InfinityHub-CI/tree/main/ansys-fluent>`_
-        - Ansys Fluent is an advanced computational fluid dynamics (CFD) tool for 
-          simulating and analyzing fluid flow, heat transfer, and related phenomena in complex systems. 
-          It offers a range of powerful features for detailed and accurate modeling of various physical 
-          processes, including turbulence, chemical reactions, and multiphase flows.
-
-      * -
        - `NEKO <https://github.com/amd/InfinityHub-CI/tree/main/neko>`_
        - Neko is a portable framework for high-order spectral element flow simulations.
          Written in modern Fortran, Neko adopts an object-oriented approach, allowing
@@ -154,26 +141,6 @@ Ubuntu versions.
        - nekRS is an open-source Navier Stokes solver based on the spectral element
          method targeting classical processors and accelerators like GPUs. 

-      * -
-        - `OpenFOAM <https://github.com/amd/InfinityHub-CI/tree/main/openfoam>`_
-        - OpenFOAM is a free, open-source computational fluid dynamics (CFD) 
-          tool developed primarily by OpenCFD Ltd. It has a large user 
-          base across most areas of engineering and science, from both commercial and 
-          academic organizations. OpenFOAM has extensive features to solve 
-          anything from complex fluid flows involving chemical reactions, turbulence, and 
-          heat transfer, to acoustics, solid mechanics, and electromagnetics.
-
-      * -
-        - `PeleC <https://github.com/amd/InfinityHub-CI/tree/main/pelec>`_
-        - PeleC is an adaptive mesh refinement(AMR) solver for compressible reacting flows.
-
-      * -
-        - `Simcenter Star-CCM+ <https://github.com/amd/InfinityHub-CI/tree/main/siemens-star-ccm>`_
-        - Simcenter Star-CCM+ is a comprehensive computational fluid dynamics (CFD) and multiphysics 
-          simulation tool developed by Siemens Digital Industries Software. It is designed to 
-          help engineers and researchers analyze and optimize the performance of products and 
-          systems across various industries.
-
      * - Computational chemistry
        - `QUDA <https://github.com/amd/InfinityHub-CI/tree/main/quda>`_
        - Library designed for efficient lattice QCD computations on
@@ -203,30 +170,12 @@ Ubuntu versions.
          developing atmosphere, ocean, and other earth-system simulation components
          for use in climate, regional climate, and weather studies.

-      * - Energy, Oil, and Gas
-        - `DevitoPRO <https://github.com/amd/InfinityHub-CI/tree/main/devitopro>`_
-        - DevitoPRO is an advanced extension of the open-source Devito platform with added 
-          features tailored for high-demand production workflows. It supports
-          high-performance computing (HPC) needs, especially in seismic imaging and inversion. 
-          It is used to perform optimized finite difference (FD) computations 
-          from high-level symbolic problem definitions. DevitoPro performs automated 
-          code generation and Just-In-time (JIT) compilation based on symbolic equations 
-          defined in SymPy to create and execute highly optimized Finite Difference stencil 
-          kernels on multiple computer platforms.
-
-      * - 
-        - `ECHELON <https://github.com/amd/InfinityHub-CI/tree/main/srt-echelon>`_
-        - ECHELON by Stone Ridge Technology is a reservoir simulation tool. With 
-          fast processing, it retains precise accuracy and preserves legacy simulator results. 
-          Faster reservoir simulation enables reservoir engineers to produce many realizations, 
-          address larger models, and use advanced physics. It opens new workflows based on 
-          ensemble methodologies for history matching and forecasting that yield 
-          increased accuracy and more predictive results.
-
      * - Benchmark
        - `rocHPL <https://github.com/amd/InfinityHub-CI/tree/main/rochpl>`_
-        - HPL, or High-Performance Linpack, is a benchmark which solves a uniformly 
-          random system of linear equations and reports floating-point execution rate.
+        - HPL, or High-Performance Linpack, is a benchmark which solves a uniformly 
+          random system of linear equations and reports floating-point execution rate. 
+          This documentation supports the implementation of the HPL benchmark on 
+          top of AMD's ROCm platform.

      * -
        - `rocHPL-MxP <https://github.com/amd/InfinityHub-CI/tree/main/hpl-mxp>`_
@@ -267,14 +216,6 @@ Ubuntu versions.
          range of hardware platforms via use of an in-built domain specific language derived
          from the Mako templating engine.

-      * -
-        - `PETSc <https://github.com/amd/InfinityHub-CI/tree/main/petsc>`_
-        - Portable, Extensible Toolkit for Scientific Computation (PETSc) is a suite of data structures 
-          and routines for the scalable (parallel) solution of scientific applications modeled by partial 
-          differential equations. It supports MPI, GPUs through CUDA, HIP, and OpenCL, 
-          as well as hybrid MPI-GPU parallelism. It also supports the NEC-SX Tsubasa Vector Engine. 
-          PETSc also includes the Toolkit for Advanced Optimization (TAO) library.
-
      * -
        - `RAJA <https://github.com/amd/InfinityHub-CI/tree/main/raja>`_
        - RAJA is a library of C++ software abstractions, primarily developed at Lawrence
--- a/docs/how-to/system-optimization/index.rst
+++ b/docs/how-to/system-optimization/index.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: Learn about AMD hardware optimization for HPC-specific and workstation workloads.
+   :description: AMD hardware optimization for specific workloads
   :keywords: high-performance computing, HPC, Instinct accelerators, Radeon,
              tuning, tuning guide, AMD, ROCm

--- a/docs/how-to/system-optimization/mi100.md
+++ b/docs/how-to/system-optimization/mi100.md
@@ -1,9 +1,9 @@
---
-myst:
-  html_meta:
-    "description": "AMD Instinct MI100 system settings optimization guide."
-    "keywords": "Instinct, MI100, microarchitecture, AMD, ROCm"
---
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="MI100 high-performance computing and tuning guide">
+  <meta name="keywords" content="MI100, high-performance computing, HPC, BIOS
+  settings, NBIO, AMD, ROCm">
+</head>

 # AMD Instinct MI100 system optimization

--- a/docs/how-to/system-optimization/mi200.md
+++ b/docs/how-to/system-optimization/mi200.md
@@ -1,9 +1,9 @@
---
-myst:
-  html_meta:
-    "description": "Learn about AMD Instinct MI200 system settings and performance tuning."
-    "keywords": "Instinct, MI200, microarchitecture, AMD, ROCm"
---
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="MI200 high-performance computing and tuning guide">
+  <meta name="keywords" content="MI200, high-performance computing, HPC, BIOS
+  settings, NBIO, AMD, ROCm">
+</head>

 # AMD Instinct MI200 system optimization

--- a/docs/how-to/system-optimization/mi300a.rst
+++ b/docs/how-to/system-optimization/mi300a.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: Learn about AMD Instinct MI300A system settings and performance tuning.
+   :description: AMD Instinct MI300A system settings
   :keywords: AMD, Instinct, MI300A, HPC, tuning, BIOS settings, NBIO, ROCm,
              environment variable, performance, accelerator, GPU, EPYC, GRUB,
              operating system
--- a/docs/how-to/system-optimization/mi300x.rst
+++ b/docs/how-to/system-optimization/mi300x.rst
@@ -1,5 +1,5 @@
 .. meta::
-   :description: Learn about AMD Instinct MI300X system settings and performance tuning.
+   :description: AMD Instinct MI300X system settings
   :keywords: AMD, Instinct, MI300X, HPC, tuning, BIOS settings, NBIO, ROCm,
              environment variable, performance, accelerator, GPU, EPYC, GRUB,
              operating system
@@ -35,7 +35,7 @@ functioning correctly before trying to improve its overall performance. In this
 section, the settings discussed mostly ensure proper functionality of your
 Instinct-based system. Some settings discussed are known to improve performance
 for most applications running on a MI300X system. See
-:doc:`../rocm-for-ai/inference-optimization/workload` for how to improve performance for
+:doc:`/how-to/tuning-guides/mi300x/workload` for how to improve performance for
 specific applications or workloads.

 .. _mi300x-bios-settings:
--- a/docs/how-to/system-optimization/w6000-v620.md
+++ b/docs/how-to/system-optimization/w6000-v620.md
@@ -1,9 +1,9 @@
---
-myst:
-  html_meta:
-    "description": "Learn about system settings and performance tuning for RDNA2-based GPUs."
-    "keywords": "RDNA2, workstation, desktop, BIOS, installation, Radeon, pro, v620, w6000"
---
+<head>
+  <meta charset="UTF-8">
+  <meta name="description" content="RDNA2 workstation tuning guide">
+  <meta name="keywords" content="RDNA2, workstation, BIOS settings, installation, AMD,
+  ROCm">
+</head>

 # AMD RDNA2 system optimization

@@ -12,7 +12,7 @@ myst:
 This chapter reviews system settings that are required to configure the system
 for ROCm virtualization on RDNA2-based AMD Radeon™ PRO GPUs. Installing ROCm on
 Bare Metal follows the routine ROCm
-{doc}`installation procedure<rocm-install-on-linux:install/install-methods/package-manager-index>`.
+{doc}`installation procedure<rocm-install-on-linux:install/native-install/index>`.

 To enable ROCm virtualization on V620, one has to setup Single Root I/O
 Virtualization (SR-IOV) in the BIOS via setting found in the following
@@ -166,4 +166,4 @@ First, assign GPU virtual function (VF) to VM using the following steps.
 Then start the VM.

 Finally install ROCm on the virtual machine (VM). For detailed instructions,
-refer to the {doc}`Linux install guide<rocm-install-on-linux:install/install-methods/package-manager-index>`.
+refer to the {doc}`Linux install guide<rocm-install-on-linux:install/native-install/index>`.
--- a/docs/how-to/tuning-guides/mi300x/index.rst
+++ b/docs/how-to/tuning-guides/mi300x/index.rst
@@ -1,7 +1,3 @@
-.. meta::
-   :description: How to configure MI300X accelerators to fully leverage their capabilities and achieve optimal performance.
-   :keywords: ROCm, AI, machine learning, MI300X, LLM, usage, tutorial, optimization, tuning
-
 ************************
 AMD MI300X tuning guides
 ************************
@@ -12,8 +8,8 @@ accelerators. They include detailed instructions on system settings and
 application tuning suggestions to help you fully leverage the capabilities of
 these accelerators, thereby achieving optimal performance.

-* :doc:`../../rocm-for-ai/inference/vllm-benchmark`
+* :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`

-* :doc:`../../system-optimization/mi300x`
+* :doc:`/how-to/tuning-guides/mi300x/system`

-* :doc:`../../rocm-for-ai/inference-optimization/workload`
+* :doc:`/how-to/tuning-guides/mi300x/workload`
--- a/docs/how-to/rocm-for-ai/inference-optimization/workload.rst
+++ b/docs/how-to/rocm-for-ai/inference-optimization/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-multiple-gpus>` to distribute
+  :ref:`tensor-parallel-size parameter <mi300x-vllm-optimize-tp-gemm>` to distribute
  tensor computations across multiple GPUs. Adjust parameters such as
  ``batch-size``, ``input-len``, and ``output-len`` based on your workload.

@@ -152,7 +152,7 @@ address any new bottlenecks that may emerge.

 ROCm provides a prebuilt optimized Docker image that has everything required to implement
 the tips in this section. It includes ROCm, vLLM, PyTorch, and tuning files in the CSV 
-format. For more information, see :doc:`../inference/vllm-benchmark`.
+format. For more information, see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.

 .. _mi300x-profiling-tools:

@@ -173,7 +173,7 @@ tools available depending on their specific profiling needs.
  For more information, see
  :doc:`ROCm Compute Profiler documentation <rocprofiler-compute:index>`.

-Refer to :doc:`profiling-and-debugging`
+Refer to :doc:`/how-to/llm-fine-tuning-optimization/profiling-and-debugging`
 to explore commonly used profiling tools and their usage patterns.

 Once performance bottlenecks are identified, you can implement an informed workload
@@ -412,7 +412,7 @@ usage with ROCm.
 ROCm provides a prebuilt optimized Docker image for validating the performance
 of LLM inference with vLLM on the MI300X accelerator. The Docker image includes
 ROCm, vLLM, PyTorch, and tuning files in the CSV format. For more information,
-see :doc:`../inference/vllm-benchmark`.
+see :doc:`/how-to/performance-validation/mi300x/vllm-benchmark`.

 .. _mi300x-vllm-throughput-measurement:

@@ -1304,7 +1304,7 @@ performance (reduce latency) and improve benchmarking stability.
 CK provides a rich set of template parameters for generating flexible accelerated 
 computing kernels for difference application scenarios.

-See :doc:`optimizing-with-composable-kernel`
+See :doc:`/how-to/llm-fine-tuning-optimization/optimizing-with-composable-kernel`
 for an overview of Composable Kernel GEMM kernels, information on tunable
 parameters, and examples.

--- a/docs/index.md
+++ b/docs/index.md
@@ -39,12 +39,14 @@ ROCm documentation is organized into the following categories:

 * [Use ROCm for AI](./how-to/rocm-for-ai/index.rst)
 * [Use ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
+* [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)
-* [Set the number of CUs](./how-to/setting-cus)
-* [Troubleshoot BAR access limitation](./how-to/Bar-Memory.rst)  
+* [Set the number of CUs](./how-to/setting-cus)  
 * [ROCm examples](https://github.com/amd/rocm-examples)
 :::

@@ -56,7 +58,7 @@ ROCm documentation is organized into the following categories:
 * [File structure (Linux FHS)](./conceptual/file-reorg.md)
 * [GPU isolation techniques](./conceptual/gpu-isolation.md)
 * [Using CMake](./conceptual/cmake-packages.rst)
-* [PCIe atomics in ROCm](./conceptual/pcie-atomics.rst)
+* [ROCm & PCIe atomics](./conceptual/More-about-how-ROCm-uses-PCIe-Atomics.rst)
 * [Inception v3 with PyTorch](./conceptual/ai-pytorch-inception.md)
 * [Oversubscription of hardware resources](./conceptual/oversubscription.rst)
 :::
@@ -69,7 +71,6 @@ ROCm documentation is organized into the following categories:
 * [ROCm tools, compilers, and runtimes](./reference/rocm-tools.md)
 * [Accelerator and  GPU hardware specifications](./reference/gpu-arch-specs.rst)
 * [Precision support](./reference/precision-support.rst)
-* [Graph safe support](./reference/graph-safe-support.rst)
 :::
 <!-- markdownlint-enable MD051 -->

--- a/docs/reference/gpu-arch-specs.rst
+++ b/docs/reference/gpu-arch-specs.rst
@@ -32,21 +32,6 @@ For more information about ROCm hardware compatibility, see the ROCm `Compatibil
          - L1 Instruction Cache (KiB)
          - VGPR File (KiB)
          - SGPR File (KiB)
-        *
-          - MI325X
-          - CDNA3
-          - gfx942
-          - 256
-          - 304 (38 per XCD)
-          - 64
-          - 64
-          - 256
-          - 32 (4 per XCD)
-          - 32
-          - 16 per 2 CUs
-          - 64 per 2 CUs
-          - 512
-          - 12.5
        *
          - MI300X
          - CDNA3
--- a/docs/reference/graph-safe-support.rst
+++ b/docs/reference/graph-safe-support.rst
@@ -1,111 +0,0 @@
-.. meta::
-    :description: This page lists supported graph safe ROCm libraries.
-    :keywords: AMD, ROCm, HIP, hipGRAPH
-
-********************************************************************************
-Graph-safe support for ROCm libraries
-********************************************************************************
-
-HIP graph-safe libraries operate safely in HIP execution graphs.
-:ref:`hip:how_to_HIP_graph` are an alternative way of executing tasks on a GPU
-that can provide performance benefits over launching kernels using the standard
-method via streams.
-
-Functions and routines from graph-safe libraries shouldn’t result in issues like
-race conditions, deadlocks, or unintended dependencies.
-
-The following table shows whether a ROCm library is graph-safe.
-
-.. list-table::
-    :header-rows: 1
-
-    *
-      - ROCm library
-      - Graph safe support
-    * 
-      - `Composable Kernel <https://github.com/ROCm/composable_kernel>`_
-      - ❌
-    * 
-      - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - ✅
-    * 
-      - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - ⚠️
-    * 
-      - `hipCUB <https://github.com/ROCm/hipCUB>`_
-      - ✅
-    * 
-      - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - ✅ (see :ref:`details <hipfft:hip-graph-support-for-hipfft>`)
-    * 
-      - `hipRAND <https://github.com/ROCm/hipRAND>`_
-      - ✅
-    * 
-      - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - ⚠️ (experimental)
-    * 
-      - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - ✅
-    * 
-      - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
-      - ⚠️ (experimental)
-    * 
-      - `hipTensor <https://github.com/ROCm/hipTensor>`_
-      - ❌
-    * 
-      - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - ❌
-    * 
-      - `RCCL <https://github.com/ROCm/rccl>`_
-      - ✅
-    * 
-      - `rocAL <https://github.com/ROCm/rocAL>`_
-      - ❌
-    * 
-      - `rocALUTION <https://github.com/ROCm/rocALUTION>`_
-      - ❌
-    * 
-      - `rocBLAS <https://github.com/ROCm/rocBLAS>`_
-      - ✅ (see :doc:`details <rocblas:reference/beta-features>`)
-    * 
-      - `rocDecode <https://github.com/ROCm/rocDecode>`_
-      - ❌
-    * 
-      - `rocFFT <https://github.com/ROCm/rocFFT>`_
-      - ✅ (see :ref:`details <rocfft:hip-graph-support-for-rocfft>`)
-    * 
-      - `rocHPCG <https://github.com/ROCm/rocHPCG>`_
-      - ❌
-    * 
-      - `rocJPEG <https://github.com/ROCm/rocJPEG>`_
-      - ❌
-    * 
-      - `rocPRIM <https://github.com/ROCm/rocPRIM>`_
-      - ✅
-    * 
-      - `rocRAND <https://github.com/ROCm/rocRAND>`_
-      - ✅
-    * 
-      - `rocSOLVER <https://github.com/ROCm/rocSOLVER>`_
-      - ⚠️ (experimental)
-    * 
-      - `rocSPARSE <https://github.com/ROCm/rocSPARSE>`_
-      - ⚠️ (experimental)
-    * 
-      - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - ❌ (see :doc:`details <rocthrust:hipgraph-support>`)
-    * 
-      - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
-      - ❌
-    * 
-      - `RPP <https://github.com/ROCm/rpp>`_
-      - ⚠️
-    * 
-      - `Tensile <https://github.com/ROCm/Tensile>`_
-      - ✅
-
-✅: full support
-
-⚠️: partial support
-
-❌: not supported
--- a/docs/reference/rocm-tools.md
+++ b/docs/reference/rocm-tools.md
@@ -1,7 +1,7 @@
 <head>
  <meta charset="UTF-8">
  <meta name="description" content="ROCm API libraries & tools">
-  <meta name="keywords" content="ROCm, API, libraries, tools, AI, artificial intelligence, development,
+  <meta name="keywords" content="ROCm, API, libraries, tools, artificial intelligence, development,
  Communications, C++ primitives, Fast Fourier transforms, FFTs, random number generators, linear
  algebra, AMD">
 </head>
--- a/docs/release/versions.md
+++ b/docs/release/versions.md
@@ -8,7 +8,6 @@

 | Version | Release date |
 | ------- | ------------ |
-| [6.3.1](https://rocm.docs.amd.com/en/docs-6.3.1/) | December 20, 2024 |
 | [6.3.0](https://rocm.docs.amd.com/en/docs-6.3.0/) | December 3, 2024 |
 | [6.2.4](https://rocm.docs.amd.com/en/docs-6.2.4/) | November 6, 2024 |
 | [6.2.2](https://rocm.docs.amd.com/en/docs-6.2.2/) | September 27, 2024 |
--- a/docs/sphinx/_toc.yml.in
+++ b/docs/sphinx/_toc.yml.in
@@ -36,62 +36,40 @@ subtrees:
    title: Use ROCm for AI
    subtrees:
    - entries:
-      - file: how-to/rocm-for-ai/training/index.rst
-        title: Training
-        subtrees:
-        - entries:
-          - file: how-to/rocm-for-ai/training/train-a-model.rst
-            title: Train a model
-          - file: how-to/rocm-for-ai/training/scale-model-training.rst
-            title: Scale model training
-      
-      - file: how-to/rocm-for-ai/fine-tuning/index.rst
-        title: Fine-tuning LLMs
-        subtrees:
-        - entries:
-          - file: how-to/rocm-for-ai/fine-tuning/overview.rst
-            title: Conceptual overview
-          - file: how-to/rocm-for-ai/fine-tuning/fine-tuning-and-inference.rst
-            title: Fine-tuning
-            subtrees:
-            - entries:
-              - file: how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference.rst
-                title: Use a single accelerator
-              - file: how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference.rst
-                title: Use multiple accelerators
-
-      - file: how-to/rocm-for-ai/inference/index.rst
-        title: Inference
-        subtrees:
-        - entries:
-          - file: how-to/rocm-for-ai/inference/install.rst
-            title: Installation
-          - file: how-to/rocm-for-ai/inference/hugging-face-models.rst
-            title: Run models from Hugging Face
-          - file: how-to/rocm-for-ai/inference/llm-inference-frameworks.rst
-            title: LLM inference frameworks
-          - file: how-to/rocm-for-ai/inference/vllm-benchmark.rst
-            title: Performance validation
-          - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
-            title: Deploy your model
-
-      - file: how-to/rocm-for-ai/inference-optimization/index.rst
-        title: Inference optimization
-        subtrees:
-        - entries:
-          - file: how-to/rocm-for-ai/inference-optimization/model-quantization.rst
-          - file: how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries.rst
-          - file: how-to/rocm-for-ai/inference-optimization/optimizing-with-composable-kernel.md
-            title: Optimize with Composable Kernel
-          - file: how-to/rocm-for-ai/inference-optimization/optimizing-triton-kernel.rst
-            title: Optimize Triton kernels
-          - file: how-to/rocm-for-ai/inference-optimization/profiling-and-debugging.rst
-            title: Profile and debug
-          - file: how-to/rocm-for-ai/inference-optimization/workload.rst
-            title: Workload tuning
-  
+      - file: how-to/rocm-for-ai/install.rst
+        title: Installation
+      - file: how-to/rocm-for-ai/train-a-model.rst
+        title: Train a model
+      - file: how-to/rocm-for-ai/scale-model-training.rst
+        title: Scale model training
+      - file: how-to/rocm-for-ai/hugging-face-models.rst
+        title: Run models from Hugging Face
+      - file: how-to/rocm-for-ai/deploy-your-model.rst
+        title: Deploy your model
  - file: how-to/rocm-for-hpc/index.rst
    title: Use ROCm for HPC
+  - file: how-to/llm-fine-tuning-optimization/index.rst
+    title: Fine-tune LLMs and inference optimization
+    subtrees:
+    - entries:
+      - file: how-to/llm-fine-tuning-optimization/overview.rst
+        title: Conceptual overview
+      - file: how-to/llm-fine-tuning-optimization/fine-tuning-and-inference.rst
+        subtrees:
+        - entries:
+          - file: how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference.rst
+            title: Use a single accelerator
+          - file: how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference.rst
+            title: Use multiple accelerators
+      - file: how-to/llm-fine-tuning-optimization/model-quantization.rst
+      - file: how-to/llm-fine-tuning-optimization/model-acceleration-libraries.rst
+      - file: how-to/llm-fine-tuning-optimization/llm-inference-frameworks.rst
+      - file: how-to/llm-fine-tuning-optimization/optimizing-with-composable-kernel.md
+        title: Optimize with Composable Kernel
+      - file: how-to/llm-fine-tuning-optimization/optimizing-triton-kernel.rst
+        title: Optimize Triton kernels
+      - file: how-to/llm-fine-tuning-optimization/profiling-and-debugging.rst
+        title: Profile and debug
  - file: how-to/system-optimization/index.rst
    title: System optimization
    subtrees:
@@ -108,6 +86,18 @@ subtrees:
        title: AMD RDNA 2
  - file: how-to/tuning-guides/mi300x/index.rst
    title: AMD MI300X performance validation and tuning
+    subtrees:
+    - entries:
+      - file: how-to/performance-validation/mi300x/vllm-benchmark.rst
+        title: Performance validation
+      - file: how-to/tuning-guides/mi300x/system.rst
+        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
@@ -120,9 +110,7 @@ subtrees:
      - url: https://rocm.docs.amd.com/projects/llvm-project/en/latest/conceptual/openmp.html
        title: OpenMP support
  - file: how-to/setting-cus
-    title: Set the number of CUs
-  - file: how-to/Bar-Memory.rst
-    title: Troubleshoot BAR access limitation  
+    title: Set the number of CUs  
  - url: https://github.com/amd/rocm-examples
    title: ROCm examples

@@ -166,8 +154,8 @@ subtrees:
    title: GPU isolation techniques
  - file: conceptual/cmake-packages.rst
    title: Using CMake
-  - file: conceptual/pcie-atomics.rst
-    title: PCIe atomics in ROCm
+  - file: conceptual/More-about-how-ROCm-uses-PCIe-Atomics.rst
+    title: ROCm & PCIe atomics
  - file: conceptual/ai-pytorch-inception.md
    title: Inception v3 with PyTorch
  - file: conceptual/oversubscription.rst
@@ -183,8 +171,6 @@ subtrees:
      title: Hardware specifications
    - file: reference/precision-support.rst
      title: Precision support
-    - file: reference/graph-safe-support.rst
-      title: Graph safe support

 - caption: Contribute
  entries:
--- a/docs/sphinx/requirements.in
+++ b/docs/sphinx/requirements.in
@@ -1,3 +1,3 @@
-rocm-docs-core==1.13.0
+rocm-docs-core==1.11.0
 sphinx-reredirects
 sphinx-sitemap
--- a/docs/sphinx/requirements.txt
+++ b/docs/sphinx/requirements.txt
@@ -16,17 +16,17 @@ beautifulsoup4==4.12.3
    # via pydata-sphinx-theme
 breathe==4.35.0
    # via rocm-docs-core
-certifi==2024.12.14
+certifi==2024.8.30
    # via requests
 cffi==1.17.1
    # via
    #   cryptography
    #   pynacl
-charset-normalizer==3.4.1
+charset-normalizer==3.4.0
    # via requests
-click==8.1.8
+click==8.1.7
    # via sphinx-external-toc
-cryptography==44.0.0
+cryptography==43.0.3
    # via pyjwt
 deprecated==1.2.15
    # via pygithub
@@ -36,17 +36,17 @@ docutils==0.21.2
    #   myst-parser
    #   pydata-sphinx-theme
    #   sphinx
-fastjsonschema==2.21.1
+fastjsonschema==2.20.0
    # via rocm-docs-core
-gitdb==4.0.12
+gitdb==4.0.11
    # via gitpython
-gitpython==3.1.44
+gitpython==3.1.43
    # via rocm-docs-core
 idna==3.10
    # via requests
 imagesize==1.4.1
    # via sphinx
-jinja2==3.1.5
+jinja2==3.1.4
    # via
    #   myst-parser
    #   sphinx
@@ -66,18 +66,18 @@ packaging==24.2
    # via sphinx
 pycparser==2.22
    # via cffi
-pydata-sphinx-theme==0.16.1
+pydata-sphinx-theme==0.16.0
    # via
    #   rocm-docs-core
    #   sphinx-book-theme
 pygithub==2.5.0
    # via rocm-docs-core
-pygments==2.19.1
+pygments==2.18.0
    # via
    #   accessible-pygments
    #   pydata-sphinx-theme
    #   sphinx
-pyjwt[crypto]==2.10.1
+pyjwt[crypto]==2.10.0
    # via pygithub
 pynacl==1.5.0
    # via pygithub
@@ -90,9 +90,9 @@ requests==2.32.3
    # via
    #   pygithub
    #   sphinx
-rocm-docs-core==1.13.0
+rocm-docs-core==1.11.0
    # via -r requirements.in
-smmap==5.0.2
+smmap==5.0.1
    # via gitdb
 snowballstemmer==2.2.0
    # via sphinx
@@ -137,15 +137,15 @@ sphinxcontrib-qthelp==2.0.0
    # via sphinx
 sphinxcontrib-serializinghtml==2.0.0
    # via sphinx
-tomli==2.2.1
+tomli==2.1.0
    # via sphinx
 typing-extensions==4.12.2
    # via
    #   pydata-sphinx-theme
    #   pygithub
-urllib3==2.3.0
+urllib3==2.2.3
    # via
    #   pygithub
    #   requests
-wrapt==1.17.1
+wrapt==1.17.0
    # via deprecated
--- a/docs/what-is-rocm.rst
+++ b/docs/what-is-rocm.rst
@@ -10,9 +10,9 @@ ROCm is a software stack, composed primarily of open-source software, that
 provides the tools for programming AMD Graphics Processing Units (GPUs), from
 low-level kernels to high-level end-user applications.

-.. image:: data/rocm-software-stack-6_3_2.jpg
+.. image:: data/rocm-software-stack-6_3_0.jpg
  :width: 800
-  :alt: AMD's ROCm software stack and enabling technologies.
+  :alt: AMD's ROCm software stack and neighboring technologies.
  :align: center

 Specifically, ROCm provides the tools for
--- a/tools/autotag/components.xml
+++ b/tools/autotag/components.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.3.1"
+    <default revision="refs/tags/rocm-6.3.0"
     remote="rocm-org"
     sync-c="true"
     sync-j="4" />
--- a/tools/autotag/templates/highlights/6.3.1.md
+++ b/tools/autotag/templates/highlights/6.3.1.md
@@ -1,61 +0,0 @@
-# ROCm 6.3.1 release notes
-
-The release notes provide a summary of notable changes since the previous ROCm release.
-
- [Release highlights](#release-highlights)
-
- [Operating system and hardware support changes](#operating-system-and-hardware-support-changes)
-
- [ROCm components versioning](#rocm-components)
-
- [Detailed component changes](#detailed-component-changes)
-
- [ROCm known issues](#rocm-known-issues)
-
- [ROCm resolved issues](#rocm-resolved-issues)
-
- [ROCm upcoming changes](#rocm-upcoming-changes)
-
-```{note}
-If you’re using Radeon™ PRO or Radeon GPUs in a workstation setting with a
-display connected, continue to use ROCm 6.2.3. See the [Use ROCm on Radeon GPUs](https://rocm.docs.amd.com/projects/radeon/en/latest/index.html)
-documentation to verify compatibility and system requirements.
-```
-## Release highlights
-
-The following are notable new features and improvements in ROCm 6.3.1. For changes to individual components, see
-[Detailed component changes](#detailed-component-changes).
-
-### Per queue resiliency for Instinct MI300 accelerators
-
-The AMDGPU driver now includes enhanced resiliency for misbehaving applications on AMD Instinct MI300 accelerators. This helps isolate the impact of misbehaving applications, ensuring other workloads running on the same accelerator are unaffected.
-
-### ROCm Runfile Installer
-
-ROCm 6.3.1 introduces the ROCm Runfile Installer, with initial support for Ubuntu 22.04. The ROCm Runfile Installer facilitates ROCm installation without using a native Linux package management system, with or without network or internet access. For more information, see the [ROCm Runfile Installer documentation](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.3.1/install/rocm-runfile-installer.html).
-
-### ROCm documentation updates
-
-ROCm documentation continues to be updated to provide clearer and more comprehensive guidance for a wider variety of user needs and use cases.
-
-* Added documentation on training a model with ROCm Megatron-LM. AMD offers a Docker image for MI300X accelerators
-  containing essential components to get started, including ROCm libraries, PyTorch, and Megatron-LM utilities. See
-  [Training a model using ROCm Megatron-LM](https://rocm.docs.amd.com/en/latest/how-to/rocm-for-ai/train-a-model.html)
-  to get started.
-
-  The new ROCm Megatron-LM training Docker accompanies the [ROCm vLLM inference
-  Docker](https://rocm.docs.amd.com/en/latest/how-to/performance-validation/mi300x/vllm-benchmark.html)
-  as a set of ready-to-use containerized solutions to get started with using ROCm
-  for AI.
-
-* Updated the [Instinct MI300X workload tuning
-  guide](https://rocm.docs.amd.com/en/latest/how-to/tuning-guides/mi300x/workload.html) with more current optimization
-  strategies. The updated sections include guidance on vLLM optimization, PyTorch TunableOp, and hipBLASLt tuning.
-
-* HIP graph-safe libraries operate safely in HIP execution graphs. [HIP graphs](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_runtime_api/hipgraph.html#how-to-hip-graph) are an alternative way of executing tasks on a GPU that can provide performance benefits over launching kernels using the standard method via streams. A topic that shows whether a [ROCm library is graph-safe](https://advanced-micro-devices-demo--3953.com.readthedocs.build/en/3953/reference/graph-safe-support.html) has been added.
-
-* The [Device memory](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_runtime_api/memory_management/device_memory.html) topic in the HIP memory management section has been updated.
-
-* The HIP documentation has expanded with new resources for developers:
-  * [Multi device management](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_runtime_api/multi_device.html)
-  * [OpenGL interoperability](https://rocm.docs.amd.com/projects/HIP/en/latest/how-to/hip_runtime_api/opengl_interop.html)
--- a/tools/autotag/templates/known_issues/6.3.1.md
+++ b/tools/autotag/templates/known_issues/6.3.1.md
@@ -1,8 +0,0 @@
-## ROCm known issues
-
-ROCm known issues are noted on {fab}`github` [GitHub](https://github.com/ROCm/ROCm/labels/Verified%20Issue). For known
-issues related to individual components, review the [Detailed component changes](#detailed-component-changes).
-
-### PCI Express Qualification Tool failure on Debian 12
-
-The PCI Express Qualification Tool (PEQT) module present in the ROCm Validation Suite (RVS) might fail due to the segmentation issue in Debian 12 (bookworm). This will result in failure to determine the characteristics of the PCIe interconnect between the host platform and the GPU like support for Gen 3 atomic completers, DMA transfer statistics, link speed, and link width. The standard PCIe command `lspci` can be used as an alternative to view the characteristics of the PCIe bus interconnect with the GPU. This issue is under investigation and will be addressed in a future release. See [GitHub issue #4175](https://github.com/ROCm/ROCm/issues/4175).
--- a/tools/autotag/templates/resolved_issues/6.3.1.md
+++ b/tools/autotag/templates/resolved_issues/6.3.1.md
@@ -1,23 +0,0 @@
-## ROCm resolved issues
-
-The following are previously known issues resolved in this release. For resolved issues related to
-individual components, review the [Detailed component changes](#detailed-component-changes).
-
-### Instinct MI300 series: backward weights convolution performance issue
-
-Fixed a performance issue affecting certain tensor shapes during backward weights convolution when using FP16 or FP32 data types on Instinct MI300 series accelerators. See [GitHub issue #4080](https://github.com/ROCm/ROCm/issues/4080).
-
-### ROCm Compute Profiler and ROCm Systems Profiler post-upgrade issues
-
-Packaging metadata for ROCm Compute Profiler (`rocprofiler-compute`) and ROCm Systems Profiler
-(`rocprofiler-systems`) has been updated to handle the renaming from Omniperf and Omnitrace,
-respectively. This fixes minor issues when upgrading from ROCm 6.2 to 6.3. For more information, see the GitHub issues
-[#4082](https://github.com/ROCm/ROCm/issues/4082) and
-[#4083](https://github.com/ROCm/ROCm/issues/4082).
-
-### Stale file due to OpenCL ICD loader deprecation
-
-When upgrading from ROCm 6.2.x to ROCm 6.3.0, the issue of removal of the `rocm-icd-loader` package
-leaving a stale file in the old `rocm-6.2.x` directory has been resolved. The stale files left during
-the upgrade from ROCm 6.2.x to ROCm 6.3.0 will be removed when upgrading to ROCm 6.3.1. For more
-information, see [GitHub issue #4084](https://github.com/ROCm/ROCm/issues/4084).
--- a/tools/autotag/templates/support/6.3.1.md
+++ b/tools/autotag/templates/support/6.3.1.md
@@ -1,9 +0,0 @@
-## Operating system and hardware support changes
-
-ROCm 6.3.1 adds support for Debian 12 (kernel: 6.1). Debian is supported only on AMD Instinct accelerators. See the installation instructions at [Debian native installation](https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.3.1/install/native-install/debian.html).
-
-ROCm 6.3.1 enables support for AMD Instinct MI325X accelerator. For more information, see [AMD Instinct™ MI325X Accelerators](https://www.amd.com/en/products/accelerators/instinct/mi300/mi325x.html).
-
-See the [Compatibility
-matrix](https://rocm.docs.amd.com/en/docs-6.3.1/compatibility/compatibility-matrix.html)
-for more information about operating system and hardware compatibility.
--- a/tools/autotag/templates/upcoming_changes/6.3.1.md
+++ b/tools/autotag/templates/upcoming_changes/6.3.1.md
@@ -1,13 +0,0 @@
-## ROCm upcoming changes
-
-The following changes to the ROCm software stack are anticipated for future releases.
-
-### AMDGPU wavefront size compiler macro deprecation
-
-The `__AMDGCN_WAVEFRONT_SIZE__` macro will be deprecated in an upcoming
-release. It is recommended to remove any use of this macro. For more information, see [AMDGPU
-support](https://rocm.docs.amd.com/projects/llvm-project/en/docs-6.3.1/LLVM/clang/html/AMDGPUSupport.html).
-
-### HIPCC Perl scripts deprecation
-
-The HIPCC Perl scripts (`hipcc.pl` and `hipconfig.pl`) will be removed in an upcoming release.
--- a/tools/rocm-build/ROCm.mk
+++ b/tools/rocm-build/ROCm.mk
@@ -66,44 +66,46 @@ endef
 # It is a space seperated list with zero or more elements.

 $(call adddep,amd_smi_lib,${ASAN_DEP})
-$(call adddep,aqlprofile,${ASAN_DEP} rocr)
+$(call adddep,aqlprofile,${ASAN_DEP} hsa)
 $(call adddep,comgr,lightning devicelibs)
-$(call adddep,dbgapi,rocr comgr)
+$(call adddep,dbgapi,hsa comgr)
 $(call adddep,devicelibs,lightning)
-$(call adddep,hip_on_rocclr,${ASAN_DEP} rocr comgr hipcc rocprofiler-register)
+$(call adddep,hip_on_rocclr,${ASAN_DEP} hsa comgr hipcc rocprofiler-register)
 $(call adddep,hipcc,)
 $(call adddep,hipify_clang,hip_on_rocclr lightning)
+$(call adddep,hsa,${ASAN_DEP} thunk lightning devicelibs rocprofiler-register)
 $(call adddep,lightning,)
-$(call adddep,opencl_on_rocclr,${ASAN_DEP} rocr comgr)
-$(call adddep,openmp_extras,lightning devicelibs rocr)
-$(call adddep,rocm_bandwidth_test,${ASAN_DEP} rocr)
+$(call adddep,omniperf,${ASAN_DEP})
+$(call adddep,omnitrace,hipcc hsa hip_on_rocclr rocm_smi_lib rocprofiler roctracer)
+$(call adddep,opencl_icd_loader,)
+$(call adddep,opencl_on_rocclr,${ASAN_DEP} hsa comgr opencl_icd_loader)
+$(call adddep,openmp_extras,thunk lightning devicelibs hsa)
+$(call adddep,rdc,${ASAN_DEP} rocm_smi_lib hsa rocprofiler)
+$(call adddep,rocclr,${ASAN_DEP} hsa comgr hipcc rocprofiler-register)
+$(call adddep,rocm_bandwidth_test,${ASAN_DEP} hsa)
 $(call adddep,rocm_smi_lib,${ASAN_DEP})
 $(call adddep,rocm-cmake,${ASAN_DEP})
 $(call adddep,rocm-core,${ASAN_DEP})
 $(call adddep,rocm-gdb,dbgapi)
-$(call adddep,rocminfo,${ASAN_DEP} rocr)
+$(call adddep,rocminfo,${ASAN_DEP} hsa)
 $(call adddep,rocprofiler-register,${ASAN_DEP})
-$(call adddep,rocprofiler-sdk,${ASAN_DEP} rocr aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
-$(call adddep,rocprofiler-systems,${ASAN_DEP} hipcc rocr hip_on_rocclr rocm_smi_lib rocprofiler roctracer rocprofiler-sdk)
-$(call adddep,rocprofiler,${ASAN_DEP} rocr roctracer aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
-$(call adddep,rocprofiler-compute,${ASAN_DEP})
-$(call adddep,rocr,${ASAN_DEP} lightning rocm_smi_lib devicelibs rocprofiler-register)
-$(call adddep,rocr_debug_agent,${ASAN_DEP} hip_on_rocclr rocr dbgapi)
-$(call adddep,roctracer,${ASAN_DEP} rocr hip_on_rocclr)
+$(call adddep,rocprofiler-sdk,${ASAN_DEP} hsa aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
+$(call adddep,rocprofiler,${ASAN_DEP} hsa roctracer aqlprofile opencl_on_rocclr hip_on_rocclr comgr)
+$(call adddep,rocr_debug_agent,${ASAN_DEP} hip_on_rocclr hsa dbgapi)
+$(call adddep,roctracer,${ASAN_DEP} hsa hip_on_rocclr)
+$(call adddep,thunk,${ASAN_DEP})

 # rocm-dev points to all possible last finish components of Stage1 build.
-rocm-dev-components :=amd_smi_lib aqlprofile comgr dbgapi devicelibs hip_on_rocclr hipcc hipify_clang \
-	lightning rocprofiler-compute opencl_on_rocclr openmp_extras rocm_bandwidth_test rocm_smi_lib \
-	rocm-cmake rocm-core rocm-gdb rocminfo rocprofiler-register rocprofiler-sdk rocprofiler-systems \
-	rocprofiler rocr rocr_debug_agent roctracer
-$(call adddep,rocm-dev,$(filter-out ${NOBUILD} kernel_ubuntu,${rocm-dev-components}))
+rocm-dev-components :=rdc hipify_clang openmp_extras \
+	omniperf omnitrace rocm-core amd_smi_lib hipcc \
+	rocm_bandwidth_test rocr_debug_agent rocm-gdb
+$(call adddep,rocm-dev,$(filter-out ${NOBUILD},${rocm-dev-components}))

-$(call adddep,amdmigraphx,hip_on_rocclr half rocblas miopen-hip lightning hipcc hiptensor)
+$(call adddep,amdmigraphx,hip_on_rocclr half rocblas miopen-hip lightning hipcc)
 $(call adddep,composable_kernel,lightning hipcc hip_on_rocclr rocm-cmake)
 $(call adddep,half,rocm-cmake)
-$(call adddep,hipblas-common,lightning)
 $(call adddep,hipblas,hip_on_rocclr rocblas rocsolver lightning hipcc)
-$(call adddep,hipblaslt,hip_on_rocclr openmp_extras lightning hipcc hipblas-common rocm-dev)
+$(call adddep,hipblaslt,hip_on_rocclr openmp_extras hipblas lightning hipcc)
 $(call adddep,hipcub,hip_on_rocclr rocprim lightning hipcc)
 $(call adddep,hipfft,hip_on_rocclr openmp_extras rocfft rocrand hiprand lightning hipcc)
 $(call adddep,hipfort,rocblas hipblas rocsparse hipsparse rocfft hipfft rocrand hiprand rocsolver hipsolver lightning hipcc)
@@ -113,25 +115,22 @@ $(call adddep,hipsparse,hip_on_rocclr rocsparse lightning hipcc)
 $(call adddep,hipsparselt,hip_on_rocclr hipsparse lightning hipcc openmp_extras)
 $(call adddep,hiptensor,hip_on_rocclr composable_kernel lightning hipcc)
 $(call adddep,miopen-deps,lightning hipcc)
-$(call adddep,miopen-hip,composable_kernel half hip_on_rocclr miopen-deps hipblas hipblaslt rocrand roctracer lightning hipcc)
+$(call adddep,miopen-hip,composable_kernel half hip_on_rocclr miopen-deps rocblas roctracer lightning hipcc)
 $(call adddep,mivisionx,amdmigraphx miopen-hip rpp lightning hipcc)
-$(call adddep,rccl,rocm-core hip_on_rocclr rocr lightning hipcc rocm_smi_lib hipify_clang)
-$(call adddep,rdc,rocm_smi_lib rocprofiler rocmvalidationsuite)
+$(call adddep,rccl,hip_on_rocclr hsa lightning hipcc rocm_smi_lib hipify_clang)
 $(call adddep,rocalution,rocblas rocsparse rocrand lightning hipcc)
-$(call adddep,rocblas,hip_on_rocclr openmp_extras lightning hipcc hipblaslt)
+$(call adddep,rocblas,hip_on_rocclr openmp_extras lightning hipcc)
 $(call adddep,rocal,mivisionx)
-$(call adddep,rocdecode,hip_on_rocclr lightning hipcc amdmigraphx)
+$(call adddep,rocdecode,hip_on_rocclr lightning hipcc)
 $(call adddep,rocfft,hip_on_rocclr rocrand hiprand lightning hipcc openmp_extras)
-$(call adddep,rocjpeg,hip_on_rocclr lightning hipcc rocm-dev)
-$(call adddep,rocmvalidationsuite,hip_on_rocclr rocr hipblas hiprand hipblaslt rocm-core lightning hipcc rocm_smi_lib)
+$(call adddep,rocmvalidationsuite,hip_on_rocclr hsa rocblas rocm-core lightning hipcc rocm_smi_lib)
 $(call adddep,rocprim,hip_on_rocclr lightning hipcc)
 $(call adddep,rocrand,hip_on_rocclr lightning hipcc)
-$(call adddep,rocsolver,hip_on_rocclr rocblas rocsparse rocprim lightning hipcc)
+$(call adddep,rocsolver,hip_on_rocclr rocblas rocsparse lightning hipcc)
 $(call adddep,rocsparse,hip_on_rocclr rocprim lightning hipcc)
 $(call adddep,rocthrust,hip_on_rocclr rocprim lightning hipcc)
 $(call adddep,rocwmma,hip_on_rocclr rocblas lightning hipcc rocm-cmake rocm_smi_lib)
 $(call adddep,rpp,half lightning hipcc openmp_extras)
-$(call adddep,transferbench,hip_on_rocclr lightning hipcc)


 # -------------------------------------------------------------------------
@@ -190,7 +189,7 @@ else # } {
 # Pass in jobserver info using the RMAKE variable
 	${RMAKE}@( if set -x && source $${INFRA_REPO}/envsetup.sh && \
 	rm -f $$@.errors $$@ $$@.repackaged && \
-	$${INFRA_REPO}/build_$1.sh -c && \
+	$${INFRA_REPO}/build_$1.sh -c && source $${INFRA_REPO}/ccache-env-mathlib.sh && \
 	time bash -x $${INFRA_REPO}/build_$1.sh $${RELEASE_FLAG} $${SANITIZER_FLAG} && $${INFRA_REPO}/post_inst_pkg.sh "$1" ; \
 	then mv $$@.inprogress $$@ ; \
 	else mv $$@.inprogress $$@.errors ; echo Error in $1 >&2 ; exit 1 ;\
@@ -217,14 +216,11 @@ $(call peval,$(foreach dep,$(strip ${components}),$(call toplevel,${dep})))
 all: $(addprefix T_,$(filter-out ${NOBUILD},${components}))
 	@echo All ROCm components built
 # Do not document this target
-upload: $(addprefix U_,$(filter-out ${NOBUILD},${components}))
+upload: $(addprefix U_,${components})
 	@echo All ROCm components built and uploaded

-upload-rocm-dev: $(addprefix U_,$(filter-out ${NOBUILD},${components}))
-	@echo All rocm-dev components built and uploaded
-
 ##help rocm-dev: Build a subset of ROCm
-rocm-dev: $(addprefix T_,$(filter-out ${NOBUILD},${components}))
+rocm-dev: T_rocm-dev
 	@echo rocm-dev built

 ${OUT_DIR}/logs:
--- a/tools/rocm-build/build_amd_smi_lib.sh
+++ b/tools/rocm-build/build_amd_smi_lib.sh
@@ -22,15 +22,15 @@ printUsage() {
    return 0
 }

-PROJ_NAME="amdsmi"
 PACKAGE_ROOT="$(getPackageRoot)"
 TARGET="build"

 PACKAGE_LIB=$(getLibPath)
 PACKAGE_INCLUDE="$(getIncludePath)"
-AMDSMI_BUILD_DIR=$(getBuildPath $PROJ_NAME)
-AMDSMI_PACKAGE_DEB_DIR="$PACKAGE_ROOT/deb/$PROJ_NAME"
-AMDSMI_PACKAGE_RPM_DIR="$PACKAGE_ROOT/rpm/$PROJ_NAME"
+
+AMDSMI_BUILD_DIR=$(getBuildPath amdsmi)
+AMDSMI_PACKAGE_DEB_DIR="$(getPackageRoot)/deb/amdsmi"
+AMDSMI_PACKAGE_RPM_DIR="$(getPackageRoot)/rpm/amdsmi"
 AMDSMI_BUILD_TYPE="debug"
 BUILD_TYPE="Debug"

@@ -57,9 +57,10 @@ do
        (-a | --address_sanitizer)
                set_asan_env_vars
                set_address_sanitizer_on
+                # TODO - support standard option of passing cmake environment vars - CFLAGS,CXXFLAGS etc., to enable address sanitizer
                ADDRESS_SANITIZER=true ; shift ;;
        (-s | --static)
-                ack_and_skip_static ;;
+                SHARED_LIBS="OFF" ; shift ;;
        (-o | --outdir)
                TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
        (-p | --package)
--- a/tools/rocm-build/build_amdmigraphx.sh
+++ b/tools/rocm-build/build_amdmigraphx.sh
@@ -10,9 +10,7 @@ build_amdmigraphx() {

    cd $COMPONENT_SRC

-    if ! command -v rbuild &> /dev/null; then
-        pip3 install https://github.com/RadeonOpenCompute/rbuild/archive/master.tar.gz
-    fi
+    pip3 install https://github.com/RadeonOpenCompute/rbuild/archive/master.tar.gz

    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
         set_asan_env_vars
@@ -22,7 +20,7 @@ build_amdmigraphx() {
    if [ -n "$GPU_ARCHS" ]; then
        GPU_TARGETS="$GPU_ARCHS"
    else
-        GPU_TARGETS="gfx900;gfx906;gfx908;gfx90a;gfx1030;gfx1100;gfx1101;gfx1102;gfx942;gfx1200;gfx1201"
+        GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
    fi
    init_rocm_common_cmake_params

@@ -31,7 +29,7 @@ build_amdmigraphx() {
        --cxx="${ROCM_PATH}/llvm/bin/clang++" \
        --cc="${ROCM_PATH}/llvm/bin/clang" \
        "${rocm_math_common_cmake_params[@]}" \
-        -DCMAKE_MODULE_LINKER_FLAGS="-Wl,--enable-new-dtags,--build-id=sha1,--rpath,$ROCM_LIB_RPATH" \
+        -DCMAKE_MODULE_LINKER_FLAGS="-Wl,--enable-new-dtags -Wl,--rpath,$ROCM_LIB_RPATH" \
 	    -DGPU_TARGETS="${GPU_TARGETS}" \
        -DCMAKE_INSTALL_RPATH=""

--- a/tools/rocm-build/build_aqlprofile.sh
+++ b/tools/rocm-build/build_aqlprofile.sh
@@ -11,9 +11,7 @@ printUsage() {
    echo "  -p,  --package <type>     Specify packaging format"
    echo "  -r,  --release            Make a release build instead of a debug build"
    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
-                                      type referred to by pkg_type"
-    echo "  -s,  --static             Component/Build does not support static builds just accepting this param & ignore. 
-                                      No effect of the param on this build"
+            type referred to by pkg_type"
    echo "  -h,  --help               Prints this help"
    echo
    echo "Possible values for <type>:"
--- a/tools/rocm-build/build_clang-ocl.sh
+++ b/tools/rocm-build/build_clang-ocl.sh
@@ -0,0 +1,136 @@
+#!/bin/bash
+
+source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
+
+printUsage() {
+    echo
+    echo "Usage: $(basename "${BASH_SOURCE}") [-c|-r|-h] [makeopts]"
+    echo
+    echo "Options:"
+    echo "  -c,  --clean              Removes all clang-ocl build artifacts"
+    echo "  -r,  --release            Build non-debug version clang-ocl (default is debug)"
+    echo "  -a,  --address_sanitizer  Enable address sanitizer"
+    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
+                                      type referred to by pkg_type"
+    echo "  -h,  --help               Prints this help"
+    echo "  -s,  --static             Supports static CI by accepting this param & not bailing out. No effect of the param though"
+    echo
+
+    return 0
+}
+
+
+TARGET="build"
+CLANG_OCL_DEST="$(getBinPath)"
+CLANG_OCL_SRC_ROOT="$CLANG_OCL_ROOT"
+CLANG_OCL_BUILD_DIR="$(getBuildPath clang-ocl)"
+
+MAKEARG="$DASH_JAY"
+PACKAGE_ROOT="$(getPackageRoot)"
+PACKAGE_UTILS="$(getUtilsPath)"
+CLANG_OCL_PACKAGE_DEB="$PACKAGE_ROOT/deb/clang-ocl"
+CLANG_OCL_PACKAGE_RPM="$PACKAGE_ROOT/rpm/clang-ocl"
+BUILD_TYPE="Debug"
+SHARED_LIBS="ON"
+CLEAN_OR_OUT=0;
+MAKETARGET="deb"
+PKGTYPE="deb"
+
+
+VALID_STR=`getopt -o hcraso:g: --long help,clean,release,clean,static,address_sanitizer,outdir:,gpu_list: -- "$@"`
+eval set -- "$VALID_STR"
+
+while true ;
+do
+    case "$1" in
+        (-h | --help)
+                printUsage ; exit 0;;
+        (-c | --clean)
+                TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
+        (-r | --release)
+                MAKEARG="$MAKEARG BUILD_TYPE=rel" ;  BUILD_TYPE="Release" ; shift ;;
+        (-a | --address_sanitizer)
+                set_asan_env_vars
+                set_address_sanitizer_on ; shift ;;
+        (-s | --static)
+                SHARED_LIBS="OFF" ; shift ;;
+        (-o | --outdir)
+                TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
+        (-g | --gpu_list )
+                GPU_LIST=$2; shift 2 ;;
+        --)     shift; break;;
+        (*)
+                echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
+    esac
+
+done
+
+RET_CONFLICT=1
+check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+if [ $RET_CONFLICT -ge 30 ]; then
+   print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+   exit $RET_CONFLICT
+fi
+
+clean_clang-ocl() {
+    echo "Removing clang-ocl"
+    rm -rf $CLANG_OCL_DEST/clang-ocl
+    rm -rf $CLANG_OCL_BUILD_DIR
+    rm -rf $CLANG_OCL_PACKAGE_DEB
+    rm -rf $CLANG_OCL_PACKAGE_RPM
+}
+
+build_clang-ocl() {
+    if [ ! -d "$CLANG_OCL_BUILD_DIR" ]; then
+        mkdir -p $CLANG_OCL_BUILD_DIR
+        pushd $CLANG_OCL_BUILD_DIR
+
+        if [ -e $PACKAGE_ROOT/lib/bitcode/opencl.amdgcn.bc ]; then
+            BC_DIR="$ROCM_INSTALL_PATH/lib"
+        else
+            BC_DIR="$ROCM_INSTALL_PATH/amdgcn/bitcode"
+        fi
+
+        cmake \
+            $(rocm_cmake_params) \
+            -DDISABLE_CHECKS="ON" \
+            -DCLANG_BIN="$ROCM_INSTALL_PATH/llvm/bin" \
+            -DBITCODE_DIR="$BC_DIR" \
+	    $(rocm_common_cmake_params) \
+            -DCPACK_SET_DESTDIR="OFF" \
+            $CLANG_OCL_SRC_ROOT
+
+        echo "Making clang-ocl:"
+        cmake --build . -- $MAKEARG
+        cmake --build . -- $MAKEARG install
+        cmake --build . -- $MAKEARG package
+        popd
+    fi
+
+    copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$CLANG_OCL_PACKAGE_DEB" $CLANG_OCL_BUILD_DIR/rocm-clang-ocl*.deb
+    copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$CLANG_OCL_PACKAGE_RPM" $CLANG_OCL_BUILD_DIR/rocm-clang-ocl*.rpm
+}
+
+
+print_output_directory() {
+     case ${PKGTYPE} in
+         ("deb")
+             echo ${CLANG_OCL_PACKAGE_DEB};;
+         ("rpm")
+             echo ${CLANG_OCL_PACKAGE_RPM};;
+         (*)
+             echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
+     esac
+     exit
+}
+
+case $TARGET in
+    (clean) clean_clang-ocl ;;
+    (build) build_clang-ocl ;;
+   (outdir) print_output_directory ;;
+        (*) die "Invalid target $TARGET" ;;
+esac
+
+echo "Operation complete"
+exit 0
+
--- a/tools/rocm-build/build_composable_kernel.sh
+++ b/tools/rocm-build/build_composable_kernel.sh
@@ -6,53 +6,73 @@ source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"

 set_component_src composable_kernel

-GPU_ARCH_LIST="gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1200;gfx1201"
-
 build_miopen_ck() {
    echo "Start Building Composable Kernel"
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
       set_asan_env_vars
       set_address_sanitizer_on
-       GPU_ARCH_LIST="gfx908:xnack+;gfx90a:xnack+;gfx942:xnack+"
-    else
-       unset_asan_env_vars
-       set_address_sanitizer_off
-    fi
-
-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        GPU_ARCH_LIST="gfx942"
-        ack_and_skip_static
-    fi
-
-    PYTHON_VERSION_WORKAROUND=''
-    echo "DISTRO_ID: ${DISTRO_ID}"
-    if [ "$DISTRO_ID" = "rhel-8.8" ] || [ "$DISTRO_ID" = "sles-15.5" ] ; then
-        EXTRA_PYTHON_PATH=/opt/Python-3.8.13
-        PYTHON_VERSION_WORKAROUND="-DCK_USE_ALTERNATIVE_PYTHON=${EXTRA_PYTHON_PATH}/bin/python3.8"
-        # For the python interpreter we need to export LD_LIBRARY_PATH.
-        export LD_LIBRARY_PATH=${EXTRA_PYTHON_PATH}/lib:$LD_LIBRARY_PATH
    fi

    cd $COMPONENT_SRC
    mkdir "$BUILD_DIR" && cd "$BUILD_DIR"
-    init_rocm_common_cmake_params

-    cmake \
-        -DBUILD_DEV=OFF \
-        "${rocm_math_common_cmake_params[@]}" \
-        ${PYTHON_VERSION_WORKAROUND} \
-        -DCPACK_GENERATOR="${PKGTYPE^^}" \
-        -DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
-        -DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
-        ${LAUNCHER_FLAGS} \
-        -DGPU_ARCHS="${GPU_ARCH_LIST}" \
-        -DCMAKE_BUILD_TYPE=Release \
-        -DCMAKE_CXX_FLAGS=" -O3 " \
-        "$COMPONENT_SRC"
+    if [ -n "$GPU_ARCHS" ]; then
+        GPU_TARGETS="-DAMDGPU_TARGETS=${GPU_ARCHS}"
+    fi
+
+    if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
+        cmake -DBUILD_DEV=OFF \
+            -DCMAKE_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'} \
+            -DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++ \
+            -DCMAKE_CXX_FLAGS=" -O3 " \
+            -DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}/lib/cmake;${ROCM_PATH%-*}/$ASAN_LIBDIR;${ROCM_PATH%-*}/llvm;${ROCM_PATH%-*}" \
+            -DCMAKE_SHARED_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_LIB_RPATH" \
+            -DCMAKE_EXE_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH" \
+            -DCMAKE_VERBOSE_MAKEFILE=1 \
+            -DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
+            -DCMAKE_INSTALL_PREFIX=${ROCM_PATH} \
+            -DCMAKE_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
+            -DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
+            -DROCM_SYMLINK_LIBS=OFF \
+            -DCPACK_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
+            -DROCM_DISABLE_LDCONFIG=ON \
+            -DROCM_PATH=${ROCM_PATH} \
+            -DCPACK_GENERATOR="${PKGTYPE^^}" \
+            ${LAUNCHER_FLAGS} \
+            -DINSTANCES_ONLY=ON \
+            -DENABLE_ASAN_PACKAGING=true \
+            "${GPU_TARGETS}" \
+            "$COMPONENT_SRC"
+    else
+        cmake -DBUILD_DEV=OFF \
+            -DCMAKE_BUILD_TYPE=Release \
+            -DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++ \
+            -DCMAKE_CXX_FLAGS=" -O3 " \
+            -DCMAKE_PREFIX_PATH=${ROCM_PATH%-*} \
+            -DCMAKE_SHARED_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN' \
+            -DCMAKE_EXE_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN/../lib' \
+            -DCMAKE_VERBOSE_MAKEFILE=1 \
+            -DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
+            -DCMAKE_INSTALL_PREFIX=${ROCM_PATH} \
+            -DCMAKE_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
+            -DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
+            -DROCM_SYMLINK_LIBS=OFF \
+            -DCPACK_PACKAGING_INSTALL_PREFIX=${ROCM_PATH} \
+            -DROCM_DISABLE_LDCONFIG=ON \
+            -DROCM_PATH=${ROCM_PATH} \
+            -DCPACK_GENERATOR="${PKGTYPE^^}" \
+            -DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
+            -DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
+            ${LAUNCHER_FLAGS} \
+            -DINSTANCES_ONLY=ON \
+            "${GPU_TARGETS}" \
+            "$COMPONENT_SRC"
+    fi

    cmake --build . -- -j${PROC} package
    cmake --build "$BUILD_DIR" -- install
    mkdir -p $PACKAGE_DIR && cp ./*.${PKGTYPE} $PACKAGE_DIR
+    rm -rf *
 }

 unset_asan_env_vars() {
@@ -68,6 +88,85 @@ set_address_sanitizer_off() {
    export LDFLAGS=""
 }

+build_miopen_ckProf() {
+    ENABLE_ADDRESS_SANITIZER=false
+    echo "Start Building Composable Kernel Profiler"
+    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
+       set_asan_env_vars
+       set_address_sanitizer_on
+    else
+       unset_asan_env_vars
+       set_address_sanitizer_off
+    fi
+
+    cd $COMPONENT_SRC
+    cd "$BUILD_DIR"
+    rm -rf *
+
+    architectures='gfx10 gfx11 gfx90 gfx94'
+    if [ -n "$GPU_ARCHS" ]; then
+        architectures=$(echo ${GPU_ARCHS} | awk -F';' '{for(i=1;i<=NF;i++) a[substr($i,1,5)]} END{for(i in a) printf i" "}')
+    fi
+
+    for arch in ${architectures}
+        do
+            if [ "${ASAN_CMAKE_PARAMS}" == "true" ] ; then
+                cmake -DBUILD_DEV=OFF \
+                    -DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}/lib/cmake;${ROCM_PATH%-*}/$ASAN_LIBDIR;${ROCM_PATH%-*}/llvm;${ROCM_PATH%-*}" \
+                    -DCMAKE_BUILD_TYPE=${BUILD_TYPE:-'RelWithDebInfo'} \
+                    -DCMAKE_SHARED_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_LIB_RPATH" \
+                    -DCMAKE_EXE_LINKER_FLAGS_INIT="-Wl,--enable-new-dtags,--rpath,$ROCM_ASAN_EXE_RPATH" \
+                    -DCMAKE_VERBOSE_MAKEFILE=1 \
+                    -DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
+                    -DCMAKE_INSTALL_PREFIX="${ROCM_PATH}" \
+                    -DCMAKE_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
+                    -DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
+                    -DROCM_SYMLINK_LIBS=OFF \
+                    -DCPACK_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
+                    -DROCM_DISABLE_LDCONFIG=ON \
+                    -DROCM_PATH="${ROCM_PATH}" \
+                    -DCPACK_GENERATOR="${PKGTYPE^^}" \
+                    -DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
+                    -DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
+                    ${LAUNCHER_FLAGS} \
+                    -DPROFILER_ONLY=ON \
+                    -DENABLE_ASAN_PACKAGING=true \
+                    -DGPU_ARCH="${arch}" \
+                    "$COMPONENT_SRC"
+            else
+                cmake -DBUILD_DEV=OFF \
+                    -DCMAKE_PREFIX_PATH="${ROCM_PATH%-*}" \
+                    -DCMAKE_BUILD_TYPE=Release \
+                    -DCMAKE_SHARED_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN' \
+                    -DCMAKE_EXE_LINKER_FLAGS_INIT='-Wl,--enable-new-dtags,--rpath,$ORIGIN/../lib' \
+                    -DCMAKE_VERBOSE_MAKEFILE=1 \
+                    -DCMAKE_INSTALL_RPATH_USE_LINK_PATH=FALSE \
+                    -DCMAKE_INSTALL_PREFIX="${ROCM_PATH}" \
+                    -DCMAKE_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
+                    -DBUILD_FILE_REORG_BACKWARD_COMPATIBILITY=OFF \
+                    -DROCM_SYMLINK_LIBS=OFF \
+                    -DCPACK_PACKAGING_INSTALL_PREFIX="${ROCM_PATH}" \
+                    -DROCM_DISABLE_LDCONFIG=ON \
+                    -DROCM_PATH="${ROCM_PATH}" \
+                    -DCPACK_GENERATOR="${PKGTYPE^^}" \
+                    -DCMAKE_CXX_COMPILER="${ROCM_PATH}/llvm/bin/clang++" \
+                    -DCMAKE_C_COMPILER="${ROCM_PATH}/llvm/bin/clang" \
+                    ${LAUNCHER_FLAGS} \
+                    -DPROFILER_ONLY=ON \
+                    -DGPU_ARCH="${arch}" \
+                    "$COMPONENT_SRC"
+            fi
+
+            cmake --build . -- -j${PROC} package
+            cp ./*ckprofiler*.${PKGTYPE} $PACKAGE_DIR
+            rm -rf *
+        done
+    rm -rf _CPack_Packages/ && find -name '*.o' -delete
+
+    echo "Finished building Composable Kernel"
+    show_build_cache_stats
+}
+
 clean_miopen_ck() {
    echo "Cleaning MIOpen-CK build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
    rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
@@ -77,7 +176,7 @@ clean_miopen_ck() {
 stage2_command_args "$@"

 case $TARGET in
-    build) build_miopen_ck ;;
+    build) build_miopen_ck; build_miopen_ckProf;;
    outdir) print_output_directory ;;
    clean) clean_miopen_ck ;;
    *) die "Invalid target $TARGET" ;;
--- a/tools/rocm-build/build_dbgapi.sh
+++ b/tools/rocm-build/build_dbgapi.sh
@@ -15,7 +15,7 @@ printUsage() {
            type referred to by pkg_type"
    echo "  -h,  --help               Prints this help"
    echo "  -M,  --skip_man_pages     Do not build the 'docs' target"
-    echo "  -s,  --static             Component/Build does not support static builds just accepting this param & ignore. No effect of the param on this build"
+    echo "  -s,  --static             Supports static CI by accepting this param & not bailing out. No effect of the param though"
    echo
    echo "Possible values for <type>:"
    echo "  deb -> Debian format (default)"
@@ -65,7 +65,7 @@ do
                set_asan_env_vars
                set_address_sanitizer_on ;;
        (-s | --static)
-                ack_and_skip_static ;;
+                SHARED_LIBS="OFF" ;;
        (-o | --outdir)
                TARGET="outdir"; PKGTYPE=$2 ; ((CLEAN_OR_OUT|=2)) ; shift 1 ;;
        (-M | --skip_man_pages) DODOCSBUILD=false;;
--- a/tools/rocm-build/build_devicelibs.sh
+++ b/tools/rocm-build/build_devicelibs.sh
@@ -96,7 +96,6 @@ build_devicelibs() {
    if [ ! -e Makefile ]; then
        cmake $(rocm_cmake_params) \
              $(rocm_common_cmake_params) \
-              -DBUILD_SHARED_LIBS=$SHARED_LIBS \
              -DROCM_DEVICE_LIBS_BITCODE_INSTALL_LOC_NEW="$bitcodeInstallLoc/amdgcn" \
              -DROCM_DEVICE_LIBS_BITCODE_INSTALL_LOC_OLD="amdgcn" \
              "$DEVICELIBS_ROOT"
--- a/tools/rocm-build/build_hip_on_rocclr.sh
+++ b/tools/rocm-build/build_hip_on_rocclr.sh
@@ -24,15 +24,14 @@ printUsage() {

 source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
 MAKEOPTS="$DASH_JAY"
-PROJ_NAME="hip-on-rocclr"

-BUILD_PATH="$(getBuildPath $PROJ_NAME)"
+BUILD_PATH="$(getBuildPath hip-on-rocclr)"

 TARGET="build"
 PACKAGE_ROOT="$(getPackageRoot)"
 PACKAGE_SRC="$(getSrcPath)"
-PACKAGE_DEB="$PACKAGE_ROOT/deb/$PROJ_NAME"
-PACKAGE_RPM="$PACKAGE_ROOT/rpm/$PROJ_NAME"
+PACKAGE_DEB="$PACKAGE_ROOT/deb/hip-on-rocclr"
+PACKAGE_RPM="$PACKAGE_ROOT/rpm/hip-on-rocclr"
 PREFIX_PATH="$PACKAGE_ROOT"
 CORE_BUILD_DIR="$(getBuildPath hsa-core)"
 ROCclr_BUILD_DIR="$(getBuildPath rocclr)"
@@ -53,7 +52,7 @@ MAKETARGET="deb"
 PKGTYPE="deb"
 OFFLOAD_ARCH=()

-DEFAULT_OFFLOAD_ARCH=(gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942 gfx1030 gfx1031 gfx1033 gfx1034 gfx1035 gfx1100 gfx1101 gfx1102 gfx1200 gfx1201)
+DEFAULT_OFFLOAD_ARCH=(gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942 gfx1030 gfx1031 gfx1033 gfx1034 gfx1035 gfx1100 gfx1101 gfx1102 gfx1103)

 VALID_STR=`getopt -o hcrast:o: --long help,clean,release,address_sanitizer,static,offload-arch=:,outdir: -- "$@"`
 eval set -- "$VALID_STR"
@@ -169,11 +168,9 @@ build_catch_tests() {
   export ROCM_PATH="$ROCM_INSTALL_PATH"
   cmake \
         -DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \
-         -DBUILD_SHARED_LIBS=$SHARED_LIBS \
         -DHIP_PLATFORM=amd \
         -DROCM_PATH="$ROCM_INSTALL_PATH" \
         -DOFFLOAD_ARCH_STR="$OFFLOAD_ARCH_STR" \
-         $(rocm_cmake_params) \
         $(rocm_common_cmake_params) \
         -DCPACK_RPM_DEBUGINFO_PACKAGE=FALSE \
         -DCPACK_DEBIAN_DEBUGINFO_PACKAGE=FALSE \
@@ -209,8 +206,6 @@ package_samples() {
   export ROCM_PATH="$ROCM_INSTALL_PATH"
   cmake \
         -DROCM_PATH="$ROCM_INSTALL_PATH" \
-         -DBUILD_SHARED_LIBS=$SHARED_LIBS \
-         $(rocm_cmake_params) \
         $(rocm_common_cmake_params) \
         -DCMAKE_MODULE_PATH="$CMAKE_PATH/hip" \
         -DCPACK_INSTALL_PREFIX="$ROCM_INSTALL_PATH" \
--- a/tools/rocm-build/build_hipblas-common.sh
+++ b/tools/rocm-build/build_hipblas-common.sh
@@ -1,41 +0,0 @@
-#!/bin/bash
-
-set -ex
-
-source "$(dirname "${BASH_SOURCE[0]}")/compute_helper.sh"
-
-set_component_src hipBLAS-common
-
-build_hipblas-common() {
-    echo "Start build"
-
-    cd $COMPONENT_SRC
-    mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
-
-    init_rocm_common_cmake_params
-    cmake \
-        "${rocm_math_common_cmake_params[@]}" \
-        "$COMPONENT_SRC"
-    cmake --build "$BUILD_DIR" -- install
-    cmake --build "$BUILD_DIR" -- package
-
-    rm -rf _CPack_Packages/ && find -name '*.o' -delete
-    mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
-
-    show_build_cache_stats
-}
-
-clean_hipblas-common() {
-    echo "Cleaning hipBLAS-common build directory: ${BUILD_DIR} ${PACKAGE_DIR}"
-    rm -rf "$BUILD_DIR" "$PACKAGE_DIR"
-    echo "Done!"
-}
-
-stage2_command_args "$@"
-
-case $TARGET in
-    build) build_hipblas-common ;;
-    outdir) print_output_directory ;;
-    clean) clean_hipblas-common ;;
-    *) die "Invalid target $TARGET" ;;
-esac
--- a/tools/rocm-build/build_hipblas.sh
+++ b/tools/rocm-build/build_hipblas.sh
@@ -10,12 +10,6 @@ build_hipblas() {
    echo "Start build"

    CXX="g++"
-    CXX_FLAG=
-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        CXX="amdclang++"
-        CXX_FLAG="-DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++"
-    fi
-
    CLIENTS_SAMPLES="ON"
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
       set_asan_env_vars
@@ -23,8 +17,6 @@ build_hipblas() {
       CLIENTS_SAMPLES="OFF"
    fi

-    SHARED_LIBS="ON"
-
    echo "C compiler: $CC"
    echo "CXX compiler: $CXX"
    echo "FC compiler: $FC"
@@ -41,12 +33,11 @@ build_hipblas() {
        ${LAUNCHER_FLAGS} \
        "${rocm_math_common_cmake_params[@]}" \
        -DUSE_CUDA=OFF \
-        -DBUILD_SHARED_LIBS=$SHARED_LIBS \
        -DBUILD_CLIENTS_TESTS=ON \
        -DBUILD_CLIENTS_BENCHMARKS=ON \
        -DBUILD_CLIENTS_SAMPLES="${CLIENTS_SAMPLES}" \
+        -DCPACK_SET_DESTDIR=OFF \
        -DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
-        ${CXX_FLAG} \
        "$COMPONENT_SRC"

    cmake --build "$BUILD_DIR" -- -j${PROC}
--- a/tools/rocm-build/build_hipblaslt.sh
+++ b/tools/rocm-build/build_hipblaslt.sh
@@ -8,10 +8,6 @@ set_component_src hipBLASLt
 build_hipblaslt() {
    echo "Start build"

-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        ack_and_skip_static
-    fi
-
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
       set_asan_env_vars
       set_address_sanitizer_on
@@ -44,6 +40,7 @@ build_hipblaslt() {
        -DBUILD_CLIENTS_SAMPLES=ON \
        -DBUILD_CLIENTS_TESTS=ON \
        -DBUILD_CLIENTS_BENCHMARKS=ON \
+        -DCPACK_SET_DESTDIR=OFF \
        -DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
        "$COMPONENT_SRC"

--- a/tools/rocm-build/build_hipcc.sh
+++ b/tools/rocm-build/build_hipcc.sh
@@ -9,12 +9,10 @@ printUsage() {
    echo "Options:"
    echo "  -a,  --address_sanitizer  Enable address sanitizer"
    echo "  -c,  --clean              Clean output and delete all intermediate work"
+    echo "  -h,  --help               Prints this help"
    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of
                            type referred to by pkg_type"
    echo "  -r,  --release            Makes a release build"
-    echo "  -h,  --help               Prints this help"
-    echo
-    echo "  -s,  --static             Build static lib (.a).  build instead of dynamic/shared(.so) "
    echo

    return 0
@@ -27,31 +25,25 @@ PROJ_NAME=$API_NAME
 TARGET="build"
 MAKEOPTS="$DASH_JAY"
 BUILD_TYPE="Debug"
-SHARED_LIBS="ON"
+
 BUILD_DIR=$(getBuildPath $API_NAME)
 PACKAGE_DEB=$(getPackageRoot)/deb/$API_NAME
 PACKAGE_RPM=$(getPackageRoot)/rpm/$API_NAME
 PACKAGE_SRC="$(getSrcPath)"

-VALID_STR=`getopt -o hcraswo:p: --long help,clean,release,address_sanitizer,static,outdir,wheel:,package: -- "$@"`
-eval set -- "$VALID_STR"
-
-while true ;
+while [ "$1" != "" ];
 do
-    case "$1" in
+    case $1 in
        (-a  | --address_sanitizer)
            ack_and_ignore_asan ;;
        (-c  | --clean)
            TARGET="clean" ;;
-        (-o  | --outdir)
+        (-o | --outdir)
            TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 1 ;;
        (-r  | --release)
            BUILD_TYPE="RelWithDebInfo" ;;
-        (-s | --static)
-            SHARED_LIBS="OFF" ;;
        (-h  | --help)
            printUsage ; exit 0 ;;
-        --)     shift; break;;
        (*)
            echo "Invalid option [$1]" >&2; printUsage; exit 1 ;;
    esac
@@ -87,7 +79,6 @@ build() {
    fi

    cmake \
-        -DBUILD_SHARED_LIBS=$SHARED_LIBS \
        $(rocm_cmake_params) \
        $(rocm_common_cmake_params) \
        -DHIPCC_BACKWARD_COMPATIBILITY=OFF \
@@ -96,7 +87,7 @@ build() {
    popd

    cmake --build "$BUILD_DIR" -- $MAKEOPTS
-
+    
    echo "Installing and Packaging hipcc"
    cmake --build "$BUILD_DIR" -- $MAKEOPTS install
    cmake --build "$BUILD_DIR" -- $MAKEOPTS package
--- a/tools/rocm-build/build_hipcub.sh
+++ b/tools/rocm-build/build_hipcub.sh
@@ -9,10 +9,6 @@ set_component_src hipCUB
 build_hipcub() {
    echo "Start build"

-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        ack_and_skip_static
-    fi
-
    cd $COMPONENT_SRC
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
         set_asan_env_vars
@@ -26,7 +22,7 @@ build_hipcub() {
    if [ -n "$GPU_ARCHS" ]; then
        GPU_TARGETS="$GPU_ARCHS"
    else
-        GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1200;gfx1201"
+        GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
    fi

    CXX=$(set_build_variables CXX)\
--- a/tools/rocm-build/build_hipfft.sh
+++ b/tools/rocm-build/build_hipfft.sh
@@ -21,7 +21,7 @@ build_hipfft() {
    if [ -n "$GPU_ARCHS" ]; then
        GPU_TARGETS="$GPU_ARCHS"
    else
-        GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1200;gfx1201"
+        GPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
    fi

    cmake \
--- a/tools/rocm-build/build_hipfort.sh
+++ b/tools/rocm-build/build_hipfort.sh
@@ -8,18 +8,11 @@ set_component_src hipfort
 build_hipfort() {
    echo "Start build"

-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        ack_and_skip_static
-    fi
-
    mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
-    cmake \
-        -DCPACK_PACKAGING_INSTALL_PREFIX=${ROCM_PATH}\
+    cmake --trace \
        -DHIPFORT_INSTALL_DIR="${ROCM_PATH}" \
        -DCMAKE_PREFIX_PATH="${ROCM_PATH}/llvm;${ROCM_PATH}" \
        -DCMAKE_BUILD_TYPE=Release \
-        -DCPACK_SET_DESTDIR="OFF" \
-        -DCPACK_RPM_PACKAGE_RELOCATABLE="ON" \
        -DHIPFORT_COMPILER="${ROCM_PATH}/${ROCM_LLVMDIR}/bin/flang" \
        -DCMAKE_Fortran_FLAGS="-Mfree" \
        -DHIPFORT_COMPILER_FLAGS="-cpp" \
--- a/tools/rocm-build/build_hipify_clang.sh
+++ b/tools/rocm-build/build_hipify_clang.sh
@@ -22,12 +22,12 @@ printUsage() {
 TARGET="build"
 MAKEOPTS="$DASH_JAY"
 HIPIFY_CLANG_BUILD_DIR="$(getBuildPath $HIPIFY_ROOT)"
+HIPIFY_CLANG_DIST_DIR="$HIPIFY_CLANG_BUILD_DIR/dist"
 BUILD_TYPE="Debug"
 PACKAGE_ROOT="$(getPackageRoot)"
 HIPIFY_CLANG_HASH=""
 LIGHTNING_PATH="$ROCM_INSTALL_PATH/llvm"
 ADDRESS_SANITIZER=false
-INSTALL_CLANG_HEADERS="OFF"
 DEB_PATH="$(getDebPath hipify)"
 RPM_PATH="$(getRpmPath hipify)"
 SHARED_LIBS="ON"
@@ -53,7 +53,7 @@ do
                set_address_sanitizer_on
                ADDRESS_SANITIZER=true ; shift ;;
        (-s | --static)
-                ack_and_skip_static ;;
+                SHARED_LIBS="OFF" ; shift ;;
        (-o | --outdir)
                TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
        --)     shift; break;;
@@ -74,6 +74,7 @@ fi
 clean_hipify() {
    echo "Cleaning hipify-clang"
    rm -rf "$HIPIFY_CLANG_BUILD_DIR"
+    rm -rf "$HIPIFY_CLANG_DIST_DIR"
    rm -rf "$DEB_PATH"
    rm -rf "$RPM_PATH"
 }
@@ -100,16 +101,16 @@ package_hipify() {
 build_hipify() {
    echo "Building hipify-clang binaries"
    mkdir -p "$HIPIFY_CLANG_BUILD_DIR"
+    mkdir -p "$HIPIFY_CLANG_DIST_DIR"

    pushd "$HIPIFY_CLANG_BUILD_DIR"
    cmake \
        -DCMAKE_BUILD_TYPE="$BUILD_TYPE" \
        $(rocm_common_cmake_params) \
-        -DCMAKE_INSTALL_PREFIX="$ROCM_INSTALL_PATH" \
+        -DCMAKE_INSTALL_PREFIX="$HIPIFY_CLANG_DIST_DIR" \
        -DCPACK_PACKAGING_INSTALL_PREFIX=$ROCM_INSTALL_PATH \
        -DCMAKE_PREFIX_PATH="$LIGHTNING_PATH" \
        -DADDRESS_SANITIZER="$ADDRESS_SANITIZER" \
-        -DHIPIFY_INSTALL_CLANG_HEADERS="$INSTALL_CLANG_HEADERS" \
        $HIPIFY_ROOT

    cmake --build . -- $MAKEOPTS install
--- a/tools/rocm-build/build_hiprand.sh
+++ b/tools/rocm-build/build_hiprand.sh
@@ -21,11 +21,6 @@ done
 build_hiprand() {
    echo "Start build"

-    SHARED_LIBS="ON"
-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        SHARED_LIBS="OFF"
-    fi
-
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
         set_asan_env_vars
         set_address_sanitizer_on
@@ -39,20 +34,17 @@ build_hiprand() {

    mkdir "$BUILD_DIR" && cd "$BUILD_DIR"

-    init_rocm_common_cmake_params
-
    if [ -n "$GPU_ARCHS" ]; then
        GPU_TARGETS="$GPU_ARCHS"
    else
-        GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1200;gfx1201"
+        GPU_TARGETS="gfx908:xnack-;gfx90a:xnack-;gfx90a:xnack+;gfx940;gfx941;gfx942;gfx1030;gfx1100;gfx1101"
    fi

    CXX=$(set_build_variables CXX)\
    cmake \
        ${LAUNCHER_FLAGS} \
-	    "${rocm_math_common_cmake_params[@]}" \
+        $(rocm_common_cmake_params) \
        -DAMDGPU_TARGETS=${GPU_TARGETS} \
-        -DBUILD_SHARED_LIBS=$SHARED_LIBS \
        -DBUILD_TEST=ON \
        -DBUILD_BENCHMARK=ON \
        -DBUILD_CRUSH_TEST=ON \
@@ -68,6 +60,7 @@ build_hiprand() {

    rm -rf _CPack_Packages/  && find -name '*.o' -delete
    mkdir -p $PACKAGE_DIR && cp ${BUILD_DIR}/*.${PKGTYPE} $PACKAGE_DIR
+
 }

 clean_hiprand() {
--- a/tools/rocm-build/build_hipsolver.sh
+++ b/tools/rocm-build/build_hipsolver.sh
@@ -9,23 +9,14 @@ set_component_src hipSOLVER
 build_hipsolver() {
    echo "Start build"

-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        CXX_FLAG="-DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++"
-    fi
-
    cd $COMPONENT_SRC

-    CXX="amdclang++"
+    CXX="g++"
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
       set_asan_env_vars
       set_address_sanitizer_on
    fi

-    SHARED_LIBS="ON"
-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        SHARED_LIBS="OFF"
-    fi
-
    echo "C compiler: $CC"
    echo "CXX compiler: $CXX"
    echo "FC compiler: $FC"
@@ -39,15 +30,13 @@ build_hipsolver() {
    init_rocm_common_cmake_params
    cmake \
        -DUSE_CUDA=OFF \
-	-DCMAKE_CXX_COMPILER=${CXX} \
        ${LAUNCHER_FLAGS} \
        "${rocm_math_common_cmake_params[@]}" \
-        -DBUILD_SHARED_LIBS=$SHARED_LIBS \
        -DBUILD_CLIENTS_TESTS=ON \
        -DBUILD_CLIENTS_BENCHMARKS=ON \
        -DBUILD_CLIENTS_SAMPLES=ON \
+        -DCPACK_SET_DESTDIR=OFF \
        -DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
-        ${CXX_FLAG} \
        "$COMPONENT_SRC"

    cmake --build "$BUILD_DIR" -- -j${PROC}
--- a/tools/rocm-build/build_hipsparse.sh
+++ b/tools/rocm-build/build_hipsparse.sh
@@ -10,26 +10,14 @@ set_component_src hipSPARSE
 build_hipsparse() {
    echo "Start build"

-    CXX="g++"
-    CXX_FLAG=
-
-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        CXX="${ROCM_PATH}/llvm/bin/clang++"
-        CXX_FLAG="-DCMAKE_CXX_COMPILER=${ROCM_PATH}/llvm/bin/clang++"
-    fi
-
    cd $COMPONENT_SRC

+    CXX="g++"
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
        set_asan_env_vars
        set_address_sanitizer_on
    fi

-    SHARED_LIBS="ON"
-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        SHARED_LIBS="OFF"
-    fi
-
    echo "C compiler: $CC"
    echo "CXX compiler: $CXX"

@@ -37,16 +25,15 @@ build_hipsparse() {
    init_rocm_common_cmake_params

    cmake \
+        -DCPACK_SET_DESTDIR=OFF \
        ${LAUNCHER_FLAGS} \
        "${rocm_math_common_cmake_params[@]}" \
-        -DBUILD_SHARED_LIBS=$SHARED_LIBS \
        -DUSE_CUDA=OFF  \
        -DBUILD_CLIENTS_SAMPLES=ON \
        -DBUILD_CLIENTS_TESTS=ON \
        -DCMAKE_INSTALL_PREFIX=${ROCM_PATH} \
        -DCMAKE_MODULE_PATH="${ROCM_PATH}/lib/cmake/hip;${ROCM_PATH}/hip/cmake"  \
        -DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
-        ${CXX_FLAG} \
        "$COMPONENT_SRC"

    cmake --build "$BUILD_DIR" -- -j${PROC}
--- a/tools/rocm-build/build_hipsparselt.sh
+++ b/tools/rocm-build/build_hipsparselt.sh
@@ -21,10 +21,6 @@ done
 build_hipsparselt() {
    echo "Start build"

-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        ack_and_skip_static
-    fi
-
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
       set_asan_env_vars
       set_address_sanitizer_on
@@ -54,6 +50,7 @@ build_hipsparselt() {
        -DBUILD_CLIENTS_SAMPLES=ON \
        -DBUILD_CLIENTS_TESTS=ON \
        -DBUILD_CLIENTS_BENCHMARKS=ON \
+        -DCPACK_SET_DESTDIR=OFF \
        -DCMAKE_INSTALL_PREFIX=${ROCM_PATH} \
        -DBUILD_ADDRESS_SANITIZER="${ADDRESS_SANITIZER}" \
        "$COMPONENT_SRC"
--- a/tools/rocm-build/build_hiptensor.sh
+++ b/tools/rocm-build/build_hiptensor.sh
@@ -9,10 +9,6 @@ set_component_src hipTensor
 build_hiptensor() {
    echo "Start build hipTensor"

-    if [ "${ENABLE_STATIC_BUILDS}" == "true" ]; then
-        ack_and_skip_static
-    fi
-
    if [ "${ENABLE_ADDRESS_SANITIZER}" == "true" ]; then
        set_asan_env_vars
        set_address_sanitizer_on
@@ -22,6 +18,7 @@ build_hiptensor() {
    mkdir -p "$BUILD_DIR" && cd "$BUILD_DIR"
    init_rocm_common_cmake_params

+
    if [ -n "$GPU_ARCHS" ]; then
        GPU_TARGETS="$GPU_ARCHS"
    else
--- a/tools/rocm-build/build_hsa.sh
+++ b/tools/rocm-build/build_hsa.sh
@@ -0,0 +1,135 @@
+#!/bin/bash
+
+source "$(dirname "${BASH_SOURCE}")/compute_utils.sh"
+
+printUsage() {
+    echo
+    echo "Usage: $(basename "${BASH_SOURCE}") [options ...] [make options]"
+    echo
+    echo "Options:"
+    echo "  -c,  --clean              Clean output and delete all intermediate work"
+    echo "  -r,  --release            Make a release build instead of a debug build"
+    echo "  -a,  --address_sanitizer  Enable address sanitizer"
+    echo "  -o,  --outdir <pkg_type>  Print path of output directory containing packages of type referred to by pkg_type"
+    echo "  -h,  --help               Prints this help"
+    echo "  -s,  --static             Build static lib (.a).  build instead of dynamic/shared(.so) "
+    echo
+    echo
+
+    return 0
+}
+
+TARGET="build"
+PACKAGE_ROOT="$(getPackageRoot)"
+PACKAGE_SRC="$(getSrcPath)"
+PACKAGE_LIB="$(getLibPath)"
+PACKAGE_BIN="$(getBinPath)"
+PACKAGE_DEB="$(getPackageRoot)/deb/rocr"
+PACKAGE_RPM="$(getPackageRoot)/rpm/rocr"
+MAKEARG=""
+CORE_BUILD_DIR="$(getBuildPath hsa-core)"
+ROCR_DEV_BUILD_DIR="$(getBuildPath hsa-rocr-dev)"
+PREFIX_PATH="$PACKAGE_ROOT"
+BUILD_TYPE="Debug"
+SHARED_LIBS="ON"
+CLEAN_OR_OUT=0;
+MAKETARGET="deb"
+PKGTYPE="deb"
+
+unset HIP_DEVICE_LIB_PATH
+unset ROCM_PATH
+
+VALID_STR=`getopt -o hcraso: --long help,clean,release,static,address_sanitizer,outdir: -- "$@"`
+eval set -- "$VALID_STR"
+
+while true ;
+do
+    case "$1" in
+        (-h | --help)
+                printUsage ; exit 0;;
+        (-c | --clean)
+                TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
+        (-r | --release)
+                BUILD_TYPE="RelWithDebInfo" ; shift ;;
+        (-a | --address_sanitizer)
+                set_asan_env_vars
+                set_address_sanitizer_on ; shift ;;
+        (-s | --static)
+                SHARED_LIBS="OFF" ; shift ;;
+        (-o | --outdir)
+                TARGET="outdir"; PKGTYPE=$2 ; OUT_DIR_SPECIFIED=1 ; ((CLEAN_OR_OUT|=2)) ; shift 2 ;;
+        --)     shift; break;;
+        (*)
+                echo " This should never come but just incase : UNEXPECTED ERROR Parm : [$1] ">&2 ; exit 20;;
+    esac
+
+done
+
+RET_CONFLICT=1
+check_conflicting_options $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+if [ $RET_CONFLICT -ge 30 ]; then
+   print_vars $API_NAME $TARGET $BUILD_TYPE $SHARED_LIBS $CLEAN_OR_OUT $PKGTYPE $MAKETARGET
+   exit $RET_CONFLICT
+fi
+
+clean_hsa() {
+    echo "Cleaning HSA"
+
+    rm -rf "$CORE_BUILD_DIR"
+    rm -rf "$PACKAGE_RPM"
+    rm -rf "$PACKAGE_DEB"
+    rm -f  "$PACKAGE_ROOT"/lib/libhsa-runtime*
+    rm -rf "$PACKAGE_ROOT/lib/cmake/hsa-runtime64"
+    rm -rf "$PACKAGE_ROOT/include/hsa"
+    rm -rf "$PACKAGE_ROOT/share/doc/hsa-runtime64"
+    rm -rf "$PACKAGE_ROOT/hsa"
+}
+
+
+build_hsa_core() {
+    echo "Build HSA"
+    local coreMakeOpts="$DASH_JAY -C $CORE_BUILD_DIR"
+
+    echo "$HSA_CORE_ROOT"
+
+    if [ ! -d "$CORE_BUILD_DIR" ]; then
+        mkdir -p "$CORE_BUILD_DIR"
+        pushd "$CORE_BUILD_DIR"
+        print_lib_type $SHARED_LIBS
+
+        cmake $(rocm_cmake_params) \
+            -DBUILD_SHARED_LIBS=$SHARED_LIBS \
+            -DENABLE_LDCONFIG=OFF \
+            $(rocm_common_cmake_params) \
+            -DADDRESS_SANITIZER="$ADDRESS_SANITIZER" \
+            "$HSA_CORE_ROOT"
+        popd
+    fi
+    time cmake --build "$CORE_BUILD_DIR" -- $coreMakeOpts
+    time cmake --build "$CORE_BUILD_DIR" -- $coreMakeOpts install
+    time cmake --build "$CORE_BUILD_DIR" -- $coreMakeOpts package
+
+    copy_if DEB "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_DEB" $CORE_BUILD_DIR/hsa-rocr*.deb
+    copy_if RPM "${CPACKGEN:-"DEB;RPM"}" "$PACKAGE_RPM" $CORE_BUILD_DIR/hsa-rocr*.rpm
+}
+
+print_output_directory() {
+    case ${PKGTYPE} in
+        ("deb")
+            echo ${PACKAGE_DEB};;
+        ("rpm")
+            echo ${PACKAGE_RPM};;
+        (*)
+            echo "Invalid package type \"${PKGTYPE}\" provided for -o" >&2; exit 1;;
+    esac
+    exit
+}
+
+case $TARGET in
+    (clean) clean_hsa ;;
+    (build) build_hsa_core;;
+    (outdir) print_output_directory ;;
+    (*) die "Invalid target $TARGET" ;;
+esac
+
+echo "Operation complete"
--- a/tools/rocm-build/build_lightning.sh
+++ b/tools/rocm-build/build_lightning.sh
@@ -11,6 +11,7 @@ printUsage() {
    echo "Usage: $(basename "${BASH_SOURCE}") [options ...]"
    echo
    echo "Options:"
+    echo "  -t,  --alt                   Build the 'alt' variant"
    echo "  -c,  --clean                 Clean output and delete all intermediate work"
    echo "  -d,  --debug                 Build a debug version of llvm (excludes packaging)"
    echo "  -r,  --release               Build a release version of the package"
@@ -32,26 +33,35 @@ printUsage() {
    return 0
 }

-PROJ_NAME="lightning"
 ROCM_LLVM_LIB_RPATH='\$ORIGIN'
 ROCM_LLVM_EXE_RPATH='\$ORIGIN/../lib:\$ORIGIN/../../../lib'

 PACKAGE_OUT="$(getPackageRoot)"
-BUILD_PATH="$(getBuildPath $PROJ_NAME)"
-DEB_PATH="$(getDebPath $PROJ_NAME)"
-RPM_PATH="$(getRpmPath $PROJ_NAME)"
+
+BUILD_PATH="$(getBuildPath lightning)"
+DEB_PATH="$(getDebPath lightning)"
+RPM_PATH="$(getRpmPath lightning)"
 INSTALL_PATH="${ROCM_INSTALL_PATH}/lib/llvm"
 LLVM_ROOT_LCL="${LLVM_ROOT}"
+ROCM_WHEEL_DIR="${BUILD_PATH}/_wheel"

 TARGET="all"
 MAKEOPTS="$DASH_JAY"
 BUILD_TYPE="Release"
-ENABLE_ASSERTIONS=0
+case "${JOB_NAME}" in
+   ( *"rel"*                  | \
+     *"afar"*                 | \
+     *"nfar"*                 )
+       ENABLE_ASSERTIONS=0 ;;
+     ( * )
+       ENABLE_ASSERTIONS=1 ;;
+esac
 SHARED_LIBS="ON"

 BUILD_LLVM_DYLIB="OFF"

 FLANG_NEW=0
+BUILD_ALT=0
 CLEAN_OR_OUT=0;
 PKGTYPE="deb"
 MAKETARGET="deb"
@@ -64,10 +74,10 @@ BUILD_MANPAGES="ON"
 STATIC_FLAG=

 SANITIZER_AMDGPU=1
-    HSA_INC_PATH="$WORK_ROOT/ROCR-Runtime/runtime/hsa-runtime/inc/"
-COMGR_INC_PATH="$COMGR_ROOT/include"
+HSA_INC_PATH="$WORK_ROOT/ROCR-Runtime/src/inc"
+COMGR_INC_PATH="$WORK_ROOT/llvm-project/amd/comgr/include"

-VALID_STR=`getopt -o hcV:v:draAswlo:BPNM --long help,clean,assert_llvm_ver_major:,assert_llvm_ver_minor:,debug,release,address_sanitizer,no_address_sanitizer,static,build_llvm_static,wheel,build,package,skip_lit_tests,skip_man_pages,outdir: -- "$@"`
+VALID_STR=`getopt -o htcV:v:draAswlo:BPNM --long help,alt,clean,assert_llvm_ver_major:,assert_llvm_ver_minor:,debug,release,address_sanitizer,no_address_sanitizer,static,build_llvm_static,wheel,build,package,skip_lit_tests,skip_man_pages,outdir: -- "$@"`
 eval set -- "$VALID_STR"

 set_dwarf_version(){
@@ -86,10 +96,11 @@ set_dwarf_version(){

 while true ;
 do
-    #echo "processing $1"
    case "$1" in
        (-h | --help)
                printUsage ; exit 0;;
+        (-t | --alt)
+                BUILD_ALT=1 ; shift ;;
        (-c | --clean)
                TARGET="clean" ; ((CLEAN_OR_OUT|=1)) ; shift ;;
        (-V | --assert_llvm_ver_major)
@@ -104,7 +115,7 @@ do
                set_dwarf_version
                SANITIZER_AMDGPU=1 ;
                HSA_INC_PATH="$WORK_ROOT/hsa/runtime/opensrc/hsa-runtime/inc" ;
-                COMGR_INC_PATH="$COMGR_ROOT/include" ; shift ;;
+                COMGR_INC_PATH="$WORK_ROOT/external/llvm-project/amd/comgr/include" ; shift ;;
        (-A | --no_address_sanitizer)
                SANITIZER_AMDGPU=0 ;
                unset HSA_INC_PATH ;
@@ -144,11 +155,24 @@ LLVM_PROJECTS="clang;lld;clang-tools-extra"
 ENABLE_RUNTIMES="compiler-rt;libunwind"
 BOOTSTRAPPING_BUILD_LIBCXX=0
 BUILD_AMDCLANG="ON"
-
-ENABLE_RUNTIMES="$ENABLE_RUNTIMES;libcxx;libcxxabi"
-BOOTSTRAPPING_BUILD_LIBCXX=1
+if [ $BUILD_ALT -eq 1 ]; then
+    BUILD_PATH="${BUILD_PATH}-alt"
+    DEB_PATH="${DEB_PATH}-alt"
+    RPM_PATH="${RPM_PATH}-alt"
+    INSTALL_PATH="${INSTALL_PATH}/alt"
+    LLVM_ROOT_LCL="${LLVM_ALT_ROOT}"
+    BUILD_AMDCLANG="OFF"
+    BUILD_MANPAGES="OFF"
+    SANITIZER_AMDGPU=0
+    unset HSA_INC_PATH
+    unset COMGR_INC_PATH
+else
+    ENABLE_RUNTIMES="$ENABLE_RUNTIMES;libcxx;libcxxabi";
+    BOOTSTRAPPING_BUILD_LIBCXX=1
+fi

 clean_lightning() {
+    rm -rf "$ROCM_WHEEL_DIR"
    rm -rf "$BUILD_PATH"
    rm -rf "$DEB_PATH"
    rm -rf "$RPM_PATH"
@@ -164,14 +188,22 @@ setup_llvm_info() {
    local LLVM_URL_BRANCH

    if [[ "${JOB_NAME}" == *rel* ]]; then
+      if [ $BUILD_ALT -eq 1 ]; then
+        LLVM_URL_BRANCH=$(git rev-parse HEAD)
+      else
        LLVM_URL_NAME="https://github.com/RadeonOpenCompute/llvm-project"
        LLVM_BRANCH_NAME="roc-${ROCM_VERSION}"
        LLVM_URL_BRANCH="${LLVM_URL_NAME} ${LLVM_BRANCH_NAME}"
+      fi
    else
-        LLVM_REMOTE_NAME=$(git remote)
-        LLVM_URL_NAME=$(git config --get remote."${LLVM_REMOTE_NAME}".url)
+      LLVM_REMOTE_NAME=$(git remote)
+      LLVM_URL_NAME=$(git config --get remote."${LLVM_REMOTE_NAME}".url)
+      if [ $BUILD_ALT -eq 1 ]; then
+        LLVM_BRANCH_NAME=$(repo manifest | sed -n 's/.*path="external\/llvm-project-alt\/llvm-project".* upstream="\([^"]*\)".*/\1/p' )
+      else
        LLVM_BRANCH_NAME=$(repo manifest | sed -n 's/.*path="external\/llvm-project".* upstream="\([^"]*\)".*/\1/p' )
-        LLVM_URL_BRANCH="${LLVM_URL_NAME} ${LLVM_BRANCH_NAME}"
+      fi
+      LLVM_URL_BRANCH="${LLVM_URL_NAME} ${LLVM_BRANCH_NAME}"
    fi

    LLVM_COMMIT_GITDATE=$(git show -s --format=@%ct | xargs | date -f - --utc +%y%U%w)
@@ -251,27 +283,24 @@ build_lightning() {
    mkdir -p "$BUILD_PATH"
    pushd "$BUILD_PATH"

-    eval EXTRA_LLVM_CMAKE_PARAMS_ARRAY=($EXTRA_LLVM_CMAKE_PARAMS)
-
    if [ ! -e Makefile ]; then
        echo "Building LLVM CMake environment"
-        LLVM_PROJECTS="$LLVM_PROJECTS;mlir"
-        if [ -e "$LLVM_ROOT_LCL/../flang/EnableFlangBuild" ]; then
+        if [ -e "$LLVM_ROOT_LCL/../flang/AFARrelease" ]; then
            FLANG_NEW=1
-            LLVM_PROJECTS="$LLVM_PROJECTS;flang"
+            LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
            ENABLE_RUNTIMES="$ENABLE_RUNTIMES;openmp";
        else
-            if [[ "${JOB_NAME}" != *afar* ]] && [ -e "$LLVM_ROOT_LCL/../flang/DoROCmRelease" ]; then
-              FLANG_NEW=1
-              LLVM_PROJECTS="$LLVM_PROJECTS;flang"
-            else
-                echo "NOT building project flang"
-            fi
+
+          if [[ "${JOB_NAME}" != *afar* ]] && [ -e "$LLVM_ROOT_LCL/../flang/DoROCmRelease" ]; then
+            FLANG_NEW=1
+            LLVM_PROJECTS="$LLVM_PROJECTS;flang;mlir"
+          else
+            echo "NOT building project flang"
+          fi
        fi
        set -x
        cmake $(rocm_cmake_params) ${GEN_NINJA} \
              ${STATIC_FLAG} \
-              ${PYTHON_VERSION_WORKAROUND} \
              -DCMAKE_INSTALL_PREFIX="$INSTALL_PATH" \
              -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" \
              -DLLVM_ENABLE_PROJECTS="$LLVM_PROJECTS" \
@@ -313,7 +342,6 @@ build_lightning() {
              -DCLANG_LINK_FLANG_LEGACY=ON \
              -DCMAKE_CXX_STANDARD=17 \
              -DFLANG_INCLUDE_DOCS=OFF \
-              "${EXTRA_LLVM_CMAKE_PARAMS_ARRAY[@]}" \
              "$LLVM_ROOT_LCL"
        set +x
        echo "CMake complete"
@@ -330,11 +358,28 @@ build_lightning() {
    echo "End Workaround for race condition"
    cmake --build . -- $MAKEOPTS

+    case "$DISTRO_ID" in
+    (rhel*|centos*)
+       RHEL_BUILD=1
+       ;;
+    (*)
+       RHEL_BUILD=0
+       ;;
+     esac
+
    if [ $SKIP_LIT_TESTS -eq 0 ]; then
-        if [ $RHEL_BUILD -eq 1 ]; then
-            cmake --build . -- $MAKEOPTS check-lld check-mlir
-        elif [ "$DISTRO_NAME" != "sles" ]; then
-            cmake --build . -- $MAKEOPTS check-llvm check-clang check-lld check-mlir
+        if [ $RHEL_BUILD -eq 1 ] && [ $BUILD_ALT != 1 ]; then
+            if [ $FLANG_NEW -eq 1 ]; then
+                cmake --build . -- $MAKEOPTS check-lld check-mlir
+            else
+                cmake --build . -- $MAKEOPTS check-lld
+            fi
+        elif [ "$DISTRO_NAME" != "sles" ] && [ $BUILD_ALT != 1 ]; then
+            if [ $FLANG_NEW -eq 1 ]; then
+                cmake --build . -- $MAKEOPTS check-llvm check-clang check-lld check-mlir
+            else
+                cmake --build . -- $MAKEOPTS check-llvm check-clang check-lld
+            fi
        fi
    fi
    cmake --build . -- $MAKEOPTS clang-tidy
@@ -351,15 +396,23 @@ package_lightning_dynamic(){

    get_llvm_version
    local llvmParsedVersion="${LLVM_VERSION_MAJOR}.${LLVM_VERSION_MINOR}.${LLVM_VERSION_PATCH}"
-    local packageName="rocm-llvm"
-    local packageSummary="ROCm compiler"
-    local packageSummaryLong="ROCm compiler based on LLVM $llvmParsedVersion"
-    local installPath="$ROCM_INSTALL_PATH/lib/llvm/"

-    if [ "$BUILD_LLVM_DYLIB" == "ON" ] ; then
-      local packageNameCore="rocm-llvm-core"
-      local packageSummaryCore="ROCm core compiler dylibs"
-      local packageSummaryLongCore="ROCm compiler based on LLVM $llvmParsedVersion"
+    if [ $BUILD_ALT -eq 1 ]; then
+        local packageName="rocm-llvm-alt"
+        local packageSummary="Proprietary ROCm compiler"
+        local packageSummaryLong="ROCm compiler, including proprietary optimizations, based on LLVM $llvmParsedVersion"
+        local installPath="$ROCM_INSTALL_PATH/lib/llvm/alt"
+    else
+        local packageName="rocm-llvm"
+        local packageSummary="ROCm compiler"
+        local packageSummaryLong="ROCm compiler based on LLVM $llvmParsedVersion"
+        local installPath="$ROCM_INSTALL_PATH/lib/llvm/"
+
+        if [ "$BUILD_LLVM_DYLIB" == "ON" ] ; then
+          local packageNameCore="rocm-llvm-core"
+          local packageSummaryCore="ROCm core compiler dylibs"
+          local packageSummaryLongCore="ROCm compiler based on LLVM $llvmParsedVersion"
+        fi
    fi

    local packageArch="amd64"
@@ -380,6 +433,9 @@ package_lightning_dynamic(){
    local prermFile="$packageDeb/DEBIAN/prerm"
    local specFile="$packageDir/$packageName.spec"
    local debDependencies="python3, libc6, libstdc++6|libstdc++8, libstdc++-5-dev|libstdc++-7-dev|libstdc++-11-dev, libgcc-5-dev|libgcc-7-dev|libgcc-11-dev, rocm-core"
+    if [ $BUILD_ALT -eq 1 ]; then
+        debDependencies="${debDependencies}, rocm-llvm"
+    fi
    local debRecommends="gcc, g++, gcc-multilib, g++-multilib"

    local packageRpm="$packageDir/rpm"
@@ -452,33 +508,42 @@ package_lightning_dynamic(){
          debDependencies="${debDependencies}, ${packageNameCore}"
        fi

-        cp -r "$LLVM_ROOT_LCL/LICENSE.TXT" "$packageDeb/$licenseDir"
+        if [ $BUILD_ALT -eq 0 ] ; then
+          cp -r "$LLVM_ROOT_LCL/LICENSE.TXT" "$packageDeb/$licenseDir"
+        else
+          cp -r "$LLVM_PROJECT_ALT_ROOT/EULA" "$packageDeb/$licenseDir"
+          cp -r "$LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt" "$packageDeb/$licenseDir"
+        fi
        cp -r "$distBin" "$packageDeb/$installPath/bin"
        cp -r "$distInc" "$packageDeb/$installPath/include"
        cp -r "$distLib" "$packageDeb/$installPath/lib"
        if [ "$BUILD_MANPAGES" == "ON" ]; then
-            for i in "${man_pages[@]}"; do
-                gzip -f "$distMan/man1/$i"
-            done
-            if [ -f "$distMan/man1/clang.1.gz" ]; then
-                for i in "${amd_man_pages[@]}"; do
-                    ln -sf "clang.1.gz" "$distMan/man1/$i"
+            if [ $BUILD_ALT -eq 0 ]; then
+                for i in "${man_pages[@]}"; do
+                    gzip -f "$distMan/man1/$i"
                done
+                if [ -f "$distMan/man1/clang.1.gz" ]; then
+                    for i in "${amd_man_pages[@]}"; do
+                        ln -sf "clang.1.gz" "$distMan/man1/$i"
+                    done
+                fi
            fi
        fi
        cp -r "$distMan" "$packageDeb/$installPath/share"

-        touch "$postinstFile" "$prermFile"
-        echo "mkdir -p \"$ROCM_INSTALL_PATH/bin\"" >> $postinstFile
-        for i in "${amd_compiler_commands[@]}"; do
-            if [ -f "$packageDeb/$installPath/bin/$i" ]; then
-                echo "ln -s \"../lib/llvm/bin/$i\" \"$ROCM_INSTALL_PATH/bin/$i\"" >> $postinstFile
-                echo "rm -f \"$ROCM_INSTALL_PATH/bin/$i\"" >> $prermFile
-            fi
-        done
-        echo "rmdir --ignore-fail-on-non-empty \"$ROCM_INSTALL_PATH/bin\"" >> $prermFile
-        chmod 0555 "$postinstFile" "$prermFile"
-        cp -P "$backwardsCompatibleSymlink" "$packageDeb/$ROCM_INSTALL_PATH"
+        if [ $BUILD_ALT -eq 0 ]; then
+            touch "$postinstFile" "$prermFile"
+            echo "mkdir -p \"$ROCM_INSTALL_PATH/bin\"" >> $postinstFile
+            for i in "${amd_compiler_commands[@]}"; do
+                if [ -f "$packageDeb/$installPath/bin/$i" ]; then
+                    echo "ln -s \"../lib/llvm/bin/$i\" \"$ROCM_INSTALL_PATH/bin/$i\"" >> $postinstFile
+                    echo "rm -f \"$ROCM_INSTALL_PATH/bin/$i\"" >> $prermFile
+                fi
+            done
+            echo "rmdir --ignore-fail-on-non-empty \"$ROCM_INSTALL_PATH/bin\"" >> $prermFile
+            chmod 0555 "$postinstFile" "$prermFile"
+            cp -P "$backwardsCompatibleSymlink" "$packageDeb/$ROCM_INSTALL_PATH"
+        fi

        echo "Package: $packageName"  > $controlFile
        echo "Architecture: $packageArch" >> $controlFile
@@ -548,12 +613,16 @@ package_lightning_dynamic(){
        echo "Release:    ${JOB_DESIGNATOR}${SLES_BUILD_ID_PREFIX}${BUILD_ID}%{?dist}" >> $specFile
        echo "Summary:    $packageSummary" >> $specFile
        echo "Group:      System Environment/Libraries" >> $specFile
-        echo "License:    ASL 2.0 with exceptions" >> $specFile
+        if [ $BUILD_ALT -eq 1 ]; then
+          echo "License:    AMD Proprietary" >> $specFile
+        else
+          echo "License:    ASL 2.0 with exceptions" >> $specFile
+        fi
        echo "Requires:   $rpmRequires" >> $specFile
-        # The following is commented as Centos 7 has a version of rpm
-        # that does not understand it. When we no longer support Centos 7
-        # then we should have a correct recommends line.
-        #echo "Recommends: $rpmRecommends" >> $specFile
+
+        if [ $BUILD_ALT -eq 1 ]; then
+          echo "%define _build_id_links none" >> $specFile
+        fi

        echo "%description" >> $specFile
        echo "$packageSummaryLong" >> $specFile
@@ -569,20 +638,28 @@ package_lightning_dynamic(){
        echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/share/man" >> $specFile
        echo "mkdir -p  \$RPM_BUILD_ROOT/$licenseDir" >> $specFile

-        echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
-        echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
+        if [ $BUILD_ALT -eq 0 ]; then
+          echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
+          echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
+        else
+          echo "cp -R $LLVM_PROJECT_ALT_ROOT/EULA \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
+          echo "cp -R $LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
+        fi
+
        echo "cp -R $distBin \$RPM_BUILD_ROOT/$installPath" >> $specFile
        echo "cp -R $distInc \$RPM_BUILD_ROOT/$installPath" >> $specFile
        echo "cp -R $distLib \$RPM_BUILD_ROOT/$installPath" >> $specFile
        if [ "$BUILD_MANPAGES" == "ON" ]; then
-            for i in "${man_pages[@]}"; do
-                echo "gzip -f $distMan/man1/$i" >> $specFile
-            done
-            if [ -f "$distMan/man1/clang.1.gz" ]; then
-                for i in "${amd_man_pages[@]}"; do
-                    echo "ln -sf clang.1.gz \"$distMan/man1/$i\"" >> $specFile
-                done
-            fi
+          if [ $BUILD_ALT -eq 0 ]; then
+              for i in "${man_pages[@]}"; do
+                  echo "gzip -f $distMan/man1/$i" >> $specFile
+              done
+              if [ -f "$distMan/man1/clang.1.gz" ]; then
+                  for i in "${amd_man_pages[@]}"; do
+                      echo "ln -sf clang.1.gz \"$distMan/man1/$i\"" >> $specFile
+                  done
+              fi
+          fi
        fi
        echo "cp -R $distMan \$RPM_BUILD_ROOT/$installPath/share" >> $specFile

@@ -599,20 +676,25 @@ package_lightning_dynamic(){
        echo "$ROCM_INSTALL_PATH" >> $specFile

        echo "%post" >> $specFile
-        echo "mkdir -p \"$ROCM_INSTALL_PATH/bin\"" >> $specFile
-        for i in "${amd_compiler_commands[@]}"; do
-            if [ -f "$distBin/$i" ]; then
-                echo "ln -sf ../lib/llvm/bin/$i \"$ROCM_INSTALL_PATH/bin/$i\"" >> $specFile
-            fi
-        done
+        if [ $BUILD_ALT -eq 0 ]; then
+            echo "mkdir -p \"$ROCM_INSTALL_PATH/bin\"" >> $specFile
+            for i in "${amd_compiler_commands[@]}"; do
+                if [ -f "$distBin/$i" ]; then
+                    echo "ln -sf ../lib/llvm/bin/$i \"$ROCM_INSTALL_PATH/bin/$i\"" >> $specFile
+                fi
+            done
+        fi

        echo "%preun" >> $specFile
-        for i in "${amd_compiler_commands[@]}"; do
-            if [ -f "$distBin/$i" ]; then
-                echo "rm -f \"$ROCM_INSTALL_PATH/bin/$i\"" >> $specFile
-            fi
-        done
-        echo "rmdir --ignore-fail-on-non-empty \"$ROCM_INSTALL_PATH/bin\"" >> $specFile
+        if [ $BUILD_ALT -eq 0 ]; then
+            for i in "${amd_compiler_commands[@]}"; do
+                if [ -f "$distBin/$i" ]; then
+                    echo "rm -f \"$ROCM_INSTALL_PATH/bin/$i\"" >> $specFile
+                fi
+            done
+            echo "rmdir --ignore-fail-on-non-empty \"$ROCM_INSTALL_PATH/bin\"" >> $specFile
+        fi
+
        echo "%postun" >> $specFile

        rpmbuild --define "_topdir $packageRpm" -ba $specFile
@@ -629,17 +711,32 @@ package_lightning_static() {
    get_llvm_version
    local llvmParsedVersion="${LLVM_VERSION_MAJOR}.${LLVM_VERSION_MINOR}.${LLVM_VERSION_PATCH}"

-    local packageName="rocm-llvm"
-    local packageSummary="ROCm core compiler"
-    local packageSummaryLong="ROCm core compiler based on LLVM $llvmParsedVersion"
-    if [ "$PACKAGEEXT" = "deb" ]; then
-        local packageNameExtra="rocm-llvm-dev"
+    if [ $BUILD_ALT -eq 1 ]; then
+        local packageName="rocm-llvm-alt"
+        local packageSummary="Proprietary ROCm core compiler"
+        local packageSummaryLong="ROCm core compiler, including proprietary optimizations based on LLVM $llvmParsedVersion"
+        if [ "$PACKAGEEXT" = "deb" ]; then
+            local packageNameExtra="rocm-llvm-alt-dev"
+        else
+            local packageNameExtra="rocm-llvm-alt-devel"
+        fi
+        local packageSummaryExtra="Proprietary ROCm compiler dev tools"
+        local packageSummaryLongExtra="ROCm compiler dev tools and documentation, including proprietary optimizations, based on LLVM $llvmParsedVersion"
+        local installPath="$ROCM_INSTALL_PATH/lib/llvm/alt"
    else
-        local packageNameExtra="rocm-llvm-devel"
+        local packageName="rocm-llvm"
+        local packageSummary="ROCm core compiler"
+        local packageSummaryLong="ROCm core compiler based on LLVM $llvmParsedVersion"
+        if [ "$PACKAGEEXT" = "deb" ]; then
+            local packageNameExtra="rocm-llvm-dev"
+        else
+            local packageNameExtra="rocm-llvm-devel"
+        fi
+        local packageSummaryExtra="ROCm compiler dev tools"
+        local packageSummaryLongExtra="ROCm compiler dev tools and documentation, based on LLVM $llvmParsedVersion"
+        local installPath="$ROCM_INSTALL_PATH/lib/llvm/"
+
    fi
-    local packageSummaryExtra="ROCm compiler dev tools"
-    local packageSummaryLongExtra="ROCm compiler dev tools and documentation, based on LLVM $llvmParsedVersion"
-    local installPath="$ROCM_INSTALL_PATH/lib/llvm/"

    local packageArch="amd64"
    local packageVersion="${llvmParsedVersion}.${LLVM_COMMIT_GITDATE}"
@@ -649,6 +746,7 @@ package_lightning_static() {
    local distLib="$INSTALL_PATH/lib"
    local distMan="$INSTALL_PATH/share/man"
    local licenseDir="$ROCM_INSTALL_PATH/share/doc/$packageName"
+    local licenseDirExtra="$ROCM_INSTALL_PATH/share/doc/$packageNameExtra"
    local packageDir="$BUILD_PATH/package"
    local backwardsCompatibleSymlink="$ROCM_INSTALL_PATH/llvm"

@@ -658,6 +756,9 @@ package_lightning_static() {
    local prermFile="$packageDeb/DEBIAN/prerm"
    local specFile="$packageDir/$packageName.spec"
    local debDependencies="python3, libc6, libstdc++6|libstdc++8, libstdc++-5-dev|libstdc++-7-dev|libstdc++-11-dev, libgcc-5-dev|libgcc-7-dev|libgcc-11-dev, rocm-core"
+    if [ $BUILD_ALT -eq 1 ]; then
+        debDependencies="${debDependencies}, rocm-llvm"
+    fi
    local debRecommends="gcc, g++, gcc-multilib, g++-multilib"

    local packageRpm="$packageDir/rpm"
@@ -666,6 +767,10 @@ package_lightning_static() {
    local specFileExtra="$packageDir/$packageNameExtra.spec"
    local rpmRequires="rocm-core"
    local rpmRequiresExtra="rocm-core, $packageName"
+    if [ $BUILD_ALT -eq 1 ]; then
+        rpmRequires+=", rocm-llvm"
+        rpmRequiresExtra+=", rocm-llvm-devel"
+    fi
    local rpmRecommends="gcc, gcc-c++, devtoolset-7-gcc-c++"

    rm -rf "$packageDir"
@@ -702,7 +807,12 @@ package_lightning_static() {
        mkdir -p "$DEB_PATH"
        mkdir -p "$packageDeb/$licenseDir"

-        cp -r "$LLVM_ROOT_LCL/LICENSE.TXT" "$packageDeb/$licenseDir"
+        if [ $BUILD_ALT -eq 0 ] ; then
+          cp -r "$LLVM_ROOT_LCL/LICENSE.TXT" "$packageDeb/$licenseDir"
+        else
+          cp -r "$LLVM_PROJECT_ALT_ROOT/EULA" "$packageDeb/$licenseDir"
+          cp -r "$LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt" "$packageDeb/$licenseDir"
+        fi

        mkdir -p "$packageDeb/$installPath/bin"
        for i in "${core_bin[@]}"; do
@@ -728,32 +838,36 @@ package_lightning_static() {
        done

        if [ "$BUILD_MANPAGES" == "ON" ]; then
-            mkdir -p "$packageDeb/$installPath/share/man1"
-            for i in "${core_man_pages[@]}"; do
-                if [ -f "$distMan/man1/$i" ]; then
-                    gzip -f "$distMan/man1/$i"
-                    cp -d "$distMan/man1/${i}.gz" "$packageDeb/$installPath/share/man1/"
-                fi
-            done
-            if [ -f "$distMan/man1/clang.1.gz" ]; then
-                for i in "${amd_man_pages[@]}"; do
-                    ln -sf "clang.1.gz" "$distMan/man1/$i"
-                    cp -d "$distMan/man1/${i}" "$packageDeb/$installPath/share/man1/"
+            if [ $BUILD_ALT -eq 0 ]; then
+                mkdir -p "$packageDeb/$installPath/share/man1"
+                for i in "${core_man_pages[@]}"; do
+                    if [ -f "$distMan/man1/$i" ]; then
+                        gzip -f "$distMan/man1/$i"
+                        cp -d "$distMan/man1/${i}.gz" "$packageDeb/$installPath/share/man1/"
+                    fi
                done
+                if [ -f "$distMan/man1/clang.1.gz" ]; then
+                    for i in "${amd_man_pages[@]}"; do
+                        ln -sf "clang.1.gz" "$distMan/man1/$i"
+                        cp -d "$distMan/man1/${i}" "$packageDeb/$installPath/share/man1/"
+                    done
+                fi
            fi
        fi

-        touch "$postinstFile" "$prermFile"
-        echo "mkdir -p \"$ROCM_INSTALL_PATH/bin\"" >> $postinstFile
-        for i in "${amd_compiler_commands[@]}"; do
-            if [ -f "$packageDeb/$installPath/bin/$i" ]; then
-                echo "ln -s \"../lib/llvm/bin/$i\" \"$ROCM_INSTALL_PATH/bin/$i\"" >> $postinstFile
-                echo "rm -f \"$ROCM_INSTALL_PATH/bin/$i\"" >> $prermFile
-            fi
-        done
-        echo "rmdir --ignore-fail-on-non-empty \"$ROCM_INSTALL_PATH/bin\"" >> $prermFile
-        chmod 0555 "$postinstFile" "$prermFile"
-        cp -P "$backwardsCompatibleSymlink" "$packageDeb/$ROCM_INSTALL_PATH"
+        if [ $BUILD_ALT -eq 0 ]; then
+            touch "$postinstFile" "$prermFile"
+            echo "mkdir -p \"$ROCM_INSTALL_PATH/bin\"" >> $postinstFile
+            for i in "${amd_compiler_commands[@]}"; do
+                if [ -f "$packageDeb/$installPath/bin/$i" ]; then
+                    echo "ln -s \"../lib/llvm/bin/$i\" \"$ROCM_INSTALL_PATH/bin/$i\"" >> $postinstFile
+                    echo "rm -f \"$ROCM_INSTALL_PATH/bin/$i\"" >> $prermFile
+                fi
+            done
+            echo "rmdir --ignore-fail-on-non-empty \"$ROCM_INSTALL_PATH/bin\"" >> $prermFile
+            chmod 0555 "$postinstFile" "$prermFile"
+            cp -P "$backwardsCompatibleSymlink" "$packageDeb/$ROCM_INSTALL_PATH"
+        fi

        {
            echo "Package: $packageName"
@@ -778,6 +892,14 @@ package_lightning_static() {
        mkdir -p "$packageDeb/$installPath"
        mkdir "${controlFile%/*}"
        mkdir -p "$DEB_PATH"
+        mkdir -p "$packageDeb/$licenseDirExtra"
+
+        if [ $BUILD_ALT -eq 0 ] ; then
+          cp -r "$LLVM_ROOT_LCL/LICENSE.TXT" "$packageDeb/$licenseDirExtra"
+        else
+          cp -r "$LLVM_PROJECT_ALT_ROOT/EULA" "$packageDeb/$licenseDirExtra"
+          cp -r "$LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt" "$packageDeb/$licenseDirExtra"
+        fi

        mkdir -p "$packageDeb/$installPath/bin"
        for i in "$distBin"/*; do
@@ -800,16 +922,21 @@ package_lightning_static() {
        fi

        if [ "$BUILD_MANPAGES" == "ON" ]; then
-            mkdir -p "$packageDeb/$installPath/share/man1"
-            for i in "${dev_man_pages[@]}"; do
-                if [ -f "$distMan/man1/$i" ]; then
-                    gzip -f "$distMan/man1/$i"
-                    cp -d "$distMan/man1/${i}.gz" "$packageDeb/$installPath/share/man1/"
-                fi
-            done
+            if [ $BUILD_ALT -eq 0 ]; then
+                mkdir -p "$packageDeb/$installPath/share/man1"
+                for i in "${dev_man_pages[@]}"; do
+                    if [ -f "$distMan/man1/$i" ]; then
+                        gzip -f "$distMan/man1/$i"
+                        cp -d "$distMan/man1/${i}.gz" "$packageDeb/$installPath/share/man1/"
+                    fi
+                done
+            fi
        fi

        debDependencies="${debDependencies}, ${packageName}"
+        if [ $BUILD_ALT -eq 1 ]; then
+            debDependencies="${debDependencies}, rocm-llvm-dev"
+        fi

        echo "Package: $packageNameExtra"  > $controlFile
        echo "Architecture: $packageArch" >> $controlFile
@@ -852,8 +979,13 @@ package_lightning_static() {
        echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/bin" >> $specFile
        echo "mkdir -p  \$RPM_BUILD_ROOT/$licenseDir" >> $specFile

-        echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
-        echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
+        if [ $BUILD_ALT -eq 0 ]; then
+            echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
+            echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFile
+        else
+            echo "cp -R $LLVM_PROJECT_ALT_ROOT/EULA \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
+            echo "cp -R $LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt \$RPM_BUILD_ROOT/$licenseDir" >> $specFile
+        fi

        for i in "${core_bin[@]}"; do
            if [ -f "$distBin/$i" ]; then
@@ -863,7 +995,9 @@ package_lightning_static() {

        echo "cp -d \"$distBin/flang\" \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile

-        echo "cp -d \"$distBin\"/*.cfg \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile
+        if [ $BUILD_ALT -eq 0 ]; then
+            echo "cp -d \"$distBin\"/*.cfg \$RPM_BUILD_ROOT/$installPath/bin/" >> $specFile
+        fi

        echo "mkdir -p \$RPM_BUILD_ROOT/$installPath/lib/clang" >> $specFile
        echo "cp -R \"$distLib/clang/\" \$RPM_BUILD_ROOT/$installPath/lib/" >> $specFile
@@ -880,18 +1014,20 @@ package_lightning_static() {
        done

        if [ "$BUILD_MANPAGES" == "ON" ]; then
-            echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFile
-            for i in "${core_man_pages[@]}"; do
-                if [ -f "$distMan/man1/$i" ]; then
-                    echo "gzip -f $distMan/man1/$i" >> $specFile
-                    echo "cp -d $distMan/man1/${i}.gz \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFile
-                fi
-            done
-            if [ -f "$distMan/man1/clang.1.gz" ]; then
-                for i in "${amd_man_pages[@]}"; do
-                    echo "ln -sf clang.1.gz \"$distMan/man1/$i\"" >> $specFile
-                    echo "cp -d $distMan/man1/${i} \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFile
+            if [ $BUILD_ALT -eq 0 ]; then
+                echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFile
+                for i in "${core_man_pages[@]}"; do
+                    if [ -f "$distMan/man1/$i" ]; then
+                        echo "gzip -f $distMan/man1/$i" >> $specFile
+                        echo "cp -d $distMan/man1/${i}.gz \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFile
+                    fi
                done
+                if [ -f "$distMan/man1/clang.1.gz" ]; then
+                    for i in "${amd_man_pages[@]}"; do
+                        echo "ln -sf clang.1.gz \"$distMan/man1/$i\"" >> $specFile
+                        echo "cp -d $distMan/man1/${i} \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFile
+                    done
+                fi
            fi
        fi

@@ -903,20 +1039,24 @@ package_lightning_static() {
            echo "$ROCM_INSTALL_PATH"

            echo "%post"
-            echo "mkdir -p \"\$RPM_INSTALL_PREFIX0/bin\""
-            for i in "${amd_compiler_commands[@]}"; do
-                if [ -f "$distBin/$i" ]; then
-                    echo "ln -sf ../lib/llvm/bin/$i \"\$RPM_INSTALL_PREFIX0/bin/$i\""
-                fi
-            done
+            if [ $BUILD_ALT -eq 0 ]; then
+                echo "mkdir -p \"$ROCM_INSTALL_PATH/bin\""
+                for i in "${amd_compiler_commands[@]}"; do
+                    if [ -f "$distBin/$i" ]; then
+                        echo "ln -sf ../lib/llvm/bin/$i \"$ROCM_INSTALL_PATH/bin/$i\""
+                    fi
+                done
+            fi

            echo "%preun"
-            for i in "${amd_compiler_commands[@]}"; do
-                if [ -f "$distBin/$i" ]; then
-                    echo "rm -f \"\$RPM_INSTALL_PREFIX0/bin/$i\""
-                fi
-            done
-            echo "rmdir --ignore-fail-on-non-empty \"\$RPM_INSTALL_PREFIX0/bin\""
+            if [ $BUILD_ALT -eq 0 ]; then
+                for i in "${amd_compiler_commands[@]}"; do
+                    if [ -f "$distBin/$i" ]; then
+                        echo "rm -f \"$ROCM_INSTALL_PATH/bin/$i\""
+                    fi
+                done
+                echo "rmdir --ignore-fail-on-non-empty \"$ROCM_INSTALL_PATH/bin\""
+            fi

            echo "%postun"
        } >> "$specFile"
@@ -931,13 +1071,16 @@ package_lightning_static() {
        echo "Release:    ${JOB_DESIGNATOR}${SLES_BUILD_ID_PREFIX}${BUILD_ID}%{?dist}" >> $specFileExtra
        echo "Summary:    $packageSummaryExtra" >> $specFileExtra
        echo "Group:      System Environment/Libraries" >> $specFileExtra
-        echo "License:    ASL 2.0 with exceptions" >> $specFileExtra
-        echo "Prefix:     $ROCM_INSTALL_PATH" >> $specFileExtra
+        if [ $BUILD_ALT -eq 1 ]; then
+          echo "License:    AMD Proprietary" >> $specFileExtra
+        else
+          echo "License:    ASL 2.0 with exceptions" >> $specFileExtra
+        fi
        echo "Requires:   $rpmRequiresExtra" >> $specFileExtra
-        # The following is commented as Centos 7 has a version of rpm
-        # that does not understand it. When we no longer support Centos 7
-        # then we should have a correct recommends line.
-        #echo "Recommends: $rpmRecommends" >> $specFileExtra
+
+        if [ $BUILD_ALT -eq 1 ]; then
+          echo "%define _build_id_links none" >> $specFileExtra
+        fi

        echo "%description" >> $specFileExtra
        echo "$packageSummaryLongExtra" >> $specFileExtra
@@ -950,8 +1093,15 @@ package_lightning_static() {
        echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/bin" >> $specFileExtra
        echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/include" >> $specFileExtra
        echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/lib" >> $specFileExtra
+        echo "mkdir -p  \$RPM_BUILD_ROOT/$licenseDirExtra" >> $specFileExtra

-        echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFileExtra
+        if [ $BUILD_ALT -eq 0 ]; then
+          echo "cp -R $LLVM_ROOT_LCL/LICENSE.TXT \$RPM_BUILD_ROOT/$licenseDirExtra" >> $specFileExtra
+          echo "cp -P $backwardsCompatibleSymlink \$RPM_BUILD_ROOT/$ROCM_INSTALL_PATH" >> $specFileExtra
+        else
+          echo "cp -R $LLVM_PROJECT_ALT_ROOT/EULA \$RPM_BUILD_ROOT/$licenseDirExtra" >> $specFileExtra
+          echo "cp -R $LLVM_PROJECT_ALT_ROOT/DISCLAIMER.txt \$RPM_BUILD_ROOT/$licenseDirExtra" >> $specFileExtra
+        fi

        for i in "$distBin"/*; do
            bin=$(basename "$i")
@@ -972,13 +1122,15 @@ package_lightning_static() {
        fi

        if [ "$BUILD_MANPAGES" == "ON" ]; then
-            echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFileExtra
-            for i in "${dev_man_pages[@]}"; do
-                if [ -f "$distMan/man1/$i" ]; then
-                    echo "gzip -f $distMan/man1/$i" >> $specFileExtra
-                    echo "cp -d \"$distMan/man1/${i}.gz\" \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFileExtra
-                fi
-            done
+            if [ $BUILD_ALT -eq 0 ]; then
+                echo "mkdir -p  \$RPM_BUILD_ROOT/$installPath/share/man/man1" >> $specFileExtra
+                for i in "${extra_man_pages[@]}"; do
+                    if [ -f "$distMan/man1/$i" ]; then
+                        echo "gzip -f $distMan/man1/$i" >> $specFileExtra
+                        echo "cp -d \"$distMan/man1/${i}.gz\" \$RPM_BUILD_ROOT/$installPath/share/man/man1/" >> $specFileExtra
+                    fi
+                done
+            fi
        fi

        echo "%clean" >> $specFileExtra
@@ -1114,7 +1266,9 @@ print_output_directory() {
 build() {
    mkdir -p "${INSTALL_PATH}"
    build_lightning
-    create_compiler_config_files
+    if [ $BUILD_ALT -eq 0 ] ; then
+        create_compiler_config_files
+    fi
 }

 create_wheel_package() {
@@ -1147,4 +1301,9 @@ case $TARGET in
    (*) die "Invalid target $TARGET" ;;
 esac

+if [[ $WHEEL_PACKAGE == true ]]; then
+    echo "Wheel Package build started !!!!"
+    create_wheel_package
+fi
+
 echo "Operation complete"
--- a/Show More
+++ b/Show More