Docs: Update JAX compatibility page

* update vllm-benchmark

fix hlist overflow

update standalone benchmarking options

update list of models

fix typo and model name

unnecessary duplicate info

update formatting

update vllm benchmark guide

- remove Llama 2 FP8
- add Jais 13B
- update commands

update docker pull tag

update MAD available models

remove extra mad models not relevant to vllm

update PyTorch version

add changelog

add model names to .wordlist.txt

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

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

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

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

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

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

* fix typo

* update link

* fix link text

* change changelog to previous versions

* fix typo

* remove "for"

---------

Co-authored-by: Pratik Basyal <pratik.basyal@amd.com>

.azuredevops/components/hipBLASLt.yml

@@ -59,14 +59,10 @@ jobs:
     value: $(Build.BinariesDirectory)/rocm
   - name: TENSILE_ROCM_ASSEMBLER_PATH
     value: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-  - name: CMAKE_CXX_COMPILER
-    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
   - name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
     value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
-  - name: TENSILE_ROCM_PATH
-    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
-  - name: PATH
-    value: $(Agent.BuildDirectory)/rocm/llvm/bin:$(Agent.BuildDirectory)/rocm/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin
+  - name: ROCM_PATH
+    value: $(Agent.BuildDirectory)/rocm
   - name: DAY_STRING
     value: $[format('{0:ddMMyyyy}', pipeline.startTime)]
   pool: ${{ variables.ULTRA_BUILD_POOL }}
@@ -154,9 +150,8 @@ jobs:
       extraEnvVars:
         - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
         - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/amdclang
-        - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/bin/hipcc
         - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
-        - TENSILE_ROCM_PATH:::/home/user/workspace/rocm/bin/hipcc
+        - ROCM_PATH:::/home/user/workspace/rocm
       extraCopyDirectories:
         - deps
 

.azuredevops/components/rocBLAS.yml

@@ -64,10 +64,10 @@ jobs:
     value: $(Build.BinariesDirectory)/rocm
   - name: TENSILE_ROCM_ASSEMBLER_PATH
     value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang
-  - name: CMAKE_CXX_COMPILER
-    value: $(Agent.BuildDirectory)/rocm/bin/hipcc
   - name: TENSILE_ROCM_OFFLOAD_BUNDLER_PATH
     value: $(Agent.BuildDirectory)/rocm/llvm/bin/clang-offload-bundler
+  - name: ROCM_PATH
+    value: $(Agent.BuildDirectory)/rocm
   pool: ${{ variables.MEDIUM_BUILD_POOL }}
   workspace:
     clean: all
@@ -96,8 +96,8 @@ jobs:
         -DCMAKE_TOOLCHAIN_FILE=toolchain-linux.cmake
         -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm/llvm;$(Agent.BuildDirectory)/rocm
         -DCMAKE_BUILD_TYPE=Release
-        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
-        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/hipcc
+        -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang++
+        -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/bin/amdclang
         -DGPU_TARGETS=$(JOB_GPU_TARGET)
         -DTensile_CODE_OBJECT_VERSION=default
         -DTensile_LOGIC=asm_full
@@ -125,8 +125,8 @@ jobs:
       extraEnvVars:
         - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
         - TENSILE_ROCM_ASSEMBLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang
-        - CMAKE_CXX_COMPILER:::/home/user/workspace/rocm/bin/hipcc
         - TENSILE_ROCM_OFFLOAD_BUNDLER_PATH:::/home/user/workspace/rocm/llvm/bin/clang-offload-bundler
+        - ROCM_PATH:::/home/user/workspace/rocm
 
 - job: rocBLAS_testing
   dependsOn: rocBLAS

.azuredevops/components/rocDecode.yml

@@ -49,21 +49,10 @@ jobs:
   workspace:
     clean: all
   steps:
-  # Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
-  - task: Bash@3
-    displayName: 'Register ROCm packages'
-    inputs:
-      targetType: inline
-      script: |
-        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
-        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
-        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
-        sudo apt update
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -104,21 +93,10 @@ jobs:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
   steps:
-  # Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
-  - task: Bash@3
-    displayName: 'Register ROCm packages'
-    inputs:
-      targetType: inline
-      script: |
-        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
-        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
-        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
-        sudo apt update
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml

.azuredevops/components/rocJPEG.yml

@@ -48,21 +48,10 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
   steps:
-  # Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
-  - task: Bash@3
-    displayName: 'Register ROCm packages'
-    inputs:
-      targetType: inline
-      script: |
-        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
-        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
-        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
-        sudo apt update
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -106,21 +95,10 @@ jobs:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
   steps:
-  # Since mesa-amdgpu-multimedia-devel is not directly available from apt, register it
-  - task: Bash@3
-    displayName: 'Register ROCm packages'
-    inputs:
-      targetType: inline
-      script: |
-        sudo mkdir --parents --mode=0755 /etc/apt/keyrings
-        wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/${{ variables.KEYRING_VERSION }}/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/${{ variables.KEYRING_VERSION }} jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
-        echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
-        sudo apt update
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml

.azuredevops/components/rocm-core.yml

@@ -36,7 +36,7 @@ jobs:
         -DCPACK_GENERATOR=DEB
         -DCPACK_DEBIAN_PACKAGE_RELEASE="local.9999~99.99"
         -DCPACK_RPM_PACKAGE_RELEASE="local.9999"
-        -DROCM_VERSION="$(next-release)"
+        -DROCM_VERSION="$(NEXT_RELEASE_VERSION)"
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml

.azuredevops/components/rocminfo.yml

@@ -35,7 +35,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
-      registerRadeon: true
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:

.azuredevops/components/rocprofiler-sdk.yml

@@ -37,6 +37,8 @@ parameters:
     - clr
     - llvm-project
     - rccl
+    - rocDecode
+    - rocJPEG
     - rocm-cmake
     - rocm-core
     - rocminfo
@@ -60,7 +62,7 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerRadeon: true
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -99,6 +101,7 @@ jobs:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
       gpuTarget: $(JOB_GPU_TARGET)
+      registerROCmPackages: true
 
 - job: rocprofiler_sdk_testing
   dependsOn: rocprofiler_sdk
@@ -119,7 +122,7 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerRadeon: true
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -155,3 +158,4 @@ jobs:
       pipModules: ${{ parameters.pipModules }}
       environment: test
       gpuTarget: $(JOB_GPU_TARGET)
+      registerROCmPackages: true

.azuredevops/components/rocprofiler-systems.yml

@@ -46,13 +46,14 @@ parameters:
 - name: rocmDependencies
   type: object
   default:
+    - amdsmi
     - aomp
     - clr
     - llvm-project
     - rccl
     - rocDecode
+    - rocJPEG
     - rocm-core
-    - rocm_smi_lib
     - rocminfo
     - ROCR-Runtime
     - rocprofiler-register
@@ -75,7 +76,7 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerRadeon: true
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -159,7 +160,7 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-      registerRadeon: true
+      registerROCmPackages: true
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:

.azuredevops/dependencies/half560.yml

@@ -19,7 +19,7 @@ jobs:
   pool:
     vmImage: ${{ variables.BASE_BUILD_POOL }}
   container:
-    image: ${{ variables.DOCKER_IMAGE_NAME }}:${{ variables.LATEST_DOCKER_VERSION }}
+    image: rocm/dev-ubuntu-22.04:${{ variables.LATEST_RELEASE_VERSION }}
   workspace:
     clean: all
   steps:

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

@@ -4,13 +4,13 @@ steps:
   inputs:
     targetType: inline
     script: |
-      export packageName=$(curl -s https://repo.radeon.com/rocm/apt/latest/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb")
+      export packageName=$(curl -s https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb")
       echo "##vso[task.setvariable variable=packageName;isreadonly=true]$packageName"
 - task: Bash@3
   displayName: 'Download aqlprofile'
   inputs:
     targetType: inline
-    script: wget -nv https://repo.radeon.com/rocm/apt/latest/pool/main/h/hsa-amd-aqlprofile/$(packageName)
+    script: wget -nv https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION)/pool/main/h/hsa-amd-aqlprofile/$(packageName)
     workingDirectory: '$(Pipeline.Workspace)'
 - task: Bash@3
   displayName: 'Extract aqlprofile'

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

@@ -6,21 +6,21 @@ parameters:
 - name: pipModules
   type: object
   default: []
-- name: registerRadeon
+- name: registerROCmPackages
   type: boolean
   default: false
 
 steps:
-- ${{ if eq(parameters.registerRadeon, true) }}:
+- ${{ if eq(parameters.registerROCmPackages, true) }}:
   - task: Bash@3
-    displayName: 'Register repo.radeon packages'
+    displayName: 'Register AMDGPU & ROCm repos'
     inputs:
       targetType: inline
       script: |
         sudo mkdir --parents --mode=0755 /etc/apt/keyrings
         wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/latest/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/latest jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$(REPO_RADEON_VERSION)/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
+        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION) jammy main" | sudo tee --append /etc/apt/sources.list.d/rocm.list
         echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
         sudo apt update
 # firefox takes time to upgrade and is not needed for CI workloads, hold version

.azuredevops/templates/steps/docker-container.yml

@@ -154,8 +154,8 @@ steps:
         script: |
           echo "RUN mkdir --parents --mode=0755 /etc/apt/keyrings" >> Dockerfile
           echo "RUN wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | tee /etc/apt/keyrings/rocm.gpg > /dev/null" >> Dockerfile
-          echo "RUN echo \"deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/latest/ubuntu jammy main\" | tee /etc/apt/sources.list.d/amdgpu.list" >> Dockerfile
-          echo "RUN echo \"deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/latest jammy main\" | tee --append /etc/apt/sources.list.d/rocm.list" >> Dockerfile
+          echo "RUN echo \"deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$(REPO_RADEON_VERSION)/ubuntu jammy main\" | tee /etc/apt/sources.list.d/amdgpu.list" >> Dockerfile
+          echo "RUN echo \"deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$(REPO_RADEON_VERSION) jammy main\" | tee --append /etc/apt/sources.list.d/rocm.list" >> Dockerfile
           echo "RUN printf 'Package: *\\nPin: release o=repo.radeon.com\\nPin-Priority: 600' > /etc/apt/preferences.d/rocm-pin-600" >> Dockerfile
           echo "RUN DEBIAN_FRONTEND=noninteractive apt-get --yes update" >> Dockerfile
   - ${{ if eq(parameters.registerCUDAPackages, true) }}:

.azuredevops/variables-global.yml

@@ -27,14 +27,14 @@ variables:
   value: rocm-ci_larger_base_disk_pool
 - name: GFX942_TEST_POOL
   value: gfx942_test_pool
+- name: LATEST_RELEASE_VERSION
+  value: 6.3.2
+- name: REPO_RADEON_VERSION
+  value: 6.3.2
+- name: NEXT_RELEASE_VERSION
+  value: 6.4.0
 - name: LATEST_RELEASE_TAG
-  value: rocm-6.1.0
-- name: DOCKER_IMAGE_NAME
-  value: rocm/dev-ubuntu-22.04
-- name: LATEST_DOCKER_VERSION
-  value: 6.1
-- name: KEYRING_VERSION
-  value: 6.3
+  value: rocm-6.3.2
 - name: AMDMIGRAPHX_GFX942_TEST_PIPELINE_ID
   value: 197
 - name: AMDMIGRAPHX_PIPELINE_ID
@@ -151,8 +151,6 @@ variables:
   value: 105
 - name: HIPTENSOR_TAGGED_PIPELINE_ID
   value: 56
-- name: LAST_RELEASE
-  value: 6.1.0
 - name: LLVM_PROJECT_PIPELINE_ID
   value: 2
 - name: LLVM_PROJECT_TAGGED_PIPELINE_ID
@@ -183,10 +181,6 @@ variables:
   value: 100
 - name: RDC_TAGGED_PIPELINE_ID
   value: 59
-- name: REIMAGE_ORG
-  value: AGS-ROCm-CI
-- name: REIMAGE_REPO
-  value: cirrascale-reimage-automation
 - name: ROCAL_PIPELINE_ID
   value: 151
 - name: ROCALUTION_GFX942_TEST_PIPELINE_ID

.github/workflows/issue_retrieval.yml

@@ -2,7 +2,7 @@ name: Issue retrieval
 
 on:
   issues:
-    types: [opened]
+    types: [opened, edited]
 
 jobs:
   auto-retrieve:
@@ -15,7 +15,7 @@ jobs:
           app_id: ${{ secrets.ACTION_APP_ID }}
           private_key: ${{ secrets.ACTION_PEM }}
       - name: 'Retrieve Issue'
-        uses: abhimeda/rocm_issue_management@main
+        uses: harkgill-amd/rocm_issue_management@main
         with:
           authentication-token: ${{ steps.generate_token.outputs.token }}
           github-organization: 'ROCm'

.wordlist.txt

@@ -74,6 +74,7 @@ Conda
 ConnectX
 CuPy
 Dashboarding
+DBRX
 DDR
 DF
 DGEMM
@@ -92,6 +93,7 @@ DataFrame
 DataLoader
 DataParallel
 Debian
+DeepSeek
 DeepSpeed
 Dependabot
 Deprecations
@@ -129,6 +131,7 @@ GDS
 GEMM
 GEMMs
 GFortran
+Gemma
 GiB
 GIM
 GL
@@ -674,6 +677,7 @@ namespace
 namespaces
 nanoGPT
 num
+numpy
 numref
 ocl
 opencl

RELEASE.md

@@ -29,8 +29,7 @@ The release notes provide a summary of notable changes since the previous ROCm r
 - [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)
+If you’re using Radeon™ PRO or Radeon GPUs in a workstation setting with a display connected, see the [Use ROCm on Radeon GPUs](https://rocm.docs.amd.com/projects/radeon/en/latest/docs/compatibility/native_linux/native_linux_compatibility.html)
 documentation to verify compatibility and system requirements.
 ```
 ## Release highlights

docs/about/license.md

@@ -62,7 +62,7 @@ additional licenses. Please review individual repositories for more information.
 | [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/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocm_bandwidth_test/blob/master/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 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) |

docs/compatibility/ml-compatibility/jax-compatibility.rst

@@ -55,7 +55,7 @@ Docker image compatibility
 
 AMD validates and publishes ready-made `ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax>`_
 with ROCm backends on Docker Hub. The following Docker image tags and
-associated inventories are validated for
+associated inventories represent the latest JAX version from the official Docker Hub and 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.
 
@@ -83,7 +83,8 @@ icon to view the image on Docker Hub.
 
 AMD publishes `Community ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax-community>`_
 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/>`_.
+associated inventories represent the latest JAX version from the official Docker Hub and are
+tested for `ROCm 6.3.1 <https://repo.radeon.com/rocm/apt/6.3.1/>`_.
 
 .. list-table:: JAX community Docker image components
     :header-rows: 1
@@ -94,25 +95,25 @@ associated inventories are tested for `ROCm 6.2.4 <https://repo.radeon.com/rocm/
       - 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>
+           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.3.1-jax0.5.0-py3.12.8/images/sha256-897d7471a954d9df7f79cd28b87ec515fbb94189fc3cf13e3a1588aa6b2a5fee?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>`_
+      - `0.5.0 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.5.0>`_
       - Ubuntu 22.04
-      - `3.12.7 <https://www.python.org/downloads/release/python-3127/>`_
+      - `3.12.8 <https://www.python.org/downloads/release/python-3128/>`_
     * - .. 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>
+           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.3.1-jax0.5.0-py3.11.11/images/sha256-f59243f324ee8da8dd54cd81b3649a860b2b454eaac8e4ce41d5c5f40e42b0e8?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>`_
+      - `0.5.0 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.5.0>`_
       - 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>
+           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.3.1-jax0.5.0-py3.10.16/images/sha256-6f12e5f6a3b5d033d2b1a43938b6804978d999978e68e402228d02984a69fb9d?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>`_
+      - `0.5.0 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.5.0>`_
       - Ubuntu 22.04
-      - `3.10.15 <https://www.python.org/downloads/release/python-31015/>`_
+      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
 
 Critical ROCm libraries for JAX
 ================================================================================
@@ -210,7 +211,7 @@ performance, and feature set available to developers.
 Supported and unsupported features
 ===============================================================================
 
-The following table maps GPU-accelerated JAX modules to their supported
+The following table maps the public JAX API modules to their supported
 ROCm and JAX versions.
 
 .. list-table::
@@ -247,21 +248,11 @@ ROCm and JAX versions.
         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
@@ -275,27 +266,10 @@ ROCm and JAX versions.
         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
@@ -322,10 +296,10 @@ ROCm and JAX versions.
       - jax_triton 0.2.0
       - 6.2.4
 
-jax.scipy module
+jax.lax module
 -------------------------------------------------------------------------------
 
-A SciPy-like API for scientific computing.
+A module for primitives operations.
 
 .. list-table::
     :header-rows: 1
@@ -333,129 +307,14 @@ A SciPy-like API for scientific computing.
     * - Module
       - Since JAX
       - Since ROCm
-    * - ``jax.scipy.cluster``
-      - 0.3.11
-      - 5.1.0
-    * - ``jax.scipy.fft``
-      - 0.1.71
+    * - ``jax.lax.linalg``
+      - 0.3.2
       - 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.
+A module for primitives operations.
 
 .. list-table::
     :header-rows: 1
@@ -463,18 +322,30 @@ Modules for JAX extensions.
     * - 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``
+    * - ``jax.extend.core``
       - 0.4.15
       - 5.5.0
+    * - ``jax.extend.core.primitives``
+      - 0.4.32
+      - 5.5.0
+
+jax.numpy module
+-------------------------------------------------------------------------------
+
+A module for primitives operations.
+
+.. list-table::
+    :header-rows: 1
+
+    * - Module
+      - Since JAX
+      - Since ROCm
+    * - ``jax.numpy.fft``
+      - 0.3.20
+      - 5.1.0
+    * - ``jax.numpy.linalg``
+      - 0.3.20
+      - 5.1.0
 
 jax.experimental module
 -------------------------------------------------------------------------------
@@ -490,9 +361,6 @@ Experimental modules and APIs.
     * - ``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
@@ -514,8 +382,11 @@ Experimental modules and APIs.
     * - ``jax.experimental.pjit``
       - 0.1.61
       - 5.0.0
-    * - ``jax.experimental.serialize_executable``
-      - 0.4.0
+    * - ``jax.experimental.roofline``
+      - 0.4.36
+      - 5.3.0
+    * - ``jax.experimental.rnn``
+      - 0.4.3
       - 5.3.0
     * - ``jax.experimental.shard_map``
       - 0.4.3
@@ -572,9 +443,6 @@ Experimental support for sparse matrix operations.
     * - ``jax.experimental.sparse.linalg``
       - 0.3.15
       - 5.2.0
-    * - ``jax.experimental.sparse.sparsify``
-      - 0.3.25
-      - ❌
 
 .. list-table::
     :header-rows: 1
@@ -622,9 +490,6 @@ ROCm.
     * - 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
 ================================================================================

docs/how-to/rocm-for-ai/fine-tuning/index.rst

@@ -16,6 +16,9 @@ Throughout the following topics, this guide discusses the goals and :ref:`challe
 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.
 
+The AI Developer Hub contains `AMD ROCm tutorials <https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/>`_ for
+training, fine-tuning, and inference. It leverages popular machine learning frameworks on AMD GPUs.
+
 - :doc:`Conceptual overview of fine-tuning LLMs <overview>`
 
 - :doc:`Fine-tuning and inference <fine-tuning-and-inference>` using a

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

@@ -12,6 +12,9 @@ You can use ROCm to perform distributed training, which enables you to train mod
  
 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. 
 
+The AI Developer Hub contains `AMD ROCm tutorials <https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/>`_ for
+training, fine-tuning, and inference. It leverages popular machine learning frameworks on AMD GPUs.
+
 In this guide, you'll learn how to use ROCm for AI:
 
 - :doc:`Training <training/index>`

docs/how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries.rst

@@ -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/native-install/index>`
+*  Install ROCm using Docker or the :doc:`package manager <rocm-install-on-linux:install/install-methods/package-manager-index>`
 *  Install the nightly `PyTorch <https://pytorch.org/>`_ build
 *  Complete the pre-build and build tasks
   

docs/how-to/rocm-for-ai/inference/index.rst

@@ -11,6 +11,9 @@ Understanding the ROCm™ software platform’s architecture and capabilities is
 
 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. 
 
+The AI Developer Hub contains `AMD ROCm tutorials <https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/>`_ for
+training, fine-tuning, and inference. It leverages popular machine learning frameworks on AMD GPUs.
+
 - :doc:`Installing ROCm and machine learning frameworks <install>`
 
 - :doc:`Running models from Hugging Face <hugging-face-models>`

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

@@ -26,7 +26,7 @@ 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/native-install/index>`
+* :doc:`Using your Linux distribution's package manager <rocm-install-on-linux:install/install-methods/package-manager-index>`
 
 * :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/amdgpu-install>`
 

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

@@ -10,49 +10,22 @@ 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:
+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 6.2.1 <https://github.com/ROCm/ROCm>`_
+* `ROCm 6.3.1 <https://github.com/ROCm/ROCm>`_
 
-* `vLLM 0.6.4 <https://docs.vllm.ai/en/latest>`_
+* `vLLM 0.6.6 <https://docs.vllm.ai/en/latest>`_
 
-* `PyTorch 2.5.0 <https://github.com/pytorch/pytorch>`_
-
-* Tuning files (in CSV format)
+* `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 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
+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:
 
@@ -91,9 +64,9 @@ MI300X accelerator with the prebuilt vLLM Docker image.
 
    .. code-block:: shell
 
-      docker pull rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
+      docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
 
-Once setup is complete, you can choose between two options to reproduce the
+Once the setup is complete, choose between two options to reproduce the
 benchmark results:
 
 -  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
@@ -130,45 +103,89 @@ 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
 ----------------
 
-.. hlist::
-   :columns: 3
+.. list-table::
+   :header-rows: 1
+   :widths: 2, 3
 
-   * ``pyt_vllm_llama-3.1-8b``
+   * - Model name
+     - Tag
 
-   * ``pyt_vllm_llama-3.1-70b``
+   * - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
+     - ``pyt_vllm_llama-3.1-8b``
 
-   * ``pyt_vllm_llama-3.1-405b``
+   * - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
+     - ``pyt_vllm_llama-3.1-70b``
 
-   * ``pyt_vllm_llama-2-7b``
+   * - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
+     - ``pyt_vllm_llama-3.1-405b``
 
-   * ``pyt_vllm_llama-2-70b``
+   * - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
+     - ``pyt_vllm_llama-3.2-11b-vision-instruct``
 
-   * ``pyt_vllm_mixtral-8x7b``
+   * - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
+     - ``pyt_vllm_llama-2-7b``
 
-   * ``pyt_vllm_mixtral-8x22b``
+   * - `Llama 2 70B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
+     - ``pyt_vllm_llama-2-70b``
 
-   * ``pyt_vllm_mistral-7b``
+   * - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
+     - ``pyt_vllm_mixtral-8x7b``
 
-   * ``pyt_vllm_qwen2-7b``
+   * - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
+     - ``pyt_vllm_mixtral-8x22b``
 
-   * ``pyt_vllm_qwen2-72b``
+   * - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
+     - ``pyt_vllm_mistral-7b``
 
-   * ``pyt_vllm_jais-13b``
+   * - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
+     - ``pyt_vllm_qwen2-7b``
 
-   * ``pyt_vllm_jais-30b``
+   * - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
+     - ``pyt_vllm_qwen2-72b``
 
-   * ``pyt_vllm_llama-3.1-8b_fp8``
+   * - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
+     - ``pyt_vllm_jais-13b``
 
-   * ``pyt_vllm_llama-3.1-70b_fp8``
+   * - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
+     - ``pyt_vllm_jais-30b``
 
-   * ``pyt_vllm_llama-3.1-405b_fp8``
+   * - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
+     - ``pyt_vllm_dbrx-instruct``
 
-   * ``pyt_vllm_mixtral-8x7b_fp8``
+   * - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
+     - ``pyt_vllm_gemma-2-27b``
 
-   * ``pyt_vllm_mixtral-8x22b_fp8``
+   * - `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:
 
@@ -181,8 +198,8 @@ 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
+   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``.
@@ -224,8 +241,8 @@ See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
 
 .. _vllm-benchmark-standalone-options:
 
-Options
--------
+Options and available models
+----------------------------
 
 .. list-table::
    :header-rows: 1
@@ -248,72 +265,100 @@ Options
      - Measure both throughput and latency
 
    * - ``$model_repo``
-     - ``meta-llama/Meta-Llama-3.1-8B-Instruct``
-     - Llama 3.1 8B
+     - ``meta-llama/Llama-3.1-8B-Instruct``
+     - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
 
    * - (``float16``)
-     - ``meta-llama/Meta-Llama-3.1-70B-Instruct``
-     - Llama 3.1 70B
+     - ``meta-llama/Llama-3.1-70B-Instruct``
+     - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
 
    * -
-     - ``meta-llama/Meta-Llama-3.1-405B-Instruct``
-     - Llama 3.1 405B
+     - ``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
+     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
 
    * -
      - ``meta-llama/Llama-2-70b-chat-hf``
-     - Llama 2 70B
+     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
 
    * -
      - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
-     - Mixtral 8x7B
+     - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
 
    * -
      - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
-     - Mixtral 8x22B
+     - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
 
    * -
      - ``mistralai/Mistral-7B-Instruct-v0.3``
-     - Mixtral 7B
+     - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
 
    * -
      - ``Qwen/Qwen2-7B-Instruct``
-     - Qwen2 7B
+     - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
 
    * -
      - ``Qwen/Qwen2-72B-Instruct``
-     - Qwen2 72B
+     - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
 
    * -
      - ``core42/jais-13b-chat``
-     - JAIS 13B
+     - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
 
    * -
      - ``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
+     - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
 
    * -
-     - ``amd/Meta-Llama-3.1-405B-Instruct-FP8-KV``
-     - Llama 3.1 405B
+     - ``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 8x7B
+     - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
 
    * -
      - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
-     - Mixtral 8x22B
+     - `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
@@ -335,34 +380,34 @@ 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.
+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/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
+   ./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/Meta-Llama-3.1-8B-Instruct_latency_report.csv``
+- ``./reports_float16/summary/Llama-3.1-70B-Instruct_latency_report.csv``
 
-- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_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 8B model on one GPU with the ``float16`` and ``float8`` data types.
+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/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
+   ./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/Meta-Llama-3.1-8B-Instruct_throughput_report.csv``
+- ``./reports_float16/summary/Llama-3.1-70B-Instruct_throughput_report.csv``
 
-- ``./reports_float8/summary/Meta-Llama-3.1-8B-Instruct-FP8-KV_throughput_report.csv``
+- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_throughput_report.csv``
 
 .. raw:: html
 
@@ -394,7 +439,7 @@ Further reading
   MI300X accelerators, see :doc:`../../system-optimization/mi300x`.
 
 - To learn how to run LLM models from Hugging Face or your own model, see
-  :doc:`Using ROCm for AI <../index>`.
+  :doc:`Running models from Hugging Face <hugging-face-models>`.
 
 - To learn how to optimize inference on LLMs, see
   :doc:`Inference optimization <../inference-optimization/index>`.
@@ -402,6 +447,32 @@ Further reading
 - To learn how to fine-tune LLMs, see
   :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
 
-- 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>`_.
+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>`_

docs/how-to/rocm-for-ai/training/index.rst

@@ -14,6 +14,9 @@ Training models on AMD GPUs with the ROCm™ software platform allows you to use
  
 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. 
 
+The AI Developer Hub contains `AMD ROCm tutorials <https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/>`_ for
+training, fine-tuning, and inference. It leverages popular machine learning frameworks on AMD GPUs.
+
 In this guide, you'll learn about:
 
 - :doc:`Training a model <train-a-model>`

docs/how-to/system-optimization/w6000-v620.md

@@ -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/native-install/index>`.
+{doc}`installation procedure<rocm-install-on-linux:install/install-methods/package-manager-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/native-install/index>`.
+refer to the {doc}`Linux install guide<rocm-install-on-linux:install/install-methods/package-manager-index>`.

docs/index.md

@@ -38,6 +38,7 @@ ROCm documentation is organized into the following categories:
 :class-body: rocm-card-banner rocm-hue-12
 
 * [Use ROCm for AI](./how-to/rocm-for-ai/index.rst)
+* [AI tutorials](https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/)
 * [Use ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
 * [System optimization](./how-to/system-optimization/index.rst)
 * [AMD Instinct MI300X performance validation and tuning](./how-to/tuning-guides/mi300x/index.rst)

docs/reference/precision-support.rst

@@ -1,19 +1,23 @@
 .. meta::
-  :description: Supported data types in ROCm
-  :keywords: int8, float8, float8 (E4M3), float8 (E5M2), bfloat8, float16, half, bfloat16, tensorfloat32, float,
-   float32, float64, double, AMD, ROCm, AMDGPU
+  :description: Supported data types of AMD GPUs and libraries in ROCm.
+  :keywords: precision, data types, HIP types, int8, float8, float8 (E4M3),
+             float8 (E5M2), bfloat8, float16, half, bfloat16, tensorfloat32,
+             float, float32, float64, double, AMD data types, HIP data types,
+             ROCm precision, ROCm data types
 
 *************************************************************
-Precision support
+Data types and precision support
 *************************************************************
 
-Use the following sections to identify data types and HIP types ROCm™ supports.
+This topic lists the supported data types of AMD GPUs and ROCm libraries.
+Corresponding :doc:`HIP <hip:index>` data types are also noted. 
 
 Integral types
 ==========================================
 
-The signed and unsigned integral types that are supported by ROCm are listed in the following table,
-together with their corresponding HIP type and a short description.
+The signed and unsigned integral types supported by ROCm are listed in
+the following table, along with their corresponding HIP type and a short
+description.
 
 
 .. list-table::
@@ -46,8 +50,8 @@ together with their corresponding HIP type and a short description.
 Floating-point types
 ==========================================
 
-The floating-point types that are supported by ROCm are listed in the following table, together with
-their corresponding HIP type and a short description.
+The floating-point types supported by ROCm are listed in the following
+table, along with their corresponding HIP type and a short description.
 
 .. image:: ../data/about/compatibility/floating-point-data-types.png
     :alt: Supported floating-point types
@@ -63,43 +67,62 @@ their corresponding HIP type and a short description.
     *
       - float8 (E4M3)
       - ``-``
-      - An 8-bit floating-point number that mostly follows IEEE-754 conventions and **S1E4M3** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_ , with expanded range and with no infinity or signed zero. NaN is represented as negative zero.
+      - An 8-bit floating-point number that mostly follows IEEE-754 conventions
+        and **S1E4M3** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_ ,
+        with expanded range and no infinity or signed zero. NaN is
+        represented as negative zero.
     *
       - float8 (E5M2)
       - ``-``
-      - An 8-bit floating-point number mostly following IEEE-754 conventions and **S1E5M2** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_ , with expanded range and with no infinity or signed zero. NaN is represented as negative zero.
+      - An 8-bit floating-point number mostly following IEEE-754 conventions and
+        **S1E5M2** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_ ,
+        with expanded range and no infinity or signed zero. NaN is
+        represented as negative zero.
     *
       - float16
       - ``half``
-      - A 16-bit floating-point number that conforms to the IEEE 754-2008 half-precision storage format.
+      - A 16-bit floating-point number that conforms to the IEEE 754-2008
+        half-precision storage format.
     *
       - bfloat16
       - ``bfloat16``
-      - A shortened 16-bit version of the IEEE 754 single-precision storage format.
+      - A shortened 16-bit version of the IEEE 754 single-precision storage
+        format.
     *
       - tensorfloat32
       - ``-``
-      - A floating-point number that occupies 32 bits or less of storage, providing improved range compared to half (16-bit) format, at (potentially) greater throughput than single-precision (32-bit) formats.
+      - A floating-point number that occupies 32 bits or less of storage,
+        providing improved range compared to half (16-bit) format, at
+        (potentially) greater throughput than single-precision (32-bit) formats.
     *
       - float32
       - ``float``
-      - A 32-bit floating-point number that conforms to the IEEE 754 single-precision storage format.
+      - A 32-bit floating-point number that conforms to the IEEE 754
+        single-precision storage format.
     *
       - float64
       - ``double``
-      - A 64-bit floating-point number that conforms to the IEEE 754 double-precision storage format.
+      - A 64-bit floating-point number that conforms to the IEEE 754
+        double-precision storage format.
 
 .. note::
 
-  * The float8 and tensorfloat32 types are internal types used in calculations in Matrix Cores and can be stored in any type of the same size.
-  * The encodings for FP8 (E5M2) and FP8 (E4M3) that are natively supported by MI300 differ from the FP8 (E5M2) and FP8 (E4M3) encodings used in H100 (`FP8 Formats for Deep Learning <https://arxiv.org/abs/2209.05433>`_).
+  * The float8 and tensorfloat32 types are internal types used in calculations
+    in Matrix Cores and can be stored in any type of the same size.
+
+  * The encodings for FP8 (E5M2) and FP8 (E4M3) that the
+    MI300 series natively supports differ from the FP8 (E5M2) and FP8 (E4M3)
+    encodings used in NVIDIA H100
+    (`FP8 Formats for Deep Learning <https://arxiv.org/abs/2209.05433>`_).
+
   * In some AMD documents and articles, float8 (E5M2) is referred to as bfloat8.
 
 ROCm support icons
 ==========================================
 
-In the following sections, we use icons to represent the level of support. These icons, described in the
-following table, are also used on the library data type support pages.
+In the following sections, icons represent the level of support. These
+icons, described in the following table, are also used in the library data type
+support pages.
 
 .. list-table::
     :header-rows: 1
@@ -121,14 +144,27 @@ following table, are also used on the library data type support pages.
 
 .. note::
 
-  * Full support means that the type is supported natively or with hardware emulation.
-  * Native support means that the operations for that type are implemented in hardware. Types that are not natively supported are emulated with the available hardware. The performance of non-natively supported types can differ from the full instruction throughput rate. For example, 16-bit integer operations can be performed on the 32-bit integer ALUs at full rate; however, 64-bit integer operations might need several instructions on the 32-bit integer ALUs.
-  * Any type can be emulated by software, but this page does not cover such cases.
+  * Full support means that the type is supported natively or with hardware
+    emulation.
 
-Hardware type support
+  * Native support means that the operations for that type are implemented in
+    hardware. Types that are not natively supported are emulated with the
+    available hardware. The performance of non-natively supported types can
+    differ from the full instruction throughput rate. For example, 16-bit
+    integer operations can be performed on the 32-bit integer ALUs at full rate;
+    however, 64-bit integer operations might need several instructions on the
+    32-bit integer ALUs.
+
+  * Any type can be emulated by software, but this page does not cover such
+    cases.
+
+Hardware data type support
 ==========================================
 
-AMD GPU hardware support for data types is listed in the following tables.
+The following tables provide information about AMD Instinct accelerators support
+for various data types. The MI200 series GPUs, which include MI210, MI250, and
+MI250X, are based on the CDNA2 architecture. The MI300 series GPUs, consisting
+of MI300A, MI300X, and MI325X, are built on the CDNA3 architecture.
 
 Compute units support
 -------------------------------------------------------------------------------
@@ -375,21 +411,23 @@ The following table lists data type support for atomic operations.
 
 .. note::
 
-  For cases that are not natively supported, you can emulate atomic operations using software.
-  Software-emulated atomic operations have high negative performance impact when they frequently
-  access the same memory address.
+  You can emulate atomic operations using software for cases that are not
+  natively supported. Software-emulated atomic operations have a high negative
+  performance impact when they frequently access the same memory address.
 
-Data Type support in ROCm Libraries
+Data type support in ROCm libraries
 ==========================================
 
-ROCm library support for int8, float8 (E4M3), float8 (E5M2), int16, float16, bfloat16, int32,
-tensorfloat32, float32, int64, and float64 is listed in the following tables.
+ROCm library support for int8, float8 (E4M3), float8 (E5M2), int16, float16,
+bfloat16, int32, tensorfloat32, float32, int64, and float64 is listed in the
+following tables.
 
 Libraries input/output type support
 -------------------------------------------------------------------------------
 
-The following tables list ROCm library support for specific input and output data types. For a detailed
-description, refer to the corresponding library data type support page.
+The following tables list ROCm library support for specific input and output
+data types. Refer to the corresponding library data type support page for a
+detailed description.
 
 .. tab-set::
 
@@ -516,8 +554,9 @@ description, refer to the corresponding library data type support page.
 Libraries internal calculations type support
 -------------------------------------------------------------------------------
 
-The following tables list ROCm library support for specific internal data types. For a detailed
-description, refer to the corresponding library data type support page.
+The following tables list ROCm library support for specific internal data types.
+Refer to the corresponding library data type support page for a detailed
+description.
 
 .. tab-set::
 

docs/sphinx/_toc.yml.in

@@ -89,7 +89,10 @@ subtrees:
             title: Profile and debug
           - file: how-to/rocm-for-ai/inference-optimization/workload.rst
             title: Workload tuning
-  
+
+      - url: https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/
+        title: AI tutorials
+
   - file: how-to/rocm-for-hpc/index.rst
     title: Use ROCm for HPC
   - file: how-to/system-optimization/index.rst
@@ -126,6 +129,7 @@ subtrees:
   - url: https://github.com/amd/rocm-examples
     title: ROCm examples
 
+
 - caption: Conceptual
   entries:
   - file: conceptual/gpu-arch.md

docs/sphinx/requirements.in

@@ -1,3 +1,3 @@
-rocm-docs-core==1.13.0
+rocm-docs-core==1.15.0
 sphinx-reredirects
 sphinx-sitemap

docs/sphinx/requirements.txt

@@ -8,6 +8,13 @@ accessible-pygments==0.0.5
     # via pydata-sphinx-theme
 alabaster==1.0.0
     # via sphinx
+asttokens==3.0.0
+    # via stack-data
+attrs==25.1.0
+    # via
+    #   jsonschema
+    #   jupyter-cache
+    #   referencing
 babel==2.16.0
     # via
     #   pydata-sphinx-theme
@@ -25,9 +32,17 @@ cffi==1.17.1
 charset-normalizer==3.4.0
     # via requests
 click==8.1.7
-    # via sphinx-external-toc
+    # via
+    #   jupyter-cache
+    #   sphinx-external-toc
+comm==0.2.2
+    # via ipykernel
 cryptography==43.0.3
     # via pyjwt
+debugpy==1.8.12
+    # via ipykernel
+decorator==5.1.1
+    # via ipython
 deprecated==1.2.15
     # via pygithub
 docutils==0.21.2
@@ -36,34 +51,103 @@ docutils==0.21.2
     #   myst-parser
     #   pydata-sphinx-theme
     #   sphinx
+exceptiongroup==1.2.2
+    # via ipython
+executing==2.2.0
+    # via stack-data
 fastjsonschema==2.20.0
-    # via rocm-docs-core
+    # via
+    #   nbformat
+    #   rocm-docs-core
 gitdb==4.0.11
     # via gitpython
 gitpython==3.1.43
     # via rocm-docs-core
+greenlet==3.1.1
+    # via sqlalchemy
 idna==3.10
     # via requests
 imagesize==1.4.1
     # via sphinx
+importlib-metadata==8.6.1
+    # via
+    #   jupyter-cache
+    #   myst-nb
+ipykernel==6.29.5
+    # via myst-nb
+ipython==8.31.0
+    # via
+    #   ipykernel
+    #   myst-nb
+jedi==0.19.2
+    # via ipython
 jinja2==3.1.5
     # via
     #   myst-parser
     #   sphinx
+jsonschema==4.23.0
+    # via nbformat
+jsonschema-specifications==2024.10.1
+    # via jsonschema
+jupyter-cache==1.0.1
+    # via myst-nb
+jupyter-client==8.6.3
+    # via
+    #   ipykernel
+    #   nbclient
+jupyter-core==5.7.2
+    # via
+    #   ipykernel
+    #   jupyter-client
+    #   nbclient
+    #   nbformat
 markdown-it-py==3.0.0
     # via
     #   mdit-py-plugins
     #   myst-parser
 markupsafe==3.0.2
     # via jinja2
+matplotlib-inline==0.1.7
+    # via
+    #   ipykernel
+    #   ipython
 mdit-py-plugins==0.4.2
     # via myst-parser
 mdurl==0.1.2
     # via markdown-it-py
-myst-parser==4.0.0
+myst-nb==1.1.2
     # via rocm-docs-core
+myst-parser==4.0.0
+    # via myst-nb
+nbclient==0.10.2
+    # via
+    #   jupyter-cache
+    #   myst-nb
+nbformat==5.10.4
+    # via
+    #   jupyter-cache
+    #   myst-nb
+    #   nbclient
+nest-asyncio==1.6.0
+    # via ipykernel
 packaging==24.2
-    # via sphinx
+    # via
+    #   ipykernel
+    #   sphinx
+parso==0.8.4
+    # via jedi
+pexpect==4.9.0
+    # via ipython
+platformdirs==4.3.6
+    # via jupyter-core
+prompt-toolkit==3.0.50
+    # via ipython
+psutil==6.1.1
+    # via ipykernel
+ptyprocess==0.7.0
+    # via pexpect
+pure-eval==0.2.3
+    # via stack-data
 pycparser==2.22
     # via cffi
 pydata-sphinx-theme==0.16.0
@@ -75,23 +159,42 @@ pygithub==2.5.0
 pygments==2.18.0
     # via
     #   accessible-pygments
+    #   ipython
     #   pydata-sphinx-theme
     #   sphinx
 pyjwt[crypto]==2.10.0
     # via pygithub
 pynacl==1.5.0
     # via pygithub
+python-dateutil==2.9.0.post0
+    # via jupyter-client
 pyyaml==6.0.2
     # via
+    #   jupyter-cache
+    #   myst-nb
     #   myst-parser
     #   rocm-docs-core
     #   sphinx-external-toc
+pyzmq==26.2.0
+    # via
+    #   ipykernel
+    #   jupyter-client
+referencing==0.36.2
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
 requests==2.32.3
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.13.0
+rocm-docs-core==1.15.0
     # via -r requirements.in
+rpds-py==0.22.3
+    # via
+    #   jsonschema
+    #   referencing
+six==1.17.0
+    # via python-dateutil
 smmap==5.0.1
     # via gitdb
 snowballstemmer==2.2.0
@@ -101,6 +204,7 @@ soupsieve==2.6
 sphinx==8.1.3
     # via
     #   breathe
+    #   myst-nb
     #   myst-parser
     #   pydata-sphinx-theme
     #   rocm-docs-core
@@ -137,15 +241,43 @@ sphinxcontrib-qthelp==2.0.0
     # via sphinx
 sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
+sqlalchemy==2.0.37
+    # via jupyter-cache
+stack-data==0.6.3
+    # via ipython
+tabulate==0.9.0
+    # via jupyter-cache
 tomli==2.1.0
     # via sphinx
+tornado==6.4.2
+    # via
+    #   ipykernel
+    #   jupyter-client
+traitlets==5.14.3
+    # via
+    #   comm
+    #   ipykernel
+    #   ipython
+    #   jupyter-client
+    #   jupyter-core
+    #   matplotlib-inline
+    #   nbclient
+    #   nbformat
 typing-extensions==4.12.2
     # via
+    #   ipython
+    #   myst-nb
     #   pydata-sphinx-theme
     #   pygithub
+    #   referencing
+    #   sqlalchemy
 urllib3==2.2.3
     # via
     #   pygithub
     #   requests
+wcwidth==0.2.13
+    # via prompt-toolkit
 wrapt==1.17.0
     # via deprecated
+zipp==3.21.0
+    # via importlib-metadata