Apply suggestion from @mattwill-amd

[Ex CI] Add libomp-dev, MIVisionX, rocDecode and dependencies

.azuredevops/components/ROCR-Runtime.yml

@@ -37,6 +37,7 @@ parameters:
     - libdrm-dev
     - libelf-dev
     - libnuma-dev
+    - libsimde-dev
     - ninja-build
     - pkg-config
 - name: rocmDependencies

.azuredevops/components/rccl.yml

@@ -70,7 +70,7 @@ parameters:
 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
   - job: rccl_build_${{ job.target }}
-    timeoutInMinutes: 90
+    timeoutInMinutes: 120
     variables:
     - group: common
     - template: /.azuredevops/variables-global.yml

.azuredevops/components/rocm-examples.yml

@@ -17,8 +17,14 @@ parameters:
     - libdw-dev
     - libglfw3-dev
     - libmsgpack-dev
+    - libomp-dev
+    - libopencv-dev
     - libtbb-dev
+    - libtiff-dev
     - libva-amdgpu-dev
+    - libavcodec-dev
+    - libavformat-dev
+    - libavutil-dev
     - ninja-build
     - python3-pip
 - name: rocmDependencies
@@ -38,7 +44,9 @@ parameters:
     - hipTensor
     - llvm-project
     - MIOpen
+    - MIVisionX
     - rocBLAS
+    - rocDecode
     - rocFFT
     - rocJPEG
     - rocPRIM
@@ -50,6 +58,7 @@ parameters:
     - rocSPARSE
     - rocThrust
     - rocWMMA
+    - rpp
 - name: rocmTestDependencies
   type: object
   default:
@@ -66,7 +75,10 @@ parameters:
     - hipSPARSE
     - hipTensor
     - llvm-project
+    - MIOpen
+    - MIVisionX
     - rocBLAS
+    - rocDecode
     - rocFFT
     - rocminfo
     - rocPRIM
@@ -80,6 +92,7 @@ parameters:
     - rocThrust
     - roctracer
     - rocWMMA
+    - rpp
 
 - name: jobMatrix
   type: object

.azuredevops/components/rocm-libraries.yml

@@ -43,9 +43,14 @@ parameters:
     - ninja-build
     - python3-pip
     - python3-venv
+    - googletest
+    - libgtest-dev
+    - libgmock-dev
+    - libboost-filesystem-dev
 - name: pipModules
   type: object
   default:
+    - msgpack
     - joblib
     - "packaging>=22.0"
     - pytest
@@ -147,6 +152,13 @@ jobs:
           echo "##vso[task.prependpath]$USER_BASE/bin"
           echo "##vso[task.setvariable variable=PytestCmakePath]$USER_BASE/share/Pytest/cmake"
         displayName: Set cmake configure paths
+    - task: Bash@3
+      displayName: Add ROCm binaries to PATH
+      inputs:
+        targetType: inline
+        script: |
+          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/bin"
+          echo "##vso[task.prependpath]$(Agent.BuildDirectory)/rocm/llvm/bin"
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}

.azuredevops/dependencies/cli11.yml

@@ -0,0 +1,63 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: cli11Version
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: cli11_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone cli11 ${{ parameters.cli11Version }}
+      inputs:
+        targetType: inline
+        script: git clone https://github.com/CLIUtils/CLI11.git -b ${{ parameters.cli11Version }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/CLI11/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/CLI11
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/dependencies/yamlcpp.yml

@@ -0,0 +1,66 @@
+parameters:
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+- name: yamlcppVersion
+  type: string
+  default: ''
+- name: aptPackages
+  type: object
+  default:
+    - cmake
+    - git
+    - ninja-build
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { os: ubuntu2204, packageManager: apt}
+      - { os: almalinux8, packageManager: dnf}
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: yamlcpp_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    pool:
+      vmImage: 'ubuntu-22.04'
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - checkout: none
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - task: Bash@3
+      displayName: Clone yaml-cpp ${{ parameters.yamlcppVersion }}
+      inputs:
+        targetType: inline
+        script: git clone  https://github.com/jbeder/yaml-cpp.git -b ${{ parameters.yamlcppVersion }}
+        workingDirectory: $(Agent.BuildDirectory)
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        cmakeBuildDir: $(Agent.BuildDirectory)/yaml-cpp/build
+        cmakeSourceDir: $(Agent.BuildDirectory)/yaml-cpp
+        useAmdclang: false
+        extraBuildFlags: >-
+          -DCMAKE_BUILD_TYPE=Release
+          -DYAML_CPP_BUILD_TOOLS=OFF
+          -DYAML_BUILD_SHARED_LIBS=OFF
+          -DYAML_CPP_INSTALL=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        os: ${{ job.os }}

.azuredevops/tag-builds/cli11.yml

@@ -0,0 +1,23 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: cli11Version
+  type: string
+  default: "main"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/cli11.yml
+    parameters:
+      cli11Version: ${{ parameters.cli11Version }}

.azuredevops/tag-builds/yaml-cpp.yml

@@ -0,0 +1,24 @@
+variables:
+- group: common
+- template: /.azuredevops/variables-global.yml
+
+parameters:
+- name: yamlcppVersion
+  type: string
+  default: "0.8.0"
+
+resources:
+  repositories:
+  - repository: pipelines_repo
+    type: github
+    endpoint: ROCm
+    name: ROCm/ROCm
+
+trigger: none
+pr: none
+
+jobs:
+  - template: ${{ variables.CI_DEPENDENCIES_PATH }}/yamlcpp.yml
+    parameters:
+      yamlcppVersion: ${{ parameters.yamlcppVersion }}
+      

CHANGELOG.md

@@ -912,11 +912,15 @@ HIP runtime has the following functional improvements which improves runtime per
 * Compatibility with NCCL 2.25.1.
 * Compatibility with NCCL 2.26.6.
 
+#### Optimized
+* Improved the performance of the `FP8` Sum operation by upcasting to `FP16`.
+
 #### Resolved issues
 
 * Resolved an issue when using more than 64 channels when multiple collectives are used in the same `ncclGroup()` call.
 * Fixed unit test failures in tests ending with the `ManagedMem` and `ManagedMemGraph` suffixes.
 * Fixed a suboptimal algorithmic switching point for AllReduce on the AMD Instinct MI300X.
+* Fixed broken functionality within the LL protocol on gfx950 by disabling inlining of LLGenericOp kernels.
 * Fixed the known issue "When splitting a communicator using `ncclCommSplit` in some GPU configurations, MSCCL initialization can cause a segmentation fault" with a design change to use `comm` instead of `rank` for `mscclStatus`. The global map for `comm` to `mscclStatus` is still not thread safe but should be explicitly handled by mutexes for read-write operations. This is tested for correctness, but there is a plan to use a thread-safe map data structure in an upcoming release.
 
 ### **rocAL** (2.3.0)
@@ -4112,7 +4116,7 @@ memory partition modes upon an invalid argument return from memory partition mod
 
 - JSON output plugin for `rocprofv2`. The JSON file matches Google Trace Format making it easy to load on Perfetto, Chrome tracing, or Speedscope. For Speedscope, use `--disable-json-data-flows` option as speedscope doesn't work with data flows.
 - `--no-serialization` flag to disable kernel serialization when `rocprofv2` is in counter collection mode. This allows `rocprofv2` to avoid deadlock when profiling certain programs in counter collection mode.
-- `FP64_ACTIVE` and `ENGINE_ACTIVE` metrics to AMD Instinct MI300 accelerator
+- `FP64_ACTIVE` and `ENGINE_ACTIVE` metrics to AMD Instinct MI300 GPU
 - New HIP APIs with struct defined inside union.
 - Early checks to confirm the eligibility of ELF file in ATT plugin
 - Support for kernel name filtering in `rocprofv2`
@@ -4136,18 +4140,18 @@ memory partition modes upon an invalid argument return from memory partition mod
 
 #### Resolved issues
 
-- Bandwidth measurement in AMD Instinct MI300 accelerator
+- Bandwidth measurement in AMD Instinct MI300 GPU
 - Perfetto plugin issue of `roctx` trace not getting displayed
 - `--help` for counter collection
 - Signal management issues in `queue.cpp`
 - Perfetto tracks for multi-GPU
 - Perfetto plugin usage with `rocsys`
 - Incorrect number of columns in the output CSV files for counter collection and kernel tracing
-- The ROCProfiler hang issue when running kernel trace, thread trace, or counter collection on Iree benchmark for AMD Instinct MI300 accelerator
+- The ROCProfiler hang issue when running kernel trace, thread trace, or counter collection on Iree benchmark for AMD Instinct MI300 GPU
 - Build errors thrown during parsing of unions
 - The system hang caused while running `--kernel-trace` with Perfetto for certain applications
 - Missing profiler records issue caused while running `--trace-period`
-- The hang issue of `ProfilerAPITest` of `runFeatureTests` on AMD Instinct MI300 accelerator
+- The hang issue of `ProfilerAPITest` of `runFeatureTests` on AMD Instinct MI300 GPU
 - Segmentation fault on Navi32
 
 
@@ -5544,7 +5548,7 @@ See [issue #3499](https://github.com/ROCm/ROCm/issues/3499) on GitHub.
   intermediary script to call the application with the necessary arguments, then call the script with Omniperf. This
   issue is fixed in a future release of Omniperf. See [#347](https://github.com/ROCm/rocprofiler-compute/issues/347).
 
-- Omniperf might not work with AMD Instinct MI300 accelerators out of the box, resulting in the following error:
+- Omniperf might not work with AMD Instinct MI300 GPUs out of the box, resulting in the following error:
   "*ERROR gfx942 is not enabled rocprofv1. Available profilers include: ['rocprofv2']*". As a workaround, add the
   environment variable `export ROCPROF=rocprofv2`.
 
@@ -5660,7 +5664,7 @@ See [issue #3498](https://github.com/ROCm/ROCm/issues/3498) on GitHub.
 
 #### Optimized
 
-* Improved performance of Level 1 `dot_batched` and `dot_strided_batched` for all precisions. Performance enhanced by 6 times for bigger problem sizes, as measured on an Instinct MI210 accelerator.
+* Improved performance of Level 1 `dot_batched` and `dot_strided_batched` for all precisions. Performance enhanced by 6 times for bigger problem sizes, as measured on an Instinct MI210 GPU.
 
 #### Removed
 

RELEASE.md

@@ -149,11 +149,11 @@ firmware, AMD GPU drivers, and the ROCm user space software.
       </tr>
       <tr>
           <td>MI250</td>
-          <td>MU5 w/ IFWI 75 (or later)</td>
+          <td>MU3 w/ IFWI 73</td>
       </tr>
       <tr>
           <td>MI210</td>
-          <td>MU5 w/ IFWI 75 (or later)</td>
+          <td>MU3 w/ IFWI 73</td>
           <td>8.4.0.K</td>
       </tr>
       <tr>
@@ -699,7 +699,7 @@ The problem occurs when attempting to debug a program that contains code that ru
  
 The ROCR Debug Agent might also become unresponsive when attempting to capture data from a program that is experiencing queue errors, memory faults, or other triggering events.
  
-For a detailed workaround, see the [Installation troubleshooting](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/install-faq.html#issue-10-rocm-debugging-tools-might-become-unresponsive-in-selinux-enabled-distributions) documentation. This issue will be fixed in a future ROCm release.
+For a detailed workaround, see the [Installation troubleshooting](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/install-faq.html#issue-10-rocm-debugging-tools-might-become-unresponsive-in-selinux-enabled-distributions) documentation. This issue will be fixed in a future ROCm release. See [GitHub issue #5498](https://github.com/ROCm/ROCm/issues/5498).
 
 ### MIGraphX Python API will fail when running on Python 3.13
 
@@ -708,11 +708,11 @@ Applications using the MIGraphX Python API will fail when running on Python 3.13
 ```
 ls -l /opt/rocm-7.0.0/lib/libmigraphx_py_*.so
 ```
-The issue will be resolved in a future ROCm release.
+The issue will be resolved in a future ROCm release. See [GitHub issue #5500](https://github.com/ROCm/ROCm/issues/5500).
 
 ### Applications using OpenCV might fail due to package incompatibility between the OS
 
-OpenCV packages built on Ubuntu 24.04 are incompatible with Debian 13 due to a version conflict. As a result, applications, tests, and samples that use OpenCV might fail. To avoid the version conflict, rebuild OpenCV with the version corresponding to Debian 13, then rebuild MIVisionX on top of it. As a workaround, rebuild OpenCV from source, followed by the application that uses OpenCV. This issue will be fixed in a future ROCm release.
+OpenCV packages built on Ubuntu 24.04 are incompatible with Debian 13 due to a version conflict. As a result, applications, tests, and samples that use OpenCV might fail. To avoid the version conflict, rebuild OpenCV with the version corresponding to Debian 13, then rebuild MIVisionX on top of it. As a workaround, rebuild OpenCV from source, followed by the application that uses OpenCV. This issue will be fixed in a future ROCm release. See [GitHub issue #5501](https://github.com/ROCm/ROCm/issues/5501).
 
 ## ROCm upcoming changes
 

docs/about/license.md

@@ -30,6 +30,7 @@ additional licenses. Please review individual repositories for more information.
 | [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) |
 | [AQLprofile](https://github.com/rocm/aqlprofile/) | [MIT](https://github.com/ROCm/aqlprofile/blob/amd-staging/LICENSE.md) |
+| [Cluster Validation Suite](https://github.com/ROCm/cvs) | [MIT](https://github.com/ROCm/cvs/blob/main/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) |

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

@@ -2,7 +2,7 @@ ROCm Version,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6
       :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,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,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,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 10.0 [#rhel-10-702-past-60]_, 9.6 [#rhel-10-702-past-60]_, 9.4 [#rhel-94-702-past-60]_","RHEL 9.6 [#rhel-10-702-past-60], 9.4 [#rhel-94-702-past-60]_","RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","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 10.0 [#rhel-10-702-past-60]_, 9.6 [#rhel-10-702-past-60]_, 9.4 [#rhel-94-702-past-60]_","RHEL 9.6 [#rhel-10-702-past-60]_, 9.4 [#rhel-94-702-past-60]_","RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","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-700-past-60]_,RHEL 8.10 [#rhel-700-past-60]_,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,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 SP7 [#sles-db-700-past-60]_,SLES 15 SP7 [#sles-db-700-past-60]_,"SLES 15 SP7, SP6","SLES 15 SP7, SP6",SLES 15 SP6,SLES 15 SP6,"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 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

docs/compatibility/compatibility-matrix.rst

@@ -10,10 +10,9 @@ Use this matrix to view the ROCm compatibility and system requirements across su
 
 You can also refer to the :ref:`past versions of ROCm compatibility matrix<past-rocm-compatibility-matrix>`.
 
-Accelerators and GPUs listed in the following table support compute workloads (no display
+GPUs listed in the following table support compute workloads (no display
 information or graphics). If you’re using ROCm with AMD Radeon GPUs or Ryzen APUs for graphics
-workloads, see the `Use ROCm on Radeon and Ryzen
-<https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/index.html>`_ to verify
+workloads, see the :docs:`Use ROCm on Radeon and Ryzen <radeon:index.html>` to verify
 compatibility and system requirements.
 
 .. |br| raw:: html
@@ -124,6 +123,7 @@ compatibility and system requirements.
       :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
       :doc:`ROCm SMI <rocm_smi_lib:index>`,7.8.0,7.8.0,7.5.0
       :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.2.0,1.2.0,1.1.0
+      :doc:`Cluster Validation Suite <cvs:index>`,1.0.0,1.0.0,N/A
       ,,,
       PERFORMANCE TOOLS,,,
       :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,2.6.0,1.4.0

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

@@ -79,7 +79,7 @@ Use cases and recommendations
 
 * 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
+  GPU 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.
 

docs/compatibility/ml-compatibility/pytorch-compatibility.rst

@@ -73,9 +73,9 @@ Use cases and recommendations
 
 * 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 helps users achieve optimal performance for
+  GPU using ROCm. This guide helps users achieve optimal performance for
   deep learning and other high-performance computing tasks on the MI300X
-  accelerator.
+  GPU.
 
 * The :doc:`Inception with PyTorch documentation </conceptual/ai-pytorch-inception>`
   describes how PyTorch integrates with ROCm for AI workloads It outlines the
@@ -417,7 +417,7 @@ Key features and enhancements for PyTorch 2.7 with ROCm 7.0
 
 - Expanded GPU architecture support: Provides optimized support for newer GPU
   architectures, including gfx1200 and gfx1201 with preferred hipBLASLt backend
-  selection, along with improvements for gfx950 and gfx1100 series GPUs.
+  selection, along with improvements for gfx950 and gfx1100 Series GPUs.
 
 - Advanced Triton Integration: AOTriton 0.10b introduces official support for
   gfx950 and gfx1201, along with experimental support for gfx1101, gfx1151,

docs/compatibility/ml-compatibility/taichi-compatibility.rst

@@ -30,8 +30,8 @@ visual effects in film and gaming, and general-purpose computing.
 
 Supported devices and features
 ===============================================================================
-There is support through the ROCm software stack for all Taichi GPU features on AMD Instinct MI250X and MI210X series GPUs with the exception of Taichi’s GPU rendering system, CGUI.
-AMD Instinct MI300X series GPUs will be supported by November.
+There is support through the ROCm software stack for all Taichi GPU features on AMD Instinct MI250X and MI210X Series GPUs with the exception of Taichi’s GPU rendering system, CGUI.
+AMD Instinct MI300X Series GPUs will be supported by November.
 
 .. _taichi-recommendations:
 

docs/conceptual/gpu-arch.md

@@ -13,22 +13,22 @@
 :gutter: 1
 
 :::{grid-item-card}
-**AMD Instinct MI300 series**
+**AMD Instinct MI300 Series**
 
-Review hardware aspects of the AMD Instinct™ MI300 series of GPU accelerators and the CDNA™ 3
+Review hardware aspects of the AMD Instinct™ MI300 Series GPUs and the CDNA™ 3
 architecture.
 
 * [AMD Instinct™ MI300 microarchitecture](./gpu-arch/mi300.md)
 * [AMD Instinct MI300/CDNA3 ISA](https://www.amd.com/content/dam/amd/en/documents/instinct-tech-docs/instruction-set-architectures/amd-instinct-mi300-cdna3-instruction-set-architecture.pdf)
 * [White paper](https://www.amd.com/content/dam/amd/en/documents/instinct-tech-docs/white-papers/amd-cdna-3-white-paper.pdf)
 * [MI300 performance counters](./gpu-arch/mi300-mi200-performance-counters.rst)
-* [MI350 series performance counters](./gpu-arch/mi350-performance-counters.rst)
+* [MI350 Series performance counters](./gpu-arch/mi350-performance-counters.rst)
 :::
 
 :::{grid-item-card}
-**AMD Instinct MI200 series**
+**AMD Instinct MI200 Series**
 
-Review hardware aspects of the AMD Instinct™ MI200 series of GPU accelerators and the CDNA™ 2
+Review hardware aspects of the AMD Instinct™ MI200 Series GPUs and the CDNA™ 2
 architecture.
 
 * [AMD Instinct™ MI250 microarchitecture](./gpu-arch/mi250.md)
@@ -41,7 +41,7 @@ architecture.
 :::{grid-item-card}
 **AMD Instinct MI100**
 
-Review hardware aspects of the AMD Instinct™ MI100 series of GPU accelerators and the CDNA™ 1
+Review hardware aspects of the AMD Instinct™ MI100 Series GPUs and the CDNA™ 1
 architecture.
 
 * [AMD Instinct™ MI100 microarchitecture](./gpu-arch/mi100.md)

docs/conceptual/gpu-arch/mi100.md

@@ -1,14 +1,14 @@
 ---
 myst:
   html_meta:
-    "description lang=en": "Learn about the AMD Instinct MI100 series architecture."
+    "description lang=en": "Learn about the AMD Instinct MI100 Series architecture."
     "keywords": "Instinct, MI100, microarchitecture, AMD, ROCm"
 ---
 
 # AMD Instinct™ MI100 microarchitecture
 
 The following image shows the node-level architecture of a system that
-comprises two AMD EPYC™ processors and (up to) eight AMD Instinct™ accelerators.
+comprises two AMD EPYC™ processors and (up to) eight AMD Instinct™ GPUs.
 The two EPYC processors are connected to each other with the AMD Infinity™
 fabric which provides a high-bandwidth (up to 18 GT/sec) and coherent links such
 that each processor can access the available node memory as a single
@@ -18,29 +18,29 @@ available to connect the processors plus one PCIe Gen 4 x16 link per processor
 can attach additional I/O devices such as the host adapters for the network
 fabric.
 
-![Structure of a single GCD in the AMD Instinct MI100 accelerator](../../data/conceptual/gpu-arch/image004.png "Node-level system architecture with two AMD EPYC™ processors and eight AMD Instinct™ accelerators.")
+![Structure of a single GCD in the AMD Instinct MI100 GPU](../../data/conceptual/gpu-arch/image004.png "Node-level system architecture with two AMD EPYC™ processors and eight AMD Instinct™ GPUs.")
 
 In a typical node configuration, each processor can host up to four AMD
-Instinct™ accelerators that are attached using PCIe Gen 4 links at 16 GT/sec,
+Instinct™ GPUs that are attached using PCIe Gen 4 links at 16 GT/sec,
 which corresponds to a peak bidirectional link bandwidth of 32 GB/sec. Each hive
-of four accelerators can participate in a fully connected, coherent AMD
-Instinct™ fabric that connects the four accelerators using 23 GT/sec AMD
+of four GPUs can participate in a fully connected, coherent AMD
+Instinct™ fabric that connects the four GPUs using 23 GT/sec AMD
 Infinity fabric links that run at a higher frequency than the inter-processor
 links. This inter-GPU link can be established in certified server systems if the
 GPUs are mounted in neighboring PCIe slots by installing the AMD Infinity
-Fabric™ bridge for the AMD Instinct™ accelerators.
+Fabric™ bridge for the AMD Instinct™ GPUs.
 
 ## Microarchitecture
 
-The microarchitecture of the AMD Instinct accelerators is based on the AMD CDNA
+The microarchitecture of the AMD Instinct GPUs is based on the AMD CDNA
 architecture, which targets compute applications such as high-performance
 computing (HPC) and AI & machine learning (ML) that run on everything from
 individual servers to the world's largest exascale supercomputers. The overall
 system architecture is designed for extreme scalability and compute performance.
 
-![Structure of the AMD Instinct accelerator (MI100 generation)](../../data/conceptual/gpu-arch/image005.png "Structure of the AMD Instinct accelerator (MI100 generation)")
+![Structure of the AMD Instinct GPU (MI100 generation)](../../data/conceptual/gpu-arch/image005.png "Structure of the AMD Instinct GPU (MI100 generation)")
 
-The above image shows the AMD Instinct accelerator with its PCIe Gen 4 x16
+The above image shows the AMD Instinct GPU with its PCIe Gen 4 x16
 link (16 GT/sec, at the bottom) that connects the GPU to (one of) the host
 processor(s). It also shows the three AMD Infinity Fabric ports that provide
 high-speed links (23 GT/sec, also at the bottom) to the other GPUs of the local
@@ -48,7 +48,7 @@ hive.
 
 On the left and right of the floor plan, the High Bandwidth Memory (HBM)
 attaches via the GPU memory controller.  The MI100 generation of the AMD
-Instinct accelerator offers four stacks of HBM generation 2 (HBM2) for a total
+Instinct GPU offers four stacks of HBM generation 2 (HBM2) for a total
 of 32GB with a 4,096bit-wide memory interface. The peak memory bandwidth of the
 attached HBM2 is 1.228 TB/sec at a memory clock frequency of 1.2 GHz.
 
@@ -64,7 +64,7 @@ Therefore, the theoretical maximum FP64 peak performance is 11.5 TFLOPS
 ![Block diagram of an MI100 compute unit with detailed SIMD view of the AMD CDNA architecture](../../data/conceptual/gpu-arch/image006.png "An MI100 compute unit with detailed SIMD view of the AMD CDNA architecture")
 
 The preceding image shows the block diagram of a single CU of an AMD Instinct™
-MI100 accelerator and summarizes how instructions flow through the execution
+MI100 GPU and summarizes how instructions flow through the execution
 engines. The CU fetches the instructions via a 32KB instruction cache and moves
 them forward to execution via a dispatcher. The CU can handle up to ten
 wavefronts at a time and feed their instructions into the execution unit. The

docs/conceptual/gpu-arch/mi250.md

@@ -1,13 +1,13 @@
 ---
 myst:
   html_meta:
-    "description lang=en": "Learn about the AMD Instinct MI250 series architecture."
+    "description lang=en": "Learn about the AMD Instinct MI250 Series architecture."
     "keywords": "Instinct, MI250, microarchitecture, AMD, ROCm"
 ---
 
 # AMD Instinct™ MI250 microarchitecture
 
-The microarchitecture of the AMD Instinct MI250 accelerators is based on the
+The microarchitecture of the AMD Instinct MI250 GPU is based on the
 AMD CDNA 2 architecture that targets compute applications such as HPC,
 artificial intelligence (AI), and machine learning (ML) and that run on
 everything from individual servers to the world’s largest exascale
@@ -40,7 +40,7 @@ execution units (also called matrix cores), which are geared toward executing
 matrix operations like matrix-matrix multiplications. For FP64, the peak
 performance of these units amounts to 90.5 TFLOPS.
 
-![Structure of a single GCD in the AMD Instinct MI250 accelerator.](../../data/conceptual/gpu-arch/image001.png "Structure of a single GCD in the AMD Instinct MI250 accelerator.")
+![Structure of a single GCD in the AMD Instinct MI250 GPU.](../../data/conceptual/gpu-arch/image001.png "Structure of a single GCD in the AMD Instinct MI250 GPU.")
 
 ```{list-table} Peak-performance capabilities of the MI250 OAM for different data types.
 :header-rows: 1
@@ -84,16 +84,9 @@ performance of these units amounts to 90.5 TFLOPS.
   - 362.1
 ```
 
-The above table summarizes the aggregated peak performance of the AMD
-Instinct MI250 OCP Open Accelerator Modules (OAM, OCP is short for Open Compute
-Platform) and its two GCDs for different data types and execution units. The
-middle column lists the peak performance (number of data elements processed in a
-single instruction) of a single compute unit if a SIMD (or matrix) instruction
-is being retired in each clock cycle. The third column lists the theoretical
-peak performance of the OAM module. The theoretical aggregated peak memory
-bandwidth of the GPU is 3.2 TB/sec (1.6 TB/sec per GCD).
+The above table summarizes the aggregated peak performance of the AMD Instinct MI250 Open Compute Platform (OCP) Open Accelerator Modules (OAMs) and its two GCDs for different data types and execution units. The middle column lists the peak performance (number of data elements processed in a single instruction) of a single compute unit if a SIMD (or matrix) instruction is being retired in each clock cycle. The third column lists the theoretical peak performance of the OAM module. The theoretical aggregated peak memory bandwidth of the GPU is 3.2 TB/sec (1.6 TB/sec per GCD).
 
-![Dual-GCD architecture of the AMD Instinct MI250 accelerators](../../data/conceptual/gpu-arch/image002.png "Dual-GCD architecture of the AMD Instinct MI250 accelerators")
+![Dual-GCD architecture of the AMD Instinct MI250 GPUs](../../data/conceptual/gpu-arch/image002.png "Dual-GCD architecture of the AMD Instinct MI250 GPUs")
 
 The following image shows the block diagram of an OAM package that consists
 of two GCDs, each of which constitutes one GPU device in the system. The two
@@ -105,18 +98,18 @@ between the two GCDs of an OAM, or a bidirectional peak transfer bandwidth of
 ## Node-level architecture
 
 The following image shows the node-level architecture of a system that is
-based on the AMD Instinct MI250 accelerator. The MI250 OAMs attach to the host
+based on the AMD Instinct MI250 GPU. The MI250 OAMs attach to the host
 system via PCIe Gen 4 x16 links (yellow lines). Each GCD maintains its own PCIe
 x16 link to the host part of the system. Depending on the server platform, the
 GCD can attach to the AMD EPYC processor directly or via an optional PCIe switch
 . Note that some platforms may offer an x8 interface to the GCDs, which reduces
 the available host-to-GPU bandwidth.
 
-![Block diagram of AMD Instinct MI250 Accelerators with 3rd Generation AMD EPYC processor](../../data/conceptual/gpu-arch/image003.png "Block diagram of AMD Instinct MI250 Accelerators with 3rd Generation AMD EPYC processor")
+![Block diagram of AMD Instinct MI250 GPUs with 3rd Generation AMD EPYC processor](../../data/conceptual/gpu-arch/image003.png "Block diagram of AMD Instinct MI250 GPUs with 3rd Generation AMD EPYC processor")
 
 The preceding image shows the node-level architecture of a system with AMD
 EPYC processors in a dual-socket configuration and four AMD Instinct MI250
-accelerators. The MI250 OAMs attach to the host processors system via PCIe Gen 4
+GPUs. The MI250 OAMs attach to the host processors system via PCIe Gen 4
 x16 links (yellow lines). Depending on the system design, a PCIe switch may
 exist to make more PCIe lanes available for additional components like network
 interfaces and/or storage devices. Each GCD maintains its own PCIe x16 link to

docs/conceptual/gpu-arch/mi300-mi200-performance-counters.rst

@@ -1,16 +1,16 @@
 .. meta::
-  :description: MI300 and MI200 series performance counters and metrics
+  :description: MI300 and MI200 Series performance counters and metrics
   :keywords: MI300, MI200, performance counters, command processor counters
 
 ***************************************************************************************************
-MI300 and MI200 series performance counters and metrics
+MI300 and MI200 Series performance counters and metrics
 ***************************************************************************************************
 
 This document lists and describes the hardware performance counters and derived metrics available
 for the AMD Instinct™ MI300 and MI200 GPU. You can also access this information using the
 :doc:`ROCprofiler-SDK <rocprofiler-sdk:how-to/using-rocprofv3>`.
 
-MI300 and MI200 series performance counters
+MI300 and MI200 Series performance counters
 ===============================================================
 
 Series performance counters include the following categories:
@@ -27,7 +27,7 @@ The following sections provide additional details for each category.
 
 .. note::
 
-  Preliminary validation of all MI300 and MI200 series performance counters is in progress. Those with
+  Preliminary validation of all MI300 and MI200 Series performance counters is in progress. Those with
   an asterisk (*) require further evaluation.
 
 .. _command-processor-counters:
@@ -171,7 +171,7 @@ Instruction mix
   "``SQ_INSTS_SMEM``", "Instr", "Number of scalar memory instructions issued"
   "``SQ_INSTS_SMEM_NORM``", "Instr", "Number of scalar memory instructions normalized to match ``smem_level`` issued"
   "``SQ_INSTS_FLAT``", "Instr", "Number of flat instructions issued"
-  "``SQ_INSTS_FLAT_LDS_ONLY``", "Instr", "**MI200 series only** Number of FLAT instructions that read/write only from/to LDS issued. Works only if ``EARLY_TA_DONE`` is enabled."
+  "``SQ_INSTS_FLAT_LDS_ONLY``", "Instr", "**MI200 Series only** Number of FLAT instructions that read/write only from/to LDS issued. Works only if ``EARLY_TA_DONE`` is enabled."
   "``SQ_INSTS_LDS``", "Instr", "Number of LDS instructions issued **(MI200: includes flat; MI300: does not include flat)**"
   "``SQ_INSTS_GDS``", "Instr", "Number of global data share instructions issued"
   "``SQ_INSTS_EXP_GDS``", "Instr", "Number of EXP and global data share instructions excluding skipped export instructions issued"
@@ -396,9 +396,9 @@ Texture cache per pipe counters
   "``TCP_UTCL1_TRANSLATION_MISS[n]``", "Req", "Number of unified translation cache (L1) translation misses", "0-15"
   "``TCP_UTCL1_PERMISSION_MISS[n]``", "Req", "Number of unified translation cache (L1) permission misses", "0-15"
   "``TCP_TOTAL_CACHE_ACCESSES[n]``", "Req", "Number of vector L1d cache accesses including hits and misses", "0-15"
-  "``TCP_TCP_LATENCY[n]``", "Cycles", "**MI200 series only** Accumulated wave access latency to vL1D over all wavefronts", "0-15"
-  "``TCP_TCC_READ_REQ_LATENCY[n]``", "Cycles", "**MI200 series only** Total vL1D to L2 request latency over all wavefronts for reads and atomics with return", "0-15"
-  "``TCP_TCC_WRITE_REQ_LATENCY[n]``", "Cycles", "**MI200 series only** Total vL1D to L2 request latency over all wavefronts for writes and atomics without return", "0-15"
+  "``TCP_TCP_LATENCY[n]``", "Cycles", "**MI200 Series only** Accumulated wave access latency to vL1D over all wavefronts", "0-15"
+  "``TCP_TCC_READ_REQ_LATENCY[n]``", "Cycles", "**MI200 Series only** Total vL1D to L2 request latency over all wavefronts for reads and atomics with return", "0-15"
+  "``TCP_TCC_WRITE_REQ_LATENCY[n]``", "Cycles", "**MI200 Series only** Total vL1D to L2 request latency over all wavefronts for writes and atomics without return", "0-15"
   "``TCP_TCC_READ_REQ[n]``", "Req", "Number of read requests to L2 cache", "0-15"
   "``TCP_TCC_WRITE_REQ[n]``", "Req", "Number of write requests to L2 cache", "0-15"
   "``TCP_TCC_ATOMIC_WITH_RET_REQ[n]``", "Req", "Number of atomic requests to L2 cache with return", "0-15"
@@ -560,7 +560,7 @@ Note the following:
   ``TCC_TAG_STALL[n]``, probes can stall the pipeline at a variety of places. There is no single point that
   can accurately measure the total stalls
 
-MI300 and MI200 series derived metrics list
+MI300 and MI200 Series derived metrics list
 ==============================================================
 
 .. csv-table::

docs/conceptual/gpu-arch/mi300.md

@@ -1,21 +1,21 @@
 ---
 myst:
   html_meta:
-    "description lang=en": "Learn about the AMD Instinct MI300 series architecture."
+    "description lang=en": "Learn about the AMD Instinct MI300 Series architecture."
     "keywords": "Instinct, MI300X, MI300A, microarchitecture, AMD, ROCm"
 ---
 
-# AMD Instinct™ MI300 series microarchitecture
+# AMD Instinct™ MI300 Series microarchitecture
 
-The AMD Instinct MI300 series accelerators are based on the AMD CDNA 3
+The AMD Instinct MI300 Series GPUs are based on the AMD CDNA 3
 architecture which was designed to deliver leadership performance for HPC, artificial intelligence (AI), and machine
-learning (ML) workloads. The AMD Instinct MI300 series accelerators are well-suited for extreme scalability and compute performance, running
+learning (ML) workloads. The AMD Instinct MI300 Series GPUs are well-suited for extreme scalability and compute performance, running
 on everything from individual servers to the world’s largest exascale supercomputers.
 
-With the MI300 series, AMD is introducing the Accelerator Complex Die (XCD), which contains the
+With the MI300 Series, AMD is introducing the Accelerator Complex Die (XCD), which contains the
 GPU computational elements of the processor along with the lower levels of the cache hierarchy.
 
-The following image depicts the structure of a single XCD in the AMD Instinct MI300 accelerator series.
+The following image depicts the structure of a single XCD in the AMD Instinct MI300 GPU Series.
 
 ```{figure} ../../data/shared/xcd-sys-arch.png
 ---
@@ -39,7 +39,7 @@ infrastructure) using the AMD Infinity Fabric™ technology as interconnect.
 The Matrix Cores inside the CDNA 3 CUs have significant improvements, emphasizing AI and machine
 learning, enhancing throughput of existing data types while adding support for new data types.
 CDNA 2 Matrix Cores support FP16 and BF16, while offering INT8 for inference. Compared to MI250X
-accelerators, CDNA 3 Matrix Cores triple the performance for FP16 and BF16, while providing a
+GPUs, CDNA 3 Matrix Cores triple the performance for FP16 and BF16, while providing a
 performance gain of 6.8 times for INT8. FP8 has a performance gain of 16 times compared to FP32,
 while TF32 has a gain of 4 times compared to FP32.
 
@@ -105,7 +105,7 @@ name: mi300-arch
 alt:
 align: center
 ---
-MI300 series system architecture showing MI300A (left) with 6 XCDs and 3 CCDs, while the MI300X (right) has 8 XCDs.
+MI300 Series system architecture showing MI300A (left) with 6 XCDs and 3 CCDs, while the MI300X (right) has 8 XCDs.
 ```
 
 ## Node-level architecture
@@ -116,11 +116,11 @@ name: mi300-node
 
 align: center
 ---
-MI300 series node-level architecture showing 8 fully interconnected MI300X OAM modules connected to (optional) PCIEe switches via retimers and HGX connectors.
+MI300 Series node-level architecture showing 8 fully interconnected MI300X OAM modules connected to (optional) PCIEe switches via retimers and HGX connectors.
 ```
 
 The image above shows the node-level architecture of a system with AMD EPYC processors in a
-dual-socket configuration and eight AMD Instinct MI300X accelerators. The MI300X OAMs attach to the
+dual-socket configuration and eight AMD Instinct MI300X GPUs. The MI300X OAMs attach to the
 host system via PCIe Gen 5 x16 links (yellow lines). The GPUs are using seven high-bandwidth,
 low-latency AMD Infinity Fabric™ links (red lines) to form a fully connected 8-GPU system.
 

docs/conceptual/gpu-arch/mi350-performance-counters.rst

@@ -1,12 +1,12 @@
 .. meta::
-  :description: MI355 series performance counters and metrics
+  :description: MI355 Series performance counters and metrics
   :keywords: MI355, MI355X, MI3XX
 
 ***********************************
-MI350 series performance counters
+MI350 Series performance counters
 ***********************************
 
-This topic lists and describes the hardware performance counters and derived metrics available on the AMD Instinct MI350 and MI355 accelerators. These counters are available for profiling using `ROCprofiler-SDK <https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/latest/index.html>`_ and `ROCm Compute Profiler <https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/>`_.
+This topic lists and describes the hardware performance counters and derived metrics available on the AMD Instinct MI350 and MI355 GPUs. These counters are available for profiling using `ROCprofiler-SDK <https://rocm.docs.amd.com/projects/rocprofiler-sdk/en/latest/index.html>`_ and `ROCm Compute Profiler <https://rocm.docs.amd.com/projects/rocprofiler-compute/en/latest/>`_.
 
 The following sections list the performance counters based on the IP blocks.
 

docs/conf.py

@@ -234,7 +234,7 @@ suppress_warnings = ["autosectionlabel.*"]
 
 html_context = {
     "project_path" : {project_path},
-    "gpu_type" : [('AMD Instinct accelerators', 'intrinsic'), ('AMD gfx families', 'gfx'), ('NVIDIA families', 'nvidia') ],
+    "gpu_type" : [('AMD Instinct GPUs', 'intrinsic'), ('AMD gfx families', 'gfx'), ('NVIDIA families', 'nvidia') ],
     "atomics_type" : [('HW atomics', 'hw-atomics'), ('CAS emulation', 'cas-atomics')],
     "pcie_type" : [('No PCIe atomics', 'nopcie'), ('PCIe atomics', 'pcie')],
     "memory_type" : [('Device DRAM', 'device-dram'), ('Migratable Host DRAM', 'migratable-host-dram'), ('Pinned Host DRAM', 'pinned-host-dram')],

docs/data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml

@@ -1,47 +1,16 @@
 dockers:
-  - pull_tag: rocm/jax-training:maxtext-v25.7-jax060
+  - pull_tag: rocm/jax-training:maxtext-v25.9
     docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
     components:
-      ROCm: 6.4.1
-      JAX: 0.6.0
-      Python: 3.10.12
-      Transformer Engine: 2.1.0+90d703dd
-      hipBLASLt: 1.1.0-499ece1c21
-  - pull_tag: rocm/jax-training:maxtext-v25.7
-    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
-    components:
-      ROCm: 6.4.1
-      JAX: 0.5.0
-      Python: 3.10.12
-      Transformer Engine: 2.1.0+90d703dd
+      ROCm: 7.0.0
+      JAX: 0.6.2
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+c91bac54
       hipBLASLt: 1.x.x
 model_groups:
   - group: Meta Llama
     tag: llama
     models:
-      - model: Llama 3.3 70B
-        mad_tag: jax_maxtext_train_llama-3.3-70b
-        model_repo: Llama-3.3-70B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3.1 8B
-        mad_tag: jax_maxtext_train_llama-3.1-8b
-        model_repo: Llama-3.1-8B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3.1 70B
-        mad_tag: jax_maxtext_train_llama-3.1-70b
-        model_repo: Llama-3.1-70B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3 8B
-        mad_tag: jax_maxtext_train_llama-3-8b
-        multinode_training_script: llama3_8b_multinode.sh
-        doc_options: ["multi-node"]
-      - model: Llama 3 70B
-        mad_tag: jax_maxtext_train_llama-3-70b
-        multinode_training_script: llama3_70b_multinode.sh
-        doc_options: ["multi-node"]
       - model: Llama 2 7B
         mad_tag: jax_maxtext_train_llama-2-7b
         model_repo: Llama-2-7B
@@ -54,6 +23,29 @@ model_groups:
         precision: bf16
         multinode_training_script: llama2_70b_multinode.sh
         doc_options: ["single-node", "multi-node"]
+      - model: Llama 3 8B (multi-node)
+        mad_tag: jax_maxtext_train_llama-3-8b
+        multinode_training_script: llama3_8b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3 70B (multi-node)
+        mad_tag: jax_maxtext_train_llama-3-70b
+        multinode_training_script: llama3_70b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3.1 8B
+        mad_tag: jax_maxtext_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 70B
+        mad_tag: jax_maxtext_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.3 70B
+        mad_tag: jax_maxtext_train_llama-3.3-70b
+        model_repo: Llama-3.3-70B
+        precision: bf16
+        doc_options: ["single-node"]
   - group: DeepSeek
     tag: deepseek
     models:

docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml

@@ -1,14 +1,21 @@
 dockers:
-  - pull_tag: rocm/megatron-lm:v25.8_py310
-    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
+  MI355X and MI350X:
+    pull_tag: rocm/megatron-lm:v25.9_gfx950
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
+    components: &docker_components
+      ROCm: 7.0.0
+      Primus: aab4234
+      PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
       Python: "3.10"
       Transformer Engine: 2.2.0.dev0+54dd2bdc
-      hipBLASLt: d1b517fc7a
-      Triton: 3.3.0
-      RCCL: 2.22.3
+      Flash Attention: 2.8.3
+      hipBLASLt: 911283acd1
+      Triton: 3.4.0+rocm7.0.0.git56765e8c
+      RCCL: 2.26.6
+  MI325X and MI300X:
+    pull_tag: rocm/megatron-lm:v25.9_gfx942
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
+    components: *docker_components
 model_groups:
   - group: Meta Llama
     tag: llama
@@ -19,8 +26,6 @@ model_groups:
         mad_tag: pyt_megatron_lm_train_llama-3.1-8b
       - model: Llama 3.1 70B
         mad_tag: pyt_megatron_lm_train_llama-3.1-70b
-      - model: Llama 3.1 70B (proxy)
-        mad_tag: pyt_megatron_lm_train_llama-3.1-70b-proxy
       - model: Llama 2 7B
         mad_tag: pyt_megatron_lm_train_llama-2-7b
       - model: Llama 2 70B

docs/data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v25.7-benchmark-models.yaml

@@ -0,0 +1,72 @@
+dockers:
+  - pull_tag: rocm/jax-training:maxtext-v25.7-jax060
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
+    components:
+      ROCm: 6.4.1
+      JAX: 0.6.0
+      Python: 3.10.12
+      Transformer Engine: 2.1.0+90d703dd
+      hipBLASLt: 1.1.0-499ece1c21
+  - pull_tag: rocm/jax-training:maxtext-v25.7
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025
+    components:
+      ROCm: 6.4.1
+      JAX: 0.5.0
+      Python: 3.10.12
+      Transformer Engine: 2.1.0+90d703dd
+      hipBLASLt: 1.x.x
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: jax_maxtext_train_llama-3.3-70b
+        model_repo: Llama-3.3-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 8B
+        mad_tag: jax_maxtext_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3.1 70B
+        mad_tag: jax_maxtext_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        precision: bf16
+        doc_options: ["single-node"]
+      - model: Llama 3 8B
+        mad_tag: jax_maxtext_train_llama-3-8b
+        multinode_training_script: llama3_8b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 3 70B
+        mad_tag: jax_maxtext_train_llama-3-70b
+        multinode_training_script: llama3_70b_multinode.sh
+        doc_options: ["multi-node"]
+      - model: Llama 2 7B
+        mad_tag: jax_maxtext_train_llama-2-7b
+        model_repo: Llama-2-7B
+        precision: bf16
+        multinode_training_script: llama2_7b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+      - model: Llama 2 70B
+        mad_tag: jax_maxtext_train_llama-2-70b
+        model_repo: Llama-2-70B
+        precision: bf16
+        multinode_training_script: llama2_70b_multinode.sh
+        doc_options: ["single-node", "multi-node"]
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V2-Lite (16B)
+        mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
+        model_repo: DeepSeek-V2-lite
+        precision: bf16
+        doc_options: ["single-node"]
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: jax_maxtext_train_mixtral-8x7b
+        model_repo: Mixtral-8x7B
+        precision: bf16
+        doc_options: ["single-node"]

docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.8-benchmark-models.yaml

@@ -0,0 +1,48 @@
+dockers:
+  - pull_tag: rocm/megatron-lm:v25.8_py310
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      hipBLASLt: d1b517fc7a
+      Triton: 3.3.0
+      RCCL: 2.22.3
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: pyt_megatron_lm_train_llama-3.3-70b
+      - model: Llama 3.1 8B
+        mad_tag: pyt_megatron_lm_train_llama-3.1-8b
+      - model: Llama 3.1 70B
+        mad_tag: pyt_megatron_lm_train_llama-3.1-70b
+      - model: Llama 3.1 70B (proxy)
+        mad_tag: pyt_megatron_lm_train_llama-3.1-70b-proxy
+      - model: Llama 2 7B
+        mad_tag: pyt_megatron_lm_train_llama-2-7b
+      - model: Llama 2 70B
+        mad_tag: pyt_megatron_lm_train_llama-2-70b
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: pyt_megatron_lm_train_deepseek-v3-proxy
+      - model: DeepSeek-V2-Lite
+        mad_tag: pyt_megatron_lm_train_deepseek-v2-lite-16b
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: pyt_megatron_lm_train_mixtral-8x7b
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-7b
+      - model: Qwen 2.5 72B
+        mad_tag: pyt_megatron_lm_train_qwen2.5-72b

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml

@@ -0,0 +1,58 @@
+dockers:
+  - pull_tag: rocm/megatron-lm:v25.8_py310
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
+    components:
+      ROCm: 6.4.3
+      Primus: 927a717
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      hipBLASLt: d1b517fc7a
+      Triton: 3.3.0
+      RCCL: 2.22.3
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.3 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
+        config_name: llama3.3_70B-pretrain.yaml
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
+        config_name: llama3.1_70B-pretrain.yaml
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
+        config_name: llama3.1_8B-pretrain.yaml
+      - model: Llama 2 7B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
+        config_name: llama2_7B-pretrain.yaml
+      - model: Llama 2 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
+        config_name: llama2_70B-pretrain.yaml
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
+        config_name: deepseek_v3-pretrain.yaml
+      - model: DeepSeek-V2-Lite
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
+        config_name: deepseek_v2_lite-pretrain.yaml
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
+        config_name: mixtral_8x7B_v0.1-pretrain.yaml
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+        config_name: mixtral_8x22B_v0.1-pretrain.yaml
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
+        config_name: primus_qwen2.5_7B-pretrain.yaml
+      - model: Qwen 2.5 72B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
+        config_name: qwen2.5_72B-pretrain.yaml

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml

@@ -0,0 +1,24 @@
+dockers:
+  - pull_tag: rocm/pytorch-training:v25.8
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+a1e66aae
+      Flash Attention: 3.0.0.post1
+      hipBLASLt: 1.1.0-d1b517fc7a
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 3.1 8B
+      mad_tag: primus_pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+    - model: Llama 3.1 70B
+      mad_tag: primus_pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B
+      precision: BF16

docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.8-benchmark-models.yaml

@@ -0,0 +1,178 @@
+dockers:
+  - pull_tag: rocm/pytorch-training:v25.8
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
+    components:
+      ROCm: 6.4.3
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+a1e66aae
+      Flash Attention: 3.0.0.post1
+      hipBLASLt: 1.1.0-d1b517fc7a
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 4 Scout 17B-16E
+      mad_tag: pyt_train_llama-4-scout-17b-16e
+      model_repo: Llama-4-17B_16E
+      url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.3 70B
+      mad_tag: pyt_train_llama-3.3-70b
+      model_repo: Llama-3.3-70B
+      url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 3.2 1B
+      mad_tag: pyt_train_llama-3.2-1b
+      model_repo: Llama-3.2-1B
+      url: https://huggingface.co/meta-llama/Llama-3.2-1B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 3B
+      mad_tag: pyt_train_llama-3.2-3b
+      model_repo: Llama-3.2-3B
+      url: https://huggingface.co/meta-llama/Llama-3.2-3B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 Vision 11B
+      mad_tag: pyt_train_llama-3.2-vision-11b
+      model_repo: Llama-3.2-Vision-11B
+      url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.2 Vision 90B
+      mad_tag: pyt_train_llama-3.2-vision-90b
+      model_repo: Llama-3.2-Vision-90B
+      url: https://huggingface.co/meta-llama/Llama-3.2-90B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.1 8B
+      mad_tag: pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+      training_modes: [pretrain, finetune_fw, finetune_lora, HF_pretrain]
+    - model: Llama 3.1 70B
+      mad_tag: pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+      precision: BF16
+      training_modes: [pretrain, finetune_fw, finetune_lora]
+    - model: Llama 3.1 405B
+      mad_tag: pyt_train_llama-3.1-405b
+      model_repo: Llama-3.1-405B
+      url: https://huggingface.co/meta-llama/Llama-3.1-405B
+      precision: BF16
+      training_modes: [finetune_qlora]
+    - model: Llama 3 8B
+      mad_tag: pyt_train_llama-3-8b
+      model_repo: Llama-3-8B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3 70B
+      mad_tag: pyt_train_llama-3-70b
+      model_repo: Llama-3-70B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-70B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 7B
+      mad_tag: pyt_train_llama-2-7b
+      model_repo: Llama-2-7B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 2 13B
+      mad_tag: pyt_train_llama-2-13b
+      model_repo: Llama-2-13B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 70B
+      mad_tag: pyt_train_llama-2-70b
+      model_repo: Llama-2-70B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_lora, finetune_qlora]
+  - group: OpenAI
+    tag: openai
+    models:
+    - model: GPT OSS 20B
+      mad_tag: pyt_train_gpt_oss_20b
+      model_repo: GPT-OSS-20B
+      url: https://huggingface.co/openai/gpt-oss-20b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+    - model: GPT OSS 120B
+      mad_tag: pyt_train_gpt_oss_120b
+      model_repo: GPT-OSS-120B
+      url: https://huggingface.co/openai/gpt-oss-120b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+  - group: Qwen
+    tag: qwen
+    models:
+    - model: Qwen 3 8B
+      mad_tag: pyt_train_qwen3-8b
+      model_repo: Qwen3-8B
+      url: https://huggingface.co/Qwen/Qwen3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 3 32B
+      mad_tag: pyt_train_qwen3-32b
+      model_repo: Qwen3-32
+      url: https://huggingface.co/Qwen/Qwen3-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 32B
+      mad_tag: pyt_train_qwen2.5-32b
+      model_repo: Qwen2.5-32B
+      url: https://huggingface.co/Qwen/Qwen2.5-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 72B
+      mad_tag: pyt_train_qwen2.5-72b
+      model_repo: Qwen2.5-72B
+      url: https://huggingface.co/Qwen/Qwen2.5-72B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2 1.5B
+      mad_tag: pyt_train_qwen2-1.5b
+      model_repo: Qwen2-1.5B
+      url: https://huggingface.co/Qwen/Qwen2-1.5B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 2 7B
+      mad_tag: pyt_train_qwen2-7b
+      model_repo: Qwen2-7B
+      url: https://huggingface.co/Qwen/Qwen2-7B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+  - group: Stable Diffusion
+    tag: sd
+    models:
+    - model: Stable Diffusion XL
+      mad_tag: pyt_huggingface_stable_diffusion_xl_2k_lora_finetuning
+      model_repo: SDXL
+      url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+      precision: BF16
+      training_modes: [finetune_lora]
+  - group: Flux
+    tag: flux
+    models:
+    - model: FLUX.1-dev
+      mad_tag: pyt_train_flux
+      model_repo: Flux
+      url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+      precision: BF16
+      training_modes: [pretrain]
+  - group: NCF
+    tag: ncf
+    models:
+    - model: NCF
+      mad_tag: pyt_ncf_training
+      model_repo:
+      url: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Recommendation/NCF
+      precision: FP32

docs/data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml

@@ -1,15 +1,22 @@
 dockers:
-  - pull_tag: rocm/megatron-lm:v25.8_py310
-    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
-    components:
-      ROCm: 6.4.3
-      Primus: 927a717
-      PyTorch: 2.8.0a0+gitd06a406
+  MI355X and MI350X:
+    pull_tag: rocm/primus:v25.9_gfx950
+    docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
+    components: &docker_components
+      ROCm: 7.0.0
+      Primus: 0.3.0
+      Primus Turbo: 0.1.1
+      PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
       Python: "3.10"
       Transformer Engine: 2.2.0.dev0+54dd2bdc
-      hipBLASLt: d1b517fc7a
-      Triton: 3.3.0
-      RCCL: 2.22.3
+      Flash Attention: 2.8.3
+      hipBLASLt: 911283acd1
+      Triton: 3.4.0+rocm7.0.0.git56765e8c
+      RCCL: 2.26.6
+  MI325X and MI300X:
+    pull_tag: rocm/primus:v25.9_gfx942
+    docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
+    components: *docker_components
 model_groups:
   - group: Meta Llama
     tag: llama

docs/data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml

@@ -1,24 +1,39 @@
 dockers:
-  - pull_tag: rocm/pytorch-training:v25.8
-    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
-      Python: 3.10.18
-      Transformer Engine: 2.2.0.dev0+a1e66aae
-      Flash Attention: 3.0.0.post1
-      hipBLASLt: 1.1.0-d1b517fc7a
+  MI355X and MI350X:
+    pull_tag: rocm/primus:v25.9_gfx950
+    docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
+    components: &docker_components
+      ROCm: 7.0.0
+      Primus: 0.3.0
+      Primus Turbo: 0.1.1
+      PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      Flash Attention: 2.8.3
+      hipBLASLt: 911283acd1
+      Triton: 3.4.0+rocm7.0.0.git56765e8c
+      RCCL: 2.26.6
+  MI325X and MI300X:
+    pull_tag: rocm/primus:v25.9_gfx942
+    docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
+    components: *docker_components
 model_groups:
   - group: Meta Llama
     tag: llama
     models:
     - model: Llama 3.1 8B
       mad_tag: primus_pyt_train_llama-3.1-8b
-      model_repo: Llama-3.1-8B
+      model_repo: meta-llama/Llama-3.1-8B
       url: https://huggingface.co/meta-llama/Llama-3.1-8B
       precision: BF16
+      config_file:
+        bf16: "./llama3_8b_fsdp_bf16.toml"
+        fp8: "./llama3_8b_fsdp_fp8.toml"
     - model: Llama 3.1 70B
       mad_tag: primus_pyt_train_llama-3.1-70b
-      model_repo: Llama-3.1-70B
+      model_repo: meta-llama/Llama-3.1-70B
       url: https://huggingface.co/meta-llama/Llama-3.1-70B
       precision: BF16
+      config_file:
+        bf16: "./llama3_70b_fsdp_bf16.toml"
+        fp8: "./llama3_70b_fsdp_fp8.toml"

docs/data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml

@@ -1,13 +1,21 @@
 dockers:
-  - pull_tag: rocm/pytorch-training:v25.8
-    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
-    components:
-      ROCm: 6.4.3
-      PyTorch: 2.8.0a0+gitd06a406
-      Python: 3.10.18
-      Transformer Engine: 2.2.0.dev0+a1e66aae
-      Flash Attention: 3.0.0.post1
-      hipBLASLt: 1.1.0-d1b517fc7a
+  MI355X and MI350X:
+    pull_tag: rocm/pytorch-training:v25.9_gfx950
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
+    components: &docker_components
+      ROCm: 7.0.0
+      Primus: aab4234
+      PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+      Python: "3.10"
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      Flash Attention: 2.8.3
+      hipBLASLt: 911283acd1
+      Triton: 3.4.0+rocm7.0.0.git56765e8c
+      RCCL: 2.26.6
+  MI325X and MI300X:
+    pull_tag: rocm/pytorch-training:v25.9_gfx942
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
+    components: *docker_components
 model_groups:
   - group: Meta Llama
     tag: llama
@@ -158,7 +166,7 @@ model_groups:
       model_repo: SDXL
       url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
       precision: BF16
-      training_modes: [finetune_lora]
+      training_modes: [posttrain-p]
   - group: Flux
     tag: flux
     models:
@@ -167,7 +175,7 @@ model_groups:
       model_repo: Flux
       url: https://huggingface.co/black-forest-labs/FLUX.1-dev
       precision: BF16
-      training_modes: [pretrain]
+      training_modes: [posttrain-p]
   - group: NCF
     tag: ncf
     models:

docs/data/reference/gpu-atomics-operation/cas-atomics_nopcie_instinct.csv

@@ -1,4 +1,4 @@
-Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X series,MI300A,MI350X series
+Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X Series,MI300A,MI350X Series
 32 bit atomicAdd,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS
 32 bit atomicSub,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS
 32 bit atomicMin,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS

docs/data/reference/gpu-atomics-operation/cas-atomics_pcie_instinct.csv

@@ -1,4 +1,4 @@
-Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X series,MI300A,MI350X series
+Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X Series,MI300A,MI350X Series
 32 bit atomicAdd,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS
 32 bit atomicSub,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS
 32 bit atomicMin,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS,✅ CAS

docs/data/reference/gpu-atomics-operation/hw-atomics_nopcie_instinct.csv

@@ -1,4 +1,4 @@
-Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X series,MI300A,MI350X series
+Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X Series,MI300A,MI350X Series
 32 bit atomicAdd,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native
 32 bit atomicSub,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native
 32 bit atomicMin,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native

docs/data/reference/gpu-atomics-operation/hw-atomics_pcie_instinct.csv

@@ -1,4 +1,4 @@
-Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X series,MI300A,MI350X series
+Atomic,MI100,MI200 PCIe,MI200 A+A,MI300X Series,MI300A,MI350X Series
 32 bit atomicAdd,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native
 32 bit atomicSub,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native
 32 bit atomicMin,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native,✅ Native

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

@@ -10,7 +10,7 @@ Deep learning frameworks provide environments for machine learning, training, fi
 
 ROCm offers a complete ecosystem for developing and running deep learning applications efficiently. It also provides ROCm-compatible versions of popular frameworks and libraries, such as PyTorch, TensorFlow, JAX, and others.
 
-The AMD ROCm organization actively contributes to open-source development and collaborates closely with framework organizations. This collaboration ensures that framework-specific optimizations effectively leverage AMD GPUs and accelerators.
+The AMD ROCm organization actively contributes to open-source development and collaborates closely with framework organizations. This collaboration ensures that framework-specific optimizations effectively leverage AMD GPUs.
 
 The table below summarizes information about ROCm-enabled deep learning frameworks. It includes details on ROCm compatibility and third-party tool support, installation steps and options, and links to GitHub resources. For a complete list of supported framework versions on ROCm, see the :doc:`Compatibility matrix <../compatibility/compatibility-matrix>` topic.
 

docs/how-to/gpu-performance/mi300x.rst

@@ -1,5 +1,5 @@
 .. meta::
-   :description: How to configure MI300X accelerators to fully leverage their capabilities and achieve optimal performance.
+   :description: How to configure MI300X GPUs to fully leverage their capabilities and achieve optimal performance.
    :keywords: ROCm, AI, machine learning, MI300X, LLM, usage, tutorial, optimization, tuning
 
 **************************************
@@ -7,11 +7,11 @@ AMD Instinct MI300X performance guides
 **************************************
 
 The following performance guides provide essential guidance on the necessary
-steps to properly `configure your system for AMD Instinct™ MI300X accelerators
+steps to properly `configure your system for AMD Instinct™ MI300X GPUs
 <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 They include detailed instructions on system settings and application
 :doc:`workload tuning </how-to/rocm-for-ai/inference-optimization/workload>` to
-help you leverage the maximum capabilities of these accelerators and achieve
+help you leverage the maximum capabilities of these GPUs and achieve
 superior performance.
 
 * `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__
@@ -19,9 +19,9 @@ superior performance.
   your AMD Instinct MI300X system for performance.
 
 * :doc:`/how-to/rocm-for-ai/inference-optimization/workload` covers steps to
-  optimize the performance of AMD Instinct MI300X series accelerators for HPC
+  optimize the performance of AMD Instinct MI300X Series GPUs for HPC
   and deep learning operations.
 
 * :doc:`/how-to/rocm-for-ai/inference/benchmark-docker/vllm` introduces a preconfigured
   environment for LLM inference, designed to help you test performance with
-  popular models on AMD Instinct MI300X series accelerators.
+  popular models on AMD Instinct MI300X Series GPUs.

docs/how-to/programming_guide.rst

@@ -25,7 +25,7 @@ execute on AMD GPUs while maintaining compatibility with CUDA-based systems.
 OpenCL (Open Computing Language) is an open standard for cross-platform,
 parallel programming of diverse processors. ROCm supports OpenCL for developers
 who want to use standard frameworks across different hardware platforms,
-including CPUs, GPUs, and other accelerators. For more information, see
+including CPUs, GPUs, and APUs. For more information, see
 `OpenCL <https://www.khronos.org/opencl/>`_.
 
 Python bindings can be found at https://github.com/ROCm/hip-python.

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

@@ -11,10 +11,10 @@ Fine-tuning using ROCm involves leveraging AMD's GPU-accelerated :doc:`libraries
 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.
 
-Single-accelerator systems, such as a machine equipped with a single accelerator or GPU, are commonly used for
+Single-accelerator systems, such as a machine equipped with a single GPU, are commonly used for
 smaller-scale deep learning tasks, including fine-tuning pre-trained models and running inference on moderately
 sized datasets. See :doc:`single-gpu-fine-tuning-and-inference`.
 
-Multi-accelerator systems, on the other hand, consist of multiple accelerators working in parallel. These systems are
+Multi-accelerator systems, on the other hand, consist of multiple GPUs working in parallel. These systems are
 typically used in LLMs and other large-scale deep learning tasks where performance, scalability, and the handling of
 massive datasets are crucial. See :doc:`multi-gpu-fine-tuning-and-inference`.

docs/how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference.rst

@@ -3,11 +3,11 @@
    :keywords: ROCm, LLM, fine-tuning, usage, tutorial, multi-GPU, distributed, inference, accelerators, PyTorch, HuggingFace, torchtune
 
 *****************************************************
-Fine-tuning and inference using multiple accelerators
+Fine-tuning and inference using multiple GPUs
 *****************************************************
 
 This section explains how to fine-tune a model on a multi-accelerator system. See
-:doc:`Single-accelerator fine-tuning <single-gpu-fine-tuning-and-inference>` for a single accelerator or GPU setup.
+:doc:`Single-accelerator fine-tuning <single-gpu-fine-tuning-and-inference>` for a single GPU setup.
 
 .. _fine-tuning-llms-multi-gpu-env:
 
@@ -20,7 +20,7 @@ This section was tested using the following hardware and software environment.
    :stub-columns: 1
 
    * - Hardware
-     - 4 AMD Instinct MI300X accelerators
+     - 4 AMD Instinct MI300X GPUs
 
    * - Software
      - ROCm 6.1, Ubuntu 22.04, PyTorch 2.1.2, Python 3.10
@@ -40,13 +40,13 @@ Setting up the base implementation environment
    :doc:`PyTorch installation guide <rocm-install-on-linux:install/3rd-party/pytorch-install>`. For consistent
    installation, it’s recommended to use official ROCm prebuilt Docker images with the framework pre-installed.
 
-#. In the Docker container, check the availability of ROCM-capable accelerators using the following command.
+#. In the Docker container, check the availability of ROCm-capable GPUs using the following command.
 
    .. code-block:: shell
 
       rocm-smi --showproductname
 
-#. Check that your accelerators are available to PyTorch.
+#. Check that your GPUs are available to PyTorch.
 
    .. code-block:: python
 
@@ -66,7 +66,7 @@ Setting up the base implementation environment
 .. tip::
 
    During training and inference, you can check the memory usage by running the ``rocm-smi`` command in your terminal.
-   This tool helps you see shows which accelerators or GPUs are involved.
+   This tool helps you see shows which GPUs are involved.
 
 
 .. _fine-tuning-llms-multi-gpu-hugging-face-accelerate:
@@ -74,9 +74,9 @@ Setting up the base implementation environment
 Hugging Face Accelerate for fine-tuning and inference
 ===========================================================
 
-`Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_ is a library that simplifies turning raw
-PyTorch code for a single accelerator into code for multiple accelerators for LLM fine-tuning and inference. It is
-integrated with `Transformers <https://huggingface.co/docs/transformers/en/index>`_ allowing you to scale your PyTorch
+`Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`__ is a library that simplifies turning raw
+PyTorch code for a single GPU into code for multiple GPUs for LLM fine-tuning and inference. It is
+integrated with `Transformers <https://huggingface.co/docs/transformers/en/index>`__, so you can scale your PyTorch
 code while maintaining performance and flexibility.
 
 As a brief example of model fine-tuning and inference using multiple GPUs, let's use Transformers and load in the Llama
@@ -107,7 +107,7 @@ Now, it's important to adjust how you load the model. Add the ``device_map`` par
    (``"auto"``, ``"balanced"``, ``"balanced_low_0"``, ``"sequential"``).
 
    It's recommended to set the ``device_map`` parameter to ``“auto”`` to allow Accelerate to automatically and
-   efficiently allocate the model given the available resources (4 accelerators in this case).
+   efficiently allocate the model given the available resources (four GPUs in this case).
 
    When you have more GPU memory available than the model size, here is the difference between each ``device_map``
    option:
@@ -130,8 +130,8 @@ After loading the model in this way, the model is fully ready to use the resourc
 torchtune for fine-tuning and inference
 =============================================
 
-`torchtune <https://pytorch.org/torchtune/main/>`_ is a PyTorch-native library for easy single and multi-accelerator or
-GPU model fine-tuning and inference with LLMs.
+`torchtune <https://pytorch.org/torchtune/main/>`_ is a PyTorch-native library for easy single and multi-GPU 
+model fine-tuning and inference with LLMs.
 
 #. Install torchtune using pip.
 

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

@@ -30,7 +30,7 @@ The challenge of fine-tuning models
 
 However, the computational cost of fine-tuning is still high, especially for complex models and large datasets, which
 poses distinct challenges related to substantial computational and memory requirements. This might be a barrier for
-accelerators or GPUs with low computing power or limited device memory resources.
+GPUs with low computing power or limited device memory resources.
 
 For example, suppose we have a language model with 7 billion (7B) parameters, represented by a weight matrix :math:`W`.
 During backpropagation, the model needs to learn a :math:`ΔW` matrix, which updates the original weights to minimize the
@@ -84,8 +84,8 @@ Walkthrough
 ===========
 
 To demonstrate the benefits of LoRA and the ideal compute compatibility of using PEFT and TRL libraries on AMD
-ROCm-compatible accelerators and GPUs, let's step through a comprehensive implementation of the fine-tuning process
-using the Llama 2 7B model with LoRA tailored specifically for question-and-answer tasks on AMD MI300X accelerators.
+ROCm-compatible GPUs, let's step through a comprehensive implementation of the fine-tuning process
+using the Llama 2 7B model with LoRA tailored specifically for question-and-answer tasks on AMD MI300X GPUs.
 
 Before starting, review and understand the key components of this walkthrough:
 

docs/how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference.rst

@@ -3,12 +3,11 @@
    :keywords: ROCm, LLM, fine-tuning, usage, tutorial, single-GPU, LoRA, PEFT, inference, SFTTrainer
 
 ****************************************************
-Fine-tuning and inference using a single accelerator
+Fine-tuning and inference using a single GPU
 ****************************************************
 
 This section explains model fine-tuning and inference techniques on a single-accelerator system. See
-:doc:`Multi-accelerator fine-tuning <multi-gpu-fine-tuning-and-inference>` for a setup with multiple accelerators or
-GPUs.
+:doc:`Multi-accelerator fine-tuning <multi-gpu-fine-tuning-and-inference>` for a setup with multiple GPUs.
 
 .. _fine-tuning-llms-single-gpu-env:
 
@@ -21,7 +20,7 @@ This section was tested using the following hardware and software environment.
    :stub-columns: 1
 
    * - Hardware
-     - AMD Instinct MI300X accelerator
+     - AMD Instinct MI300X GPU
 
    * - Software
      - ROCm 6.1, Ubuntu 22.04, PyTorch 2.1.2, Python 3.10
@@ -41,7 +40,7 @@ Setting up the base implementation environment
    :doc:`PyTorch installation guide <rocm-install-on-linux:install/3rd-party/pytorch-install>`. For a consistent
    installation, it’s recommended to use official ROCm prebuilt Docker images with the framework pre-installed.
 
-#. In the Docker container, check the availability of ROCm-capable accelerators using the following command.
+#. In the Docker container, check the availability of ROCm-capable GPUs using the following command.
 
    .. code-block:: shell
 
@@ -53,14 +52,14 @@ Setting up the base implementation environment
 
       ============================ ROCm System Management Interface ============================
       ====================================== Product Info ======================================
-      GPU[0]          : Card series:          AMD Instinct MI300X OAM
+      GPU[0]          : Card Series:          AMD Instinct MI300X OAM
       GPU[0]          : Card model:           0x74a1
       GPU[0]          : Card vendor:          Advanced Micro Devices, Inc. [AMD/ATI]
       GPU[0]          : Card SKU:             MI3SRIOV
       ==========================================================================================
       ================================== End of ROCm SMI Log ===================================
 
-#. Check that your accelerators are available to PyTorch.
+#. Check that your GPUs are available to PyTorch.
 
    .. code-block:: python
 
@@ -502,9 +501,9 @@ Let's look at achieving model inference using these types of models.
          # Token generation
          print(pipe("What is a large language model?")[0]["generated_text"])
 
-If using multiple accelerators, see
+If using multiple GPUs, see
 :ref:`Multi-accelerator fine-tuning and inference <fine-tuning-llms-multi-gpu-hugging-face-accelerate>` to explore
-popular libraries that simplify fine-tuning and inference in a multi-accelerator system.
+popular libraries that simplify fine-tuning and inference in a multiple-GPU system.
 
 Read more about inference frameworks like vLLM and Hugging Face TGI in
 :doc:`LLM inference frameworks <../inference/llm-inference-frameworks>`.

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

@@ -45,7 +45,7 @@ ROCm provides two different implementations of Flash Attention 2 modules. They c
          # Install from source
          git clone https://github.com/ROCm/flash-attention.git
          cd flash-attention/
-         GPU_ARCHS=gfx942 python setup.py install #MI300 series
+         GPU_ARCHS=gfx942 python setup.py install #MI300 Series
 
       Hugging Face Transformers can easily deploy the CK Flash Attention 2 module by passing an argument
       ``attn_implementation="flash_attention_2"`` in the ``from_pretrained`` class.
@@ -526,7 +526,7 @@ follow these instructions:
    python -m pytest -v -rsx -s -W ignore::pytest.PytestCollectionWarning split_table_batched_embeddings_test.py
 
 To run the FBGEMM_GPU ``uvm`` test, use these commands. These tests only support the AMD MI210 and 
-more recent accelerators. 
+more recent GPUs. 
 
 .. code-block:: shell
 

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

@@ -7,7 +7,7 @@ Model quantization techniques
 *****************************
 
 Quantization reduces the model size compared to its native full-precision version, making it easier to fit large models
-onto accelerators or GPUs with limited memory usage. This section explains how to perform LLM quantization using AMD Quark, GPTQ
+onto GPUs with limited memory usage. This section explains how to perform LLM quantization using AMD Quark, GPTQ
 and bitsandbytes on AMD Instinct hardware.
 
 .. _quantize-llms-quark:
@@ -311,7 +311,7 @@ ExLlama-v2 support
 ExLlama is a Python/C++/CUDA implementation of the Llama model that is
 designed for faster inference with 4-bit GPTQ weights. The ExLlama
 kernel is activated by default when users create a ``GPTQConfig`` object. To
-boost inference speed even further on Instinct accelerators, use the ExLlama-v2
+boost inference speed even further on Instinct GPUs, use the ExLlama-v2
 kernels by configuring the ``exllama_config`` parameter as the following.
 
 .. code-block:: python
@@ -332,7 +332,7 @@ The `ROCm-aware bitsandbytes <https://github.com/ROCm/bitsandbytes>`_ library is
 a lightweight Python wrapper around CUDA custom functions, in particular 8-bit optimizer, matrix multiplication, and
 8-bit and 4-bit quantization functions. The library includes quantization primitives for 8-bit and 4-bit operations
 through ``bitsandbytes.nn.Linear8bitLt`` and ``bitsandbytes.nn.Linear4bit`` and 8-bit optimizers through the
-``bitsandbytes.optim`` module. These modules are supported on AMD Instinct accelerators.
+``bitsandbytes.optim`` module. These modules are supported on AMD Instinct GPUs.
 
 Installing bitsandbytes
 -----------------------

docs/how-to/rocm-for-ai/inference-optimization/optimizing-with-composable-kernel.md

@@ -9,13 +9,13 @@ myst:
 
 The AMD ROCm Composable Kernel (CK) library provides a programming model for writing performance-critical kernels for machine learning workloads. It generates a general-purpose kernel during the compilation phase through a C++ template, enabling developers to achieve operation fusions on different data precisions.
 
-This article gives a high-level overview of CK General Matrix Multiplication (GEMM) kernel based on the design example of `03_gemm_bias_relu`. It also outlines the steps to construct the kernel and run it. Moreover, the article provides a detailed implementation of running SmoothQuant quantized INT8 models on AMD Instinct MI300X accelerators using CK.
+This article gives a high-level overview of CK General Matrix Multiplication (GEMM) kernel based on the design example of `03_gemm_bias_relu`. It also outlines the steps to construct the kernel and run it. Moreover, the article provides a detailed implementation of running SmoothQuant quantized INT8 models on AMD Instinct MI300X GPUs using CK.
 
 ## High-level overview: a CK GEMM instance
 
 GEMM is a fundamental block in linear algebra, machine learning, and deep neural networks. It is defined as the operation:
 {math}`E = α \times (A \times B) + β \times (D)`, with A and B as matrix inputs, α and β as scalar inputs, and D as a pre-existing matrix.
-Take the commonly used linear transformation in a fully connected layer as an example. These terms correspond to input activation (A), weight (B), bias (D), and output (E), respectively. The example employs a `DeviceGemmMultipleD_Xdl_CShuffle` struct from CK library as the fundamental instance to explore the compute capability of AMD Instinct accelerators for the computation of GEMM. The implementation of the instance contains two phases:
+Take the commonly used linear transformation in a fully connected layer as an example. These terms correspond to input activation (A), weight (B), bias (D), and output (E), respectively. The example employs a `DeviceGemmMultipleD_Xdl_CShuffle` struct from CK library as the fundamental instance to explore the compute capability of AMD Instinct GPUs for the computation of GEMM. The implementation of the instance contains two phases:
 
 - [Template parameter definition](#template-parameter-definition)
 - [Instantiating and running the templated kernel](#instantiating-and-running-the-templated-kernel)
@@ -108,7 +108,7 @@ These parameters include Block Size, M/N/K Per Block, M/N per XDL, AK1, BK1, etc
 
 - Block Size determines the number of threads in the thread block.
 - M/N/K Per Block determines the size of tile that each thread block is responsible for calculating.
-- M/N Per XDL refers to M/N size for Instinct accelerator Matrix Fused Multiply Add (MFMA) instructions operating on a per-wavefront basis.
+- M/N Per XDL refers to M/N size for Instinct GPU Matrix Fused Multiply Add (MFMA) instructions operating on a per-wavefront basis.
 - A/B K1 is related to the data type. It can be any value ranging from 1 to K Per Block. To achieve the optimal load/store performance, 128bit per load is suggested. In addition, the A/B loading parameters must be changed accordingly to match the A/B K1 value; otherwise, it will result in compilation errors.
 
 Conditions for achieving computational load balancing on different hardware platforms can vary.
@@ -133,7 +133,7 @@ Templated kernel launching consists of kernel instantiation, making arguments by
 
 ## Developing fused INT8 kernels for SmoothQuant models
 
-[SmoothQuant](https://github.com/mit-han-lab/smoothquant) (SQ) is a quantization algorithm that enables an INT8 quantization of both weights and activations for all the matrix multiplications in LLM. The required GPU kernel functionalities used to accelerate the inference of SQ models on Instinct accelerators are shown in the following table.
+[SmoothQuant](https://github.com/mit-han-lab/smoothquant) (SQ) is a quantization algorithm that enables an INT8 quantization of both weights and activations for all the matrix multiplications in LLM. The required GPU kernel functionalities used to accelerate the inference of SQ models on Instinct GPUs are shown in the following table.
 
 :::{table} Functionalities used to implement SmoothQuant model inference.
 
@@ -164,7 +164,7 @@ The CK library contains many fundamental instances that implement different func
 
 Second, consider whether the format of input data meets your actual calculation needs. For SQ models, the 8-bit integer data format (INT8) is applied for matrix calculations.
 
-Third, consider the platform for implementing CK instances. The instances suffixed with `xdl` only run on AMD Instinct accelerators after being compiled and cannot run on Radeon-series GPUs. This is due to the underlying device-specific instruction sets for implementing these basic instances.
+Third, consider the platform for implementing CK instances. The instances suffixed with `xdl` only run on AMD Instinct GPUs after being compiled and cannot run on Radeon-Series GPUs. This is due to the underlying device-specific instruction sets for implementing these basic instances.
 
 Here, we use [DeviceBatchedGemmMultiD_Xdl](https://github.com/ROCm/composable_kernel/tree/develop/example/24_batched_gemm) as the fundamental instance to implement the functionalities in the previous table.
 
@@ -435,7 +435,7 @@ 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
-The implementation architecture of running SmoothQuant models on AMD MI300X accelerators.
+The implementation architecture of running SmoothQuant models on AMD MI300X GPUs.
 ```
 
 For the target [SQ quantized model](https://huggingface.co/mit-han-lab/opt-13b-smoothquant), each decoder layer contains three major components: attention calculation, layer normalization, and linear transformation in fully connected layers.  The corresponding implementation classes for these components are:
@@ -447,21 +447,21 @@ For the target [SQ quantized model](https://huggingface.co/mit-han-lab/opt-13b-s
  These classes' underlying implementation logits will harness the functions in previous table. Note that for the example, the `LayerNormQ` module is implemented by the torch native module.
 
 Testing environment:
-The hardware platform used for testing equips with 256 AMD EPYC 9534 64-Core Processor, 8 AMD Instinct MI300X accelerators and 1.5T memory. The testing was done in a publicly available Docker image from Docker Hub:
+The hardware platform used for testing equips with 256 AMD EPYC 9534 64-Core Processor, 8 AMD Instinct MI300X GPUs and 1.5T memory. The testing was done in a publicly available Docker image from Docker Hub:
 [`rocm/pytorch:rocm6.1_ubuntu22.04_py3.10_pytorch_2.1.2`](https://hub.docker.com/layers/rocm/pytorch/rocm6.1_ubuntu22.04_py3.10_pytorch_2.1.2/images/sha256-f6ea7cee8aae299c7f6368187df7beed29928850c3929c81e6f24b34271d652b)
 
 The tested models are OPT-1.3B, 2.7B, 6.7B and 13B FP16 models and the corresponding SmoothQuant INT8 OPT models were obtained from Hugging Face.
 
 Note that since the default values were used for the tunable parameters of the fundamental instance, the performance of the INT8 kernel is suboptimal.
 
-Figure 8 shows the performance comparisons between the original FP16 and the SmoothQuant-quantized INT8 models on a single MI300X accelerator. The GPU memory footprints of SmoothQuant-quantized models are significantly reduced. It also indicates the per-sample inference latency is significantly reduced for all SmoothQuant-quantized OPT models (illustrated in (b)). Notably, the performance of the CK instance-based INT8 kernel steadily improves with an increase in model size.
+Figure 8 shows the performance comparisons between the original FP16 and the SmoothQuant-quantized INT8 models on a single MI300X GPU. The GPU memory footprints of SmoothQuant-quantized models are significantly reduced. It also indicates the per-sample inference latency is significantly reduced for all SmoothQuant-quantized OPT models (illustrated in (b)). Notably, the performance of the CK instance-based INT8 kernel steadily improves with an increase in model size.
 
 <!-- 
 ================
  ### Figure 8
 ================ -->
 ```{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.
+Performance comparisons between the original FP16 and the SmoothQuant-quantized INT8 models on a single MI300X GPU.
 ```
 
 For accuracy comparisons between the original FP16 and INT8 models, the evaluation is done by using the first 1,000 samples from the LAMBADA dataset's validation set. We employ the same Last Token Prediction Accuracy method introduced in [SmoothQuant Real-INT8 Inference for PyTorch](https://github.com/mit-han-lab/smoothquant/blob/main/examples/smoothquant_opt_real_int8_demo.ipynb) as our evaluation metric. The comparison results are shown in Table 2.
@@ -482,4 +482,4 @@ CK provides a rich set of template parameters for generating flexible accelerate
 
 CK supports multiple instruction sets of AMD Instinct GPUs, operator fusion and different data precisions. Its composability helps users quickly construct operator performance verification.
 
-With CK, you can build more effective AI applications with higher flexibility and better performance on different AMD accelerator platforms.
+With CK, you can build more effective AI applications with higher flexibility and better performance on different AMD GPU platforms.

docs/how-to/rocm-for-ai/inference-optimization/workload.rst

@@ -1,15 +1,15 @@
 .. meta::
-   :description: Learn about workload tuning on AMD Instinct MI300X accelerators for optimal performance.
+   :description: Learn about workload tuning on AMD Instinct MI300X GPUs for optimal performance.
    :keywords: AMD, Instinct, MI300X, HPC, tuning, BIOS settings, NBIO, ROCm,
               environment variable, performance, HIP, Triton, PyTorch TunableOp, vLLM, RCCL,
-              MIOpen, accelerator, GPU, resource utilization
+              MIOpen, GPU, resource utilization
 
 *****************************************
 AMD Instinct MI300X workload optimization
 *****************************************
 
 This document provides guidelines for optimizing the performance of AMD
-Instinct™ MI300X accelerators, with a particular focus on GPU kernel
+Instinct™ MI300X GPUs, with a particular focus on GPU kernel
 programming, high-performance computing (HPC), and deep learning operations
 using PyTorch. It delves into specific workloads such as
 :ref:`model inference <mi300x-vllm-optimization>`, offering strategies to
@@ -25,7 +25,7 @@ Workload tuning strategy
 
 By following a structured approach, you can systematically address
 performance issues and enhance the efficiency of your workloads on AMD Instinct
-MI300X accelerators.
+MI300X GPUs.
 
 Measure the current workload
 ----------------------------
@@ -86,7 +86,7 @@ Optimize model inference with vLLM
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 vLLM provides tools and techniques specifically designed for efficient model
-inference on AMD Instinct MI300X accelerators. See :ref:`fine-tuning-llms-vllm`
+inference on AMD Instinct MI300X GPUs. See :ref:`fine-tuning-llms-vllm`
 for installation guidance. Optimizing performance with vLLM
 involves configuring tensor parallelism, leveraging advanced features, and
 ensuring efficient execution. Here’s how to optimize vLLM performance:
@@ -239,7 +239,7 @@ benchmarking process.
 
 With AMD's profiling tools, developers are able to gain important insight into how efficiently their application is
 using hardware resources and effectively diagnose potential bottlenecks contributing to poor performance. Developers
-working with AMD Instinct accelerators have multiple tools depending on their specific profiling needs; these include:
+working with AMD Instinct GPUs have multiple tools depending on their specific profiling needs; these include:
 
 * :ref:`ROCProfiler <mi300x-rocprof>`
 
@@ -257,11 +257,11 @@ metrics, commonly called *performance counters*. These counters quantify the per
 showcasing which pieces of the computational pipeline and memory hierarchy are being utilized.
 
 Your ROCm installation contains a script or executable command called ``rocprof`` which provides the ability to list all
-available hardware counters for your specific accelerator or GPU, and run applications while collecting counters during
+available hardware counters for your specific GPU, and run applications while collecting counters during
 their execution.
 
 This ``rocprof`` utility also depends on the :doc:`ROCTracer and ROC-TX libraries <roctracer:index>`, giving it the
-ability to collect timeline traces of the accelerator software stack as well as user-annotated code regions.
+ability to collect timeline traces of the GPU software stack as well as user-annotated code regions.
 
 .. note::
 
@@ -276,16 +276,16 @@ ROCm Compute Profiler
 ^^^^^^^^^^^^^^^^^^^^^
 
 :doc:`ROCm Compute Profiler <rocprofiler-compute:index>` is a system performance profiler for high-performance computing (HPC) and
-machine learning (ML) workloads using Instinct accelerators. Under the hood, ROCm Compute Profiler uses
+machine learning (ML) workloads using Instinct GPUs. Under the hood, ROCm Compute Profiler uses
 :ref:`ROCProfiler <mi300x-rocprof>` to collect hardware performance counters. The ROCm Compute Profiler tool performs
 system profiling based on all approved hardware counters for Instinct
-accelerator architectures. It provides high level performance analysis features including System Speed-of-Light, IP
+GPU architectures. It provides high level performance analysis features including System Speed-of-Light, IP
 block Speed-of-Light, Memory Chart Analysis, Roofline Analysis, Baseline Comparisons, and more.
 
 ROCm Compute Profiler takes the guesswork out of profiling by removing the need to provide text input files with lists of counters
 to collect and analyze raw CSV output files as is the case with ROCProfiler. Instead, ROCm Compute Profiler automates the collection
 of all available hardware counters in one command and provides graphical interfaces to help users understand and
-analyze bottlenecks and stressors for their computational workloads on AMD Instinct accelerators.
+analyze bottlenecks and stressors for their computational workloads on AMD Instinct GPUs.
 
 .. note::
 
@@ -411,7 +411,7 @@ for additional performance tips. :ref:`fine-tuning-llms-vllm` describes vLLM
 usage with ROCm.
 
 ROCm provides a prebuilt optimized Docker image for validating the performance
-of LLM inference with vLLM on MI300X series accelerators. The Docker image includes
+of LLM inference with vLLM on MI300X Series GPUs. The Docker image includes
 ROCm, vLLM, and PyTorch. For more information, see
 :doc:`/how-to/rocm-for-ai/inference/benchmark-docker/vllm`.
 
@@ -449,7 +449,7 @@ Maximizing vLLM instances on a single node
 The general guideline is to maximize per-node throughput by running as many vLLM instances as possible.
 However, running too many instances might lead to insufficient memory for the KV-cache, which can affect performance.
 
-The Instinct MI300X accelerator is equipped with 192GB of HBM3 memory capacity and bandwidth.
+The Instinct MI300X GPU is equipped with 192 GB of HBM3 memory capacity and bandwidth.
 For models that fit in one GPU -- to maximize the accumulated throughput -- you can run as many as eight vLLM instances
 simultaneously on one MI300X node (with eight GPUs). To do so, use the GPU isolation environment
 variable ``CUDA_VISIBLE_DEVICES``.
@@ -468,7 +468,7 @@ The total throughput achieved by running ``N`` instances of vLLM is generally mu
 single vLLM instance across ``N`` GPUs simultaneously (that is, configuring ``tensor_parallel_size`` as N or
 using the ``-tp`` N option, where ``1 < N ≤ 8``).
 
-vLLM on MI300X accelerators can run a variety of model weights, including Llama 2 (7b, 13b, 70b), Llama 3 (8b, 70b), Qwen2 (7b, 72b), Mixtral-8x7b, Mixtral-8x22b, and so on.
+vLLM on MI300X GPUs can run a variety of model weights, including Llama 2 (7b, 13b, 70b), Llama 3 (8b, 70b), Qwen2 (7b, 72b), Mixtral-8x7b, Mixtral-8x22b, and so on.
 Notable configurations include Llama2-70b and Llama3-70b models on a single MI300X GPU, and the Llama3.1 405b model can fit on one single node with 8 MI300X GPUs.
 
 .. _mi300x-vllm-gpu-memory-utilization:
@@ -917,7 +917,7 @@ ROCm library tuning involves optimizing the performance of routine computational
 operations (such as ``GEMM``) provided by ROCm libraries like
 :ref:`hipBLASLt <mi300x-hipblaslt>`, :ref:`Composable Kernel <mi300x-ck>`,
 :ref:`MIOpen <mi300x-miopen>`, and :ref:`RCCL <mi300x-rccl>`. This tuning aims
-to maximize efficiency and throughput on Instinct MI300X accelerators to gain 
+to maximize efficiency and throughput on Instinct MI300X GPUs to gain 
 improved application performance.
 
 .. _mi300x-library-gemm:
@@ -1451,7 +1451,7 @@ you can only use a fraction of the potential bandwidth on the node.
 The following figure shows an
 :doc:`MI300X node-level architecture </conceptual/gpu-arch/mi300>` of a
 system with AMD EPYC processors in a dual-socket configuration and eight
-AMD Instinct MI300X accelerators. The MI300X OAMs attach to the host system via
+AMD Instinct MI300X GPUs. The MI300X OAMs attach to the host system via
 PCIe Gen 5 x16 links (yellow lines). The GPUs use seven high-bandwidth,
 low-latency AMD Infinity Fabric™ links (red lines) to form a fully connected
 8-GPU system.
@@ -1460,7 +1460,7 @@ low-latency AMD Infinity Fabric™ links (red lines) to form a fully connected
 
 .. figure:: ../../../data/shared/mi300-node-level-arch.png
 
-   MI300 series node-level architecture showing 8 fully interconnected MI300X
+   MI300 Series node-level architecture showing 8 fully interconnected MI300X
    OAM modules connected to (optional) PCIe switches via re-timers and HGX
    connectors.
 
@@ -1653,7 +1653,7 @@ Auto-tunable kernel configuration involves adjusting memory access and computati
 resources assigned to each compute unit. It encompasses the usage of
 :ref:`LDS <mi300x-cu-fig>`, register, and task scheduling on a compute unit.
 
-The accelerator or GPU contains global memory, local data share (LDS), and
+The GPU contains global memory, local data share (LDS), and
 registers. Global memory has high access latency, but is large. LDS access has
 much lower latency, but is smaller. It is a fast on-CU software-managed memory
 that can be used to efficiently share data between all work items in a block.
@@ -1666,11 +1666,11 @@ Register access is the fastest yet smallest among the three.
    Schematic representation of a CU in the CDNA2 or CDNA3 architecture.
 
 The following is a list of kernel arguments used for tuning performance and
-resource allocation on AMD accelerators, which helps in optimizing the
+resource allocation on AMD GPUs, which helps in optimizing the
 efficiency and throughput of various computational kernels.
 
 ``num_stages=n``
-   Adjusts the number of pipeline stages for different types of kernels. On AMD accelerators, set ``num_stages``
+   Adjusts the number of pipeline stages for different types of kernels. On AMD GPUs, set ``num_stages``
    according to the following rules:
 
    * For kernels with a single GEMM, set to ``2``.
@@ -1697,15 +1697,15 @@ efficiency and throughput of various computational kernels.
    * The occupancy of the kernel is limited by VGPR usage, and
 
    * The current VGPR usage is only a few above a boundary in
-     :ref:`Occupancy related to VGPR usage in an Instinct MI300X accelerator <mi300x-occupancy-vgpr-table>`.
+     :ref:`Occupancy related to VGPR usage in an Instinct MI300X GPU <mi300x-occupancy-vgpr-table>`.
 
 .. _mi300x-occupancy-vgpr-table:
 
 .. figure:: ../../../data/shared/occupancy-vgpr.png
-   :alt: Occupancy related to VGPR usage in an Instinct MI300X accelerator.
+   :alt: Occupancy related to VGPR usage in an Instinct MI300X GPU.
    :align: center
 
-   Occupancy related to VGPRs usage on an Instinct MI300X accelerator
+   Occupancy related to VGPRs usage on an Instinct MI300X GPU
 
 For example, according to the table, each Execution Unit (EU) has 512 available
 VGPRs, which are allocated in blocks of 16. If the current VGPR usage is 170,
@@ -1730,7 +1730,7 @@ VGPR usage so that it might fit 3 waves per EU.
 
    -  ``matrix_instr_nonkdim = 32``: ``mfma_32x32`` is used.
 
-   For GEMM kernels on an MI300X accelerator, ``mfma_16x16`` typically outperforms ``mfma_32x32``, even for large
+   For GEMM kernels on an MI300X GPU, ``mfma_16x16`` typically outperforms ``mfma_32x32``, even for large
    tile/GEMM sizes.
 
 
@@ -1749,7 +1749,7 @@ the number of CUs a kernel can distribute its task across.
 
    XCD-level system architecture showing 40 compute units,
    each with 32 KB L1 cache, a unified compute system with 4 ACE compute
-   accelerators, shared 4MB of L2 cache, and a hardware scheduler (HWS).
+   GPUs, shared 4MB of L2 cache, and a hardware scheduler (HWS).
 
 You can query hardware resources with the command ``rocminfo`` in the
 ``/opt/rocm/bin`` directory. For instance, query the number of CUs, number of

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.0-20250812.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -23,9 +23,9 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   accelerators and includes the following components:
+   inference performance on AMD Instinct™ MI300X Series GPUs. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
+   GPUs and includes the following components:
 
    .. list-table::
       :header-rows: 1
@@ -47,7 +47,7 @@ vLLM inference performance testing
 
 With this Docker image, you can quickly test the :ref:`expected
 inference performance numbers <vllm-benchmark-performance-measurements-812>` for
-MI300X series accelerators.
+MI300X Series GPUs.
 
 What's new
 ==========
@@ -139,7 +139,7 @@ page provides reference throughput and serving measurements for inferencing popu
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
    only reflects the latest version of this inference benchmarking environment.
-   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================
@@ -424,7 +424,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.1-20250909.rst

@@ -21,8 +21,8 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
+   inference performance on AMD Instinct™ MI300X Series accelerators. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
    accelerators and includes the following components:
 
    .. list-table::
@@ -38,7 +38,7 @@ vLLM inference performance testing
 
 With this Docker image, you can quickly test the :ref:`expected
 inference performance numbers <vllm-benchmark-performance-measurements-909>` for
-MI300X series accelerators.
+MI300X Series accelerators.
 
 What's new
 ==========
@@ -430,7 +430,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
   a brief introduction to vLLM and optimization strategies.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.4.3.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the unified
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the unified
                  ROCm Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -18,9 +18,9 @@ vLLM inference performance testing
 
 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
+(LLM) inference performance on the AMD Instinct™ MI300X GPU. This
 ROCm vLLM Docker image integrates vLLM and PyTorch tailored specifically for the
-MI300X accelerator and includes the following components:
+MI300X GPU and includes the following components:
 
 * `ROCm 6.2.0 <https://github.com/ROCm/ROCm>`_
 
@@ -31,7 +31,7 @@ MI300X accelerator and includes the following components:
 * 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
+performance numbers on the MI300X GPU. This topic also provides tips on
 optimizing performance with popular AI models.
 
 .. _vllm-benchmark-vllm:
@@ -51,7 +51,7 @@ Getting started
 ===============
 
 Use the following procedures to reproduce the benchmark results on an
-MI300X accelerator with the prebuilt vLLM Docker image.
+MI300X GPU with the prebuilt vLLM Docker image.
 
 .. _vllm-benchmark-get-started:
 
@@ -267,7 +267,7 @@ Options
 
 .. _vllm-benchmark-run-benchmark-v043:
 
-Running the benchmark on the MI300X accelerator
+Running the benchmark on the MI300X GPU
 -----------------------------------------------
 
 Here are some examples of running the benchmark with various options.
@@ -328,7 +328,7 @@ Further reading
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - To learn how to run community models from Hugging Face on AMD GPUs, see
   :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.6.4.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the unified
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the unified
                  ROCm Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -18,9 +18,9 @@ vLLM inference performance testing
 
 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
+(LLM) inference performance on the AMD Instinct™ MI300X GPU. This
 ROCm vLLM Docker image integrates vLLM and PyTorch tailored specifically for the
-MI300X accelerator and includes the following components:
+MI300X GPU and includes the following components:
 
 * `ROCm 6.2.1 <https://github.com/ROCm/ROCm>`_
 
@@ -31,7 +31,7 @@ MI300X accelerator and includes the following components:
 * 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
+performance numbers on the MI300X GPU. This topic also provides tips on
 optimizing performance with popular AI models.
 
 .. hlist::
@@ -74,7 +74,7 @@ Getting started
 ===============
 
 Use the following procedures to reproduce the benchmark results on an
-MI300X accelerator with the prebuilt vLLM Docker image.
+MI300X GPU with the prebuilt vLLM Docker image.
 
 .. _vllm-benchmark-get-started:
 
@@ -332,7 +332,7 @@ Options
 
 .. _vllm-benchmark-run-benchmark-v064:
 
-Running the benchmark on the MI300X accelerator
+Running the benchmark on the MI300X GPU
 -----------------------------------------------
 
 Here are some examples of running the benchmark with various options.
@@ -398,7 +398,7 @@ Further reading
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - To learn how to run community models from Hugging Face on AMD GPUs, see
   :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.6.6.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -18,9 +18,9 @@ LLM inference performance validation on AMD Instinct MI300X
 
 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
+inference performance on the AMD Instinct™ MI300X GPU. This ROCm vLLM
 Docker image integrates vLLM and PyTorch tailored specifically for the MI300X
-accelerator and includes the following components:
+GPU and includes the following components:
 
 * `ROCm 6.3.1 <https://github.com/ROCm/ROCm>`_
 
@@ -29,7 +29,7 @@ accelerator and includes the following components:
 * `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
+performance numbers for the MI300X GPU. 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-v066-models>`
 and :ref:`standalone benchmarking <vllm-benchmark-standalone-v066-options>`.
@@ -47,7 +47,7 @@ Getting started
 ===============
 
 Use the following procedures to reproduce the benchmark results on an
-MI300X accelerator with the prebuilt vLLM Docker image.
+MI300X GPU with the prebuilt vLLM Docker image.
 
 .. _vllm-benchmark-get-started:
 
@@ -377,7 +377,7 @@ Options and available models
 
 .. _vllm-benchmark-run-benchmark-v066:
 
-Running the benchmark on the MI300X accelerator
+Running the benchmark on the MI300X GPU
 -----------------------------------------------
 
 Here are some examples of running the benchmark with various options.
@@ -443,7 +443,7 @@ Further reading
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - To learn how to run community models from Hugging Face on AMD GPUs, see
   :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.7.3-20250325.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -23,9 +23,9 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerator. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   accelerators and includes the following components:
+   inference performance on AMD Instinct™ MI300X Series GPU. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
+   GPUs and includes the following components:
 
    * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
 
@@ -37,7 +37,7 @@ vLLM inference performance testing
 
    With this Docker image, you can quickly test the :ref:`expected
    inference performance numbers <vllm-benchmark-performance-measurements-v073>` for
-   MI300X series accelerators.
+   MI300X Series GPUs.
 
    .. _vllm-benchmark-available-models-v073:
 
@@ -110,7 +110,7 @@ vLLM inference performance testing
       The performance data presented in
       `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
       only reflects the :doc:`latest version of this inference benchmarking environment <../vllm>`.
-      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
    Advanced features and known issues
    ==================================
@@ -122,7 +122,7 @@ vLLM inference performance testing
    ===============
 
    Use the following procedures to reproduce the benchmark results on an
-   MI300X accelerator with the prebuilt vLLM Docker image.
+   MI300X GPU with the prebuilt vLLM Docker image.
 
    .. _vllm-benchmark-get-started:
 
@@ -311,7 +311,7 @@ Further reading
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - To learn how to run community models from Hugging Face on AMD GPUs, see
   :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.3-20250415.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -18,9 +18,9 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   accelerators and includes the following components:
+   inference performance on AMD Instinct™ MI300X Series GPUs. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
+   GPUs and includes the following components:
 
    * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
 
@@ -32,7 +32,7 @@ vLLM inference performance testing
 
    With this Docker image, you can quickly test the :ref:`expected
    inference performance numbers <vllm-benchmark-performance-measurements-v083>` for
-   MI300X series accelerators.
+   MI300X Series GPUs.
 
    .. _vllm-benchmark-available-models-v083:
 
@@ -105,7 +105,7 @@ vLLM inference performance testing
       The performance data presented in
       `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
       only reflects the :doc:`latest version of this inference benchmarking environment <../vllm>`.
-      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
    Advanced features and known issues
    ==================================
@@ -327,7 +327,7 @@ Further reading
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - To learn how to run community models from Hugging Face on AMD GPUs, see
   :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250513.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -23,9 +23,9 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   accelerators and includes the following components:
+   inference performance on AMD Instinct™ MI300X Series GPUs. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
+   GPUs and includes the following components:
 
    * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
 
@@ -37,7 +37,7 @@ vLLM inference performance testing
 
    With this Docker image, you can quickly test the :ref:`expected
    inference performance numbers <vllm-benchmark-performance-measurements-v085-20250513>` for
-   MI300X series accelerators.
+   MI300X Series GPUs.
 
    .. _vllm-benchmark-available-models-v085-20250513:
 
@@ -114,7 +114,7 @@ vLLM inference performance testing
       The performance data presented in
       `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
       only reflects the :doc:`latest version of this inference benchmarking environment <../vllm>`.
-      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
    Advanced features and known issues
    ==================================
@@ -333,7 +333,7 @@ Further reading
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250521.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -23,9 +23,9 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   accelerators and includes the following components:
+   inference performance on AMD Instinct™ MI300X Series GPUs. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
+   GPUs and includes the following components:
 
    * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
 
@@ -37,7 +37,7 @@ vLLM inference performance testing
 
    With this Docker image, you can quickly test the :ref:`expected
    inference performance numbers <vllm-benchmark-performance-measurements-v085-20250521>` for
-   MI300X series accelerators.
+   MI300X Series GPUs.
 
    .. _vllm-benchmark-available-models-v085-20250521:
 
@@ -114,7 +114,7 @@ vLLM inference performance testing
       The performance data presented in
       `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
       should not be interpreted as the peak performance achievable by AMD
-      Instinct MI325X and MI300X accelerators or ROCm software.
+      Instinct MI325X and MI300X GPUs or ROCm software.
 
    Advanced features and known issues
    ==================================
@@ -333,7 +333,7 @@ Further reading
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.0.1-20250605.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -23,9 +23,9 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   accelerators and includes the following components:
+   inference performance on AMD Instinct™ MI300X Series GPUs. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
+   GPUs and includes the following components:
 
    * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
 
@@ -37,7 +37,7 @@ vLLM inference performance testing
 
    With this Docker image, you can quickly test the :ref:`expected
    inference performance numbers <vllm-benchmark-performance-measurements-v0901-20250605>` for
-   MI300X series accelerators.
+   MI300X Series GPUs.
 
    .. _vllm-benchmark-available-models-v0901-20250605:
 
@@ -113,7 +113,7 @@ vLLM inference performance testing
       The performance data presented in
       `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
       only reflects the latest version of this inference benchmarking environment.
-      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
    Advanced features and known issues
    ==================================
@@ -332,7 +332,7 @@ Further reading
   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 `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.1-20250702.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -23,9 +23,9 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   accelerators and includes the following components:
+   inference performance on AMD Instinct™ MI300X Series GPUs. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
+   GPUs and includes the following components:
 
    * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
 
@@ -37,7 +37,7 @@ vLLM inference performance testing
 
    With this Docker image, you can quickly test the :ref:`expected
    inference performance numbers <vllm-benchmark-performance-measurements-20250702>` for
-   MI300X series accelerators.
+   MI300X Series GPUs.
 
    .. _vllm-benchmark-available-models-20250702:
 
@@ -113,7 +113,7 @@ vLLM inference performance testing
       The performance data presented in
       `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
       only reflects the latest version of this inference benchmarking environment.
-      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+      The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
    Advanced features and known issues
    ==================================
@@ -332,7 +332,7 @@ Further reading
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.1-20250715.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
@@ -23,9 +23,9 @@ vLLM inference performance testing
 
    The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
    a prebuilt, optimized environment for validating large language model (LLM)
-   inference performance on AMD Instinct™ MI300X series accelerators. This ROCm vLLM
-   Docker image integrates vLLM and PyTorch tailored specifically for MI300X series
-   accelerators and includes the following components:
+   inference performance on AMD Instinct™ MI300X Series GPUs. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for MI300X Series
+   GPUs and includes the following components:
 
    .. list-table::
       :header-rows: 1
@@ -47,7 +47,7 @@ vLLM inference performance testing
 
 With this Docker image, you can quickly test the :ref:`expected
 inference performance numbers <vllm-benchmark-performance-measurements-715>` for
-MI300X series accelerators.
+MI300X Series GPUs.
 
 What's new
 ==========
@@ -145,7 +145,7 @@ page provides reference throughput and latency measurements for inferencing popu
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`_
    only reflects the latest version of this inference benchmarking environment.
-   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================
@@ -429,7 +429,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

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

@@ -1,5 +1,5 @@
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the
                  ROCm PyTorch Docker image.
    :keywords: model, MAD, automation, dashboarding, validate, pytorch
 
@@ -15,7 +15,7 @@ PyTorch inference performance testing
    {% set model_groups = data.pytorch_inference_benchmark.model_groups %}
 
    The `ROCm PyTorch Docker <https://hub.docker.com/r/rocm/pytorch/tags>`_ image offers a prebuilt,
-   optimized environment for testing model inference performance on AMD Instinct™ MI300X series
+   optimized environment for testing model inference performance on AMD Instinct™ MI300X Series
    GPUs. This guide demonstrates how to use the AMD Model Automation and Dashboarding (MAD)
    tool with the ROCm PyTorch container to test inference performance on various models efficiently.
 
@@ -175,7 +175,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`../../inference-optimization/workload`.

docs/how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst

@@ -22,7 +22,7 @@ improved efficiency and throughput.
    `SGLang <https://docs.sglang.ai>`__ is a high-performance inference and
    serving engine for large language models (LLMs) and vision models. The
    ROCm-enabled `SGLang base Docker image <{{ docker.docker_hub_url }}>`__
-   bundles SGLang with PyTorch, which is optimized for AMD Instinct MI300X series
+   bundles SGLang with PyTorch, which is optimized for AMD Instinct MI300X Series
    GPUs. It includes the following software components:
 
    .. list-table::
@@ -37,7 +37,7 @@ improved efficiency and throughput.
       {% endfor %}
 
 The following guides on setting up and running SGLang and Mooncake for disaggregated
-distributed inference on a Slurm cluster using AMD Instinct MI300X series GPUs backed by
+distributed inference on a Slurm cluster using AMD Instinct MI300X Series GPUs backed by
 Mellanox CX-7 NICs.
 
 Prerequisites
@@ -236,7 +236,7 @@ Further reading
 - See the base upstream Docker image on `Docker Hub <https://hub.docker.com/layers/lmsysorg/sglang/v0.5.2rc1-rocm700-mi30x/images/sha256-10c4ee502ddba44dd8c13325e6e03868bfe7f43d23d0a44780a8ee8b393f4729>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__.
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__.
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

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

@@ -1,5 +1,5 @@
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and SGLang
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and SGLang
    :keywords: model, MAD, automation, dashboarding, validate
 
 *****************************************************************
@@ -15,8 +15,8 @@ SGLang inference performance testing DeepSeek-R1-Distill-Qwen-32B
    `SGLang <https://docs.sglang.ai>`__ is a high-performance inference and
    serving engine for large language models (LLMs) and vision models. The
    ROCm-enabled `SGLang Docker image <{{ docker.docker_hub_url }}>`__
-   bundles SGLang with PyTorch, optimized for AMD Instinct MI300X series
-   accelerators. It includes the following software components:
+   bundles SGLang with PyTorch, optimized for AMD Instinct MI300X Series
+   GPUs. It includes the following software components:
 
    .. list-table::
       :header-rows: 1
@@ -255,7 +255,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__.
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__.
 
 - For application performance optimization strategies for HPC and AI workloads,
   including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.

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

@@ -1,5 +1,5 @@
 .. meta::
-   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the ROCm vLLM Docker image.
+   :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the ROCm vLLM Docker image.
    :keywords: model, MAD, automation, dashboarding, validate
 
 **********************************
@@ -457,7 +457,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
   a brief introduction to vLLM and optimization strategies.

docs/how-to/rocm-for-ai/inference/deploy-your-model.rst

@@ -44,9 +44,9 @@ Validating vLLM performance
 ---------------------------
 
 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 
+on the MI300X GPU. The Docker image includes ROCm, vLLM, PyTorch, and tuning files in the CSV 
 format. For more information, see the guide to 
-`LLM inference performance testing with vLLM on the AMD Instinct™ MI300X accelerator <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_ 
+`LLM inference performance testing with vLLM on the AMD Instinct™ MI300X GPU <https://github.com/ROCm/MAD/blob/develop/benchmark/vllm/README.md>`_ 
 on the ROCm GitHub repository.
 
 .. _rocm-for-ai-serve-hugging-face-tgi:
@@ -61,7 +61,7 @@ The `Hugging Face Text Generation Inference <https://huggingface.co/docs/text-ge
 TGI installation
 ----------------
 
-The easiest way to use Hugging Face TGI with ROCm on AMD Instinct accelerators is to use the official Docker image at
+The easiest way to use Hugging Face TGI with ROCm on AMD Instinct GPUs is to use the official Docker image at
 `<https://github.com/huggingface/text-generation-inference/pkgs/container/text-generation-inference>`__.
 
 TGI walkthrough

docs/how-to/rocm-for-ai/inference/hugging-face-models.rst

@@ -10,7 +10,7 @@ Running models from Hugging Face
 transformer models. Hugging Face models and tools significantly enhance productivity, performance, and accessibility in
 developing and deploying AI solutions.
 
-This section describes how to run popular community transformer models from Hugging Face on AMD accelerators and GPUs.
+This section describes how to run popular community transformer models from Hugging Face on AMD GPUs.
 
 .. _rocm-for-ai-hugging-face-transformers:
 
@@ -62,11 +62,11 @@ Using Hugging Face with Optimum-AMD
 
 Optimum-AMD is the interface between Hugging Face libraries and the ROCm software stack.
 
-For a deeper dive into using Hugging Face libraries on AMD accelerators and GPUs, refer to the
+For a deeper dive into using Hugging Face libraries on AMD GPUs, refer to the
 `Optimum-AMD <https://huggingface.co/docs/optimum/main/en/amd/amdgpu/overview>`_ page on Hugging Face for guidance on
 using Flash Attention 2, GPTQ quantization and the ONNX Runtime integration.
 
-Hugging Face libraries natively support AMD Instinct accelerators. For other
+Hugging Face libraries natively support AMD Instinct GPUs. For other
 :doc:`ROCm-capable hardware <rocm-install-on-linux:reference/system-requirements>`, support is currently not
 validated, but most features are expected to work without issues.
 
@@ -139,7 +139,7 @@ To enable `GPTQ <https://arxiv.org/abs/2210.17323>`_, hosted wheels are availabl
 
       pip install auto-gptq --no-build-isolation --extra-index-url https://huggingface.github.io/autogptq-index/whl/rocm573/
 
-   Or, to install from source for AMD accelerators supporting ROCm, specify the ``ROCM_VERSION`` environment variable.
+   Or, to install from source for AMD GPUs supporting ROCm, specify the ``ROCM_VERSION`` environment variable.
 
    .. code-block:: shell
 

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

@@ -9,7 +9,7 @@ AI inference is a process of deploying a trained machine learning model to make
 
 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. 
+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 GPUs 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.

docs/how-to/rocm-for-ai/inference/llm-inference-frameworks.rst

@@ -60,7 +60,7 @@ Installing vLLM
                vllm-rocm \
                bash
 
-      3. Inside the container, start the API server to run on a single accelerator on port 8000 using the following command.
+      3. Inside the container, start the API server to run on a single GPU on port 8000 using the following command.
 
          .. code-block:: shell
 
@@ -113,7 +113,7 @@ Installing vLLM
             python -m vllm.entrypoints.api_server --model /app/model --dtype float16 -tp 2 --port 8000 &
 
       4. To run multiple instances of API Servers, specify different ports for each server, and use ``ROCR_VISIBLE_DEVICES`` to
-         isolate each instance to a different accelerator.
+         isolate each instance to a different GPU.
 
          For example, to run two API servers, one on port 8000 using GPU 0 and 1, one on port 8001 using GPU 2 and 3, use a
          a command like the following.
@@ -140,7 +140,7 @@ Installing vLLM
    See :ref:`mi300x-vllm-optimization` for performance optimization tips.
 
    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, and PyTorch.
+   on the MI300X GPU. The Docker image includes ROCm, vLLM, and PyTorch.
    For more information, see :doc:`/how-to/rocm-for-ai/inference/benchmark-docker/vllm`.
 
 .. _fine-tuning-llms-tgi:
@@ -178,7 +178,7 @@ Install TGI
    .. tab-item:: TGI on a single-accelerator system
       :sync: single
 
-      2. Inside the container, launch a model using TGI server on a single accelerator.
+      2. Inside the container, launch a model using TGI server on a single GPU.
 
          .. code-block:: shell
 
@@ -199,7 +199,7 @@ Install TGI
 
    .. tab-item:: TGI on a multi-accelerator system
 
-      2. Inside the container, launch a model using TGI server on multiple accelerators (4 in this case).
+      2. Inside the container, launch a model using TGI server on multiple GPUs (four in this case).
 
          .. code-block:: shell
 

docs/how-to/rocm-for-ai/system-setup/multi-node-setup.rst

@@ -1,6 +1,6 @@
 .. meta::
    :description: Multi-node setup for AI training
-   :keywords: gpu, accelerator, system, health, validation, bench, perf, performance, rvs, rccl, babel, mi300x, mi325x, flops, bandwidth, rbt, training
+   :keywords: gpu, system, health, validation, bench, perf, performance, rvs, rccl, babel, mi300x, mi325x, flops, bandwidth, rbt, training
 
 .. _rocm-for-ai-multi-node-setup:
 
@@ -21,7 +21,7 @@ Before starting, ensure your environment meets the following requirements:
 
 * Multi-node networking: your cluster should have a configured multi-node network. For setup
   instructions, see the `Multi-node network configuration for AMD Instinct
-  accelerators
+  GPUs
   <https://instinct.docs.amd.com/projects/gpu-cluster-networking/en/latest/how-to/multi-node-config.html>`__
   guide in the Instinct documentation.
 
@@ -54,8 +54,8 @@ Compile and install the RoCE library
 
 If you're using Broadcom NICs, you need to compile and install the RoCE (RDMA
 over Converged Ethernet) library. See `RoCE cluster network configuration guide
-for AMD Instinct accelerators
-<https://instinct.docs.amd.com/projects/gpu-cluster-networking/en/latest/how-to/roce-network-config.html#roce-cluster-network-configuration-guide-for-amd-instinct-accelerators>`__
+for AMD Instinct GPUs
+<https://instinct.docs.amd.com/projects/gpu-cluster-networking/en/latest/how-to/roce-network-config.html>`__
 for more information.
 
 See the `Ethernet networking guide for AMD
@@ -315,6 +315,6 @@ Megatron-LM
 Further reading
 ===============
 
-* `Multi-node network configuration for AMD Instinct accelerators <https://instinct.docs.amd.com/projects/gpu-cluster-networking/en/latest/how-to/multi-node-config.html>`__
+* `Multi-node network configuration for AMD Instinct GPUs <https://instinct.docs.amd.com/projects/gpu-cluster-networking/en/latest/how-to/multi-node-config.html>`__
 
 * `Ethernet networking guide for AMD Instinct MI300X GPU clusters: Compiling Broadcom NIC software from source <https://docs.broadcom.com/doc/957608-AN2XX#page=81>`__

docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst

@@ -6,14 +6,8 @@
 Training a model with JAX MaxText on ROCm
 ******************************************
 
-MaxText is a high-performance, open-source framework built on the Google JAX
-machine learning library to train LLMs at scale. The MaxText framework for
-ROCm is an optimized fork of the upstream
-`<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
-on AMD MI300X series GPUs.
-
 The MaxText for ROCm training Docker image
-provides a prebuilt environment for training on AMD Instinct MI300X and MI325X GPUs,
+provides a prebuilt environment for training on AMD Instinct MI355X, MI350X, MI325X, and MI300X GPUs,
 including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
 It includes the following software components:
 
@@ -61,15 +55,15 @@ MaxText with on ROCm provides the following key features to train large language
 
 - Multi-node support
 
-- NANOO FP8 quantization support
+- NANOO FP8 (for MI300X series GPUs) and FP8 (for MI355X and MI350X) quantization support
 
-.. _amd-maxtext-model-support-v257:
+.. _amd-maxtext-model-support-v259:
 
 Supported models
 ================
 
-The following models are pre-optimized for performance on AMD Instinct MI300
-series GPUs. Some instructions, commands, and available training
+The following models are pre-optimized for performance on AMD Instinct
+GPUs. Some instructions, commands, and available training
 configurations in this documentation might vary by model -- select one to get
 started.
 
@@ -139,22 +133,13 @@ Use the following command to pull the Docker image from Docker Hub.
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
 
-   {% set dockers = data.dockers %}
-   .. tab-set::
+   {% set docker = data.dockers[0] %}
 
-      {% for docker in dockers %}
-      {% set jax_version = docker.components["JAX"] %}
+   .. code-block:: shell
 
-      .. tab-item:: JAX {{ jax_version }}
-         :sync: {{ docker.pull_tag }}
+      docker pull {{ docker.pull_tag }}
 
-         .. code-block:: shell
-
-            docker pull {{ docker.pull_tag }}
-
-      {% endfor %}
-
-.. _amd-maxtext-multi-node-setup-v257:
+.. _amd-maxtext-multi-node-setup-v259:
 
 Multi-node configuration
 ------------------------
@@ -162,7 +147,7 @@ Multi-node configuration
 See :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your
 environment for multi-node training.
 
-.. _amd-maxtext-get-started-v257:
+.. _amd-maxtext-get-started-v259:
 
 Benchmarking
 ============
@@ -174,7 +159,7 @@ benchmark results:
 
    .. _vllm-benchmark-mad:
 
-   {% set dockers = data.dockers %}
+   {% set docker = data.dockers[0] %}
    {% set model_groups = data.model_groups %}
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
@@ -186,6 +171,9 @@ benchmark results:
          {% if model.mad_tag and "single-node" in model.doc_options %}
          .. tab-item:: MAD-integrated benchmarking
 
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`amd-maxtext-model-support-v259` to switch to another available model.
+
             1. 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.
 
@@ -214,22 +202,19 @@ benchmark results:
 
          .. tab-item:: Standalone benchmarking
 
+            The following commands are optimized for {{ model.model }}. See
+            :ref:`amd-maxtext-model-support-v259` to switch to another
+            available model. Some instructions and resources might not be
+            available for all models and configurations.
+
             .. rubric:: Download the Docker image and required scripts
 
             Run the JAX MaxText benchmark tool independently by starting the
             Docker container as shown in the following snippet.
 
-            .. tab-set::
-               {% for docker in dockers %}
-               {% set jax_version = docker.components["JAX"] %}
+            .. code-block:: shell
 
-               .. tab-item:: JAX {{ jax_version }}
-                  :sync: {{ docker.pull_tag }}
-
-                  .. code-block:: shell
-
-                     docker pull {{ docker.pull_tag }}
-               {% endfor %}
+               docker pull {{ docker.pull_tag }}
 
             {% if model.model_repo and "single-node" in model.doc_options %}
             .. rubric:: Single node training
@@ -250,33 +235,25 @@ benchmark results:
 
             2. Launch the Docker container.
 
-               .. tab-set::
-                  {% for docker in dockers %}
-                  {% set jax_version = docker.components["JAX"] %}
+               .. code-block:: shell
 
-                  .. tab-item:: JAX {{ jax_version }}
-                     :sync: {{ docker.pull_tag }}
-
-                     .. code-block:: shell
-
-                        docker run -it \
-                            --device=/dev/dri \
-                            --device=/dev/kfd \
-                            --network host \
-                            --ipc host \
-                            --group-add video \
-                            --cap-add=SYS_PTRACE \
-                            --security-opt seccomp=unconfined \
-                            --privileged \
-                            -v $HOME:$HOME \
-                            -v $HOME/.ssh:/root/.ssh \
-                            -v $HF_HOME:/hf_cache \
-                            -e HF_HOME=/hf_cache \
-                            -e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
-                            --shm-size 64G \
-                            --name training_env \
-                            {{ docker.pull_tag }}
-                  {% endfor %}
+                  docker run -it \
+                      --device=/dev/dri \
+                      --device=/dev/kfd \
+                      --network host \
+                      --ipc host \
+                      --group-add video \
+                      --cap-add=SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --privileged \
+                      -v $HOME:$HOME \
+                      -v $HOME/.ssh:/root/.ssh \
+                      -v $HF_HOME:/hf_cache \
+                      -e HF_HOME=/hf_cache \
+                      -e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
+                      --shm-size 64G \
+                      --name training_env \
+                      {{ docker.pull_tag }}
 
             3. In the Docker container, clone the ROCm MAD repository and navigate to the
                benchmark scripts directory at ``MAD/scripts/jax-maxtext``.
@@ -299,11 +276,27 @@ benchmark results:
 
                   ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }}
 
-               For quantized training, use the following command:
+               For quantized training, run the script with the appropriate option for your Instinct GPU.
 
-               .. code-block:: shell
+               .. tab-set::
 
-                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8
+                  .. tab-item:: MI355X and MI350X
+
+                     For ``fp8`` quantized training on MI355X and MI350X GPUs, use the following command:
+
+                     .. code-block:: shell
+
+                        ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q fp8
+
+                  {% if model.model_repo not in ["Llama-3.1-70B", "Llama-3.3-70B"] %}
+                  .. tab-item:: MI325X and MI300X
+
+                     For ``nanoo_fp8`` quantized training on MI300X series GPUs, use the following command:
+
+                     .. code-block:: shell
+
+                        ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8
+                  {% endif %}
 
             {% endif %}
             {% if model.multinode_training_script and "multi-node" in model.doc_options %}
@@ -335,7 +328,7 @@ benchmark results:
          {% else %}
             .. rubric:: Multi-node training
 
-            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v257`
+            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v259`
             with an available `multi-node training script <https://github.com/ROCm/MAD/tree/develop/scripts/jax-maxtext/gpu-rocm>`__.
          {% endif %}
       {% endfor %}
@@ -347,7 +340,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For a list of other ready-made Docker images for AI with ROCm, see
   `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.

docs/how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst

@@ -10,6 +10,12 @@ Training a model with Megatron-LM on ROCm
 
 .. caution::
 
+   For a unified training solution on AMD GPUs with ROCm, the `rocm/megatron-lm
+   <https://hub.docker.com/r/rocm/megatron-lm/>`__ Docker Hub registry will be
+   deprecated soon in favor of `rocm/primus <https://hub.docker.com/r/rocm/primus>`__.
+   The ``rocm/primus`` Docker containers will cover PyTorch training ecosystem frameworks,
+   including Megatron-LM, `torchtitan, and torchtune <primus-pytorch>`__.
+
    Primus with Megatron is designed to replace this ROCm Megatron-LM training workflow.
    To learn how to migrate workloads from Megatron-LM to Primus with Megatron,
    see :doc:`previous-versions/megatron-lm-primus-migration-guide`.
@@ -17,30 +23,25 @@ Training a model with Megatron-LM on ROCm
 The `Megatron-LM framework for ROCm <https://github.com/ROCm/Megatron-LM>`_ is
 a specialized fork of the robust Megatron-LM, designed to enable efficient
 training of large-scale language models on AMD GPUs. By leveraging AMD
-Instinct™ MI300X series GPUs, Megatron-LM delivers enhanced
-scalability, performance, and resource utilization for AI workloads. It is
+Instinct™ GPUs, Megatron-LM delivers enhanced scalability, performance, and
+resource utilization for AI workloads. It is
 purpose-built to support models like Llama, DeepSeek, and Mixtral,
 enabling developers to train next-generation AI models more
 efficiently.
 
-AMD provides ready-to-use Docker images for MI300X series GPUs containing
-essential components, including PyTorch, ROCm libraries, and Megatron-LM
-utilities. It contains the following software components to accelerate training
-workloads:
-
-.. note::
-
-   This Docker environment is based on Python 3.10 and Ubuntu 22.04. For an alternative environment with
-   Python 3.12 and Ubuntu 24.04, see the :doc:`previous ROCm Megatron-LM v25.6 Docker release <previous-versions/megatron-lm-v25.6>`.
+AMD provides ready-to-use Docker images for MI355X, MI350X, MI325X, and MI300X
+GPUs containing essential components, including PyTorch, ROCm libraries, and
+Megatron-LM utilities. It contains the following software components to
+accelerate training workloads:
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
 
    {% set dockers = data.dockers %}
    .. tab-set::
 
-      {% for docker in dockers %}
-      .. tab-item:: ``{{ docker.pull_tag }}``
-         :sync: {{ docker.pull_tag }}
+   {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}
 
          .. list-table::
             :header-rows: 1
@@ -51,17 +52,15 @@ workloads:
             {% for component_name, component_version in docker.components.items() %}
             * - {{ component_name }}
               - {{ component_version }}
-
             {% endfor %}
-      {% endfor %}
-
+   {% endfor %}
    .. _amd-megatron-lm-model-support:
 
    Supported models
    ================
 
    The following models are supported for training performance benchmarking with Megatron-LM and ROCm
-   on AMD Instinct MI300X series GPUs.
+   on AMD Instinct MI300X Series GPUs.
    Some instructions, commands, and training recommendations in this documentation might
    vary by model -- select one to get started.
 
@@ -138,7 +137,7 @@ Environment setup
 =================
 
 Use the following instructions to set up the environment, configure the script to train models, and
-reproduce the benchmark results on MI300X series GPUs with the AMD Megatron-LM Docker
+reproduce the benchmark results on MI300X Series GPUs with the AMD Megatron-LM Docker
 image.
 
 .. _amd-megatron-lm-requirements:
@@ -151,33 +150,24 @@ Download the Docker image
    {% set dockers = data.dockers %}
    1. Use the following command to pull the Docker image from Docker Hub.
 
-      {% if dockers|length > 1 %}
       .. tab-set::
 
-         {% for docker in data.dockers %}
-         .. tab-item:: {{ docker.doc_name }}
-            :sync: {{ docker.pull_tag }}
+         {% for supported_gpus, docker in dockers.items() %}
+         .. tab-item:: {{ supported_gpus }}
+            :sync: {{ supported_gpus }}
 
             .. code-block:: shell
 
                docker pull {{ docker.pull_tag }}
-
          {% endfor %}
-      {% elif dockers|length == 1 %}
-      {% set docker = dockers[0] %}
-      .. code-block:: shell
 
-         docker pull {{ docker.pull_tag }}
-
-      {% endif %}
    2. Launch the Docker container.
 
-      {% if dockers|length > 1 %}
       .. tab-set::
 
-         {% for docker in dockers %}
-         .. tab-item:: {{ docker.doc_name }}
-            :sync: {{ docker.pull_tag }}
+         {% for supported_gpus, docker in dockers.items() %}
+         .. tab-item:: {{ supported_gpus }}
+            :sync: {{ supported_gpus }}
 
             .. code-block:: shell
 
@@ -195,28 +185,7 @@ Download the Docker image
                    --shm-size 128G \
                    --name megatron_training_env \
                    {{ docker.pull_tag }}
-
          {% endfor %}
-      {% elif dockers|length == 1 %}
-      {% set docker = dockers[0] %}
-      .. code-block:: shell
-
-         docker run -it \
-             --device /dev/dri \
-             --device /dev/kfd \
-             --device /dev/infiniband \
-             --network host --ipc host \
-             --group-add video \
-             --cap-add SYS_PTRACE \
-             --security-opt seccomp=unconfined \
-             --privileged \
-             -v $HOME:$HOME \
-             -v $HOME/.ssh:/root/.ssh \
-             --shm-size 128G \
-             --name megatron_training_env \
-             {{ docker.pull_tag }}
-
-      {% endif %}
 
 3. Use these commands if you exit the ``megatron_training_env`` container and need to return to it.
 
@@ -234,8 +203,8 @@ Download the Docker image
       pip uninstall megatron-core
       pip install -e .
 
-The Docker container hosts
-`<https://github.com/ROCm/Megatron-LM/tree/rocm_dev>`__ at verified commit ``e8e9edc``.
+The Docker container hosts a verified commit of
+`<https://github.com/ROCm/Megatron-LM/tree/rocm_dev>`__.
 
 .. _amd-megatron-lm-environment-setup:
 
@@ -533,7 +502,7 @@ Run training
 
 Use the following example commands to set up the environment, configure
 :ref:`key options <amd-megatron-lm-benchmark-test-vars>`, and run training on
-MI300X series GPUs with the AMD Megatron-LM environment.
+MI300X Series GPUs with the AMD Megatron-LM environment.
 
 Single node training
 --------------------
@@ -572,31 +541,73 @@ Single node training
    To run training on a single node for Llama 3.1 8B FP8, navigate to the Megatron-LM folder and use the
    following command.
 
-   .. code-block:: shell
+   .. tab-set::
 
-      TEE_OUTPUT=1 \
-      MBS=2 \
-      BS=128 \
-      TP=1 \
-      TE_FP8=1 \
-      SEQ_LENGTH=8192 \
-      MODEL_SIZE=8 \
-      TOTAL_ITERS=50 \
-      bash examples/llama/train_llama3.sh
+      .. tab-item:: MI355X and MI350X
+         :sync: MI355X and MI350X
+
+         .. code-block:: shell
+
+            TEE_OUTPUT=1 \
+            MBS=4 \
+            BS=512 \
+            TP=1 \
+            TE_FP8=1 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=8 \
+            TOTAL_ITERS=10 \
+            GEMM_TUNING=0 \
+            bash examples/llama/train_llama3.sh
+
+      .. tab-item:: MI300X
+         :sync: MI325X and MI300X
+
+         .. code-block:: shell
+
+            TEE_OUTPUT=1 \
+            MBS=2 \
+            BS=128 \
+            TP=1 \
+            TE_FP8=1 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=8 \
+            TOTAL_ITERS=50 \
+            bash examples/llama/train_llama3.sh
 
    For Llama 3.1 8B BF16, use the following command:
 
-   .. code-block:: shell
+   .. tab-set::
 
-      TEE_OUTPUT=1 \
-      MBS=2 \
-      BS=128 \
-      TP=1 \
-      TE_FP8=0 \
-      SEQ_LENGTH=8192 \
-      MODEL_SIZE=8 \
-      TOTAL_ITERS=50 \
-      bash examples/llama/train_llama3.sh
+      .. tab-item:: MI355X and MI350X
+         :sync: MI355X and MI350X
+
+         .. code-block:: shell
+
+            TEE_OUTPUT=1 \
+            MBS=4 \
+            BS=512 \
+            TP=1 \
+            TE_FP8=0 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=8 \
+            TOTAL_ITERS=10 \
+            GEMM_TUNING=1 \
+            bash examples/llama/train_llama3.sh
+
+      .. tab-item:: MI300X
+         :sync: MI325X and MI300X
+
+         .. code-block:: shell
+
+            TEE_OUTPUT=1 \
+            MBS=2 \
+            BS=128 \
+            TP=1 \
+            TE_FP8=0 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=8 \
+            TOTAL_ITERS=50 \
+            bash examples/llama/train_llama3.sh
 
 .. container:: model-doc pyt_megatron_lm_train_llama-3.1-70b
 
@@ -625,29 +636,60 @@ Single node training
       parallelism, MCore's distributed optimizer, gradient accumulation fusion,
       or FP16.
 
-.. container:: model-doc pyt_megatron_lm_train_llama-3.1-70b-proxy
-
-   To run the training on a single node for Llama 3.1 70B with proxy, use the following command.
-
-   .. code-block:: shell
-
-      CKPT_FORMAT=torch_dist \
-      TEE_OUTPUT=1 \
-      RECOMPUTE=1 \
-      MBS=3 \
-      BS=24 \
-      TP=1 \
-      TE_FP8=1 \
-      SEQ_LENGTH=8192 \
-      MODEL_SIZE=70 \
-      FSDP=1 \
-      TOTAL_ITERS=10 \
-      NUM_LAYERS=40 \
-      bash examples/llama/train_llama3.sh
+   To run the training on a single node for Llama 3.1 70B FP8, use the
+   following command.
 
    .. note::
 
-      Use two or more nodes to run the *full* Llama 70B model with FP8 precision.
+      The MI300X configuration uses a proxy model. On MI300X GPUs, use two or more nodes
+      to run the full Llama 3.1 70B model with FP8 precision. MI355X and MI350X GPUs
+      can support the full 70B model with FP8 precision on a single node.
+
+   .. tab-set::
+
+      .. tab-item:: MI355X and MI350X
+         :sync: MI355X and MI350X
+
+         .. code-block:: shell
+
+            CKPT_FORMAT=torch_dist \
+            TEE_OUTPUT=1 \
+            RECOMPUTE=1 \
+            MBS=3 \
+            BS=24 \
+            TP=1 \
+            TE_FP8=1 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=70 \
+            FSDP=1 \
+            TOTAL_ITERS=10 \
+            bash examples/llama/train_llama3.sh
+
+      .. tab-item:: MI300X
+         :sync: MI325X and MI300X
+
+         .. code-block:: shell
+
+            FP8_WEIGHT_TRANSPOSE_CACHE=0 \
+            CKPT_FORMAT=torch_dist \
+            TEE_OUTPUT=1 \
+            RECOMPUTE=1 \
+            MBS=3 \
+            BS=24 \
+            TP=1 \
+            TE_FP8=1 \
+            SEQ_LENGTH=8192 \
+            MODEL_SIZE=70 \
+            FSDP=1 \
+            TOTAL_ITERS=10 \
+            NUM_LAYERS=40 \
+            bash examples/llama/train_llama3.sh
+
+   .. note::
+
+      The MI300X configuration uses a proxy model. On MI300X GPUs, use two or more nodes
+      to run the full Llama 3.1 70B model with FP8 precision. MI355X and MI350X GPUs
+      can support the full 70B model with FP8 precision on a single node.
 
    .. note::
 
@@ -987,6 +1029,11 @@ The benchmark tests support the following sets of variables.
 ``RECOMPUTE_NUM_LAYERS``
   Number of layers used for checkpointing recompute.
 
+Known issues
+============
+
+PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
+
 Previous versions
 =================
 

docs/how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry.rst

@@ -16,7 +16,7 @@ environment for the MPT-30B model using the ``rocm/pytorch-training:v25.5``
 base `Docker image <https://hub.docker.com/layers/rocm/pytorch-training/v25.5/images/sha256-d47850a9b25b4a7151f796a8d24d55ea17bba545573f0d50d54d3852f96ecde5>`_
 and the `LLM Foundry <https://github.com/mosaicml/llm-foundry>`_ framework.
 This environment packages the following software components to train
-on AMD Instinct MI300X series accelerators:
+on AMD Instinct MI300X Series GPUs:
 
 +--------------------------+--------------------------------+
 | Software component       | Version                        |
@@ -182,7 +182,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For a list of other ready-made Docker images for AI with ROCm, see
   `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-history.rst

@@ -17,27 +17,35 @@ previous releases of the ``ROCm/jax-training`` Docker image on `Docker Hub <http
      - Components
      - Resources
 
-   * - 25.7 (latest)
-     - 
+   * - 25.9 (latest)
+     -
+       * ROCm 7.0.0
+       * JAX 0.6.2
+     -
+       * :doc:`Documentation <../jax-maxtext>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7-jax060/images/sha256-7352212ae033a76dca2b9dceffc23c1b5f1a61a7a560082cf747a9bf1acfc9ce>`__
+
+   * - 25.7
+     -
        * ROCm 6.4.1
        * JAX 0.6.0, 0.5.0
-     - 
-       * :doc:`Documentation <../jax-maxtext>`
+     -
+       * :doc:`Documentation <jax-maxtext-v25.7>`
        * `Docker Hub (JAX 0.6.0) <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7-jax060/images/sha256-7352212ae033a76dca2b9dceffc23c1b5f1a61a7a560082cf747a9bf1acfc9ce>`__
        * `Docker Hub (JAX 0.5.0) <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.7/images/sha256-45f4c727d4019a63fc47313d3a5f5a5105569539294ddfd2d742218212ae9025>`__
 
    * - 25.5
-     - 
+     -
        * ROCm 6.3.4
        * JAX 0.4.35
-     - 
+     -
        * :doc:`Documentation <jax-maxtext-v25.5>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.5/images/sha256-4e0516358a227cae8f552fb866ec07e2edcf244756f02e7b40212abfbab5217b>`__
 
    * - 25.4
-     - 
+     -
        * ROCm 6.3.0
        * JAX 0.4.31
-     - 
+     -
        * :doc:`Documentation <jax-maxtext-v25.4>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/jax-training/maxtext-v25.4/images/sha256-fb3eb71cd74298a7b3044b7130cf84113f14d518ff05a2cd625c11ea5f6a7b01>`__

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.4.rst

@@ -17,10 +17,10 @@ MaxText is a high-performance, open-source framework built on the Google JAX
 machine learning library to train LLMs at scale. The MaxText framework for
 ROCm is an optimized fork of the upstream
 `<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
-on AMD MI300X series accelerators.
+on AMD MI300X Series GPUs.
 
 The MaxText for ROCm training Docker (``rocm/jax-training:maxtext-v25.4``) image
-provides a prebuilt environment for training on AMD Instinct MI300X and MI325X accelerators,
+provides a prebuilt environment for training on AMD Instinct MI300X and MI325X GPUs,
 including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
 It includes the following software components:
 
@@ -53,7 +53,7 @@ MaxText provides the following key features to train large language models effic
 
 .. _amd-maxtext-model-support-v254:
 
-The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+The following models are pre-optimized for performance on AMD Instinct MI300X Series GPUs.
 
 * Llama 3.1 8B
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.5.rst

@@ -17,10 +17,10 @@ MaxText is a high-performance, open-source framework built on the Google JAX
 machine learning library to train LLMs at scale. The MaxText framework for
 ROCm is an optimized fork of the upstream
 `<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
-on AMD MI300X series accelerators.
+on AMD MI300X Series GPUs.
 
 The MaxText for ROCm training Docker (``rocm/jax-training:maxtext-v25.5``) image
-provides a prebuilt environment for training on AMD Instinct MI300X and MI325X accelerators,
+provides a prebuilt environment for training on AMD Instinct MI300X and MI325X GPUs,
 including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
 It includes the following software components:
 
@@ -53,7 +53,7 @@ MaxText provides the following key features to train large language models effic
 
 .. _amd-maxtext-model-support-v255:
 
-The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+The following models are pre-optimized for performance on AMD Instinct MI300X Series GPUs.
 
 * Llama 3.3 70B
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.7.rst

@@ -0,0 +1,366 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using JAX MaxText for ROCm.
+   :keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
+
+******************************************
+Training a model with JAX MaxText on ROCm
+******************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm JAX MaxText
+   training performance documentation. See :doc:`../jax-maxtext` for the latest version.
+
+MaxText is a high-performance, open-source framework built on the Google JAX
+machine learning library to train LLMs at scale. The MaxText framework for
+ROCm is an optimized fork of the upstream
+`<https://github.com/AI-Hypercomputer/maxtext>`__ enabling efficient AI workloads
+on AMD MI300X series GPUs.
+
+The MaxText for ROCm training Docker image
+provides a prebuilt environment for training on AMD Instinct MI300X and MI325X GPUs,
+including essential components like JAX, XLA, ROCm libraries, and MaxText utilities.
+It includes the following software components:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   .. tab-set::
+
+      {% for docker in dockers %}
+      {% set jax_version = docker.components["JAX"] %}
+
+      .. tab-item:: ``{{ docker.pull_tag }}``
+         :sync: {{ docker.pull_tag }}
+
+         .. list-table::
+            :header-rows: 1
+
+            * - Software component
+              - Version
+
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+
+            {% endfor %}
+         {% if jax_version == "0.6.0" %}
+         .. note::
+
+            Shardy is a new config in JAX 0.6.0. You might get related errors if it's
+            not configured correctly. For now you can turn it off by setting
+            ``shardy=False`` during the training run. You can also follow the `migration
+            guide <https://docs.jax.dev/en/latest/shardy_jax_migration.html>`__ to enable
+            it.
+         {% endif %}
+
+      {% endfor %}
+
+MaxText with on ROCm provides the following key features to train large language models efficiently:
+
+- Transformer Engine (TE)
+
+- Flash Attention (FA) 3 -- with or without sequence input packing
+
+- GEMM tuning
+
+- Multi-node support
+
+- NANOO FP8 quantization support
+
+.. _amd-maxtext-model-support-v257:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on AMD Instinct MI300
+series GPUs. Some instructions, commands, and available training
+configurations in this documentation might vary by model -- select one to get
+started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+.. note::
+
+   Some models, such as Llama 3, require an external license agreement through
+   a third party (for example, Meta).
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+Environment setup
+=================
+
+This Docker image is optimized for specific model configurations outlined
+as follows. Performance can vary for other training workloads, as AMD
+doesn’t validate configurations and run conditions outside those described.
+
+Pull the Docker image
+---------------------
+
+Use the following command to pull the Docker image from Docker Hub.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   .. tab-set::
+
+      {% for docker in dockers %}
+      {% set jax_version = docker.components["JAX"] %}
+
+      .. tab-item:: JAX {{ jax_version }}
+         :sync: {{ docker.pull_tag }}
+
+         .. code-block:: shell
+
+            docker pull {{ docker.pull_tag }}
+
+      {% endfor %}
+
+.. _amd-maxtext-multi-node-setup-v257:
+
+Multi-node configuration
+------------------------
+
+See :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your
+environment for multi-node training.
+
+.. _amd-maxtext-get-started-v257:
+
+Benchmarking
+============
+
+Once the setup is complete, choose between two options to reproduce the
+benchmark results:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+
+   .. _vllm-benchmark-mad:
+
+   {% set dockers = data.dockers %}
+   {% set model_groups = data.model_groups %}
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. tab-set::
+
+         {% if model.mad_tag and "single-node" in model.doc_options %}
+         .. tab-item:: MAD-integrated benchmarking
+
+            1. 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
+
+            2. Use this command to run the performance benchmark test on the {{ model.model }} model
+               using one GPU with the :literal:`{{model.precision}}` data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{model.mad_tag}} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+            MAD launches a Docker container with the name
+            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
+            model are collected in the following path: ``~/MAD/perf.csv/``.
+         {% endif %}
+
+         .. tab-item:: Standalone benchmarking
+
+            .. rubric:: Download the Docker image and required scripts
+
+            Run the JAX MaxText benchmark tool independently by starting the
+            Docker container as shown in the following snippet.
+
+            .. tab-set::
+               {% for docker in dockers %}
+               {% set jax_version = docker.components["JAX"] %}
+
+               .. tab-item:: JAX {{ jax_version }}
+                  :sync: {{ docker.pull_tag }}
+
+                  .. code-block:: shell
+
+                     docker pull {{ docker.pull_tag }}
+               {% endfor %}
+
+            {% if model.model_repo and "single-node" in model.doc_options %}
+            .. rubric:: Single node training
+
+            1. Set up environment variables.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN=<Your Hugging Face token>
+                  export HF_HOME=<Location of saved/cached Hugging Face models>
+
+               ``MAD_SECRETS_HFTOKEN`` is your Hugging Face access token to access models, tokenizers, and data.
+               See `User access tokens <https://huggingface.co/docs/hub/en/security-tokens>`__.
+
+               ``HF_HOME`` is where ``huggingface_hub`` will store local data. See `huggingface_hub CLI <https://huggingface.co/docs/huggingface_hub/main/en/guides/cli#huggingface-cli-download>`__.
+               If you already have downloaded or cached Hugging Face artifacts, set this variable to that path.
+               Downloaded files typically get cached to ``~/.cache/huggingface``.
+
+            2. Launch the Docker container.
+
+               .. tab-set::
+                  {% for docker in dockers %}
+                  {% set jax_version = docker.components["JAX"] %}
+
+                  .. tab-item:: JAX {{ jax_version }}
+                     :sync: {{ docker.pull_tag }}
+
+                     .. code-block:: shell
+
+                        docker run -it \
+                            --device=/dev/dri \
+                            --device=/dev/kfd \
+                            --network host \
+                            --ipc host \
+                            --group-add video \
+                            --cap-add=SYS_PTRACE \
+                            --security-opt seccomp=unconfined \
+                            --privileged \
+                            -v $HOME:$HOME \
+                            -v $HOME/.ssh:/root/.ssh \
+                            -v $HF_HOME:/hf_cache \
+                            -e HF_HOME=/hf_cache \
+                            -e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
+                            --shm-size 64G \
+                            --name training_env \
+                            {{ docker.pull_tag }}
+                  {% endfor %}
+
+            3. In the Docker container, clone the ROCm MAD repository and navigate to the
+               benchmark scripts directory at ``MAD/scripts/jax-maxtext``.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD/scripts/jax-maxtext
+
+            4. Run the setup scripts to install libraries and datasets needed
+               for benchmarking.
+
+               .. code-block:: shell
+
+                  ./jax-maxtext_benchmark_setup.sh -m {{ model.model_repo }}
+
+            5. To run the training benchmark without quantization, use the following command:
+
+               .. code-block:: shell
+
+                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }}
+
+               For quantized training, use the following command:
+
+               .. code-block:: shell
+
+                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8
+
+            {% endif %}
+            {% if model.multinode_training_script and "multi-node" in model.doc_options %}
+            .. rubric:: Multi-node training
+
+            The following examples use SLURM to run on multiple nodes.
+
+            .. note::
+
+               The following scripts will launch the Docker container and run the
+               benchmark. Run them outside of any Docker container.
+
+            1. Make sure ``$HF_HOME`` is set before running the test. See
+               `ROCm benchmarking <https://github.com/ROCm/MAD/blob/develop/scripts/jax-maxtext/gpu-rocm/readme.md>`__
+               for more details on downloading the Llama models before running the
+               benchmark.
+
+            2. To run multi-node training for {{ model.model }},
+               use the
+               `multi-node training script <https://github.com/ROCm/MAD/blob/develop/scripts/jax-maxtext/gpu-rocm/{{ model.multinode_training_script }}>`__
+               under the ``scripts/jax-maxtext/gpu-rocm/`` directory.
+
+            3. Run the multi-node training benchmark script.
+
+               .. code-block:: shell
+
+                  sbatch -N <num_nodes> {{ model.multinode_training_script }}
+
+         {% else %}
+            .. rubric:: Multi-node training
+
+            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v257`
+            with an available `multi-node training script <https://github.com/ROCm/MAD/tree/develop/scripts/jax-maxtext/gpu-rocm>`__.
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`jax-maxtext-history` to find documentation for previous releases
+of the ``ROCm/jax-training`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-history.rst

@@ -16,62 +16,73 @@ previous releases of the ``ROCm/megatron-lm`` Docker image on `Docker Hub <https
      - Components
      - Resources
 
-   * - v25.8 (latest)
-     - 
-       * ROCm 6.4.3
-       * PyTorch 2.8.0a0+gitd06a406
-     - 
+   * - v25.9 (latest)
+     -
+       * ROCm 7.0.0
+       * Primus 0.3.0
+       * PyTorch 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+     -
        * :doc:`Primus Megatron documentation <../primus-megatron>`
        * :doc:`Megatron-LM (legacy) documentation <../megatron-lm>`
-       * `Docker Hub (py310) <https://hub.docker.com/r/rocm/megatron-lm/tags>`__
+       * `Docker Hub (gfx950) <https://hub.docker.com/layers/rocm/primus/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6>`__
+       * `Docker Hub (gfx942) <https://hub.docker.com/layers/rocm/primus/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357>`__
+
+   * - v25.8
+     -
+       * ROCm 6.4.3
+       * PyTorch 2.8.0a0+gitd06a406
+     -
+       * :doc:`Primus Megatron documentation <primus-megatron-v25.8>`
+       * :doc:`Megatron-LM (legacy) documentation <megatron-lm-v25.8>`
+       * `Docker Hub (py310) <https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-0030c4a3dcb233c66dd5f61135821f9f5c4e321cbe0a2cdc74f110752f28c869>`__
 
    * - v25.7
-     - 
+     -
        * ROCm 6.4.2
        * PyTorch 2.8.0a0+gitd06a406
-     - 
+     -
        * :doc:`Primus Megatron documentation <primus-megatron-v25.7>`
        * :doc:`Megatron-LM (legacy) documentation <megatron-lm-v25.7>`
        * `Docker Hub (py310) <https://hub.docker.com/layers/rocm/megatron-lm/v25.7_py310/images/sha256-6189df849feeeee3ae31bb1e97aef5006d69d2b90c134e97708c19632e20ab5a>`__
 
    * - v25.6
-     - 
+     -
        * ROCm 6.4.1
        * PyTorch 2.8.0a0+git7d205b2
-     - 
+     -
        * :doc:`Documentation <megatron-lm-v25.6>`
        * `Docker Hub (py312) <https://hub.docker.com/layers/rocm/megatron-lm/v25.6_py312/images/sha256-482ff906532285bceabdf2bda629bd32cb6174d2d07f4243a736378001b28df0>`__
        * `Docker Hub (py310) <https://hub.docker.com/layers/rocm/megatron-lm/v25.6_py310/images/sha256-9627bd9378684fe26cb1a10c7dd817868f553b33402e49b058355b0f095568d6>`__
 
    * - v25.5
-     - 
+     -
        * ROCm 6.3.4
        * PyTorch 2.8.0a0+gite2f9759
-     - 
+     -
        * :doc:`Documentation <megatron-lm-v25.5>`
        * `Docker Hub (py312) <https://hub.docker.com/layers/rocm/megatron-lm/v25.5_py312/images/sha256-4506f18ba188d24189c6b1f95130b425f52c528a543bb3f420351824edceadc2>`__
        * `Docker Hub (py310) <https://hub.docker.com/layers/rocm/megatron-lm/v25.5_py310/images/sha256-743fbf1ceff7a44c4452f938d783a7abf143737d1c15b2b95f6f8a62e0fd048b>`__
 
    * - v25.4
-     - 
+     -
        * ROCm 6.3.0
-       * PyTorch 2.7.0a0+git637433 
-     - 
+       * PyTorch 2.7.0a0+git637433
+     -
        * :doc:`Documentation <megatron-lm-v25.4>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/v25.4/images/sha256-941aa5387918ea91c376c13083aa1e6c9cab40bb1875abbbb73bbb65d8736b3f>`__
 
    * - v25.3
-     - 
+     -
        * ROCm 6.3.0
-       * PyTorch 2.7.0a0+git637433 
-     - 
+       * PyTorch 2.7.0a0+git637433
+     -
        * :doc:`Documentation <megatron-lm-v25.3>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/v25.3/images/sha256-1e6ed9bdc3f4ca397300d5a9907e084ab5e8ad1519815ee1f868faf2af1e04e2>`__
 
    * - v24.12-dev
-     - 
+     -
        * ROCm 6.1.0
        * PyTorch 2.4.0
-     - 
+     -
        * :doc:`Documentation <megatron-lm-v24.12-dev>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/megatron-lm/24.12-dev/images/sha256-5818c50334ce3d69deeeb8f589d83ec29003817da34158ebc9e2d112b929bf2e>`__

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev.rst

@@ -17,12 +17,12 @@ Training a model with ROCm Megatron-LM
 
 The ROCm Megatron-LM framework is a specialized fork of the robust Megatron-LM, designed to
 enable efficient training of large-scale language models on AMD GPUs. By leveraging AMD Instinct™ MI300X
-accelerators, AMD Megatron-LM delivers enhanced scalability, performance, and resource utilization for AI
+GPUs, AMD Megatron-LM delivers enhanced scalability, performance, and resource utilization for AI
 workloads. It is purpose-built to :ref:`support models <amd-megatron-lm-model-support-24-12>`
 like Meta's Llama 2, Llama 3, and Llama 3.1, enabling developers to train next-generation AI models with greater
 efficiency. See the GitHub repository at `<https://github.com/ROCm/Megatron-LM>`__.
 
-For ease of use, AMD provides a ready-to-use Docker image for MI300X accelerators containing essential
+For ease of use, AMD provides a ready-to-use Docker image for MI300X GPUs containing essential
 components, including PyTorch, PyTorch Lightning, ROCm libraries, and Megatron-LM utilities. It contains the
 following software to accelerate training workloads:
 
@@ -69,7 +69,7 @@ Megatron-LM provides the following key features to train large language models e
 
 .. _amd-megatron-lm-model-support-24-12:
 
-The following models are pre-optimized for performance on the AMD Instinct MI300X accelerator.
+The following models are pre-optimized for performance on the AMD Instinct MI300X GPU.
 
 * Llama 2 7B
 
@@ -208,14 +208,14 @@ Use the following script to run the RCCL test for four MI300X GPU nodes. Modify
 
 .. _mi300x-amd-megatron-lm-training-v2412:
 
-Start training on MI300X accelerators
+Start training on MI300X GPUs
 =====================================
 
 The pre-built ROCm Megatron-LM environment allows users to quickly validate system performance, conduct
 training benchmarks, and achieve superior performance for models like Llama 2 and Llama 3.1.
 
 Use the following instructions to set up the environment, configure the script to train models, and
-reproduce the benchmark results on the MI300X accelerators with the AMD Megatron-LM Docker
+reproduce the benchmark results on the MI300X GPUs with the AMD Megatron-LM Docker
 image.
 
 .. _amd-megatron-lm-requirements-v2412:

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.3.rst

@@ -15,13 +15,13 @@ Training a model with Megatron-LM for ROCm
 
 The Megatron-LM framework for ROCm is a specialized fork of the robust Megatron-LM,
 designed to enable efficient training of large-scale language models on AMD
-GPUs. By leveraging AMD Instinct™ MI300X series accelerators, Megatron-LM delivers
+GPUs. By leveraging AMD Instinct™ MI300X Series GPUs, Megatron-LM delivers
 enhanced scalability, performance, and resource utilization for AI workloads.
 It is purpose-built to support models like Llama 2, Llama 3, Llama 3.1, and
 DeepSeek, enabling developers to train next-generation AI models more
 efficiently. See the GitHub repository at `<https://github.com/ROCm/Megatron-LM>`__.
 
-AMD provides a ready-to-use Docker image for MI300X accelerators containing
+AMD provides a ready-to-use Docker image for MI300X GPUs containing
 essential components, including PyTorch, ROCm libraries, and Megatron-LM
 utilities. It contains the following software components to accelerate training
 workloads:
@@ -69,7 +69,7 @@ Megatron-LM provides the following key features to train large language models e
 
 .. _amd-megatron-lm-model-support-25-3:
 
-The following models are pre-optimized for performance on the AMD Instinct MI300X accelerator.
+The following models are pre-optimized for performance on the AMD Instinct MI300X GPU.
 
 * Llama 2 7B
 
@@ -123,7 +123,7 @@ The pre-built ROCm Megatron-LM environment allows users to quickly validate syst
 training benchmarks, and achieve superior performance for models like Llama 3.1, Llama 2, and DeepSeek V2.
 
 Use the following instructions to set up the environment, configure the script to train models, and
-reproduce the benchmark results on the MI300X accelerators with the AMD Megatron-LM Docker
+reproduce the benchmark results on the MI300X GPUs with the AMD Megatron-LM Docker
 image.
 
 .. _amd-megatron-lm-requirements-v253:
@@ -334,7 +334,7 @@ Multi-node training
         inside a Docker, either install the drivers inside the Docker container or pass the network
         drivers from the host while creating the Docker container.
 
-Start training on AMD Instinct accelerators
+Start training on AMD Instinct GPUs
 ===========================================
 
 The prebuilt Megatron-LM with ROCm training environment allows users to quickly validate
@@ -345,8 +345,8 @@ can expect the container to perform in the model configurations described in
 the following section, but other configurations are not validated by AMD.
 
 Use the following instructions to set up the environment, configure the script
-to train models, and reproduce the benchmark results on MI300X series
-accelerators with the AMD Megatron-LM Docker image.
+to train models, and reproduce the benchmark results on MI300X Series
+GPUs with the AMD Megatron-LM Docker image.
 
 .. tab-set::
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.4.rst

@@ -15,13 +15,13 @@ Training a model with Megatron-LM for ROCm
 
 The Megatron-LM framework for ROCm is a specialized fork of the robust Megatron-LM,
 designed to enable efficient training of large-scale language models on AMD
-GPUs. By leveraging AMD Instinct™ MI300X series accelerators, Megatron-LM delivers
+GPUs. By leveraging AMD Instinct™ MI300X Series GPUs, Megatron-LM delivers
 enhanced scalability, performance, and resource utilization for AI workloads.
 It is purpose-built to support models like Llama 2, Llama 3, Llama 3.1, and
 DeepSeek, enabling developers to train next-generation AI models more
 efficiently. See the GitHub repository at `<https://github.com/ROCm/Megatron-LM>`__.
 
-AMD provides a ready-to-use Docker image for MI300X series accelerators containing
+AMD provides a ready-to-use Docker image for MI300X Series GPUs containing
 essential components, including PyTorch, ROCm libraries, and Megatron-LM
 utilities. It contains the following software components to accelerate training
 workloads:
@@ -69,7 +69,7 @@ Megatron-LM provides the following key features to train large language models e
 
 .. _amd-megatron-lm-model-support-25-4:
 
-The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+The following models are pre-optimized for performance on AMD Instinct MI300X Series GPUs.
 
 * Llama 3.1 8B
 
@@ -105,7 +105,7 @@ popular AI models.
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`__
    only reflects the :doc:`latest version of this training benchmarking environment <../megatron-lm>`.
-   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================
@@ -124,7 +124,7 @@ The prebuilt ROCm Megatron-LM environment allows users to quickly validate syste
 training benchmarks, and achieve superior performance for models like Llama 3.1, Llama 2, and DeepSeek V2.
 
 Use the following instructions to set up the environment, configure the script to train models, and
-reproduce the benchmark results on MI300X series accelerators with the AMD Megatron-LM Docker
+reproduce the benchmark results on MI300X Series GPUs with the AMD Megatron-LM Docker
 image.
 
 .. _amd-megatron-lm-requirements-v254:
@@ -367,7 +367,7 @@ Multi-node training
            # Specify which RDMA interfaces to use for communication
            export NCCL_IB_HCA=rdma0,rdma1,rdma2,rdma3,rdma4,rdma5,rdma6,rdma7
 
-Start training on AMD Instinct accelerators
+Start training on AMD Instinct GPUs
 ===========================================
 
 The prebuilt Megatron-LM with ROCm training environment allows users to quickly validate
@@ -378,8 +378,8 @@ can expect the container to perform in the model configurations described in
 the following section, but other configurations are not validated by AMD.
 
 Use the following instructions to set up the environment, configure the script
-to train models, and reproduce the benchmark results on MI300X series
-accelerators with the AMD Megatron-LM Docker image.
+to train models, and reproduce the benchmark results on MI300X Series
+GPUs with the AMD Megatron-LM Docker image.
 
 .. tab-set::
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.5.rst

@@ -16,13 +16,13 @@ Training a model with Megatron-LM for ROCm
 The `Megatron-LM framework for ROCm <https://github.com/ROCm/Megatron-LM>`_ is
 a specialized fork of the robust Megatron-LM, designed to enable efficient
 training of large-scale language models on AMD GPUs. By leveraging AMD
-Instinct™ MI300X series accelerators, Megatron-LM delivers enhanced
+Instinct™ MI300X Series GPUs, Megatron-LM delivers enhanced
 scalability, performance, and resource utilization for AI workloads. It is
 purpose-built to support models like Llama, DeepSeek, and Mixtral,
 enabling developers to train next-generation AI models more
 efficiently.
 
-AMD provides a ready-to-use Docker image for MI300X series accelerators containing
+AMD provides a ready-to-use Docker image for MI300X Series GPUs containing
 essential components, including PyTorch, ROCm libraries, and Megatron-LM
 utilities. It contains the following software components to accelerate training
 workloads:
@@ -69,7 +69,7 @@ Megatron-LM provides the following key features to train large language models e
 
 .. _amd-megatron-lm-model-support-v255:
 
-The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+The following models are pre-optimized for performance on AMD Instinct MI300X Series GPUs.
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.5-benchmark-models.yaml
 
@@ -131,7 +131,7 @@ popular AI models.
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`__
    only reflects the latest version of this training benchmarking environment.
-   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================
@@ -154,7 +154,7 @@ Environment setup
 =================
 
 Use the following instructions to set up the environment, configure the script to train models, and
-reproduce the benchmark results on MI300X series accelerators with the AMD Megatron-LM Docker
+reproduce the benchmark results on MI300X Series GPUs with the AMD Megatron-LM Docker
 image.
 
 .. _amd-megatron-lm-requirements-v255:
@@ -536,7 +536,7 @@ Run training
 
 Use the following example commands to set up the environment, configure
 :ref:`key options <amd-megatron-lm-benchmark-test-vars-v255>`, and run training on
-MI300X series accelerators with the AMD Megatron-LM environment.
+MI300X Series GPUs with the AMD Megatron-LM environment.
 
 Single node training
 ^^^^^^^^^^^^^^^^^^^^

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.6.rst

@@ -16,13 +16,13 @@ Training a model with Megatron-LM for ROCm
 The `Megatron-LM framework for ROCm <https://github.com/ROCm/Megatron-LM>`__ is
 a specialized fork of the robust Megatron-LM, designed to enable efficient
 training of large-scale language models on AMD GPUs. By leveraging AMD
-Instinct™ MI300X series accelerators, Megatron-LM delivers enhanced
+Instinct™ MI300X Series GPUs, Megatron-LM delivers enhanced
 scalability, performance, and resource utilization for AI workloads. It is
 purpose-built to support models like Llama, DeepSeek, and Mixtral,
 enabling developers to train next-generation AI models more
 efficiently.
 
-AMD provides ready-to-use Docker images for MI300X series accelerators containing
+AMD provides ready-to-use Docker images for MI300X Series GPUs containing
 essential components, including PyTorch, ROCm libraries, and Megatron-LM
 utilities. It contains the following software components to accelerate training
 workloads:
@@ -65,7 +65,7 @@ workloads:
 
    .. _amd-megatron-lm-model-support-v256:
 
-   The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+   The following models are pre-optimized for performance on AMD Instinct MI300X Series GPUs.
 
    Supported models
    ================
@@ -124,7 +124,7 @@ popular AI models.
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`__
    only reflects the latest version of this training benchmarking environment.
-   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================
@@ -147,7 +147,7 @@ Environment setup
 =================
 
 Use the following instructions to set up the environment, configure the script to train models, and
-reproduce the benchmark results on MI300X series accelerators with the AMD Megatron-LM Docker
+reproduce the benchmark results on MI300X Series GPUs with the AMD Megatron-LM Docker
 image.
 
 .. _amd-megatron-lm-requirements-v256:
@@ -589,7 +589,7 @@ Run training
 
 Use the following example commands to set up the environment, configure
 :ref:`key options <amd-megatron-lm-benchmark-test-vars-v256>`, and run training on
-MI300X series accelerators with the AMD Megatron-LM environment.
+MI300X Series GPUs with the AMD Megatron-LM environment.
 
 Single node training
 --------------------

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.7.rst

@@ -22,13 +22,13 @@ Training a model with Megatron-LM for ROCm
 The `Megatron-LM framework for ROCm <https://github.com/ROCm/Megatron-LM>`_ is
 a specialized fork of the robust Megatron-LM, designed to enable efficient
 training of large-scale language models on AMD GPUs. By leveraging AMD
-Instinct™ MI300X series accelerators, Megatron-LM delivers enhanced
+Instinct™ MI300X Series GPUs, Megatron-LM delivers enhanced
 scalability, performance, and resource utilization for AI workloads. It is
 purpose-built to support models like Llama, DeepSeek, and Mixtral,
 enabling developers to train next-generation AI models more
 efficiently.
 
-AMD provides ready-to-use Docker images for MI300X series accelerators containing
+AMD provides ready-to-use Docker images for MI300X Series GPUs containing
 essential components, including PyTorch, ROCm libraries, and Megatron-LM
 utilities. It contains the following software components to accelerate training
 workloads:
@@ -66,7 +66,7 @@ workloads:
    ================
 
    The following models are supported for training performance benchmarking with Megatron-LM and ROCm
-   on AMD Instinct MI300X series accelerators.
+   on AMD Instinct MI300X Series GPUs.
    Some instructions, commands, and training recommendations in this documentation might
    vary by model -- select one to get started.
 
@@ -120,7 +120,7 @@ popular AI models.
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html>`__
    only reflects the latest version of this training benchmarking environment.
-   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X accelerators or ROCm software.
+   The listed measurements should not be interpreted as the peak performance achievable by AMD Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================
@@ -143,7 +143,7 @@ Environment setup
 =================
 
 Use the following instructions to set up the environment, configure the script to train models, and
-reproduce the benchmark results on MI300X series accelerators with the AMD Megatron-LM Docker
+reproduce the benchmark results on MI300X Series GPUs with the AMD Megatron-LM Docker
 image.
 
 .. _amd-megatron-lm-requirements-v257:
@@ -592,7 +592,7 @@ Run training
 
 Use the following example commands to set up the environment, configure
 :ref:`key options <amd-megatron-lm-benchmark-test-vars-v257>`, and run training on
-MI300X series accelerators with the AMD Megatron-LM environment.
+MI300X Series GPUs with the AMD Megatron-LM environment.
 
 Single node training
 --------------------

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.7.rst

@@ -15,7 +15,7 @@ Training a model with Primus and Megatron-LM
 
 `Primus <https://github.com/AMD-AGI/Primus>`__ is a unified and flexible
 LLM training framework designed to streamline training. It streamlines LLM
-training on AMD Instinct accelerators using a modular, reproducible configuration paradigm.
+training on AMD Instinct GPUs using a modular, reproducible configuration paradigm.
 Primus is backend-agnostic and supports multiple training engines -- including Megatron.
 
 .. note::
@@ -25,7 +25,7 @@ Primus is backend-agnostic and supports multiple training engines -- including M
    workloads from Megatron-LM to Primus with Megatron, see
    :doc:`megatron-lm-primus-migration-guide`.
 
-For ease of use, AMD provides a ready-to-use Docker image for MI300 series accelerators
+For ease of use, AMD provides a ready-to-use Docker image for MI300 Series GPUs
 containing essential components for Primus and Megatron-LM.
 
 .. note::
@@ -53,7 +53,7 @@ containing essential components for Primus and Megatron-LM.
 Supported models
 ================
 
-The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+The following models are pre-optimized for performance on AMD Instinct MI300X Series GPUs.
 Some instructions, commands, and training examples in this documentation might
 vary by model -- select one to get started.
 
@@ -120,7 +120,7 @@ system's configuration.
    =================
 
    Use the following instructions to set up the environment, configure the script to train models, and
-   reproduce the benchmark results on MI300X series accelerators with the ``{{ docker.pull_tag }}`` image.
+   reproduce the benchmark results on MI300X Series GPUs with the ``{{ docker.pull_tag }}`` image.
 
    .. _amd-primus-megatron-lm-requirements-v257:
 
@@ -231,7 +231,7 @@ Run training
 
 Use the following example commands to set up the environment, configure
 :ref:`key options <amd-primus-megatron-lm-benchmark-test-vars>`, and run training on
-MI300X series accelerators with the AMD Megatron-LM environment.
+MI300X Series GPUs with the AMD Megatron-LM environment.
 
 Single node training
 --------------------

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.8.rst

@@ -0,0 +1,667 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using Megatron-LM for ROCm.
+   :keywords: ROCm, AI, LLM, train, Megatron-LM, megatron, Llama, tutorial, docker, torch
+
+********************************************
+Training a model with Primus and Megatron-LM
+********************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm Megatron-LM
+   training performance documentation. See :doc:`../primus-megatron` for the latest version.
+
+`Primus <https://github.com/AMD-AGI/Primus>`__ is a unified and flexible
+LLM training framework designed to streamline training. It streamlines LLM
+training on AMD Instinct GPUs using a modular, reproducible configuration paradigm.
+Primus is backend-agnostic and supports multiple training engines -- including Megatron.
+
+.. note::
+
+   Primus with Megatron is designed to replace the :doc:`ROCm Megatron-LM training <../megatron-lm>` workflow.
+   To learn how to migrate workloads from Megatron-LM to Primus with Megatron,
+   see :doc:`megatron-lm-primus-migration-guide`.
+
+For ease of use, AMD provides a ready-to-use Docker image for MI300 series GPUs
+containing essential components for Primus and Megatron-LM. This Docker is powered by Primus
+Turbo optimizations for performance; this release adds support for Primus Turbo
+with optimized attention and grouped GEMM kernels.
+
+.. note::
+
+   This Docker environment is based on Python 3.10 and Ubuntu 22.04. For an alternative environment with
+   Python 3.12 and Ubuntu 24.04, see the :doc:`previous ROCm Megatron-LM v25.6 Docker release <megatron-lm-v25.6>`.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+.. _amd-primus-megatron-lm-model-support:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on AMD Instinct MI300X series GPUs.
+Some instructions, commands, and training examples in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+.. note::
+
+   Some models, such as Llama, require an external license agreement through
+   a third party (for example, Meta).
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+.. _mi300x-amd-primus-megatron-lm-training:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+      {% set docker = dockers[0] %}
+
+   Environment setup
+   =================
+
+   Use the following instructions to set up the environment, configure the script to train models, and
+   reproduce the benchmark results on MI300X series GPUs with the ``{{ docker.pull_tag }}`` image.
+
+   .. _amd-primus-megatron-lm-requirements:
+
+   Download the Docker image
+   -------------------------
+
+   1. Use the following command to pull the Docker image from Docker Hub.
+
+      .. code-block:: shell
+
+         docker pull {{ docker.pull_tag }}
+
+   2. Launch the Docker container.
+
+      .. code-block:: shell
+
+         docker run -it \
+             --device /dev/dri \
+             --device /dev/kfd \
+             --device /dev/infiniband \
+             --network host --ipc host \
+             --group-add video \
+             --cap-add SYS_PTRACE \
+             --security-opt seccomp=unconfined \
+             --privileged \
+             -v $HOME:$HOME \
+             --shm-size 128G \
+             --name primus_training_env \
+             {{ docker.pull_tag }}
+
+3. Use these commands if you exit the ``primus_training_env`` container and need to return to it.
+
+   .. code-block:: shell
+
+      docker start primus_training_env
+      docker exec -it primus_training_env bash
+
+The Docker container hosts verified commit ``927a717`` of the `Primus
+<https://github.com/AMD-AGI/Primus/tree/927a71702784347a311ca48fd45f0f308c6ef6dd>`__ repository.
+
+.. _amd-primus-megatron-lm-environment-setup:
+
+Configuration
+=============
+
+Primus defines a training configuration in YAML for each model in
+`examples/megatron/configs <https://github.com/AMD-AGI/Primus/tree/927a71702784347a311ca48fd45f0f308c6ef6dd/examples/megatron/configs>`__.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+   .. container:: model-doc {{ model.mad_tag }}
+
+      To update training parameters for {{ model.model }}, you can update ``examples/megatron/configs/{{ model.config_name }}``.
+      Note that training configuration YAML files for other models follow this naming convention.
+
+      {% endfor %}
+   {% endfor %}
+
+.. note::
+
+   See :ref:`Key options <amd-primus-megatron-lm-benchmark-test-vars>` for more information on configuration options.
+
+Dataset options
+---------------
+
+You can use either mock data or real data for training.
+
+* Mock data can be useful for testing and validation. Use the ``mock_data`` field to toggle between mock and real data. The default
+  value is ``true`` for enabled.
+
+  .. code-block:: yaml
+
+     mock_data: true
+
+* If you're using a real dataset, update the ``train_data_path`` field to point to the location of your dataset.
+
+  .. code-block:: bash
+
+     mock_data: false
+     train_data_path: /path/to/your/dataset
+
+  Ensure that the files are accessible inside the Docker container.
+
+.. _amd-primus-megatron-lm-tokenizer:
+
+Tokenizer
+---------
+
+Set the ``HF_TOKEN`` environment variable with
+right permissions to access the tokenizer for each model.
+
+.. code-block:: bash
+
+   # Export your HF_TOKEN in the workspace
+   export HF_TOKEN=<your_hftoken>
+
+.. note::
+
+   In Primus, each model uses a tokenizer from Hugging Face. For example, Llama
+   3.1 8B model uses ``tokenizer_model: meta-llama/Llama-3.1-8B`` and
+   ``tokenizer_type: Llama3Tokenizer`` defined in the `llama3.1-8B model
+   <https://github.com/AMD-AGI/Primus/blob/927a71702784347a311ca48fd45f0f308c6ef6dd/examples/megatron/configs/llama3.1_8B-pretrain.yaml>`__
+   definition.
+
+.. _amd-primus-megatron-lm-run-training:
+
+Run training
+============
+
+Use the following example commands to set up the environment, configure
+:ref:`key options <amd-primus-megatron-lm-benchmark-test-vars>`, and run training on
+MI300X series GPUs with the AMD Megatron-LM environment.
+
+Single node training
+--------------------
+
+To run training on a single node, navigate to ``/workspace/Primus`` and use the following setup command:
+
+.. code-block:: shell
+
+   pip install -r requirements.txt
+   export HSA_NO_SCRATCH_RECLAIM=1
+   export NVTE_CK_USES_BWD_V3=1
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.3-70b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Llama 3.3 70B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run pre-training for Llama 3.3 70B BF16, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+          --micro_batch_size 2 \
+          --global_batch_size 16 \
+          --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-8b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Llama 3.1 8B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run pre-training for Llama 3.1 8B FP8, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+          --train_iters 50 \
+          --fp8 hybrid
+
+   For Llama 3.1 8B BF16, use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-70b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Llama 3.1 70B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run pre-training for Llama 3.1 70B BF16, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+           --train_iters 50
+
+   To run the training on a single node for Llama 3.1 70B FP8 with proxy, use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+          --train_iters 50 \
+          --num_layers 40 \
+          --fp8 hybrid
+
+   .. note::
+
+      Use two or more nodes to run the *full* Llama 70B model with FP8 precision.
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-7b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Llama 2 7B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run pre-training for Llama 2 7B FP8, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama2_7B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh \
+          --train_iters 50 \
+          --fp8 hybrid
+
+   To run pre-training for Llama 2 7B BF16, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama2_7B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-70b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Llama 2 70B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run pre-training for Llama 2 70B BF16, run:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
+      bash ./examples/run_pretrain.sh --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_deepseek-v3-proxy
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to DeepSeek-V3.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run training on a single node for DeepSeek-V3 (MoE with expert parallel) with 3-layer proxy,
+   use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/deepseek_v3-pretrain.yaml \
+      bash examples/run_pretrain.sh \
+          --num_layers 3 \
+          --moe_layer_freq 1 \
+          --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to DeepSeek-V2-Lite.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run training on a single node for DeepSeek-V2-Lite (MoE with expert parallel),
+   use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/deepseek_v2_lite-pretrain.yaml \
+      bash examples/run_pretrain.sh \
+          --global_batch_size 256 \
+          --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x7b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Mixtral 8x7B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run training on a single node for Mixtral 8x7B (MoE with expert parallel),
+   use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/mixtral_8x7B_v0.1-pretrain.yaml \
+      bash examples/run_pretrain.sh --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Mixtral 8x22B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run training on a single node for Mixtral 8x22B (MoE with expert parallel) with 4-layer proxy,
+   use the following command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/mixtral_8x22B_v0.1-pretrain.yaml \
+      bash examples/run_pretrain.sh \
+          --num_layers 4 \
+          --pipeline_model_parallel_size 1 \
+          --micro_batch_size 1 \
+          --global_batch_size 16 \
+          --train_iters 50
+
+.. container:: model-doc primus_pyt_megatron_lm_train_qwen2.5-7b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Qwen 2.5 7B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run training on a single node for Qwen 2.5 7B BF16, use the following
+   command:
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/qwen2.5_7B-pretrain.yaml \
+      bash examples/run_pretrain.sh --train_iters 50
+
+   For FP8, use the following command.
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/qwen2.5_7B-pretrain.yaml \
+      bash examples/run_pretrain.sh \
+          --train_iters 50 \
+          --fp8 hybrid
+
+.. container:: model-doc primus_pyt_megatron_lm_train_qwen2.5-72b
+
+   Once setup is complete, run the appropriate training command.
+   The following run commands are tailored to Qwen 2.5 72B.
+   See :ref:`amd-primus-megatron-lm-model-support` to switch to another available model.
+
+   To run the training on a single node for Qwen 2.5 72B BF16, use the following command.
+
+   .. code-block:: shell
+
+      EXP=examples/megatron/configs/qwen2.5_72B-pretrain.yaml \
+      bash examples/run_pretrain.sh --train_iters 50
+
+.. _amd-primus-megatron-multi-node-examples:
+
+Multi-node training examples
+----------------------------
+
+Refer to :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your environment for multi-node
+training.
+
+To run training on multiple nodes, you can use the
+`run_slurm_pretrain.sh <https://github.com/AMD-AGI/Primus/blob/927a71702784347a311ca48fd45f0f308c6ef6dd/examples/run_slurm_pretrain.sh>`__
+to launch the multi-node workload. Use the following steps to setup your environment:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+
+   .. code-block:: shell
+
+      cd /workspace/Primus/
+      export DOCKER_IMAGE={{ docker.pull_tag }}
+      export HF_TOKEN=<your_HF_token>
+      export HSA_NO_SCRATCH_RECLAIM=1
+      export NVTE_CK_USES_BWD_V3=1
+      export NCCL_IB_HCA=<your_NCCL_IB_HCA> # specify which RDMA interfaces to use for communication
+      export NCCL_SOCKET_IFNAME=<your_NCCL_SOCKET_IFNAME> # your Network Interface
+      export GLOO_SOCKET_IFNAME=<your_GLOO_SOCKET_IFNAME> # your Network Interface
+      export NCCL_IB_GID_INDEX=3 # Set InfiniBand GID index for NCCL communication. Default is 3 for ROCE
+
+.. note::
+
+   * Make sure correct network drivers are installed on the nodes. If inside a Docker, either install the drivers inside the Docker container or pass the network drivers from the host while creating Docker container.
+   * If ``NCCL_IB_HCA`` and ``NCCL_SOCKET_IFNAME`` are not set, Primus will try to auto-detect. However, since NICs can vary accross different cluster, it is encouraged to explicitly export your NCCL parameters for the cluster.
+   * To find your network interface, you can use ``ip a``.
+   * To find RDMA interfaces, you can use ``ibv_devices`` to get the list of all the RDMA/IB  devices.
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.3-70b
+
+   To train Llama 3.3 70B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 1 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --fp8 hybrid
+
+   To train Llama 3.3 70B BF16 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 1 \
+          --global_batch_size 256 \
+          --recompute_num_layers 12
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-8b
+
+   To train Llama 3.1 8B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      # Adjust the training parameters. For e.g., `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case
+      NNODES=8 EXP=examples/megatron/configs/llama3.1_8B-pretrain.yaml \
+      bash ./examples/run_slurm_pretrain.sh \
+          --global_batch_size 1024 \
+          --fp8 hybrid
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-70b
+
+   To train Llama 3.1 70B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 1 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --fp8 hybrid
+
+   To train Llama 3.1 70B BF16 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 1 \
+          --global_batch_size 256 \
+          --recompute_num_layers 12
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-7b
+
+   To train Llama 2 8B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      # Adjust the training parameters. For e.g., `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case
+      NNODES=8 EXP=examples/megatron/configs/llama2_7B-pretrain.yaml bash ./examples/run_slurm_pretrain.sh --global_batch_size 2048 --fp8 hybrid
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-70b
+
+   To train Llama 2 70B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 2 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --fp8 hybrid
+
+   To train Llama 2 70B BF16 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
+      bash ./examples/run_slurm_pretrain.sh \
+          --micro_batch_size 2 \
+          --global_batch_size 1536 \
+          --recompute_num_layers 12
+
+.. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x7b
+
+   To train Mixtral 8x7B BF16 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/mixtral_8x7B_v0.1-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 2 \
+          --global_batch_size 256
+
+.. container:: model-doc primus_pyt_megatron_lm_train_qwen2.5-72b
+
+   To train Qwen2.5 72B FP8 on 8 nodes, run:
+
+   .. code-block:: shell
+
+      NNODES=8 EXP=examples/megatron/configs/qwen2.5_72B-pretrain.yaml \
+      bash examples/run_slurm_pretrain.sh \
+          --micro_batch_size 4 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --fp8 hybrid
+
+.. _amd-primus-megatron-lm-benchmark-test-vars:
+
+Key options
+-----------
+
+The following are key options to take note of
+
+fp8
+  ``hybrid`` enables FP8 GEMMs.
+
+use_torch_fsdp2
+  ``use_torch_fsdp2: 1``  enables torch fsdp-v2. If FSDP is enabled,
+  set ``use_distributed_optimizer`` and ``overlap_param_gather`` to ``false``.
+
+profile
+  To enable PyTorch profiling, set these parameters:
+
+  .. code-block:: yaml
+
+     profile: true
+     use_pytorch_profiler: true
+     profile_step_end: 7
+     profile_step_start: 6
+
+train_iters
+  The total number of iterations (default: 50).
+
+mock_data
+  True by default.
+
+micro_batch_size
+  Micro batch size.
+
+global_batch_size
+  Global batch size.
+
+recompute_granularity
+  For activation checkpointing.
+
+num_layers
+  For using a reduced number of layers as with proxy models.
+
+Further reading
+===============
+
+- For an introduction to Primus, see `Primus: A Lightweight, Unified Training
+  Framework for Large Models on AMD GPUs <https://rocm.blogs.amd.com/software-tools-optimization/primus/README.html>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`megatron-lm-history` to find documentation for previous releases
+of the ``ROCm/megatron-lm`` Docker image.
+
+This training environment now uses Primus with Megatron as the primary
+configuration. Limited support for the legacy ROCm Megatron-LM is still
+available; see the :doc:`../megatron-lm` documentation.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-pytorch-v25.8.rst

@@ -0,0 +1,312 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using PyTorch for ROCm.
+   :keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
+
+****************************************
+Training a model with Primus and PyTorch
+****************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm Primus PyTorch training
+   performance benchmark documentation. See :doc:`../primus-pytorch` for the latest version.
+
+`Primus <https://github.com/AMD-AGI/Primus>`__ is a unified and flexible
+LLM training framework designed to streamline training. It streamlines LLM
+training on AMD Instinct GPUs using a modular, reproducible configuration paradigm.
+Primus now supports the PyTorch torchtitan backend.
+
+.. note::
+
+   Primus with the PyTorch torchtitan backend is designed to replace the :doc:`ROCm PyTorch training <../pytorch-training>` workflow.
+   See :doc:`../pytorch-training` to see steps to run workloads without Primus.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+   For ease of use, AMD provides a ready-to-use Docker image -- ``{{
+   docker.pull_tag }}`` -- for MI300X series GPUs containing essential
+   components for Primus and PyTorch training with
+   Primus Turbo optimizations.
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+.. _amd-primus-pytorch-model-support-v258:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
+Some instructions, commands, and training recommendations in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0" style="display: none;">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+.. seealso::
+
+   For additional workloads, including Llama 3.3, Llama 3.2, Llama 2, GPT OSS, Qwen, and Flux models,
+   see the documentation :doc:`../pytorch-training` (without Primus)
+
+.. _amd-primus-pytorch-performance-measurements-v258:
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+This Docker image is optimized for specific model configurations outlined
+below. Performance can vary for other training workloads, as AMD
+doesn’t test configurations and run conditions outside those described.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.8-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+
+   Pull the Docker image
+   =====================
+
+   Use the following command to pull the `Docker image <{{ unified_docker.docker_hub_url }}>`_ from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ unified_docker.pull_tag }}
+
+   Run training
+   ============
+
+   {% set model_groups = data.model_groups %}
+
+   Once the setup is complete, choose between the following two workflows to start benchmarking training.
+   For fine-tuning workloads and multi-node training examples, see :doc:`../pytorch-training` (without Primus).
+
+   .. tab-set::
+
+      .. tab-item:: MAD-integrated benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available model.
+
+            1. 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
+
+            2. For example, use this command to run the performance benchmark test on the {{ model.model }} model
+               using one node with the {{ model.precision }} data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{ model.mad_tag }} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+               MAD launches a Docker container with the name
+               ``container_ci-{{ model.mad_tag }}``. The latency and throughput reports of the
+               model are collected in ``~/MAD/perf.csv``.
+
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Standalone benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run commands are tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available model.
+
+            .. rubric:: Download the Docker image and required packages
+
+            1. Use the following command to pull the Docker image from Docker Hub.
+
+               .. code-block:: shell
+
+                  docker pull {{ unified_docker.pull_tag }}
+
+            2. Run the Docker container.
+
+               .. code-block:: shell
+
+                  docker run -it \
+                      --device /dev/dri \
+                      --device /dev/kfd \
+                      --network host \
+                      --ipc host \
+                      --group-add video \
+                      --cap-add SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --privileged \
+                      -v $HOME:$HOME \
+                      -v $HOME/.ssh:/root/.ssh \
+                      --shm-size 64G \
+                      --name training_env \
+                      {{ unified_docker.pull_tag }}
+
+               Use these commands if you exit the ``training_env`` container and need to return to it.
+
+               .. code-block:: shell
+
+                  docker start training_env
+                  docker exec -it training_env bash
+
+            3. In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
+               repository and navigate to the benchmark scripts directory
+               ``/workspace/MAD/scripts/pytorch_train``.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD/scripts/pytorch_train
+
+            .. rubric:: Prepare training datasets and dependencies
+
+            1. The following benchmarking examples require downloading models and datasets
+               from Hugging Face. To ensure successful access to gated repos, set your
+               ``HF_TOKEN``.
+
+               .. code-block:: shell
+
+                  export HF_TOKEN=$your_personal_hugging_face_access_token
+
+            2. Run the setup script to install libraries and datasets needed for benchmarking.
+
+               .. code-block:: shell
+
+                  ./pytorch_benchmark_setup.sh
+
+            .. rubric:: Pretraining
+
+            To start the pretraining benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t pretrain \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if model.mad_tag == "primus_pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Currently, only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+
+            .. rubric:: Benchmarking examples
+
+            Use the following command to run train {{ model.model }} with BF16 precision using Primus torchtitan.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -m {{ model.model_repo }}
+
+            To train {{ model.model }} with FP8 precision, use the following command.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -m {{ model.model_repo }} -p FP8
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- For an introduction to Primus, see `Primus: A Lightweight, Unified Training
+  Framework for Large Models on AMD GPUs <https://rocm.blogs.amd.com/software-tools-optimization/primus/README.html>`__.
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`pytorch-training-history` to find documentation for previous releases
+of the ``ROCm/pytorch-training`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-history.rst

@@ -16,51 +16,62 @@ previous releases of the ``ROCm/pytorch-training`` Docker image on `Docker Hub <
      - Components
      - Resources
 
-   * - v25.8 (latest)
-     - 
-       * ROCm 6.4.3
-       * PyTorch 2.8.0a0+gitd06a406
-     - 
+   * - v25.9 (latest)
+     -
+       * ROCm 7.0.0
+       * Primus 0.3.0
+       * PyTorch 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+     -
        * :doc:`Primus PyTorch Training documentation <../primus-pytorch>`
        * :doc:`PyTorch training (legacy) documentation <../pytorch-training>`
-       * `Docker Hub <https://hub.docker.com/r/rocm/pytorch-training/tags>`__
+       * `Docker Hub (gfx950) <https://hub.docker.com/layers/rocm/primus/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6>`__
+       * `Docker Hub (gfx942) <https://hub.docker.com/layers/rocm/primus/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357>`__
+
+   * - v25.8
+     -
+       * ROCm 6.4.3
+       * PyTorch 2.8.0a0+gitd06a406
+     -
+       * :doc:`Primus PyTorch Training documentation <primus-pytorch-v25.8>`
+       * :doc:`PyTorch training (legacy) documentation <pytorch-training-v25.8>`
+       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5>`__
 
    * - v25.7
-     - 
+     -
        * ROCm 6.4.2
        * PyTorch 2.8.0a0+gitd06a406
-     - 
+     -
        * :doc:`Documentation <pytorch-training-v25.7>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.7/images/sha256-cc6fd840ab89cb81d926fc29eca6d075aee9875a55a522675a4b9231c9a0a712>`__
 
    * - v25.6
-     - 
+     -
        * ROCm 6.3.4
        * PyTorch 2.8.0a0+git7d205b2
-     - 
+     -
        * :doc:`Documentation <pytorch-training-v25.6>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.6/images/sha256-a4cea3c493a4a03d199a3e81960ac071d79a4a7a391aa9866add3b30a7842661>`__
 
    * - v25.5
-     - 
+     -
        * ROCm 6.3.4
        * PyTorch 2.7.0a0+git637433
-     - 
+     -
        * :doc:`Documentation <pytorch-training-v25.5>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.5/images/sha256-d47850a9b25b4a7151f796a8d24d55ea17bba545573f0d50d54d3852f96ecde5>`__
 
    * - v25.4
-     - 
+     -
        * ROCm 6.3.0
        * PyTorch 2.7.0a0+git637433
-     - 
+     -
        * :doc:`Documentation <pytorch-training-v25.4>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.4/images/sha256-fa98a9aa69968e654466c06f05aaa12730db79b48b113c1ab4f7a5fe6920a20b>`__
 
    * - v25.3
-     - 
+     -
        * ROCm 6.3.0
        * PyTorch 2.7.0a0+git637433
-     - 
+     -
        * :doc:`Documentation <pytorch-training-v25.3>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.3/images/sha256-0ffdde1b590fd2787b1c7adf5686875b100980b0f314090901387c44253e709b>`__

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.3.rst

@@ -18,7 +18,7 @@ model training with GPU-optimized components for transformer-based models.
 
 The PyTorch for ROCm training Docker (``rocm/pytorch-training:v25.3``) image
 provides a prebuilt optimized environment for fine-tuning and pretraining a
-model on AMD Instinct MI325X and MI300X accelerators. It includes the following
+model on AMD Instinct MI325X and MI300X GPUs. It includes the following
 software components to accelerate training workloads:
 
 +--------------------------+--------------------------------+
@@ -44,7 +44,7 @@ software components to accelerate training workloads:
 Supported models
 ================
 
-The following models are pre-optimized for performance on the AMD Instinct MI300X accelerator.
+The following models are pre-optimized for performance on the AMD Instinct MI300X GPU.
 
 * Llama 3.1 8B
 
@@ -237,7 +237,7 @@ Along with the following datasets:
 
 * `bghira/pseudo-camera-10k <https://huggingface.co/datasets/bghira/pseudo-camera-10k>`_
 
-Start training on AMD Instinct accelerators
+Start training on AMD Instinct GPUs
 ===========================================
 
 The prebuilt PyTorch with ROCm training environment allows users to quickly validate
@@ -248,8 +248,8 @@ can expect the container to perform in the model configurations described in
 the following section, but other configurations are not validated by AMD.
 
 Use the following instructions to set up the environment, configure the script
-to train models, and reproduce the benchmark results on MI300X series
-accelerators with the AMD PyTorch training Docker image.
+to train models, and reproduce the benchmark results on MI300X Series
+GPUs with the AMD PyTorch training Docker image.
 
 Once your environment is set up, use the following commands and examples to start benchmarking.
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.4.rst

@@ -18,7 +18,7 @@ model training with GPU-optimized components for transformer-based models.
 
 The PyTorch for ROCm training Docker (``rocm/pytorch-training:v25.4``) image
 provides a prebuilt optimized environment for fine-tuning and pretraining a
-model on AMD Instinct MI325X and MI300X accelerators. It includes the following
+model on AMD Instinct MI325X and MI300X GPUs. It includes the following
 software components to accelerate training workloads:
 
 +--------------------------+--------------------------------+
@@ -44,7 +44,7 @@ software components to accelerate training workloads:
 Supported models
 ================
 
-The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X accelerators.
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
 
 * Llama 3.1 8B
 
@@ -76,7 +76,7 @@ popular AI models.
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
    should not be interpreted as the peak performance achievable by AMD
-   Instinct MI325X and MI300X accelerators or ROCm software.
+   Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================
@@ -260,7 +260,7 @@ the following section, but other configurations are not validated by AMD.
 
 Use the following instructions to set up the environment, configure the script
 to train models, and reproduce the benchmark results on MI325X and MI300X
-accelerators with the AMD PyTorch training Docker image.
+GPUs with the AMD PyTorch training Docker image.
 
 Once your environment is set up, use the following commands and examples to start benchmarking.
 

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.5.rst

@@ -19,7 +19,7 @@ model training with GPU-optimized components for transformer-based models.
 The `PyTorch for ROCm training Docker <https://hub.docker.com/layers/rocm/pytorch-training/v25.5/images/sha256-d47850a9b25b4a7151f796a8d24d55ea17bba545573f0d50d54d3852f96ecde5>`_
 (``rocm/pytorch-training:v25.5``) image
 provides a prebuilt optimized environment for fine-tuning and pretraining a
-model on AMD Instinct MI325X and MI300X accelerators. It includes the following
+model on AMD Instinct MI325X and MI300X GPUs. It includes the following
 software components to accelerate training workloads:
 
 +--------------------------+--------------------------------+
@@ -45,7 +45,7 @@ software components to accelerate training workloads:
 Supported models
 ================
 
-The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X accelerators.
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
 
 * Llama 3.3 70B
 
@@ -79,7 +79,7 @@ popular AI models.
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
    should not be interpreted as the peak performance achievable by AMD
-   Instinct MI325X and MI300X accelerators or ROCm software.
+   Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.6.rst

@@ -18,7 +18,7 @@ model training with GPU-optimized components for transformer-based models.
 
 The `PyTorch for ROCm training Docker <https://hub.docker.com/layers/rocm/pytorch-training/v25.6/images/sha256-a4cea3c493a4a03d199a3e81960ac071d79a4a7a391aa9866add3b30a7842661>`_
 (``rocm/pytorch-training:v25.6``) image provides a prebuilt optimized environment for fine-tuning and pretraining a
-model on AMD Instinct MI325X and MI300X accelerators. It includes the following software components to accelerate
+model on AMD Instinct MI325X and MI300X GPUs. It includes the following software components to accelerate
 training workloads:
 
 +--------------------------+--------------------------------+
@@ -44,7 +44,7 @@ training workloads:
 Supported models
 ================
 
-The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X accelerators.
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.6-benchmark-models.yaml
 
@@ -99,7 +99,7 @@ The following models are pre-optimized for performance on the AMD Instinct MI325
       The performance data presented in
       `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
       should not be interpreted as the peak performance achievable by AMD
-      Instinct MI325X and MI300X accelerators or ROCm software.
+      Instinct MI325X and MI300X GPUs or ROCm software.
 
    System validation
    =================
@@ -444,7 +444,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For a list of other ready-made Docker images for AI with ROCm, see
   `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.7.rst

@@ -10,7 +10,7 @@ Training a model with PyTorch for ROCm
 
 .. caution::
 
-   This documentation does not reflect the latest version of ROCm vLLM
+   This documentation does not reflect the latest version of ROCm PyTorch training
    performance benchmark documentation. See :doc:`../pytorch-training` for the latest version.
 
 PyTorch is an open-source machine learning framework that is widely used for
@@ -22,7 +22,7 @@ model training with GPU-optimized components for transformer-based models.
    {% set docker = dockers[0] %}
    The `PyTorch for ROCm training Docker <{{ docker.docker_hub_url }}>`__
    (``{{ docker.pull_tag }}``) image provides a prebuilt optimized environment for fine-tuning and pretraining a
-   model on AMD Instinct MI325X and MI300X accelerators. It includes the following software components to accelerate
+   model on AMD Instinct MI325X and MI300X GPUs. It includes the following software components to accelerate
    training workloads:
 
    .. list-table::
@@ -41,7 +41,7 @@ model training with GPU-optimized components for transformer-based models.
 Supported models
 ================
 
-The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X accelerators.
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
 Some instructions, commands, and training recommendations in this documentation might
 vary by model -- select one to get started.
 
@@ -124,7 +124,7 @@ popular AI models.
    The performance data presented in
    `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
    should not be interpreted as the peak performance achievable by AMD
-   Instinct MI325X and MI300X accelerators or ROCm software.
+   Instinct MI325X and MI300X GPUs or ROCm software.
 
 System validation
 =================
@@ -555,7 +555,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For a list of other ready-made Docker images for AI with ROCm, see
   `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.8.rst

@@ -0,0 +1,588 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using PyTorch for ROCm.
+   :keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
+
+**************************************
+Training a model with PyTorch on ROCm
+**************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm PyTorch training
+   performance benchmark documentation. See :doc:`../pytorch-training` for the latest version.
+
+PyTorch is an open-source machine learning framework that is widely used for
+model training with GPU-optimized components for transformer-based models.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.8-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+   The `PyTorch for ROCm training Docker <{{ docker.docker_hub_url }}>`__
+   (``{{ docker.pull_tag }}``) image provides a prebuilt optimized environment for fine-tuning and pretraining a
+   model on AMD Instinct MI325X and MI300X GPUs. It includes the following software components to accelerate
+   training workloads:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+.. _amd-pytorch-training-model-support:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
+Some instructions, commands, and training recommendations in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.8-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+
+   .. _amd-pytorch-training-supported-training-modes:
+
+   The following table lists supported training modes per model.
+
+   .. dropdown:: Supported training modes
+
+      .. list-table::
+         :header-rows: 1
+
+         * - Model
+           - Supported training modes
+
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+         {% if model.training_modes %}
+         * - {{ model.model }}
+           - ``{{ model.training_modes | join('``, ``') }}``
+
+         {% endif %}
+         {% endfor %}
+      {% endfor %}
+
+      .. note::
+
+         Some model and fine-tuning combinations are not listed. This is
+         because the `upstream torchtune repository <https://github.com/pytorch/torchtune>`__
+         doesn't provide default YAML configurations for them.
+         For advanced usage, you can create a custom configuration to enable
+         unlisted fine-tuning methods by using an existing file in the
+         ``/workspace/torchtune/recipes/configs`` directory as a template.
+
+.. _amd-pytorch-training-performance-measurements:
+
+Performance measurements
+========================
+
+To evaluate performance, the
+`Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
+page provides reference throughput and latency measurements for training
+popular AI models.
+
+.. note::
+
+   The performance data presented in
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
+   should not be interpreted as the peak performance achievable by AMD
+   Instinct MI325X and MI300X GPUs or ROCm software.
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+This Docker image is optimized for specific model configurations outlined
+below. Performance can vary for other training workloads, as AMD
+doesn’t test configurations and run conditions outside those described.
+
+Run training
+============
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.8-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+
+   Once the setup is complete, choose between two options to start benchmarking training:
+
+   .. tab-set::
+
+      .. tab-item:: MAD-integrated benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`amd-pytorch-training-model-support` to switch to another available model.
+
+            1. 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
+
+            2. For example, use this command to run the performance benchmark test on the {{ model.model }} model
+               using one node with the {{ model.precision }} data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{ model.mad_tag }} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+               MAD launches a Docker container with the name
+               ``container_ci-{{ model.mad_tag }}``. The latency and throughput reports of the
+               model are collected in ``~/MAD/perf.csv``.
+
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Standalone benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following commands are tailored to {{ model.model }}.
+            See :ref:`amd-pytorch-training-model-support` to switch to another available model.
+
+      {% endfor %}
+   {% endfor %}
+
+         .. rubric:: Download the Docker image and required packages
+
+         1. Use the following command to pull the Docker image from Docker Hub.
+
+            .. code-block:: shell
+
+               docker pull {{ unified_docker.pull_tag }}
+
+         2. Run the Docker container.
+
+            .. code-block:: shell
+
+               docker run -it \
+                   --device /dev/dri \
+                   --device /dev/kfd \
+                   --network host \
+                   --ipc host \
+                   --group-add video \
+                   --cap-add SYS_PTRACE \
+                   --security-opt seccomp=unconfined \
+                   --privileged \
+                   -v $HOME:$HOME \
+                   -v $HOME/.ssh:/root/.ssh \
+                   --shm-size 64G \
+                   --name training_env \
+                   {{ unified_docker.pull_tag }}
+
+            Use these commands if you exit the ``training_env`` container and need to return to it.
+
+            .. code-block:: shell
+
+               docker start training_env
+               docker exec -it training_env bash
+
+         3. In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
+            repository and navigate to the benchmark scripts directory
+            ``/workspace/MAD/scripts/pytorch_train``.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/pytorch_train
+
+         .. rubric:: Prepare training datasets and dependencies
+
+         1. The following benchmarking examples require downloading models and datasets
+            from Hugging Face. To ensure successful access to gated repos, set your
+            ``HF_TOKEN``.
+
+            .. code-block:: shell
+
+               export HF_TOKEN=$your_personal_hugging_face_access_token
+
+         2. Run the setup script to install libraries and datasets needed for benchmarking.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_setup.sh
+
+            .. container:: model-doc pyt_train_llama-3.1-8b
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 8B:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``accelerate``
+                    - `Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
+
+            .. container:: model-doc pyt_train_llama-3.1-70b
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 70B:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
+
+                  * - ``torchdata``
+                    - `TorchData <https://meta-pytorch.org/data/beta/index.html#torchdata>`__
+
+                  * - ``tomli``
+                    - `Tomli <https://pypi.org/project/tomli/>`__
+
+                  * - ``tiktoken``
+                    - `tiktoken <https://github.com/openai/tiktoken>`__
+
+                  * - ``blobfile``
+                    - `blobfile <https://pypi.org/project/blobfile/>`__
+
+                  * - ``tabulate``
+                    - `tabulate <https://pypi.org/project/tabulate/>`__
+
+                  * - ``wandb``
+                    - `Weights & Biases <https://github.com/wandb/wandb>`__
+
+                  * - ``sentencepiece``
+                    - `SentencePiece <https://github.com/google/sentencepiece>`__ 0.2.0
+
+                  * - ``tensorboard``
+                    - `TensorBoard <https://www.tensorflow.org/tensorboard>`__ 2.18.0
+
+            .. container:: model-doc pyt_train_flux
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for FLUX:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``accelerate``
+                    - `Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`__ 3.2.0
+
+                  * - ``sentencepiece``
+                    - `SentencePiece <https://github.com/google/sentencepiece>`__ 0.2.0
+
+                  * - ``tensorboard``
+                    - `TensorBoard <https://www.tensorflow.org/tensorboard>`__ 2.18.0
+
+                  * - ``csvkit``
+                    - `csvkit <https://csvkit.readthedocs.io/en/latest/>`__ 2.0.1
+
+                  * - ``deepspeed``
+                    - `DeepSpeed <https://github.com/deepspeedai/DeepSpeed>`__ 0.16.2
+
+                  * - ``diffusers``
+                    - `Hugging Face Diffusers <https://huggingface.co/docs/diffusers/en/index>`__ 0.31.0
+
+                  * - ``GitPython``
+                    - `GitPython <https://github.com/gitpython-developers/GitPython>`__ 3.1.44
+
+                  * - ``opencv-python-headless``
+                    - `opencv-python-headless <https://pypi.org/project/opencv-python-headless/>`__ 4.10.0.84
+
+                  * - ``peft``
+                    - `PEFT <https://huggingface.co/docs/peft/en/index>`__ 0.14.0
+
+                  * - ``protobuf``
+                    - `Protocol Buffers <https://github.com/protocolbuffers/protobuf>`__ 5.29.2
+
+                  * - ``pytest``
+                    - `PyTest <https://docs.pytest.org/en/stable/>`__ 8.3.4
+
+                  * - ``python-dotenv``
+                    - `python-dotenv <https://pypi.org/project/python-dotenv/>`__ 1.0.1
+
+                  * - ``seaborn``
+                    - `Seaborn <https://seaborn.pydata.org/>`__ 0.13.2
+
+                  * - ``transformers``
+                    - `Transformers <https://huggingface.co/docs/transformers/en/index>`__ 4.47.0
+
+            ``pytorch_benchmark_setup.sh`` downloads the following datasets from Hugging Face:
+
+            * `bghira/pseudo-camera-10k <https://huggingface.co/datasets/bghira/pseudo-camera-10k>`__
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+         {% set training_modes = model.training_modes %}
+         {% set training_mode_descs = {
+            "pretrain": "Benchmark pre-training.",
+            "HF_pretrain": "Llama 3.1 8B pre-training with FP8 precision."
+         } %}
+         {% set available_modes = training_modes | select("in", ["pretrain", "HF_pretrain"]) | list %}
+         {% if available_modes %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Pre-training
+
+            To start the pre-training benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t {% if available_modes | length == 1 %}{{ available_modes[0] }}{% else %}$training_mode{% endif %} \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+            {% if model.mad_tag == "pyt_train_flux" %}
+            .. container:: model-doc {{ model.mad_tag }}
+
+               .. note::
+
+                  Currently, FLUX models are not supported out-of-the-box on {{ unified_docker.pull_tag }}.
+                  To use FLUX, refer to ``rocm/pytorch-training`` Docker: :doc:`pytorch-training-v25.6`
+
+                  Occasionally, downloading the Flux dataset might fail. In the event of this
+                  error, manually download it from Hugging Face at
+                  `black-forest-labs/FLUX.1-dev <https://huggingface.co/black-forest-labs/FLUX.1-dev>`_
+                  and save it to `/workspace/FluxBenchmark`. This ensures that the test script can access
+                  the required dataset.
+            {% endif %}
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if model.mad_tag == "pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+         {% endif %}
+
+         {% set training_mode_descs = {
+            "finetune_fw": "Full weight fine-tuning (BF16 and FP8 supported).",
+            "finetune_lora": "LoRA fine-tuning (BF16 supported).",
+            "finetune_qlora": "QLoRA fine-tuning (BF16 supported).",
+            "HF_finetune_lora": "LoRA fine-tuning with Hugging Face PEFT.",
+         } %}
+         {% set available_modes = training_modes | select("in", ["finetune_fw", "finetune_lora", "finetune_qlora", "HF_finetune_lora"]) | list %}
+         {% if available_modes %}
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Fine-tuning
+
+            To start the fine-tuning benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+            See :ref:`supported training modes <amd-pytorch-training-supported-training-modes>`.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t $training_mode \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if "finetune_fw" in available_modes %} or ``FP8``{% endif %}
+                 - All models support BF16.{% if "finetune_fw" in available_modes %} FP8 is only available for full weight fine-tuning.{% endif %}
+
+               * - ``$sequence_length``
+                 - Between 2048 and 16384.
+                 - Sequence length for the language model.
+
+            {% if model.mad_tag in ["pyt_train_llama3.2-vision-11b", "pyt_train_llama-3.2-vision-90b"] %}
+            .. note::
+
+               For LoRA and QLoRA support with vision models (Llama 3.2 11B and 90B),
+               use the following torchtune commit for compatibility:
+
+               .. code-block:: shell
+
+                  git checkout 48192e23188b1fc524dd6d127725ceb2348e7f0e
+
+            {% elif model.mad_tag in ["pyt_train_llama-2-7b", "pyt_train_llama-2-13b", "pyt_train_llama-2-70b"] %}
+            .. note::
+
+               You might encounter the following error with Llama 2: ``ValueError: seq_len (16384) of
+               input tensor should be smaller than max_seq_len (4096)``.
+               This error indicates that an input sequence is longer than the model's maximum context window.
+
+               Ensure your tokenized input does not exceed the model's ``max_seq_len`` (4096
+               tokens in this case). You can resolve this by truncating the input or splitting
+               it into smaller chunks before passing it to the model.
+
+               Note on reproducibility: The results in this guide are based on
+               commit ``b4c98ac`` from the upstream
+               `<https://github.com/pytorch/torchtune>`__ repository. For the
+               latest updates, you can use the main branch.
+
+            {% endif %}
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+
+            .. rubric:: Benchmarking examples
+
+            For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.
+
+.. _amd-pytorch-training-multinode-examples:
+
+Multi-node training
+-------------------
+
+Refer to :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your environment for multi-node
+training. See :ref:`rocm-for-ai-multi-node-setup-pyt-train-example` for example Slurm run commands.
+
+Pre-training
+~~~~~~~~~~~~
+
+Multi-node training with torchtitan is supported. The provided SLURM script is pre-configured for Llama 3 70B.
+
+To launch the training job on a SLURM cluster for Llama 3 70B, run the following commands from the MAD repository.
+
+.. code-block:: shell
+
+   # In the MAD repository
+   cd scripts/pytorch_train
+   sbatch run_slurm_train.sh
+
+Fine-tuning
+~~~~~~~~~~~
+
+Multi-node training with torchtune is supported. The provided SLURM script is pre-configured for Llama 3.3 70B.
+
+To launch the training job on a SLURM cluster for Llama 3.3 70B, run the following commands from the MAD repository.
+
+.. code-block:: shell
+
+   huggingface-cli login # Get access to HF Llama model space
+   huggingface-cli download meta-llama/Llama-3.3-70B-Instruct --local-dir ./models/Llama-3.3-70B-Instruct # Download the Llama 3.3 model locally
+   # In the MAD repository
+   cd scripts/pytorch_train
+   sbatch Torchtune_Multinode.sh
+
+.. note::
+
+   Information regarding benchmark setup:
+
+   * By default, Llama 3.3 70B is fine-tuned using ``alpaca_dataset``.
+   * You can adjust the torchtune `YAML configuration file
+     <https://github.com/pytorch/torchtune/blob/main/recipes/configs/llama3_3/70B_full_multinode.yaml>`__
+     if you're using a different model.
+   * The number of nodes and other parameters can be tuned in the SLURM script ``Torchtune_Multinode.sh``.
+   * Set the ``mounting_paths`` inside the SLURM script.
+
+Once the run is finished, you can find the log files in the ``result_torchtune/`` directory.
+
+Further reading
+===============
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`pytorch-training-history` to find documentation for previous releases
+of the ``ROCm/pytorch-training`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst

@@ -13,30 +13,42 @@ Primus now supports the PyTorch torchtitan backend.
 
 .. note::
 
-   Primus with the PyTorch torchtitan backend is designed to replace the :doc:`ROCm PyTorch training <pytorch-training>` workflow.
-   See :doc:`pytorch-training` to see steps to run workloads without Primus.
+   For a unified training solution on AMD GPUs with ROCm, the `rocm/pytorch-training
+   <https://hub.docker.com/r/rocm/pytorch-training/>`__ Docker Hub registry will be
+   deprecated soon in favor of `rocm/primus <https://hub.docker.com/r/rocm/primus>`__.
+   The ``rocm/primus`` Docker containers will cover PyTorch training ecosystem frameworks,
+   including `Megatron-LM <primus-megatron>`__, torchtitan, and torchtune.
+
+   Primus with the PyTorch torchtitan backend is designed to replace the
+   :doc:`ROCm PyTorch training <pytorch-training>` workflow. See
+   :doc:`pytorch-training` to see steps to run workloads without Primus.
+
+AMD provides a ready-to-use Docker image for MI355X, MI350X, MI325X, and
+MI300X GPUs containing essential components for Primus and PyTorch training
+with Primus Turbo optimizations.
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
 
    {% set dockers = data.dockers %}
-   {% set docker = dockers[0] %}
-   For ease of use, AMD provides a ready-to-use Docker image -- ``{{
-   docker.pull_tag }}`` -- for MI300X series GPUs containing essential
-   components for Primus and PyTorch training with
-   Primus Turbo optimizations.
+   .. tab-set::
 
-   .. list-table::
-      :header-rows: 1
+   {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}
 
-      * - Software component
-        - Version
+         .. list-table::
+            :header-rows: 1
 
-      {% for component_name, component_version in docker.components.items() %}
-      * - {{ component_name }}
-        - {{ component_version }}
-      {% endfor %}
+            * - Software component
+              - Version
 
-.. _amd-primus-pytorch-model-support-v258:
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}
+   {% endfor %}
+
+.. _amd-primus-pytorch-model-support-v259:
 
 Supported models
 ================
@@ -47,22 +59,21 @@ vary by model -- select one to get started.
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
 
-   {% set unified_docker = data.dockers[0] %}
    {% set model_groups = data.model_groups %}
    .. raw:: html
 
       <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
-         <div class="row gx-0" style="display: none;">
+         <div class="row gx-0">
             <div class="col-2 me-1 px-2 model-param-head">Model</div>
             <div class="row col-10 pe-0">
       {% for model_group in model_groups %}
-               <div class="col-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+               <div class="col-12 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
       {% endfor %}
             </div>
          </div>
 
          <div class="row gx-0 pt-1">
-            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
             <div class="row col-10 pe-0">
       {% for model_group in model_groups %}
          {% set models = model_group.models %}
@@ -83,7 +94,7 @@ vary by model -- select one to get started.
    For additional workloads, including Llama 3.3, Llama 3.2, Llama 2, GPT OSS, Qwen, and Flux models,
    see the documentation :doc:`pytorch-training` (without Primus)
 
-.. _amd-primus-pytorch-performance-measurements-v258:
+.. _amd-primus-pytorch-performance-measurements-v259:
 
 System validation
 =================
@@ -109,25 +120,34 @@ Pull the Docker image
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
 
-   {% set unified_docker = data.dockers[0] %}
+   {% set dockers = data.dockers %}
 
-   Use the following command to pull the `Docker image <{{ unified_docker.docker_hub_url }}>`_ from Docker Hub.
+   Use the following command to pull the Docker image from Docker Hub.
 
-   .. code-block:: shell
+   .. tab-set::
 
-      docker pull {{ unified_docker.pull_tag }}
+      {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}
+
+         .. code-block:: shell
+
+            docker pull {{ docker.pull_tag }}
+      {% endfor %}
 
 Run training
 ============
 
+Once the setup is complete, choose between the following two workflows to start benchmarking training.
+For fine-tuning workloads and multi-node training examples, see :doc:`pytorch-training` (without Primus).
+For best performance on MI325X, MI350X, and MI355X GPUs, you might need to
+tweak some configurations (such as batch sizes).
+
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
 
-   {% set unified_docker = data.dockers[0] %}
+   {% set dockers = data.dockers %}
    {% set model_groups = data.model_groups %}
 
-   Once the setup is complete, choose between the following two workflows to start benchmarking training.
-   For fine-tuning workloads and multi-node training examples, see :doc:`pytorch-training` (without Primus).
-
    .. tab-set::
 
       .. tab-item:: MAD-integrated benchmarking
@@ -138,7 +158,7 @@ Run training
          .. container:: model-doc {{ model.mad_tag }}
 
             The following run command is tailored to {{ model.model }}.
-            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available model.
+            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
 
             1. 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.
@@ -165,10 +185,17 @@ Run training
                ``container_ci-{{ model.mad_tag }}``. The latency and throughput reports of the
                model are collected in ``~/MAD/perf.csv``.
 
+               .. note::
+
+                  Currently, Primus torchtitan models are run with Primus Turbo
+                  enabled for enhanced performance. To disable Primus Turbo,
+                  modify respective configuration file
+                  ``scripts/primus/pytorch_train/primus_torchtitan_scripts/llama3_[8B|70B]-[BF16|FP8].yaml``.
+
       {% endfor %}
    {% endfor %}
 
-      .. tab-item:: Standalone benchmarking
+      .. tab-item:: Primus benchmarking
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
@@ -176,34 +203,48 @@ Run training
          .. container:: model-doc {{ model.mad_tag }}
 
             The following run commands are tailored to {{ model.model }}.
-            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available model.
+            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
 
             .. rubric:: Download the Docker image and required packages
 
-            1. Use the following command to pull the Docker image from Docker Hub.
+            1. Pull the appropriate Docker image for your AMD GPU architecture from Docker Hub.
 
-               .. code-block:: shell
+               .. tab-set::
 
-                  docker pull {{ unified_docker.pull_tag }}
+                  {% for supported_gpus, docker in dockers.items() %}
+                  .. tab-item:: {{ supported_gpus }}
+                     :sync: {{ supported_gpus }}
+
+                     .. code-block:: shell
+
+                        docker pull {{ docker.pull_tag }}
+                  {% endfor %}
 
             2. Run the Docker container.
 
-               .. code-block:: shell
+               .. tab-set::
 
-                  docker run -it \
-                      --device /dev/dri \
-                      --device /dev/kfd \
-                      --network host \
-                      --ipc host \
-                      --group-add video \
-                      --cap-add SYS_PTRACE \
-                      --security-opt seccomp=unconfined \
-                      --privileged \
-                      -v $HOME:$HOME \
-                      -v $HOME/.ssh:/root/.ssh \
-                      --shm-size 64G \
-                      --name training_env \
-                      {{ unified_docker.pull_tag }}
+                  {% for supported_gpus, docker in dockers.items() %}
+                  .. tab-item:: {{ supported_gpus }}
+                     :sync: {{ supported_gpus }}
+
+                     .. code-block:: shell
+
+                        docker run -it \
+                            --device /dev/dri \
+                            --device /dev/kfd \
+                            --network host \
+                            --ipc host \
+                            --group-add video \
+                            --cap-add SYS_PTRACE \
+                            --security-opt seccomp=unconfined \
+                            --privileged \
+                            -v $HOME:$HOME \
+                            -v $HOME/.ssh:/root/.ssh \
+                            --shm-size 64G \
+                            --name training_env \
+                            {{ docker.pull_tag }}
+                  {% endfor %}
 
                Use these commands if you exit the ``training_env`` container and need to return to it.
 
@@ -212,16 +253,249 @@ Run training
                   docker start training_env
                   docker exec -it training_env bash
 
-            3. In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
-               repository and navigate to the benchmark scripts directory
-               ``/workspace/MAD/scripts/pytorch_train``.
+            .. rubric:: Prepare training datasets and dependencies
+
+            The following benchmarking examples require downloading models and datasets
+            from Hugging Face. To ensure successful access to gated repos, set your
+            ``HF_TOKEN``.
+
+            .. code-block:: shell
+
+               export HF_TOKEN=$your_personal_hugging_face_access_token
+
+            .. rubric:: Pretraining
+
+            To get started, navigate to the ``Primus`` directory in your container.
+
+            .. code-block::
+
+               cd /workspace/Primus
+
+            Now, to start the pretraining benchmark, use the ``run_pretrain.sh`` script
+            included with Primus with the appropriate options.
+
+            .. rubric:: Benchmarking examples
+
+            .. container:: model-doc primus_pyt_train_llama-3.1-8b
+
+               Use the following command to run train Llama 3.1 8B with BF16 precision using Primus torchtitan.
+
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 5
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 6
+
+                  .. tab-item:: MI300X
+                     :sync: MI325X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 4
+
+
+               To train Llama 3.1 8B with FP8 precision, use the following command.
+
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 8
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 7
+
+                  .. tab-item:: MI300X
+                     :sync: MI325X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_8B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 5
+
+            .. container:: model-doc primus_pyt_train_llama-3.1-70b
+
+               Use the following command to run train Llama 3.1 70B with BF16 precision using Primus torchtitan.
+
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 8
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 6
+
+                  .. tab-item:: MI300X
+                     :sync: MI325X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-BF16-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 4
+
+               To train Llama 3.1 70B with FP8 precision, use the following command.
+
+               .. tab-set::
+
+                  .. tab-item:: MI355X and MI350X
+                     :sync: MI355X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 6
+
+                  .. tab-item:: MI325X
+                     :sync: MI325X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 5
+
+                  .. tab-item:: MI300X
+                     :sync: MI325X and MI300X
+
+                     .. code-block:: shell
+
+                        EXP=examples/torchtitan/configs/llama3.1_70B-FP8-pretrain.yaml \
+                        bash examples/run_pretrain.sh \
+                            --metrics.enable_tensorboard false \
+                            --profiling.enable_profiling false \
+                            --training.batch_size 3
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Standalone torchtitan benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run commands are tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v259` to switch to another available model.
+
+            .. rubric:: Download the Docker image and required packages
+
+            1. Pull the appropriate Docker image for your AMD GPU architecture from Docker Hub.
+
+               .. tab-set::
+
+                  {% for supported_gpus, docker in dockers.items() %}
+                  .. tab-item:: {{ supported_gpus }}
+                     :sync: {{ supported_gpus }}
+
+                     .. code-block:: shell
+
+                        docker pull {{ docker.pull_tag }}
+                  {% endfor %}
+
+            2. Run the Docker container.
+
+               .. tab-set::
+
+                  {% for supported_gpus, docker in dockers.items() %}
+                  .. tab-item:: {{ supported_gpus }}
+                     :sync: {{ supported_gpus }}
+
+                     .. code-block:: shell
+
+                        docker run -it \
+                            --device /dev/dri \
+                            --device /dev/kfd \
+                            --network host \
+                            --ipc host \
+                            --group-add video \
+                            --cap-add SYS_PTRACE \
+                            --security-opt seccomp=unconfined \
+                            --privileged \
+                            -v $HOME:$HOME \
+                            -v $HOME/.ssh:/root/.ssh \
+                            --shm-size 64G \
+                            --name training_env \
+                            {{ docker.pull_tag }}
+                  {% endfor %}
+
+               Use these commands if you exit the ``training_env`` container and need to return to it.
 
                .. code-block:: shell
 
-                  git clone https://github.com/ROCm/MAD
-                  cd MAD/scripts/pytorch_train
+                  docker start training_env
+                  docker exec -it training_env bash
 
-            .. rubric:: Prepare training datasets and dependencies
+            3. Navigate to the ``torchtitan`` workspace directory.
+
+               .. code-block:: shell
+
+                  cd /workspace/torchtitan
+
+            .. rubric:: Download the tokenizer
 
             1. The following benchmarking examples require downloading models and datasets
                from Hugging Face. To ensure successful access to gated repos, set your
@@ -231,62 +505,47 @@ Run training
 
                   export HF_TOKEN=$your_personal_hugging_face_access_token
 
-            2. Run the setup script to install libraries and datasets needed for benchmarking.
+            2. Download the tokenizer for your model.
+
+               .. container:: model-doc {{ model.mad_tag }}
+
+                  .. code-block:: shell
+
+                     python3 scripts/download_tokenizer.py \
+                        --repo_id {{ model.model_repo }} \
+                        --tokenizer_path "original" \
+                        --hf_token=${HF_TOKEN}
+
+            .. rubric:: Pretraining examples
+
+            Run the training script with the appropriate configuration file.
+
+            For train with BF16 precicion, use the following command:
+
+            .. container:: model-doc {{ model.mad_tag }}
 
                .. code-block:: shell
 
-                  ./pytorch_benchmark_setup.sh
+                  CONFIG_FILE={{ model.config_file.bf16 }} \
+                  .run_train.sh
 
-            .. rubric:: Pretraining
+            For train with BF16 precicion, use the following command:
 
-            To start the pretraining benchmark, use the following command with the
-            appropriate options. See the following list of options and their descriptions.
+            .. container:: model-doc {{ model.mad_tag }}
 
-            .. code-block:: shell
+               .. code-block:: shell
 
-               ./pytorch_benchmark_report.sh -t pretrain \
-                   -m {{ model.model_repo }} \
-                   -p $datatype \
-                   -s $sequence_length
-
-
-            .. list-table::
-               :header-rows: 1
-
-               * - Name
-                 - Options
-                 - Description
-
-               {% for mode in available_modes %}
-               * - {% if loop.first %}``$training_mode``{% endif %}
-                 - ``{{ mode }}``
-                 - {{ training_mode_descs[mode] }}
-               {% endfor %}
-
-               * - ``$datatype``
-                 - ``BF16``{% if model.mad_tag == "primus_pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
-                 - Currently, only Llama 3.1 8B supports FP8 precision.
-
-               * - ``$sequence_length``
-                 - Sequence length for the language model.
-                 - Between 2048 and 8192. 8192 by default.
-
-            .. rubric:: Benchmarking examples
-
-            Use the following command to run train {{ model.model }} with BF16 precision using Primus torchtitan.
-
-            .. code-block:: shell
-
-               ./pytorch_benchmark_report.sh -m {{ model.model_repo }}
-
-            To train {{ model.model }} with FP8 precision, use the following command.
-
-            .. code-block:: shell
-
-               ./pytorch_benchmark_report.sh -m {{ model.model_repo }} -p FP8
+                  CONFIG_FILE={{ model.config_file.fp8 }} \
+                  .run_train.sh
       {% endfor %}
    {% endfor %}
 
+Known issues
+============
+
+PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
+
+
 Further reading
 ===============
 
@@ -296,7 +555,7 @@ Further reading
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For a list of other ready-made Docker images for AI with ROCm, see
   `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.

docs/how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst

@@ -10,44 +10,54 @@ Training a model with PyTorch on ROCm
 
 .. note::
 
-   Primus with the PyTorch torchtitan backend is designed to replace :doc:`ROCm PyTorch training <pytorch-training>` workflow.
+   For a unified training solution on AMD GPUs with ROCm, the `rocm/pytorch-training
+   <https://hub.docker.com/r/rocm/pytorch-training/>`__ Docker Hub registry will be
+   deprecated soon in favor of `rocm/primus <https://hub.docker.com/r/rocm/primus>`__.
+   The ``rocm/primus`` Docker containers will cover PyTorch training ecosystem frameworks,
+   including `Megatron-LM <primus-megatron>`__, torchtitan, and torchtune.
+
    See :doc:`primus-pytorch` for details.
 
 PyTorch is an open-source machine learning framework that is widely used for
 model training with GPU-optimized components for transformer-based models.
+The PyTorch for ROCm training Docker image provides a prebuilt optimized
+environment for fine-tuning and pretraining a model on AMD Instinct MI325X
+and MI300X GPUs. It includes the following software components to accelerate
+training workloads:
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
 
    {% set dockers = data.dockers %}
-   {% set docker = dockers[0] %}
-   The `PyTorch for ROCm training Docker <{{ docker.docker_hub_url }}>`__
-   (``{{ docker.pull_tag }}``) image provides a prebuilt optimized environment for fine-tuning and pretraining a
-   model on AMD Instinct MI325X and MI300X GPUs. It includes the following software components to accelerate
-   training workloads:
+   .. tab-set::
 
-   .. list-table::
-      :header-rows: 1
+   {% for supported_gpus, docker in dockers.items() %}
+      .. tab-item:: {{ supported_gpus }}
+         :sync: {{ supported_gpus }}
 
-      * - Software component
-        - Version
+         .. list-table::
+            :header-rows: 1
 
-      {% for component_name, component_version in docker.components.items() %}
-      * - {{ component_name }}
-        - {{ component_version }}
-      {% endfor %}
+            * - Software component
+              - Version
 
-.. _amd-pytorch-training-model-support:
+            {% for component_name, component_version in docker.components.items() %}
+            * - {{ component_name }}
+              - {{ component_version }}
+            {% endfor %}
+   {% endfor %}
+
+.. _amd-pytorch-training-model-support-v259:
 
 Supported models
 ================
 
-The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
-Some instructions, commands, and training recommendations in this documentation might
-vary by model -- select one to get started.
+The following models are pre-optimized for performance on the AMD Instinct
+MI355X, MI350X, MI325X, and MI300X GPUs. Some instructions, commands, and
+training recommendations in this documentation might vary by model -- select
+one to get started.
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
 
-   {% set unified_docker = data.dockers[0] %}
    {% set model_groups = data.model_groups %}
    .. raw:: html
 
@@ -78,11 +88,13 @@ vary by model -- select one to get started.
          </div>
       </div>
 
+.. _amd-pytorch-training-supported-training-modes-v259:
 
-   .. _amd-pytorch-training-supported-training-modes:
+The following table lists supported training modes per model.
 
-   The following table lists supported training modes per model.
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
 
+   {% set model_groups = data.model_groups %}
    .. dropdown:: Supported training modes
 
       .. list-table::
@@ -111,7 +123,7 @@ vary by model -- select one to get started.
          unlisted fine-tuning methods by using an existing file in the
          ``/workspace/torchtune/recipes/configs`` directory as a template.
 
-.. _amd-pytorch-training-performance-measurements:
+.. _amd-pytorch-training-performance-measurements-v259:
 
 Performance measurements
 ========================
@@ -152,7 +164,7 @@ Run training
 
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
 
-   {% set unified_docker = data.dockers[0] %}
+   {% set dockers = data.dockers %}
    {% set model_groups = data.model_groups %}
 
    Once the setup is complete, choose between two options to start benchmarking training:
@@ -167,7 +179,7 @@ Run training
          .. container:: model-doc {{ model.mad_tag }}
 
             The following run command is tailored to {{ model.model }}.
-            See :ref:`amd-pytorch-training-model-support` to switch to another available model.
+            See :ref:`amd-pytorch-training-model-support-v259` to switch to another available model.
 
             1. 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.
@@ -205,7 +217,7 @@ Run training
          .. container:: model-doc {{ model.mad_tag }}
 
             The following commands are tailored to {{ model.model }}.
-            See :ref:`amd-pytorch-training-model-support` to switch to another available model.
+            See :ref:`amd-pytorch-training-model-support-v259` to switch to another available model.
 
       {% endfor %}
    {% endfor %}
@@ -214,28 +226,42 @@ Run training
 
          1. Use the following command to pull the Docker image from Docker Hub.
 
-            .. code-block:: shell
+            .. tab-set::
 
-               docker pull {{ unified_docker.pull_tag }}
+               {% for supported_gpus, docker in dockers.items() %}
+               .. tab-item:: {{ supported_gpus }}
+                  :sync: {{ supported_gpus }}
 
-         2. Run the Docker container.
+                  .. code-block:: shell
 
-            .. code-block:: shell
+                     docker pull {{ docker.pull_tag }}
+               {% endfor %}
 
-               docker run -it \
-                   --device /dev/dri \
-                   --device /dev/kfd \
-                   --network host \
-                   --ipc host \
-                   --group-add video \
-                   --cap-add SYS_PTRACE \
-                   --security-opt seccomp=unconfined \
-                   --privileged \
-                   -v $HOME:$HOME \
-                   -v $HOME/.ssh:/root/.ssh \
-                   --shm-size 64G \
-                   --name training_env \
-                   {{ unified_docker.pull_tag }}
+         2. Launch the Docker container.
+
+            .. tab-set::
+
+               {% for supported_gpus, docker in dockers.items() %}
+               .. tab-item:: {{ supported_gpus }}
+                  :sync: {{ supported_gpus }}
+
+                  .. code-block:: shell
+
+                     docker run -it \
+                         --device /dev/dri \
+                         --device /dev/kfd \
+                         --network host \
+                         --ipc host \
+                         --group-add video \
+                         --cap-add SYS_PTRACE \
+                         --security-opt seccomp=unconfined \
+                         --privileged \
+                         -v $HOME:$HOME \
+                         -v $HOME/.ssh:/root/.ssh \
+                         --shm-size 64G \
+                         --name training_env \
+                         {{ docker.pull_tag }}
+               {% endfor %}
 
             Use these commands if you exit the ``training_env`` container and need to return to it.
 
@@ -379,7 +405,7 @@ Run training
 
             ``pytorch_benchmark_setup.sh`` downloads the following datasets from Hugging Face:
 
-            * `bghira/pseudo-camera-10k <https://huggingface.co/datasets/bghira/pseudo-camera-10k>`__
+            * `frank-chieng/chinese_architecture_siheyuan <https://huggingface.co/datasets/frank-chieng/chinese_architecture_siheyuan>`__
 
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
@@ -410,7 +436,7 @@ Run training
 
                .. note::
 
-                  Currently, FLUX models are not supported out-of-the-box on {{ unified_docker.pull_tag }}.
+                  Currently, FLUX models are not supported out-of-the-box on this Docker.
                   To use FLUX, refer to ``rocm/pytorch-training`` Docker: :doc:`previous-versions/pytorch-training-v25.6`
 
                   Occasionally, downloading the Flux dataset might fail. In the event of this
@@ -442,6 +468,49 @@ Run training
                  - Between 2048 and 8192. 8192 by default.
          {% endif %}
 
+         {% set training_modes = model.training_modes %}
+         {% set training_mode_descs = {
+            "posttrain": "Benchmark post-training.",
+         } %}
+         {% set available_modes = training_modes | select("in", ["posttrain"]) | list %}
+         {% if available_modes %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Post-training
+
+            To start the post-training benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t {% if available_modes | length == 1 %}{{ available_modes[0] }}{% else %}$training_mode{% endif %} \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if model.mad_tag == "pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+         {% endif %}
+
          {% set training_mode_descs = {
             "finetune_fw": "Full weight fine-tuning (BF16 and FP8 supported).",
             "finetune_lora": "LoRA fine-tuning (BF16 supported).",
@@ -456,7 +525,7 @@ Run training
 
             To start the fine-tuning benchmark, use the following command with the
             appropriate options. See the following list of options and their descriptions.
-            See :ref:`supported training modes <amd-pytorch-training-supported-training-modes>`.
+            See :ref:`supported training modes <amd-pytorch-training-supported-training-modes-v259>`.
 
             .. code-block:: shell
 
@@ -521,7 +590,7 @@ Run training
 
             For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.
 
-.. _amd-pytorch-training-multinode-examples:
+.. _amd-pytorch-training-multinode-examples-v259:
 
 Multi-node training
 -------------------
@@ -570,13 +639,18 @@ To launch the training job on a SLURM cluster for Llama 3.3 70B, run the followi
 
 Once the run is finished, you can find the log files in the ``result_torchtune/`` directory.
 
+Known issues
+============
+
+PyTorch Profiler may produce inaccurate traces when CPU activity profiling is enabled.
+
 Further reading
 ===============
 
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
 - For a list of other ready-made Docker images for AI with ROCm, see
   `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.

docs/how-to/rocm-for-ai/training/scale-model-training.rst

@@ -6,9 +6,9 @@
 Scaling model training
 **********************
 
-To train a large-scale model like OpenAI GPT-2 or Meta Llama 2 70B, a single accelerator or GPU cannot store all the
-model parameters required for training. This immense scale presents a fundamental challenge: no single GPU or
-accelerator can simultaneously store and process the entire model's parameters during training. PyTorch
+To train a large-scale model like OpenAI GPT-2 or Meta Llama 2 70B, a single GPU cannot store all the
+model parameters required for training. This immense scale presents a fundamental challenge: no single GPU
+can simultaneously store and process the entire model's parameters during training. PyTorch
 provides an answer to this computational constraint through its distributed training frameworks.
 
 .. _rocm-for-ai-pytorch-distributed:
@@ -26,9 +26,9 @@ Features in ``torch.distributed`` are categorized into three main components:
 - `Collective communication <https://pytorch.org/docs/stable/distributed.html>`_
 
 In this topic, the focus is on the distributed data-parallelism strategy as it’s the most popular. To get started with DDP,
-you need to first understand how to coordinate the model and its training data across multiple accelerators or GPUs.
+you need to first understand how to coordinate the model and its training data across multiple GPUs.
 
-The DDP workflow on multiple accelerators or GPUs is as follows:
+The DDP workflow on multiple GPUs is as follows:
 
 #. Split the current global training batch into small local batches on each GPU. For instance, if you have 8 GPUs and
    the global batch is set at 32 samples, each of the 8 GPUs will have a local batch size of 4 samples.
@@ -46,7 +46,7 @@ In DDP training, each process or worker owns a replica of the model and processe
 
 See the following developer blogs for more in-depth explanations and examples.
 
-*  `Multi GPU training with DDP — PyTorch Tutorials <https://pytorch.org/tutorials/beginner/ddp_series_multigpu.html>`_
+*  `Multi GPU training with DDP — PyTorch Tutorials <https://pytorch.org/tutorials/beginner/ddp_Series_multigpu.html>`_
 
 *  `Building a decoder transformer model on AMD GPUs — ROCm Blogs
    <https://rocm.blogs.amd.com/artificial-intelligence/decoder-transformer/README.html#distributed-training-on-multiple-gpus>`_
@@ -82,7 +82,7 @@ the training pillar.
 
 See `Pre-training a large language model with Megatron-DeepSpeed on multiple AMD GPUs
 <https://rocm.blogs.amd.com/artificial-intelligence/megatron-deepspeed-pretrain/README.html>`_ for a detailed example of
-training with DeepSpeed on an AMD accelerator or GPU.
+training with DeepSpeed on an AMD GPU.
 
 .. _rocm-for-ai-automatic-mixed-precision:
 
@@ -95,7 +95,7 @@ can take to reduce training time and memory usage through `automatic mixed preci
 
 See `Automatic mixed precision in PyTorch using AMD GPUs — ROCm Blogs
 <https://rocm.blogs.amd.com/artificial-intelligence/automatic-mixed-precision/README.html#automatic-mixed-precision-in-pytorch-using-amd-gpus>`_
-for more information about running AMP on an AMD accelerator.
+for more information about running AMP on an AMD Instinct-Series GPU.
 
 .. _rocm-for-ai-fine-tune:
 
@@ -107,7 +107,7 @@ example, LoRA, QLoRA, PEFT, and FSDP.
 
 Learn more about challenges and solutions for model fine-tuning in :doc:`../fine-tuning/index`.
 
-The following developer blogs showcase examples of fine-tuning a model on an AMD accelerator or GPU.
+The following developer blogs showcase examples of fine-tuning a model on an AMD GPU.
 
 * Fine-tuning Llama2 with LoRA
 

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

@@ -7,14 +7,14 @@ Using ROCm for HPC
 ******************
 
 The ROCm open-source software stack is optimized to extract high-performance
-computing (HPC) workload performance from AMD Instinct™ accelerators
+computing (HPC) workload performance from AMD Instinct™ GPUs
 while maintaining compatibility with industry software frameworks.
 
 ROCm enhances support and access for developers by providing streamlined and
 improved tools that significantly increase productivity. Being open-source, ROCm
 fosters innovation, differentiation, and collaboration within the developer
 community, making it a powerful and accessible solution for leveraging the full
-potential of AMD accelerators' capabilities in diverse computational
+potential of AMD GPUs' capabilities in diverse computational
 applications.
 
 * For more information, see :doc:`What is ROCm? <../../what-is-rocm>`.
@@ -24,7 +24,7 @@ applications.
   and operating system support.
 
 Some of the most popular HPC frameworks are part of the ROCm platform, including
-those to help parallelize operations across multiple accelerators and servers,
+those to help parallelize operations across multiple GPUs and servers,
 handle memory hierarchies, and solve linear systems.
 
 .. image:: ../../data/how-to/rocm-for-hpc/hpc-stack-2024_6_20.png
@@ -38,7 +38,7 @@ science, genomics, geophysics, molecular dynamics, and physics computing.
 
 Refer to the resources in the following table for instructions on building,
 running, and deploying these applications on ROCm-capable systems with AMD
-Instinct accelerators. Each build container provides parameters to specify
+Instinct GPUs. Each build container provides parameters to specify
 different source code branches, release versions of ROCm, OpenMPI, UCX, and
 Ubuntu versions.
 
@@ -76,6 +76,14 @@ Ubuntu versions.
           single node workstations, multi and many-core nodes, clusters of nodes via
           QMP, and classic vector computers.
 
+      * -
+        - `Grid <https://github.com/amd/InfinityHub-CI/tree/main/grid/>`_
+        - Grid is a library for lattice QCD calculations that employs a high-level data parallel
+          approach while using a number of techniques to target multiple types of parallelism.
+          The library currently supports MPI, OpenMP, and short vector parallelism. The SIMD
+          instruction sets covered include SSE, AVX, AVX2, FMA4, IMCI, and AVX512. Recent
+          releases expanded this support to include GPU offloading.
+
       * -
         - `MILC <https://github.com/amd/InfinityHub-CI/tree/main/milc/>`_
         - The MILC Code is a set of research codes developed by MIMD Lattice Computation
@@ -88,7 +96,7 @@ Ubuntu versions.
       * - 
         - `QUDA <https://github.com/amd/InfinityHub-CI/tree/main/quda>`_
         - Library designed for efficient lattice QCD computations on
-          accelerators. It includes optimized Dirac operators and a variety of
+          GPUs. It includes optimized Dirac operators and a variety of
           fermion solvers and conjugate gradient (CG) implementations, enhancing
           performance and accuracy in lattice QCD simulations.
 
@@ -148,24 +156,6 @@ Ubuntu versions.
           backends ranging from general-purpose processors, CUDA and HIP enabled
           accelerators to SX-Aurora vector processors.
 
-      * -
-        - `nekRS <https://github.com/amd/InfinityHub-CI/tree/main/nekrs>`_
-        - 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
@@ -199,15 +189,6 @@ Ubuntu versions.
           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
@@ -240,6 +221,10 @@ Ubuntu versions.
         - Base container for GPU-aware MPI with ROCm for HPC applications. This
           project provides a boilerplate for building and running a Docker
           container with ROCm supporting GPU-aware MPI implementations using MPICH.
+
+      * - 
+        - `AMD ROCm with Conda Environment Container <https://github.com/amd/InfinityHub-CI/tree/main/conda-rocm-environment>`_
+        - Container recipe that uses the `base-gpu-mpi-rocm-docker` as the base and adds Conda. The container can be used as a base for applications that require conda applications.
       
       * -
         - `Kokkos <https://github.com/amd/InfinityHub-CI/tree/main/kokkos>`_
@@ -258,14 +243,6 @@ 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
@@ -278,4 +255,9 @@ Ubuntu versions.
           within an object-oriented software framework for the solution of large-scale,
           complex multi-physics engineering and scientific problems.
 
+      * -
+        - `VLLM <https://github.com/amd/InfinityHub-CI/tree/main/vllm>`_
+        - The VLLM project helps to build a Dockerfile for performance testing of the LLAMA2 applications.
+          This Dockerfile uses a base install that includes Ubuntu 20.04, ROCm 6.1.2 and Python 3.9. The container can host the LLAMA2 applications (LLMs) and requires some large input files for testing.
+
 To learn about ROCm for AI applications, see :doc:`../rocm-for-ai/index`.

docs/how-to/system-optimization/index.rst

@@ -1,6 +1,6 @@
 .. meta::
    :description: Learn about AMD hardware optimization for HPC-specific and workstation workloads.
-   :keywords: high-performance computing, HPC, Instinct accelerators, Radeon,
+   :keywords: high-performance computing, HPC, Instinct GPUs, Radeon,
               tuning, tuning guide, AMD, ROCm
 
 *******************