Fix almalinux dependency issue

Fix almalinux dependency; get publish test results step working
Dependency fix in origami.yml
2026-01-10 07:08:08 -05:00 · 2025-09-24 20:31:03 +00:00 · 2025-09-24 20:11:49 +00:00 · 2025-09-24 19:54:23 +00:00 · 2025-09-24 19:31:34 +00:00 · 2025-09-24 13:58:26 -05:00
40 changed files with 2503 additions and 713 deletions
--- a/.azuredevops/components/HIPIFY.yml
+++ b/.azuredevops/components/HIPIFY.yml
@@ -79,7 +79,7 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - task: Bash@3
      displayName: Add lit to PATH
      inputs:
--- a/.azuredevops/components/MIOpen.yml
+++ b/.azuredevops/components/MIOpen.yml
@@ -131,7 +131,7 @@ jobs:
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
@@ -212,7 +212,7 @@ jobs:
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/hipBLASLt.yml
+++ b/.azuredevops/components/hipBLASLt.yml
@@ -144,7 +144,7 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/hipSPARSELt.yml
+++ b/.azuredevops/components/hipSPARSELt.yml
@@ -110,7 +110,7 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/hipfort.yml
+++ b/.azuredevops/components/hipfort.yml
@@ -71,7 +71,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/origami.yml
+++ b/.azuredevops/components/origami.yml
@@ -39,6 +39,9 @@ parameters:
    - python3
    - python3-dev
    - python3-pip
+    - libgtest-dev
+    - libboost-filesystem-dev
+    - libboost-program-options-dev
 - name: pipModules
  type: object
  default:
@@ -107,8 +110,12 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
@@ -125,7 +132,7 @@ jobs:
      parameters:
        os: ${{ job.os }}
        extraBuildFlags: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/vendor
          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
          -DORIGAMI_BUILD_SHARED_LIBS=ON
          -DORIGAMI_ENABLE_PYTHON=ON
@@ -206,7 +213,15 @@ jobs:
          ${{ if parameters.triggerDownstreamJobs }}:
            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          os: ${{ job.os }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './origami-tests'
+          testParameters: '--yaml origami-tests.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
      - script: |
+          set -e
          export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH

          echo "--- Running origami_test.py ---"
--- a/.azuredevops/components/rccl.yml
+++ b/.azuredevops/components/rccl.yml
@@ -83,7 +83,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/rocBLAS.yml
+++ b/.azuredevops/components/rocBLAS.yml
@@ -154,7 +154,7 @@ jobs:
        aptPackages: ${{ parameters.aptPackages }}
        pipModules: ${{ parameters.pipModules }}
        packageManager: ${{ job.packageManager }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/rocm-examples.yml
+++ b/.azuredevops/components/rocm-examples.yml
@@ -33,6 +33,7 @@ parameters:
    - hipRAND
    - hipSOLVER
    - hipSPARSE
+    - hipTensor
    - llvm-project
    - rocBLAS
    - rocFFT
@@ -43,6 +44,7 @@ parameters:
    - rocSOLVER
    - rocSPARSE
    - rocThrust
+    - rocWMMA
 - name: rocmTestDependencies
  type: object
  default:
@@ -57,6 +59,7 @@ parameters:
    - hipRAND
    - hipSOLVER
    - hipSPARSE
+    - hipTensor
    - llvm-project
    - rocBLAS
    - rocFFT
@@ -69,6 +72,7 @@ parameters:
    - rocSPARSE
    - rocThrust
    - roctracer
+    - rocWMMA

 - name: jobMatrix
  type: object
@@ -97,6 +101,9 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.25.0'
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
@@ -158,6 +165,9 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
+      parameters:
+        cmakeVersion: '3.25.0'
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
--- a/.azuredevops/components/rocm-libraries.yml
+++ b/.azuredevops/components/rocm-libraries.yml
@@ -102,7 +102,7 @@ jobs:
    workspace:
      clean: all
    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-custom.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
--- a/.azuredevops/templates/steps/dependencies-cmake-custom.yml
+++ b/.azuredevops/templates/steps/dependencies-cmake-custom.yml
@@ -1,10 +1,15 @@
+parameters:
+  - name: cmakeVersion
+    type: string
+    default: '3.31.0'
+
 steps:
 - task: Bash@3
-  displayName: Install CMake 3.31
+  displayName: Install CMake ${{ parameters.cmakeVersion }}
  inputs:
    targetType: inline
    script: |
-      CMAKE_VERSION=3.31.0
+      CMAKE_VERSION=${{ parameters.cmakeVersion }}
      CMAKE_ROOT="$(Pipeline.Workspace)/cmake"

      echo "Downloading CMake $CMAKE_VERSION..."
--- a/.azuredevops/templates/steps/dependencies-rocm.yml
+++ b/.azuredevops/templates/steps/dependencies-rocm.yml
@@ -126,6 +126,10 @@ parameters:
      pipelineId: 80
      developBranch: develop
      hasGpuTarget: true
+    origami:
+      pipelineId: 364
+      developBranch: develop
+      hasGpuTarget: true
    rccl:
      pipelineId: 107
      developBranch: develop
@@ -215,8 +219,8 @@ parameters:
      developBranch: develop
      hasGpuTarget: false
    rocprofiler-sdk:
-      pipelineId: 347
-      developBranch: develop
+      pipelineId: 246
+      developBranch: amd-staging
      hasGpuTarget: true
    rocprofiler-systems:
      pipelineId: 255
--- a/RELEASE.md
+++ b/RELEASE.md
--- a/default.xml
+++ b/default.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-7.0.0"
+    <default revision="refs/tags/rocm-7.0.1"
     remote="rocm-org"
     sync-c="true"
     sync-j="4" />
--- a/docs/compatibility/compatibility-matrix-historical-6.0.csv
+++ b/docs/compatibility/compatibility-matrix-historical-6.0.csv
@@ -1,4 +1,4 @@
-ROCm Version,7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
+ROCm Version,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.3,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, 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"
@@ -51,8 +51,8 @@ ROCm Version,7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6
      Thrust,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
      CUB,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
 ,,,,,,,,,,,,,,,,,,,
-      KMD & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
-      :doc:`KMD versions <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.10, 6.4.x, 6.3.x, 6.2.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
+     DRIVER & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
+      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x, 6.3.x, 6.2.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
      ,,,,,,,,,,,,,,,,,,,
      ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
      :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
@@ -96,7 +96,7 @@ ROCm Version,7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6
      ,,,,,,,,,,,,,,,,,,,
      SUPPORT LIBS,,,,,,,,,,,,,,,,,,,
      `hipother <https://github.com/ROCm/hipother>`_,7.0.51830,6.4.43483,6.4.43483,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,20240607.5.7,20240607.5.7,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
      ,,,,,,,,,,,,,,,,,,,
      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
--- a/docs/compatibility/compatibility-matrix.rst
+++ b/docs/compatibility/compatibility-matrix.rst
@@ -23,7 +23,7 @@ compatibility and system requirements.
 .. container:: format-big-table

  .. csv-table::
-      :header: "ROCm Version", "7.0.0", "6.4.3", "6.3.0"
+      :header: "ROCm Version", "7.0.1/7.0.0", "6.4.3", "6.3.0"
      :stub-columns: 1

      :ref:`Operating systems & kernels <OS-kernel-versions>`,Ubuntu 24.04.3,Ubuntu 24.04.2,Ubuntu 24.04.2
@@ -70,8 +70,8 @@ compatibility and system requirements.
      Thrust,2.6.0,2.5.0,2.3.2
      CUB,2.6.0,2.5.0,2.3.2
      ,,,
-      KMD & USER SPACE [#kfd_support]_,.. _kfd-userspace-support-compatibility-matrix:,,
-      :doc:`KMD versions <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.10, 6.4.x, 6.3.x, 6.2.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x"
+      DRIVER & USER SPACE [#kfd_support]_,.. _kfd-userspace-support-compatibility-matrix:,,
+      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.10.1 [#driver_patch]_, 30.10, 6.4.x, 6.3.x, 6.2.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x"
      ,,,
      ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix:,,
      :doc:`Composable Kernel <composable_kernel:index>`,1.1.0,1.1.0,1.1.0
@@ -115,7 +115,7 @@ compatibility and system requirements.
      ,,,
      SUPPORT LIBS,,,
      `hipother <https://github.com/ROCm/hipother>`_,7.0.51830,6.4.43483,6.3.42131
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.0,6.4.3,6.3.0
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.0.1/7.0.0,6.4.3,6.3.0
      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr]_,N/A [#ROCT-rocr]_,N/A [#ROCT-rocr]_
      ,,,
      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix:,,
@@ -156,26 +156,27 @@ compatibility and system requirements.
 .. rubric:: Footnotes

 .. [#rhel-700] RHEL 8.10 is only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, MI210, and MI100 GPUs.
-.. [#ol-700-mi300x] **For ROCm 7.0.0** - Oracle Linux 9 is supported only on AMD Instinct MI355X, MI350X, and MI300X GPUs. Oracle Linux 8 is supported only on AMD Instinct MI300X GPUs.
+.. [#ol-700-mi300x] **For ROCm 7.0.x** - Oracle Linux 9 is supported only on AMD Instinct MI355X, MI350X, and MI300X GPUs. Oracle Linux 8 is supported only on AMD Instinct MI300X GPUs.
 .. [#ol-mi300x] **Prior ROCm 7.0.0** - Oracle Linux is supported only on AMD Instinct MI300X GPUs.
-.. [#sles-db-700] **For ROCm 7.0.0** - SLES 15 SP7 and Debian 12 are only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, and MI210 GPUs.
+.. [#sles-db-700] **For ROCm 7.0.x** - SLES 15 SP7 and Debian 12 are only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, and MI210 GPUs.
 .. [#az-mi300x] Starting ROCm 6.4.0, Azure Linux 3.0 is supported only on AMD Instinct MI300X and AMD Radeon PRO V710.
 .. [#rl-700] Rocky Linux 9 is only supported on AMD Instinct MI300X and MI300A GPUs.
 .. [#single-node] **Prior to ROCm 7.0.0** - Debian 12 is supported only on AMD Instinct MI300X for single-node functionality.
 .. [#mi350x-os] AMD Instinct MI355X (gfx950) and MI350X(gfx950) GPUs are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and Oracle Linux 9.
-.. [#RDNA-OS-700] **For ROCm 7.0.0** - AMD Radeon PRO AI PRO R9700 (gfx1201), AMD Radeon RX 9070 XT (gfx1201), AMD Radeon RX 9070 GRE (gfx1201), AMD Radeon RX 9070 (gfx1201), AMD Radeon RX 9060 XT (gfx1200), AMD Radeon RX 7800 XT (gfx1101), AMD Radeon RX 7700 XT (gfx1101), AMD Radeon PRO W7700 (gfx1101), and AMD Radeon PRO W6800 (gfx1030) are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, and RHEL 9.6.
+.. [#RDNA-OS-700] **For ROCm 7.0.x** - AMD Radeon PRO AI PRO R9700 (gfx1201), AMD Radeon RX 9070 XT (gfx1201), AMD Radeon RX 9070 GRE (gfx1201), AMD Radeon RX 9070 (gfx1201), AMD Radeon RX 9060 XT (gfx1200), AMD Radeon RX 7800 XT (gfx1101), AMD Radeon RX 7700 XT (gfx1101), AMD Radeon PRO W7700 (gfx1101), and AMD Radeon PRO W6800 (gfx1030) are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, and RHEL 9.6.
 .. [#RDNA-OS] **Prior ROCm 7.0.0** - Radeon AI PRO R9700, Radeon RX 9070 XT (gfx1201), Radeon RX 9060 XT (gfx1200), Radeon PRO W7700 (gfx1101), and Radeon RX 7800 XT (gfx1101) are supported only on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
-.. [#rd-v710] **For ROCm 7.0.0** - AMD Radeon PRO V710 (gfx1101) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and Azure Linux 3.0.
-.. [#rd-v620] **For ROCm 7.0.0** - AMD Radeon PRO V620 (gfx1030) is only supported on Ubuntu 24.04.3 and Ubuntu 22.04.5.
-.. [#mi325x-os] **For ROCm 7.0.0** - AMD Instinct MI325X GPU (gfx942) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
-.. [#mi300x-os] **For ROCm 7.0.0** - AMD Instinct MI300X GPU (gfx942) is supported on all listed :ref:`supported_distributions`.
-.. [#mi300A-os] **For ROCm 7.0.0** - AMD Instinct MI300A GPU (gfx942) is supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, Debian 12, and Rocky Linux 9.
-.. [#mi200x-os] **For ROCm 7.0.0** - AMD Instinct MI200 Series GPUs (gfx90a) are supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, and Debian 12.
-.. [#mi100-os] **For ROCm 7.0.0** - AMD Instinct MI100 GPU (gfx908) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
+.. [#rd-v710] **For ROCm 7.0.x** - AMD Radeon PRO V710 (gfx1101) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and Azure Linux 3.0.
+.. [#rd-v620] **For ROCm 7.0.x** - AMD Radeon PRO V620 (gfx1030) is only supported on Ubuntu 24.04.3 and Ubuntu 22.04.5.
+.. [#mi325x-os] **For ROCm 7.0.x** - AMD Instinct MI325X GPU (gfx942) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
+.. [#mi300x-os] **For ROCm 7.0.x** - AMD Instinct MI300X GPU (gfx942) is supported on all listed :ref:`supported_distributions`.
+.. [#mi300A-os] **For ROCm 7.0.x** - AMD Instinct MI300A GPU (gfx942) is supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, Debian 12, and Rocky Linux 9.
+.. [#mi200x-os] **For ROCm 7.0.x** - AMD Instinct MI200 Series GPUs (gfx90a) are supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, and Debian 12.
+.. [#mi100-os] **For ROCm 7.0.x** - AMD Instinct MI100 GPU (gfx908) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
 .. [#7700XT-OS] **Prior ROCm 7.0.0** - Radeon RX 7700 XT (gfx1101) is supported only on Ubuntu 24.04.2 and RHEL 9.6.
 .. [#stanford-megatron-lm_compat] Stanford Megatron-LM is only supported on ROCm 6.3.0.
 .. [#megablocks_compat] Megablocks is only supported on ROCm 6.3.0.
-.. [#kfd_support] As of ROCm 6.4.0, forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
+.. [#driver_patch] AMD GPU Driver (amdgpu) 30.10.1 is a quality release that resolves an issue identified in the 30.10 release. There are no other significant changes or feature additions in ROCm 7.0.1 from ROCm 7.0.0. AMD GPU Driver (amdgpu) 30.10.1 is compatible with ROCm 7.0.1 and ROCm 7.0.0.
+.. [#kfd_support] As of ROCm 6.4.0, forward and backward compatibility between the AMD GPU Driver (amdgpu) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and AMD GPU Driver support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
 .. [#ROCT-rocr] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.


@@ -247,24 +248,24 @@ Expand for full historical view of:

   .. rubric:: Footnotes

-   .. [#rhel-700-past-60] **For ROCm 7.0.0** - RHEL 8.10 is only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, MI210, and MI100 GPUs.
-   .. [#ol-700-mi300x-past-60] **For ROCm 7.0.0** - Oracle Linux 9 is supported only on AMD Instinct MI300X, MI350X, and MI355X. Oracle Linux 8 is only supported on AMD Instinct MI300X.
+   .. [#rhel-700-past-60] **For ROCm 7.0.x** - RHEL 8.10 is only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, MI210, and MI100 GPUs.
+   .. [#ol-700-mi300x-past-60] **For ROCm 7.0.x** - Oracle Linux 9 is supported only on AMD Instinct MI300X, MI350X, and MI355X. Oracle Linux 8 is only supported on AMD Instinct MI300X.
   .. [#mi300x-past-60] **Prior ROCm 7.0.0** - Oracle Linux is supported only on AMD Instinct MI300X.
-   .. [#sles-db-700-past-60] **For ROCm 7.0.0** - SLES 15 SP7 and Debian 12 are only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, and MI210 GPUs.
+   .. [#sles-db-700-past-60] **For ROCm 7.0.x** - SLES 15 SP7 and Debian 12 are only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, and MI210 GPUs.
   .. [#single-node-past-60] **Prior to ROCm 7.0.0** - Debian 12 is supported only on AMD Instinct MI300X for single-node functionality.
   .. [#az-mi300x-past-60] Starting from ROCm 6.4.0, Azure Linux 3.0 is supported only on AMD Instinct MI300X and AMD Radeon PRO V710.
   .. [#az-mi300x-630-past-60] **Prior ROCm 6.4.0**- Azure Linux 3.0 is supported only on AMD Instinct MI300X.
   .. [#rl-700-past-60] Rocky Linux 9 is only supported on AMD Instinct MI300X and MI300A GPUs.
   .. [#mi350x-os-past-60] AMD Instinct MI355X (gfx950) and MI350X(gfx950) GPUs are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and Oracle Linux 9.
-   .. [#RDNA-OS-700-past-60] **For ROCm 7.0.0** AMD Radeon PRO AI PRO R9700 (gfx1201), AMD Radeon RX 9070 XT (gfx1201), AMD Radeon RX 9070 GRE (gfx1201), AMD Radeon RX 9070 (gfx1201), AMD Radeon RX 9060 XT (gfx1200), AMD Radeon RX 7800 XT (gfx1101), AMD Radeon RX 7700 XT (gfx1101), AMD Radeon PRO W7700 (gfx1101), and AMD Radeon PRO W6800 (gfx1030) are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, and RHEL 9.6.
+   .. [#RDNA-OS-700-past-60] **For ROCm 7.0.x** AMD Radeon PRO AI PRO R9700 (gfx1201), AMD Radeon RX 9070 XT (gfx1201), AMD Radeon RX 9070 GRE (gfx1201), AMD Radeon RX 9070 (gfx1201), AMD Radeon RX 9060 XT (gfx1200), AMD Radeon RX 7800 XT (gfx1101), AMD Radeon RX 7700 XT (gfx1101), AMD Radeon PRO W7700 (gfx1101), and AMD Radeon PRO W6800 (gfx1030) are only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, and RHEL 9.6.
   .. [#RDNA-OS-past-60] **Prior ROCm 7.0.0** - Radeon AI PRO R9700, Radeon RX 9070 XT (gfx1201), Radeon RX 9060 XT (gfx1200), Radeon PRO W7700 (gfx1101), and Radeon RX 7800 XT (gfx1101) are supported only on Ubuntu 24.04.2, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
-   .. [#rd-v710-past-60] **For ROCm 7.0.0** - AMD Radeon PRO V710 (gfx1101) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and Azure Linux 3.0.
-   .. [#rd-v620-past-60] **For ROCm 7.0.0** - AMD Radeon PRO V620 (gfx1030) is only supported on Ubuntu 24.04.3 and Ubuntu 22.04.5.
-   .. [#mi325x-os-past-60] **For ROCm 7.0.0** - AMD Instinct MI325X GPU (gfx942) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
-   .. [#mi300x-os-past-60] **For ROCm 7.0.0** - AMD Instinct MI300X GPU (gfx942) is supported on all listed :ref:`supported_distributions`.
-   .. [#mi300A-os-past-60] **For ROCm 7.0.0** - AMD Instinct MI300A GPU (gfx942) is supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, Debian 12, and Rocky Linux 9.
-   .. [#mi200x-os-past-60] **For ROCm 7.0.0** - AMD Instinct MI200 Series GPUs (gfx90a) are supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, and Debian 12.
-   .. [#mi100-os-past-60] **For ROCm 7.0.0** - AMD Instinct MI100 GPU (gfx908) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
+   .. [#rd-v710-past-60] **For ROCm 7.0.x** - AMD Radeon PRO V710 (gfx1101) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and Azure Linux 3.0.
+   .. [#rd-v620-past-60] **For ROCm 7.0.x** - AMD Radeon PRO V620 (gfx1030) is only supported on Ubuntu 24.04.3 and Ubuntu 22.04.5.
+   .. [#mi325x-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI325X GPU (gfx942) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, and RHEL 9.4.
+   .. [#mi300x-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI300X GPU (gfx942) is supported on all listed :ref:`supported_distributions`.
+   .. [#mi300A-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI300A GPU (gfx942) is supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, Debian 12, and Rocky Linux 9.
+   .. [#mi200x-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI200 Series GPUs (gfx90a) are supported only on Ubuntu 24.04, Ubuntu 22.04, RHEL 9.6, RHEL 9.4, RHEL 8.10, SLES 15 SP7, and Debian 12.
+   .. [#mi100-os-past-60] **For ROCm 7.0.x** - AMD Instinct MI100 GPU (gfx908) is only supported on Ubuntu 24.04.3, Ubuntu 22.04.5, RHEL 9.6, RHEL 9.4, and RHEL 8.10.
   .. [#7700XT-OS-past-60] Radeon RX 7700 XT (gfx1101) is supported only on Ubuntu 24.04.2 and RHEL 9.6.
   .. [#mi300_624-past-60] **For ROCm 6.2.4** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
   .. [#mi300_622-past-60] **For ROCm 6.2.2** - MI300X (gfx942) is supported on listed operating systems *except* Ubuntu 22.04.5 [6.8 HWE] and Ubuntu 22.04.4 [6.5 HWE].
@@ -282,6 +283,7 @@ Expand for full historical view of:
   .. [#taichi_compat-past-60] Taichi is only supported on ROCm 6.3.2.
   .. [#ray_compat-past-60] Ray is only supported on ROCm 6.4.1.
   .. [#llama-cpp_compat-past-60] llama.cpp is only supported on ROCm 6.4.0.
-   .. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD Kernel-mode GPU Driver (KMD) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
+   .. [#driver_patch-past-60] AMD GPU Driver (amdgpu) 30.10.1 is a quality release that resolves an issue identified in the 30.10 release. There are no other significant changes or feature additions in ROCm 7.0.1 from ROCm 7.0.0. AMD GPU Driver (amdgpu) 30.10.1 is compatible with ROCm 7.0.1 and ROCm 7.0.0.
+   .. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD GPU Driver (amdgpu) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and AMD GPU Driver support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
   .. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
   
--- a/docs/compatibility/ml-compatibility/jax-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/jax-compatibility.rst
@@ -90,75 +90,15 @@ For more use cases and recommendations, see `ROCm JAX blog posts <https://rocm.b
 Docker image compatibility
 ================================================================================

-.. |docker-icon| raw:: html
+AMD provides preconfigured Docker images with JAX and the ROCm backend.
+These images are published on `Docker Hub <https://hub.docker.com/r/rocm/jax>`__ and are the
+recommended way to get started with deep learning with JAX on ROCm.
+For ``jax-community`` images, see `rocm/jax-community
+<https://hub.docker.com/r/rocm/jax-community/tags>`__ on Docker Hub.

-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes ready-made `ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax>`_
-with ROCm backends on Docker Hub. The following Docker image tags and
-associated inventories represent the latest JAX version from the official Docker Hub and are validated for
-`ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`_. Click the |docker-icon|
-icon to view the image on Docker Hub.
-
-.. list-table:: JAX Docker image components
-    :header-rows: 1
-
-    * - Docker image
-      - JAX
-      - Linux
-      - Python
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.2-jax0.4.35-py3.12/images/sha256-8918fa806a172c1a10eb2f57131eb31b5d7c8fa1656b8729fe7d3d736112de83"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
-
-      - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
-      - Ubuntu 24.04
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`_
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.2-jax0.4.35-py3.10/images/sha256-a394be13c67b7fc602216abee51233afd4b6cb7adaa57ca97e688fba82f9ad79"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
-
-      - `0.4.35 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.4.35>`_
-      - Ubuntu 22.04
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`_
-
-AMD publishes `Community ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax-community>`_
-with ROCm backends on Docker Hub. The following Docker image tags and
-associated inventories are tested for `ROCm 6.3.2 <https://repo.radeon.com/rocm/apt/6.3.2/>`_.
-
-.. list-table:: JAX community Docker image components
-    :header-rows: 1
-
-    * - Docker image
-      - JAX
-      - Linux
-      - Python
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.3.2-jax0.5.0-py3.12.8/images/sha256-25dfaa0183e274bd0a3554a309af3249c6f16a1793226cb5373f418e39d3146a"><i class="fab fa-docker fa-lg"></i> rocm/jax-community</a>
-
-      - `0.5.0 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.5.0>`_
-      - Ubuntu 22.04
-      - `3.12.8 <https://www.python.org/downloads/release/python-3128/>`_
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.3.2-jax0.5.0-py3.11.11/images/sha256-ff9baeca9067d13e6c279c911e5a9e5beed0817d24fafd424367cc3d5bd381d7"><i class="fab fa-docker fa-lg"></i> rocm/jax-community</a>
-
-      - `0.5.0 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.5.0>`_
-      - Ubuntu 22.04
-      - `3.11.11 <https://www.python.org/downloads/release/python-31111/>`_
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/jax-community/rocm6.3.2-jax0.5.0-py3.10.16/images/sha256-8bab484be1713655f74da51a191ed824bb9d03db1104fd63530a1ac3c37cf7b1"><i class="fab fa-docker fa-lg"></i> rocm/jax-community</a>
-
-      - `0.5.0 <https://github.com/ROCm/jax/releases/tag/rocm-jax-v0.5.0>`_
-      - Ubuntu 22.04
-      - `3.10.16 <https://www.python.org/downloads/release/python-31016/>`_
+To find the right image tag, see the :ref:`JAX on ROCm installation
+documentation <rocm-install-on-linux:jax-docker-support>` for a list of
+available ``rocm/jax`` images.

 .. _key_rocm_libraries:

--- a/docs/compatibility/ml-compatibility/pytorch-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/pytorch-compatibility.rst
@@ -89,141 +89,13 @@ For more use cases and recommendations, see `ROCm PyTorch blog posts <https://ro
 Docker image compatibility
 ================================================================================

-.. |docker-icon| raw:: html
+AMD provides preconfigured Docker images with PyTorch and the ROCm backend.
+These images are published on `Docker Hub <https://hub.docker.com/r/rocm/pytorch>`__ and are the
+recommended way to get started with deep learning with PyTorch on ROCm.

-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes `PyTorch images <https://hub.docker.com/r/rocm/pytorch>`__
-with ROCm backends on Docker Hub. The following Docker image tags and associated
-inventories were tested on `ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__.
-Click |docker-icon| to view the image on Docker Hub.
-
-.. list-table:: PyTorch Docker image components
-    :header-rows: 1
-    :class: docker-image-compatibility
-
-    * - Docker
-      - PyTorch
-      - Ubuntu
-      - Python
-      - Apex
-      - torchvision
-      - TensorBoard
-      - MAGMA
-      - UCX
-      - OMPI
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-6a287591500b4048a9556c1ecc92bc411fd3d552f6c8233bc399f18eb803e8d6"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.6.0 <https://github.com/ROCm/pytorch/tree/release/2.6>`__
-      - 24.04
-      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
-      - `1.6.0 <https://github.com/ROCm/apex/tree/release/1.6.0>`__
-      - `0.21.0 <https://github.com/pytorch/vision/tree/v0.21.0>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
-      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.6.0/images/sha256-06b967629ba6657709f04169832cd769a11e6b491e8b1394c361d42d7a0c8b43"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.6.0 <https://github.com/ROCm/pytorch/tree/release/2.6>`__
-      - 22.04
-      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `1.6.0 <https://github.com/ROCm/apex/tree/release/1.6.0>`__
-      - `0.21.0 <https://github.com/pytorch/vision/tree/v0.21.0>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
-      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.5.1/images/sha256-62022414217ef6de33ac5b1341e57db8a48e8573fa2ace12d48aa5edd4b99ef0"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
-      - 24.04
-      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
-      - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
-      - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.10.0>`__
-      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.11_pytorch_release_2.5.1/images/sha256-469a7f74fc149aff31797e011ee41978f6a190adc69fa423b3c6a718a77bd985"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
-      - 22.04
-      - `3.11 <https://www.python.org/downloads/release/python-31113/>`__
-      - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
-      - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
-      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.5.1/images/sha256-37f41a1cd94019688669a1b20d33ea74156e0c129ef6b8270076ef214a6a1a2c"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.5.1 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
-      - 22.04
-      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `1.5.0 <https://github.com/ROCm/apex/tree/release/1.5.0>`__
-      - `0.20.1 <https://github.com/pytorch/vision/tree/v0.20.1>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
-      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-60824ba83dc1b9d94164925af1f81c0235c105dd555091ec04c57e05177ead1b"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`__
-      - 24.04
-      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
-      - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`__
-      - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
-      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-fe944fe083312f901be6891ab4d3ffebf2eaf2cf4f5f0f435ef0b76ec714fabd"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.4.1 <https://github.com/ROCm/pytorch/tree/release/2.4>`__
-      - 22.04
-      - `3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `1.4.0 <https://github.com/ROCm/apex/tree/release/1.4.0>`__
-      - `0.19.0 <https://github.com/pytorch/vision/tree/v0.19.0>`__
-      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.12.1~rc2-1 <https://github.com/openucx/ucx/tree/v1.12.1>`__
-      - `4.1.2-2ubuntu1 <https://github.com/open-mpi/ompi/tree/v4.1.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.2_ubuntu24.04_py3.12_pytorch_release_2.3.0/images/sha256-1d59251c47170c5b8960d1172a4dbe52f5793d8966edd778f168eaf32d56661a"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`__
-      - 24.04
-      - `3.12 <https://www.python.org/downloads/release/python-31210/>`__
-      - `1.3.0 <https://github.com/ROCm/apex/tree/release/1.3.0>`__
-      - `0.18.0 <https://github.com/pytorch/vision/tree/v0.18.0>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`__
-      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.16.0+ds-5ubuntu1 <https://github.com/openucx/ucx/tree/v1.16.0>`__
-      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
+To find the right image tag, see the :ref:`PyTorch on ROCm installation
+documentation <rocm-install-on-linux:pytorch-docker-support>` for a list of
+available ``rocm/pytorch`` images.

 Key ROCm libraries for PyTorch
 ================================================================================
--- a/docs/compatibility/ml-compatibility/tensorflow-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/tensorflow-compatibility.rst
@@ -47,80 +47,15 @@ fixes, updates, and support for the latest ROCM versions.
 .. _tensorflow-docker-compat:

 Docker image compatibility
-===============================================================================
+================================================================================

-.. |docker-icon| raw:: html
+AMD provides preconfigured Docker images with TensorFlow and the ROCm backend.
+These images are published on `Docker Hub <https://hub.docker.com/r/rocm/tensorflow>`__ and are the
+recommended way to get started with deep learning with TensorFlow on ROCm.

-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes ready-made `TensorFlow images
-<https://hub.docker.com/r/rocm/tensorflow>`__ with ROCm backends on
-Docker Hub. The following Docker image tags and associated inventories are
-validated for `ROCm 6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__. Click
-the |docker-icon| icon to view the image on Docker Hub.
-
-.. list-table:: TensorFlow Docker image components
-    :header-rows: 1
-
-    * - Docker image
-      - TensorFlow
-      - Ubuntu
-      - Python
-      - TensorBoard
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.18-dev/images/sha256-96754ce2d30f729e19b497279915b5212ba33d5e408e7e5dd3f2304d87e3441e"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/>`__
-      - 24.04
-      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
-      - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.18-dev/images/sha256-fa741508d383858e86985a9efac85174529127408102558ae2e3a4ac894eea1e"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/>`__
-      - 22.04
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `TensorBoard 2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.17-dev/images/sha256-3a0aef09f2a8833c2b64b85874dd9449ffc2ad257351857338ff5b706c03a418"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/>`__
-      - 24.04
-      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
-      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.17-dev/images/sha256-bc7341a41ebe7ab261aa100732874507c452421ef733e408ac4f05ed453b0bc5"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/>`__
-      - 22.04
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.12-tf2.16-dev/images/sha256-4841a8df7c340dab79bf9362dad687797649a00d594e0832eb83ea6880a40d3b"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/>`__
-      - 24.04
-      - `Python 3.12 <https://www.python.org/downloads/release/python-31210/>`__
-      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.2-py3.10-tf2.16-dev/images/sha256-883fa95aba960c58a3e46fceaa18f03ede2c7df89b8e9fd603ab2d47e0852897"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.2/>`__
-      - 22.04
-      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
-      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
+To find the right image tag, see the :ref:`TensorFlow on ROCm installation
+documentation <rocm-install-on-linux:tensorflow-docker-support>` for a list of
+available ``rocm/tensorflow`` images.


 Critical ROCm libraries for TensorFlow
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -89,15 +89,15 @@ project = "ROCm Documentation"
 project_path = os.path.abspath(".").replace("\\", "/")
 author = "Advanced Micro Devices, Inc."
 copyright = "Copyright (c) 2025 Advanced Micro Devices, Inc. All rights reserved."
-version = "7.0.0"
-release = "7.0.0"
+version = "7.0.1"
+release = "7.0.1"
 setting_all_article_info = True
 all_article_info_os = ["linux", "windows"]
 all_article_info_author = ""

 # pages with specific settings
 article_pages = [
-    {"file": "about/release-notes", "os": ["linux"], "date": "2025-09-16"},
+    {"file": "about/release-notes", "os": ["linux"], "date": "2025-09-17"},
    {"file": "release/changelog", "os": ["linux"],},
    {"file": "compatibility/compatibility-matrix", "os": ["linux"]},
    {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
@@ -127,7 +127,9 @@ article_pages = [
    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.4", "os": ["linux"]},
    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.5", "os": ["linux"]},
    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.6", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.7", "os": ["linux"]},
    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-primus-migration-guide", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.7", "os": ["linux"]},
    {"file": "how-to/rocm-for-ai/training/benchmark-docker/primus-megatron", "os": ["linux"]},
    {"file": "how-to/rocm-for-ai/training/benchmark-docker/pytorch-training", "os": ["linux"]},
    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-history", "os": ["linux"]},
--- a/docs/data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml
@@ -1,12 +1,4 @@
 dockers:
-  - 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
  - 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:
@@ -15,6 +7,14 @@ dockers:
      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
--- a/docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
@@ -1,13 +1,12 @@
 dockers:
-  - pull_tag: rocm/megatron-lm:v25.7_py310
-    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.7_py310/images/sha256-6189df849feeeee3ae31bb1e97aef5006d69d2b90c134e97708c19632e20ab5a
+  - 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: 6.4.2
-      Primus: v0.1.0-rc1
+      ROCm: 6.4.3
      PyTorch: 2.8.0a0+gitd06a406
      Python: "3.10"
-      Transformer Engine: 2.1.0.dev0+ba586519
-      hipBLASLt: 37ba1d36
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      hipBLASLt: d1b517fc7a
      Triton: 3.3.0
      RCCL: 2.22.3
 model_groups:
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.7-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.7-benchmark-models.yaml
@@ -0,0 +1,49 @@
+dockers:
+  - pull_tag: rocm/megatron-lm:v25.7_py310
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.7_py310/images/sha256-6189df849feeeee3ae31bb1e97aef5006d69d2b90c134e97708c19632e20ab5a
+    components:
+      ROCm: 6.4.2
+      Primus: v0.1.0-rc1
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: "3.10"
+      Transformer Engine: 2.1.0.dev0+ba586519
+      hipBLASLt: 37ba1d36
+      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
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.7-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.7-benchmark-models.yaml
@@ -0,0 +1,58 @@
+dockers:
+  - pull_tag: rocm/megatron-lm:v25.7_py310
+    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.7_py310/images/sha256-6189df849feeeee3ae31bb1e97aef5006d69d2b90c134e97708c19632e20ab5a
+    components:
+      ROCm: 6.4.2
+      Primus: v0.1.0-rc1
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: "3.10"
+      Transformer Engine: 2.1.0.dev0+ba586519
+      hipBLASLt: 37ba1d36
+      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
--- a/docs/data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
@@ -1,13 +1,13 @@
 dockers:
-  - pull_tag: rocm/megatron-lm:v25.7_py310
-    docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.7_py310/images/sha256-6189df849feeeee3ae31bb1e97aef5006d69d2b90c134e97708c19632e20ab5a
+  - 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: 6.4.2
-      Primus: v0.1.0-rc1
+      ROCm: 6.4.3
+      Primus: 927a717
      PyTorch: 2.8.0a0+gitd06a406
      Python: "3.10"
-      Transformer Engine: 2.1.0.dev0+ba586519
-      hipBLASLt: 37ba1d36
+      Transformer Engine: 2.2.0.dev0+54dd2bdc
+      hipBLASLt: d1b517fc7a
      Triton: 3.3.0
      RCCL: 2.22.3
 model_groups:
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250521.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250521.rst
@@ -120,7 +120,7 @@ vLLM inference performance testing
   ==================================

   For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
-   see the developer's guide at `<https://github.com/ROCm/vllm/blob/main/docs/dev-docker/README.md>`__.
+   see the developer's guide at `<https://github.com/ROCm/vllm/blob/7bb0618b1fe725b7d4fad9e525aa44da12c94a8b/docs/dev-docker/README.md>`__.

   System validation
   =================
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
@@ -111,7 +111,7 @@ Build the Docker image
 ----------------------

 Get the Dockerfile located in
-`<https://github.com/ROCm/MAD/blob/develop/docker/sglang_dissag_inference.ubuntu.amd.Dockerfile>`__.
+`<https://github.com/ROCm/MAD/blob/develop/docker/sglang_disagg_inference.ubuntu.amd.Dockerfile>`__.
 It uses `lmsysorg/sglang:v0.5.2rc1-rocm700-mi30x
 <https://hub.docker.com/layers/lmsysorg/sglang/v0.4.9.post1-rocm630/images/sha256-2f6b1748e4bcc70717875a7da76c87795fd8aa46a9646e08d38aa7232fc78538>`__
 as the base Docker image and installs the necessary components for Mooncake, etcd, and Mellanox network
@@ -128,7 +128,7 @@ drivers.
 Benchmarking
 ============

-The `<https://github.com/ROCm/MAD/tree/develop/scripts/sglang_dissag>`__
+The `<https://github.com/ROCm/MAD/tree/develop/scripts/sglang_disagg>`__
 repository contains scripts to launch SGLang inference with prefill/decode
 disaggregation via Mooncake for supported models.

--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
@@ -230,7 +230,7 @@ system's configuration.
            .. seealso::

               For more information on configuration, see the `config files
-               <https://github.com/ROCm/MAD-private/tree/develop/scripts/vllm/configs>`__
+               <https://github.com/ROCm/MAD/tree/develop/scripts/vllm/configs>`__
               in the MAD repository. Refer to the `vLLM engine <https://docs.vllm.ai/en/latest/configuration/engine_args.html#engineargs>`__
               for descriptions of available configuration options
               and `Benchmarking vLLM <https://github.com/vllm-project/vllm/blob/main/benchmarks/README.md>`__ for
@@ -352,6 +352,9 @@ system's configuration.

            .. note::

+               For improved performance with certain Mixture of Experts models, such as Mixtral 8x22B,
+               try adding ``export VLLM_ROCM_USE_AITER=1`` to your commands.
+
               If you encounter the following error, pass your access-authorized Hugging
               Face token to the gated models.

--- a/docs/how-to/rocm-for-ai/system-health-check.rst
+++ b/docs/how-to/rocm-for-ai/system-health-check.rst
@@ -31,7 +31,7 @@ installed, run the following command:
   sudo apt install rocm-validation-suite

 See the `ROCm Validation Suite installation instructions <https://rocm.docs.amd.com/projects/ROCmValidationSuite/en/latest/install/installation.html>`_,
-and `System validation tests <https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/system-validation.html#system-validation-tests>`_
+and `System validation tests <https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/system-validation.html>`_
 in the Instinct documentation for more detailed instructions.

 Benchmark, stress, and qualification tests
@@ -41,7 +41,7 @@ The GPU stress test runs various GEMM computations as workloads to stress the GP
 meets the configured target GFLOPS.

 Run the benchmark, stress, and qualification tests included with RVS. See the `Benchmark, stress, qualification
-<https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/system-validation.html#benchmark-stress-qualification>`_
+<https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/system-validation.html#benchmark-stress-qualification>`_
 section of the Instinct documentation for usage instructions.

 BabelStream test
@@ -53,7 +53,7 @@ BabelStream tests are included with the RVS package as part of the `BABEL module
 <https://rocm.docs.amd.com/projects/ROCmValidationSuite/en/latest/conceptual/rvs-modules.html#babel-benchmark-test-babel-module>`_.

 For more information, see `Performance benchmarking
-<https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/performance-bench.html#babelstream-benchmarking-results>`_
+<https://instinct.docs.amd.com/projects/system-acceptance/en/latest/common/system-validation.html#babelstream>`_
 in the Instinct documentation.

 RCCL tests
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
@@ -47,10 +47,6 @@ It includes the following software components:
            ``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.
-
-            The provided multi-node training scripts in this documentation are
-            not currently supported with JAX 0.6.0. For multi-node training, use the JAX 0.5.0
-            Docker image.
         {% endif %}

      {% endfor %}
@@ -361,12 +357,6 @@ benchmark results:

                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8

-               .. important::
-
-                  Quantized training is not supported with the JAX 0.6.0 Docker image; support
-                  will be added in a future release. For quantized training, use the JAX 0.5.0
-                  Docker image: ``rocm/jax-training:maxtext-v25.7``.
-
            {% endif %}
            {% if model.multinode_training_script and "multi-node" in model.doc_options %}
            .. rubric:: Multi-node training
@@ -383,7 +373,7 @@ benchmark results:
               for more details on downloading the Llama models before running the
               benchmark.

-            2. To run multi-node training for {{ model.model }}, 
+            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.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.5.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.5.rst
@@ -213,16 +213,14 @@ Getting started

 The following examples demonstrate how to get started with single node
 and multi-node training using the benchmarking scripts provided at
-`<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__.
+`<https://github.com/ROCm/maxtext/>`__.

 .. important::

   The provided scripts launch a Docker container and execute a benchmark. Ensure you run these commands outside of any existing Docker container.

 Before running any benchmarks, ensure the ``$HF_HOME`` environment variable is
-set correctly and points to your Hugging Face cache directory. Refer to the
-README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/>`__
-for more detailed instructions.
+set correctly and points to your Hugging Face cache directory.

 Single node training benchmarking examples
 ------------------------------------------
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-history.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-history.rst
@@ -16,12 +16,22 @@ previous releases of the ``ROCm/megatron-lm`` Docker image on `Docker Hub <https
     - Components
     - Resources

-   * - v25.7 (latest)
+   * - v25.8 (latest)
     - 
-       * ROCm 
-       * PyTorch 
+       * ROCm 6.4.3
+       * PyTorch 2.8.0a0+gitd06a406
     - 
-       * :doc:`Documentation <../megatron-lm>`
+       * :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>`__
+
+   * - 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
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-primus-migration-guide.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-primus-migration-guide.rst
@@ -1,12 +1,12 @@
 :orphan:

-**********************************************************************
-Migrating workloads to Primus (Megatron-Core backend) from Megatron-LM
-**********************************************************************
+*****************************************************************
+Migrating workloads to Primus (Megatron backend) from Megatron-LM
+*****************************************************************

 Primus supports Megatron-Core as backend optimization library,
 replacing ROCm Megatron-LM. This document outlines the steps to migrate
-workload from ROCm Megatron-LM to Primus with the Megatron-Core backend.
+workload from ROCm Megatron-LM to Primus with the Megatron backend.

 Model architecture
 ==================
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.7.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.7.rst
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.7.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.7.rst
@@ -0,0 +1,604 @@
+: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 accelerators using a modular, reproducible configuration paradigm.
+Primus is backend-agnostic and supports multiple training engines -- including Megatron.
+
+.. note::
+
+   Primus with the Megatron backend is intended to replace ROCm
+   Megatron-LM in this Dockerized training environment. 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 accelerators
+containing essential components for Primus and Megatron-LM.
+
+.. 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-v25.7-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-v257:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on AMD Instinct MI300X series accelerators.
+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-v25.7-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-v257:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.7-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 accelerators with the ``{{ docker.pull_tag }}`` image.
+
+   .. _amd-primus-megatron-lm-requirements-v257:
+
+   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 release tag ``v0.1.0-rc1`` of the `Primus
+<https://github.com/AMD-AIG-AIMA/Primus/tree/v0.1.0-rc1>`__ repository.
+
+.. _amd-primus-megatron-lm-environment-setup-v257:
+
+Configuration
+=============
+
+Primus defines a training configuration in YAML for each model in
+`examples/megatron/configs <https://github.com/AMD-AIG-AIMA/Primus/tree/v0.1.0-rc1/examples/megatron/configs>`__.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.7-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-v257:
+
+Tokenizer
+---------
+
+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-AIG-AIMA/Primus/tree/v0.1.0-rc1/primus/configs/models/megatron/llama3.1_8B.yaml>`__
+definition. As such, you need to 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>
+
+.. _amd-primus-megatron-lm-run-training-v257:
+
+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.
+
+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
+
+Once setup is complete, run the appropriate training command.
+
+.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.3-70b
+
+   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
+
+   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
+
+   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 \
+          --no_fp8_weight_transpose_cache true
+
+   .. 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
+
+   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
+
+   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
+
+   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
+
+   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
+
+   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
+
+   To run training on a single node for Mixtral 8x7B (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
+
+   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
+
+   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
+
+Multi-node training examples
+----------------------------
+
+To run training on multiple nodes, you can use the
+`run_slurm_pretrain.sh <https://github.com/AMD-AIG-AIMA/Primus/tree/v0.1.0-rc1/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-v25.7-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 4 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --no_fp8_weight_transpose_cache true \
+          --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 4 \
+          --global_batch_size 256 \
+          --recompute_num_layers 80 \
+          --no_fp8_weight_transpose_cache true \
+          --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 10 \
+          --global_batch_size 640 \
+          --recompute_num_layers 80 \
+          --no_fp8_weight_transpose_cache true \
+          --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 8 \
+          --global_batch_size 512 \
+          --recompute_num_layers 80 \
+          --no_fp8_weight_transpose_cache true \
+          --fp8 hybrid
+
+.. _amd-primus-megatron-lm-benchmark-test-vars-v257:
+
+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.
+
+Previous versions
+=================
+
+See :doc:`megatron-lm-history` to find documentation for previous releases
+of the ``ROCm/megatron-lm`` Docker image.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
@@ -2,24 +2,25 @@
   :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-Core
-**********************************************
+********************************************
+Training a model with Primus and Megatron-LM
+********************************************

-`Primus <https://github.com/AMD-AIG-AIMA/Primus>`__ is a unified and flexible
+`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.
-Primus is backend-agnostic and supports multiple training engines -- including Megatron-Core.
+Primus is backend-agnostic and supports multiple training engines -- including Megatron.

 .. note::

-   Primus with the Megatron-Core backend is intended to replace ROCm
-   Megatron-LM in this Dockerized training environment. To learn how to migrate
-   workloads from Megatron-LM to Primus with Megatron-Core, see
-   :doc:`previous-versions/megatron-lm-primus-migration-guide`.
+   Primus with Megatron supersedes the :doc:`ROCm Megatron-LM training <megatron-lm>` workflow.
+   To learn how to migrate workloads from Megatron-LM to Primus with Megatron,
+   see :doc:`previous-versions/megatron-lm-primus-migration-guide`.

 For ease of use, AMD provides a ready-to-use Docker image for MI300 series accelerators
-containing essential components for Primus and Megatron-Core.
+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::

@@ -151,8 +152,8 @@ system's configuration.
      docker start primus_training_env
      docker exec -it primus_training_env bash

-The Docker container hosts verified release tag ``v0.1.0-rc1`` of the `Primus
-<https://github.com/AMD-AIG-AIMA/Primus/tree/v0.1.0-rc1>`__ repository.
+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:

@@ -160,7 +161,7 @@ Configuration
 =============

 Primus defines a training configuration in YAML for each model in
-`examples/megatron/configs <https://github.com/AMD-AIG-AIMA/Primus/tree/v0.1.0-rc1/examples/megatron/configs>`__.
+`examples/megatron/configs <https://github.com/AMD-AGI/Primus/tree/927a71702784347a311ca48fd45f0f308c6ef6dd/examples/megatron/configs>`__.

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

@@ -205,11 +206,7 @@ You can use either mock data or real data for training.
 Tokenizer
 ---------

-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-AIG-AIMA/Primus/tree/v0.1.0-rc1/primus/configs/models/megatron/llama3.1_8B.yaml>`__
-definition. As such, you need to set the ``HF_TOKEN`` environment variable with
+Set the ``HF_TOKEN`` environment variable with
 right permissions to access the tokenizer for each model.

 .. code-block:: bash
@@ -217,6 +214,14 @@ right permissions to access the tokenizer for each model.
   # 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
@@ -237,10 +242,12 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
   export HSA_NO_SCRATCH_RECLAIM=1
   export NVTE_CK_USES_BWD_V3=1

-Once setup is complete, run the appropriate training command.
-
 .. 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
@@ -253,6 +260,10 @@ Once setup is complete, run the appropriate training command.

 .. 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
@@ -271,6 +282,10 @@ Once setup is complete, run the appropriate training command.

 .. 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
@@ -287,8 +302,7 @@ Once setup is complete, run the appropriate training command.
      bash ./examples/run_pretrain.sh \
          --train_iters 50 \
          --num_layers 40 \
-          --fp8 hybrid \
-          --no_fp8_weight_transpose_cache true
+          --fp8 hybrid

   .. note::

@@ -296,6 +310,10 @@ Once setup is complete, run the appropriate training command.

 .. 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
@@ -314,6 +332,10 @@ Once setup is complete, run the appropriate training command.

 .. 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
@@ -323,6 +345,10 @@ Once setup is complete, run the appropriate training command.

 .. 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:

@@ -336,6 +362,10 @@ Once setup is complete, run the appropriate training command.

 .. 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:

@@ -348,6 +378,10 @@ Once setup is complete, run the appropriate training command.

 .. 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:

@@ -358,7 +392,11 @@ Once setup is complete, run the appropriate training command.

 .. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x22b-proxy

-   To run training on a single node for Mixtral 8x7B (MoE with expert parallel) with 4-layer 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
@@ -373,6 +411,10 @@ Once setup is complete, run the appropriate training command.

 .. 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:

@@ -392,6 +434,10 @@ Once setup is complete, run the appropriate training command.

 .. 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
@@ -403,7 +449,7 @@ Multi-node training examples
 ----------------------------

 To run training on multiple nodes, you can use the
-`run_slurm_pretrain.sh <https://github.com/AMD-AIG-AIMA/Primus/tree/v0.1.0-rc1/examples/run_slurm_pretrain.sh>`__
+`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/primus-megatron-benchmark-models.yaml
@@ -438,10 +484,9 @@ to launch the multi-node workload. Use the following steps to setup your environ

      NNODES=8 EXP=examples/megatron/configs/llama3.3_70B-pretrain.yaml \
      bash examples/run_slurm_pretrain.sh \
-          --micro_batch_size 4 \
+          --micro_batch_size 1 \
          --global_batch_size 256 \
          --recompute_num_layers 80 \
-          --no_fp8_weight_transpose_cache true \
          --fp8 hybrid

   To train Llama 3.3 70B BF16 on 8 nodes, run:
@@ -474,10 +519,9 @@ to launch the multi-node workload. Use the following steps to setup your environ

      NNODES=8 EXP=examples/megatron/configs/llama3.1_70B-pretrain.yaml \
      bash examples/run_slurm_pretrain.sh \
-          --micro_batch_size 4 \
+          --micro_batch_size 1 \
          --global_batch_size 256 \
          --recompute_num_layers 80 \
-          --no_fp8_weight_transpose_cache true \
          --fp8 hybrid

   To train Llama 3.1 70B BF16 on 8 nodes, run:
@@ -507,10 +551,9 @@ to launch the multi-node workload. Use the following steps to setup your environ

      NNODES=8 EXP=examples/megatron/configs/llama2_70B-pretrain.yaml \
      bash examples/run_slurm_pretrain.sh \
-          --micro_batch_size 10 \
-          --global_batch_size 640 \
+          --micro_batch_size 2 \
+          --global_batch_size 256 \
          --recompute_num_layers 80 \
-          --no_fp8_weight_transpose_cache true \
          --fp8 hybrid

   To train Llama 2 70B BF16 on 8 nodes, run:
@@ -542,10 +585,9 @@ to launch the multi-node workload. Use the following steps to setup your environ

      NNODES=8 EXP=examples/megatron/configs/qwen2.5_72B-pretrain.yaml \
      bash examples/run_slurm_pretrain.sh \
-          --micro_batch_size 8 \
-          --global_batch_size 512 \
+          --micro_batch_size 4 \
+          --global_batch_size 256 \
          --recompute_num_layers 80 \
-          --no_fp8_weight_transpose_cache true \
          --fp8 hybrid

 .. _amd-primus-megatron-lm-benchmark-test-vars:
@@ -590,6 +632,18 @@ recompute_granularity
 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 accelerators, 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
 =================

@@ -598,5 +652,4 @@ 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. For instructions on using ROCm Megatron-LM, see the
-:doc:`megatron-lm` document.
+available; see the :doc:`megatron-lm` documentation.
--- a/docs/index.md
+++ b/docs/index.md
@@ -16,7 +16,7 @@ ROCm supports multiple programming languages and programming interfaces such as
 {doc}`HIP (Heterogeneous-Compute Interface for Portability)<hip:index>`, OpenCL,
 and OpenMP, as explained in the [Programming guide](./how-to/programming_guide.rst).

-If you're using AMD Radeon™ PRO or Radeon GPUs in a workstation setting with a display connected, review {doc}`Radeon-specific ROCm documentation<radeon:index>`.
+If you're using AMD Radeon GPUs or Ryzen APUs in a workstation setting with a display connected, review [ROCm on Radeon and Ryzen documentation](https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/index.html).

 ROCm documentation is organized into the following categories:

--- a/docs/release/versions.md
+++ b/docs/release/versions.md
@@ -10,6 +10,7 @@

 | Version | Release date |
 | ------- | ------------ |
+| [7.0.1](https://rocm.docs.amd.com/en/docs-7.0.1/) | September 17, 2025 |
 | [7.0.0](https://rocm.docs.amd.com/en/docs-7.0.0/) | September 16, 2025 |
 | [6.4.3](https://rocm.docs.amd.com/en/docs-6.4.3/) | August 7, 2025 |
 | [6.4.2](https://rocm.docs.amd.com/en/docs-6.4.2/) | July 21, 2025 |
--- a/docs/sphinx/_toc.yml.in
+++ b/docs/sphinx/_toc.yml.in
@@ -23,8 +23,8 @@ subtrees:
    title: ROCm on Linux
  - url: https://rocm.docs.amd.com/projects/install-on-windows/en/latest/
    title: HIP SDK on Windows
-  - url: https://rocm.docs.amd.com/projects/radeon/en/latest/index.html
-    title: ROCm on Radeon GPUs
+  - url: https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/index.html
+    title: ROCm on Radeon and Ryzen
  - file: how-to/deep-learning-rocm.md
    title: Deep learning frameworks
    subtrees:
--- a/tools/rocm-build/rocm-7.0.1.xml
+++ b/tools/rocm-build/rocm-7.0.1.xml
@@ -0,0 +1,70 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest>
+    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
+    <default revision="refs/tags/rocm-7.0.1"
+     remote="rocm-org"
+     sync-c="true"
+     sync-j="4" />
+<!--list of projects for ROCm-->
+    <project name="ROCm" revision="roc-7.0.x" />
+    <project name="ROCK-Kernel-Driver" />
+    <project name="ROCR-Runtime" />
+    <project name="amdsmi" />
+    <project name="aqlprofile" />
+    <project name="rdc" />
+    <project name="rocm_bandwidth_test" />
+    <project name="rocm_smi_lib" />
+    <project name="rocm-core" />
+    <project name="rocm-examples" />
+    <project name="rocminfo" />
+    <project name="rocprofiler" />
+    <project name="rocprofiler-register" />
+    <project name="rocprofiler-sdk" />
+    <project name="rocprofiler-compute" />
+    <project name="rocprofiler-systems" />
+    <project name="roctracer" />
+<!--HIP Projects-->
+    <project name="hip" />
+    <project name="hip-tests" />
+    <project name="HIPIFY" />
+    <project name="clr" />
+    <project name="hipother" />
+<!-- The following projects are all associated with the AMDGPU LLVM compiler -->
+    <project name="half" />
+    <project name="llvm-project" />
+    <project name="spirv-llvm-translator" />
+<!-- gdb projects -->
+    <project name="ROCdbgapi" />
+    <project name="ROCgdb" />
+    <project name="rocr_debug_agent" />
+<!-- ROCm Libraries -->
+    <project groups="mathlibs" name="AMDMIGraphX" />
+    <project groups="mathlibs" name="MIVisionX" />
+    <project groups="mathlibs" name="ROCmValidationSuite" />
+    <project groups="mathlibs" name="composable_kernel" />
+    <project groups="mathlibs" name="hipSOLVER" />
+    <project groups="mathlibs" name="hipTensor" />
+    <project groups="mathlibs" name="hipfort" />
+    <project groups="mathlibs" name="rccl" />
+    <project groups="mathlibs" name="rocAL" />
+    <project groups="mathlibs" name="rocALUTION" />
+    <project groups="mathlibs" name="rocDecode" />
+    <project groups="mathlibs" name="rocJPEG" />
+    <!-- The following components have been migrated to rocm-libraries:
+        hipBLAS-common hipBLAS hipBLASLt hipCUB
+        hipFFT hipRAND hipSPARSE hipSPARSELt
+        MIOpen rocBLAS rocFFT rocPRIM rocRAND
+        rocSPARSE rocThrust Tensile -->
+    <project groups="mathlibs" name="rocm-libraries" />
+    <project groups="mathlibs" name="rocPyDecode" />
+    <project groups="mathlibs" name="rocSHMEM" />
+    <project groups="mathlibs" name="rocSOLVER" />
+    <project groups="mathlibs" name="rocWMMA" />
+    <project groups="mathlibs" name="rocm-cmake" />
+    <project groups="mathlibs" name="rpp" />
+    <project groups="mathlibs" name="TransferBench" />
+<!-- Projects for OpenMP-Extras -->
+    <project name="aomp" path="openmp-extras/aomp" />
+    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
+    <project name="flang" path="openmp-extras/flang" />
+</manifest>
Author	SHA1	Message	Date
Ibrahim Wani	de7bd42be9	Fix almalinux dependency issue	2025-09-24 20:31:03 +00:00
Ibrahim Wani	7edefe9716	Fix almalinux dependency; get publish test results step working	2025-09-24 20:11:49 +00:00
Ibrahim Wani	c78a4f0def	Dependency fix in origami.yml	2025-09-24 19:54:23 +00:00
Ibrahim Wani	c319bd7128	Add origami yaml tests	2025-09-24 19:31:34 +00:00
Pratik Basyal	6cf6b34b2e	TOC for ROCm on Radeon and Ryzen updated (#5429 )	2025-09-24 13:58:26 -05:00
Pratik Basyal	c35a0a121a	ROR link and text updated (#5426 )	2025-09-24 13:28:13 -05:00
amd-hsivasun	412e383654	[Ex CI] Update pipeline Id for rocprofiler-sdk	2025-09-23 15:56:49 -04:00
Pratik Basyal	39f6fc187d	rocm-core version updated (#5418 )	2025-09-23 15:49:33 -04:00
amd-hsivasun	05b480fb28	Update rocm-examples.yml	2025-09-23 12:10:11 -04:00
amd-hsivasun	4fa44d90db	Updated dependencies-cmake-custom.yml default ver	2025-09-23 12:10:11 -04:00
amd-hsivasun	c9ef13d823	Added Custom Cmake to testjobs	2025-09-23 12:10:11 -04:00
amd-hsivasun	f02172050b	Added rocWMMA dependency	2025-09-23 12:10:11 -04:00
amd-hsivasun	154dbe297a	Updated File to take custom cmake version	2025-09-23 12:10:11 -04:00
amd-hsivasun	993a0a4fd4	[Ex CI] Update cmake	2025-09-23 12:10:11 -04:00
amd-hsivasun	c03662f410	[Ex CI] Update pipeline Id for origami to monorepo	2025-09-23 11:17:39 -04:00
Peter Park	442d7e4750	Add env var note to vllm.rst for MoE models and fix links in docs (#5415 ) * docs(vllm.rst): add performance note for MoE models * docs: fix links update vllm readme link 20250521 fix links	2025-09-22 15:58:43 -04:00
Pratik Basyal	a09a8f517e	PLDM version for 7.0.0 updated (#5412 )	2025-09-22 11:14:07 -04:00
Pratik Basyal	0bbaab645d	rocSHMEM and ROCprofiler-SDK highlight update (#5408 ) (#5409 ) * rocSHMEM and ROCprofiler-SDK highlight update (#5408) * Update RELEASE.md	2025-09-22 10:26:12 -04:00
Ibrahim Wani	4b80405e2e	Add set -e to exit when test fails (#5398 )	2025-09-19 10:43:35 -06:00
Peter Park	d92e5b6c12	Update Primus Megatron doc v25.8 (#5396 ) * megatron: update previous versions list update wording * megatron: update rst and yaml update primus repo link update mig guide * update headings and anchors * megatron: update doc * update docker hub urls	2025-09-19 08:09:21 -04:00
Pratik Basyal	91fce2e134	rocpd highlight updated (#5393 )	2025-09-18 19:00:36 -04:00
Peter Park	27d53cf082	Remove duplicate ML FW docker image support table (#5389 )	2025-09-18 17:06:53 -04:00
Pratik Basyal	bc084246be	Reference to AMD GPU Driver 30.10 release notes updated (#5380 )	2025-09-18 13:34:46 -05:00
Peter Park	9827ba7ff2	docs: MaxText v25.7 patch update (#5372 ) * remove jax 0.6.0 nanoo fp8 caveat note * reorder maxtext docker images in data sheet	2025-09-17 16:25:46 -04:00
Pratik Basyal	bafda50153	Link updated (#5369 )	2025-09-17 15:03:29 -05:00
Pratik Basyal	cae65c6c43	Link reset (#5368 )	2025-09-17 13:49:04 -05:00
pbhandar-amd	6a66167486	Merge pull request #5367 from ROCm/amd/pbhandar/rocm_701_internal_to_external_sync Sync internal to external develop branch for ROCm 7.0.1	2025-09-17 14:26:03 -04:00
Parag Bhandari	0f3543d6e8	Merge branch 'develop-internal' into develop	2025-09-17 14:15:05 -04:00
pbhandar-amd	678691c3d7	Merge pull request #563 from ROCm/amd/pbhandar/rocm_701_external_to_internal_sync Sync external develop into internal develop for ROCm 7.0.1	2025-09-17 14:14:40 -04:00
pbhandar-amd	5cb3debed9	Merge branch 'develop' into amd/pbhandar/rocm_701_external_to_internal_sync	2025-09-17 14:09:59 -04:00
pbhandar-amd	dd5d710727	Update versions.md	2025-09-17 14:09:49 -04:00
pbhandar-amd	eca1ecde92	Merge branch 'develop' into amd/pbhandar/rocm_701_external_to_internal_sync	2025-09-17 13:48:36 -04:00
pbhandar-amd	ed1e414710	Update versions.md	2025-09-17 13:42:20 -04:00
Pratik Basyal	20c90fc406	Footnote updated (#564 )	2025-09-17 12:24:03 -05:00
JeniferC99	6e39614b22	7.0.1 GA update (#5365 ) * Update default.xml - Change 7.0.0 to 7.0.1 * add rocm-7.0.1.xml	2025-09-17 13:18:01 -04:00
Pratik Basyal	f7873ac74e	Long cell in compatibility matrix updated 701 (#562 ) * Long cell updated * Long cell updated * Historical comaptibility updated	2025-09-17 11:57:35 -05:00
Parag Bhandari	a86fba556b	Merge branch 'develop' into develop-internal	2025-09-17 12:35:50 -04:00
Pratik Basyal	7603fed080	Release 7.0.1 demo release notes (#536 ) * Mono repo highlight added * Leo's feedback incorporated * Minor wording change * Randy's feedback incorp * Update for upcoming change * Minor feedback added * Ram's feedback incorporated * Reworded for clarity * ROCM 7.0.1 draft * Minor change * Release 7.0.0 notes appended * Heading order updated for 7.0.1 * 700 GA changes synced * Issue updated * Review feedback added * Conf file updated * Tensorflow change added * review feedback added * GPU depencency matrix updated * Compatibility updated * Minor change * New update note * AMD GPU Driver notes updated * Footnotes updated	2025-09-17 10:57:15 -05:00
randyh62	1c3dae75e1	Revert "Update RELEASE.md (#560 )" (#561 ) This reverts commit `f216b371a0`.	2025-09-16 13:02:13 -07:00
randyh62	f216b371a0	Update RELEASE.md (#560 ) Update llvm-project URL	2025-09-16 09:39:26 -07:00
Pratik Basyal	7316031fe6	7.0.0 Release notes update Batch 9 (#559 ) * Changelog synced * Compatibilty updated * Compatibilty update * Compiler highlight updated * wordlist updated	2025-09-16 07:03:32 -04:00