Add set -e to exit when test fails

* 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

.azuredevops/components/hipSPARSELt.yml

@@ -40,6 +40,7 @@ parameters:
     - gfortran
     - libgfortran5
     - libopenblas-dev
+    - liblapack-dev
 - name: pipModules
   type: object
   default:
@@ -125,10 +126,13 @@ jobs:
         aggregatePipeline: ${{ parameters.aggregatePipeline }}
         ${{ if parameters.triggerDownstreamJobs }}:
           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+  # NOTE: content between `---` is for transition support between old/new build systems
+  # and should be removed once transition is complete.
+  # -----------------------------
   # Build and install gtest and lapack
   # $(Pipeline.Workspace)/deps is a temporary folder for the build process
   # $(Pipeline.Workspace)/s/deps is part of the hipSPARSELt repo
-    - script: mkdir $(Pipeline.Workspace)/deps
+    - script: mkdir -p $(Pipeline.Workspace)/deps
       displayName: Create temp folder for external dependencies
   # hipSPARSELt already has a CMake script for external deps, so we can just run that
   # https://github.com/ROCm/hipSPARSELt/blob/develop/deps/CMakeLists.txt
@@ -144,22 +148,35 @@ jobs:
     - script: sudo make install
       displayName: Install hipSPARSELt external dependencies
       workingDirectory: $(Pipeline.Workspace)/deps
+  # -----------------------------
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         os: ${{ job.os }}
+        # NOTE: the following options are old build only 
+        # and can be removed after full transition to new build
+        # -DAMDGPU_TARGETS=${{ job.target }}
+        # -DCMAKE_Fortran_COMPILER=f95
+        # -DTensile_LOGIC=
+        # -DTensile_CPU_THREADS=
+        # -DTensile_LIBRARY_FORMAT=msgpack
+        # -DROCM_PATH=$(Agent.BuildDirectory)/rocm
+        # -DBUILD_CLIENTS_TESTS=ON
+        # -DBUILD_USE_LOCAL_TENSILE=OFF
         extraBuildFlags: >-
           -DCMAKE_BUILD_TYPE=Release
           -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
           -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
-          -DCMAKE_Fortran_COMPILER=f95
+          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
+          -DGPU_TARGETS=${{ job.target }}
           -DAMDGPU_TARGETS=${{ job.target }}
+          -DCMAKE_Fortran_COMPILER=f95
           -DTensile_LOGIC=
           -DTensile_CPU_THREADS=
           -DTensile_LIBRARY_FORMAT=msgpack
-          -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm"
           -DROCM_PATH=$(Agent.BuildDirectory)/rocm
           -DBUILD_CLIENTS_TESTS=ON
           -DBUILD_USE_LOCAL_TENSILE=OFF
+          -DHIPSPARSELT_ENABLE_FETCH=ON
           -GNinja
         ${{ if ne(parameters.sparseCheckoutDir, '') }}:
           cmakeSourceDir: $(Build.SourcesDirectory)/projects/hipsparselt

.azuredevops/components/origami.yml

@@ -207,6 +207,7 @@ jobs:
             downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
       - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
       - script: |
+          set -e
           export PYTHONPATH=$(Agent.BuildDirectory)/s/build/python:$PYTHONPATH
 
           echo "--- Running origami_test.py ---"

.wordlist.txt

@@ -72,6 +72,7 @@ CU
 CUDA
 CUs
 CXX
+CX
 Cavium
 CentOS
 ChatGPT
@@ -118,6 +119,8 @@ Dependabot
 Deprecations
 DevCap
 DirectX
+Disaggregated
+disaggregated
 Dockerfile
 Dockerized
 Doxygen
@@ -127,6 +130,7 @@ ENDPGM
 EPYC
 ESXi
 EoS
+etcd
 fas
 FBGEMM
 FIFOs
@@ -178,6 +182,7 @@ GPUs
 Graphbolt
 GraphSage
 GRBM
+GRE
 GenAI
 GenZ
 GitHub
@@ -301,6 +306,7 @@ MirroredStrategy
 Mixtral
 MosaicML
 MoEs
+Mooncake
 Mpops
 Multicore
 Multithreaded
@@ -445,6 +451,7 @@ SKU
 SKUs
 SLES
 SLURM
+Slurm
 SMEM
 SMFMA
 SMI
@@ -615,6 +622,7 @@ coalescable
 codename
 collater
 comgr
+compat
 completers
 composable
 concretization
@@ -776,6 +784,7 @@ lossy
 macOS
 matchers
 maxtext
+megablocks
 megatron
 microarchitecture
 migraphx
@@ -934,6 +943,7 @@ softmax
 spack
 spmm
 src
+stanford
 stochastically
 strided
 subcommand

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" />

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

@@ -1,15 +1,15 @@
-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"
       ,"RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
-      ,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
-      ,SLES 15 SP7,"SLES 15 SP7, SP6","SLES 15 SP7, SP6",SLES 15 SP6,SLES 15 SP6,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
+      ,RHEL 8.10 [#rhel-700-past-60]_,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
+      ,SLES 15 SP7 [#sles-db-700-past-60]_,"SLES 15 SP7, SP6","SLES 15 SP7, SP6",SLES 15 SP6,SLES 15 SP6,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
       ,,,,,,,,,,,,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
       ,"Oracle Linux 9, 8 [#ol-700-mi300x-past-60]_","Oracle Linux 9, 8 [#mi300x-past-60]_","Oracle Linux 9, 8 [#mi300x-past-60]_","Oracle Linux 9, 8 [#mi300x-past-60]_","Oracle Linux 9, 8 [#mi300x-past-60]_",Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.10 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,Oracle Linux 8.9 [#mi300x-past-60]_,,,
-      ,Debian 12,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,,,,,,,,,,,
+      ,Debian 12 [#sles-db-700-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,Debian 12 [#single-node-past-60]_,,,,,,,,,,,
       ,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-past-60]_,Azure Linux 3.0 [#az-mi300x-630-past-60]_,Azure Linux 3.0 [#az-mi300x-630-past-60]_,,,,,,,,,,,,
-,Rocky Linux 9,,,,,,,,,,,,,,,,,,
+,Rocky Linux 9 [#rl-700-past-60]_,,,,,,,,,,,,,,,,,,
       ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
       :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,,,,,,,,,,,,,,,,,,
 ,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
@@ -19,25 +19,27 @@ 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
       ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
       ,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
       ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx950,,,,,,,,,,,,,,,,,,
-,gfx1201 [#RDNA-OS-past-60]_,gfx1201 [#RDNA-OS-past-60]_,gfx1201 [#RDNA-OS-past-60]_,gfx1201 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
-      ,gfx1200 [#RDNA-OS-past-60]_,gfx1200 [#RDNA-OS-past-60]_,gfx1200 [#RDNA-OS-past-60]_,gfx1200 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
-,gfx1101 [#RDNA-OS-past-60]_ [#7700XT-OS-past-60]_,gfx1101 [#RDNA-OS-past-60]_ [#7700XT-OS-past-60]_,gfx1101 [#RDNA-OS-past-60]_ [#7700XT-OS-past-60]_,gfx1101 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
-      ,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
-      ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
-      ,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942 [#mi300_624-past-60]_,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
-      ,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
-      ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx950 [#mi350x-os-past-60]_,,,,,,,,,,,,,,,,,,
+,gfx1201 [#RDNA-OS-700-past-60]_,gfx1201 [#RDNA-OS-past-60]_,gfx1201 [#RDNA-OS-past-60]_,gfx1201 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
+      ,gfx1200 [#RDNA-OS-700-past-60]_,gfx1200 [#RDNA-OS-past-60]_,gfx1200 [#RDNA-OS-past-60]_,gfx1200 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
+,gfx1101 [#RDNA-OS-700-past-60]_ [#rd-v710-past-60]_,gfx1101 [#RDNA-OS-past-60]_ [#7700XT-OS-past-60]_,gfx1101 [#RDNA-OS-past-60]_ [#7700XT-OS-past-60]_,gfx1101 [#RDNA-OS-past-60]_,,,,,,,,,,,,,,,
+      ,gfx1100 [#RDNA-OS-700-past-60]_,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
+      ,gfx1030 [#RDNA-OS-700-past-60]_ [#rd-v620-past-60]_,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
+      ,gfx942 [#mi325x-os-past-60]_ [#mi300x-os-past-60]_ [#mi300A-os-past-60]_,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942 [#mi300_624-past-60]_,gfx942 [#mi300_622-past-60]_,gfx942 [#mi300_621-past-60]_,gfx942 [#mi300_620-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_612-past-60]_, gfx942 [#mi300_611-past-60]_, gfx942 [#mi300_610-past-60]_, gfx942 [#mi300_602-past-60]_, gfx942 [#mi300_600-past-60]_
+      ,gfx90a [#mi200x-os-past-60]_,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
+      ,gfx908 [#mi100-os-past-60]_,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
 ,,,,,,,,,,,,,,,,,,,
       FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,
       :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.7, 2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
       :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.19.1, 2.18.1","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
       :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.6.0,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
-      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A,
-      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,N/A,N/A,N/A,85f95ae,85f95ae,85f95ae,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,
-      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,
-      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`,N/A,N/A,N/A,N/A,N/A,0.7.0,0.7.0,0.7.0,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,
-      :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat]_,N/A,N/A,N/A,N/A,N/A,N/A,1.8.0b1,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,
+      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat-past-60]_,N/A,N/A,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,1.8.0b1,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+:doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,N/A,2.48.0.post0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+:doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat-past-60]_,N/A,N/A,N/A,N/A,b5997,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.22.0,1.20.0,1.20.0,1.20.0,1.20.0,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
 ,,,,,,,,,,,,,,,,,,,
       ,,,,,,,,,,,,,,,,,,,
@@ -49,8 +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

docs/compatibility/compatibility-matrix.rst

@@ -23,16 +23,16 @@ 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
       ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5
       ,"RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.5, 9.4"
-      ,RHEL 8.10 [#rhel-700]_,RHEL 8.10 [#rhel-700],RHEL 8.10 [#rhel-700]
-      ,SLES 15 SP7,"SLES 15 SP7, SP6","SLES 15 SP6, SP5"
+      ,RHEL 8.10 [#rhel-700]_,RHEL 8.10,RHEL 8.10
+      ,SLES 15 SP7 [#sles-db-700]_,"SLES 15 SP7, SP6","SLES 15 SP6, SP5"
       ,"Oracle Linux 9, 8 [#ol-700-mi300x]_","Oracle Linux 9, 8 [#ol-mi300x]_",Oracle Linux 8.10 [#ol-mi300x]_
-      ,Debian 12,Debian 12 [#single-node]_,
+      ,Debian 12 [#sles-db-700]_,Debian 12 [#single-node]_,
       ,Azure Linux 3.0 [#az-mi300x]_,Azure Linux 3.0 [#az-mi300x]_,
       ,Rocky Linux 9 [#rl-700]_,,
       ,.. _architecture-support-compatibility-matrix:,,
@@ -44,25 +44,22 @@ compatibility and system requirements.
       ,RDNA3,RDNA3,RDNA3
       ,RDNA2,RDNA2,RDNA2
       ,.. _gpu-support-compatibility-matrix:,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx950,,
-      ,gfx1201 [#RDNA-OS]_,gfx1201 [#RDNA-OS]_,
-      ,gfx1200 [#RDNA-OS]_,gfx1200 [#RDNA-OS]_,
-      ,gfx1101 [#RDNA-OS]_ [#7700XT-OS]_,gfx1101 [#RDNA-OS]_ [#7700XT-OS]_,
-      ,gfx1100,gfx1100,gfx1100
-      ,gfx1030,gfx1030,gfx1030
-      ,gfx942,gfx942,gfx942
-      ,gfx90a,gfx90a,gfx90a
-      ,gfx908,gfx908,gfx908
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`,gfx950 [#mi350x-os]_,,
+      ,gfx1201 [#RDNA-OS-700]_,gfx1201 [#RDNA-OS]_,
+      ,gfx1200 [#RDNA-OS-700]_,gfx1200 [#RDNA-OS]_,
+      ,gfx1101 [#RDNA-OS-700]_ [#rd-v710]_,gfx1101 [#RDNA-OS]_ [#7700XT-OS]_,
+      ,gfx1100 [#RDNA-OS-700]_,gfx1100,gfx1100
+      ,gfx1030 [#RDNA-OS-700]_ [#rd-v620]_,gfx1030,gfx1030
+      ,gfx942 [#mi325x-os]_ [#mi300x-os]_ [#mi300A-os]_,gfx942,gfx942
+      ,gfx90a [#mi200x-os]_,gfx90a,gfx90a
+      ,gfx908 [#mi100-os]_,gfx908,gfx908
       ,,,
       FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix:,,
       :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.7, 2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 2.1, 2.0, 1.13"
       :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.19.1, 2.18.1","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1"
       :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.6.0,0.4.35,0.4.31
-      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat]_,N/A,N/A,N/A
-      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,85f95ae
-      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,N/A
-      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`,N/A,N/A,0.7.0
-      :doc:`Taichi <../compatibility/ml-compatibility/taichi-compatibility>` [#taichi_compat]_,N/A,N/A,N/A
+      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat]_,N/A,N/A,85f95ae
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat]_,N/A,N/A,0.7.0
       `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.22.0,1.20.0,1.17.3
       ,,,
       THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
@@ -73,8 +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
@@ -159,16 +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** - Oracle Linux 9 is supported only on AMD Instinct MI300X, MI350X, and MI355X. Oracle Linux 8 is only supported on AMD Instinct MI300X.
-.. [#ol-mi300x] **Prior ROCm 7.0** - Oracle Linux is supported only on AMD Instinct MI300X.
-.. [#sles-db-700] SLES 15 SP7 and Debian 12 are only supported on AMD Instinct MI300X, MI300A, MI250X, MI250, and MI210 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.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.
-.. [#az-mi300x] Starting from ROCm 6.4.0, Azure Linux 3.0 is supported only on AMD Instinct MI300X and AMD Radeon PRO V710.
-.. [#RDNA-OS] 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.
-.. [#7700XT-OS] Radeon RX 7700 XT (gfx1101) is supported only on Ubuntu 24.04.2 and RHEL 9.6.
-.. [#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>`_.
+.. [#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.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.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.
+.. [#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.
 
 
@@ -240,12 +248,24 @@ Expand for full historical view of:
 
    .. rubric:: Footnotes
 
-   .. [#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.
-   .. [#mi300x-past-60] **Prior to ROCm 7.0.0** - Oracle Linux is supported only on AMD Instinct MI300X.
-   .. [#single-node-past-60] **Prior to ROCm 7.0.0 ** - Debian 12 is supported only on AMD Instinct MI300X for single-node functionality.
+   .. [#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.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.
-   .. [#RDNA-OS-past-60] 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.
+   .. [#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.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.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].
@@ -256,13 +276,14 @@ Expand for full historical view of:
    .. [#mi300_610-past-60] **For ROCm 6.1.0** - MI300A (gfx942) is supported on Ubuntu 22.04.4, RHEL 9.4, RHEL 9.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.4.
    .. [#mi300_602-past-60] **For ROCm 6.0.2** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
    .. [#mi300_600-past-60] **For ROCm 6.0.0** - MI300A (gfx942) is supported on Ubuntu 22.04.3, RHEL 8.9, and SLES 15 SP5. MI300X (gfx942) is only supported on Ubuntu 22.04.3.
-   .. [#verl_compat] verl is only supported on ROCm 6.2.0.
-   .. [#stanford-megatron-lm_compat] Stanford Megatron-LM is only supported on ROCm 6.3.0.
-   .. [#dgl_compat] DGL is only supported on ROCm 6.4.0.
-   .. [#megablocks_compat] Megablocks is only supported on ROCm 6.3.0.
-   .. [#taichi_compat] Taichi is only supported on ROCm 6.3.2.
-   .. [#ray_compat] Ray is only supported on ROCm 6.4.1.
-   .. [#llama-cpp_compat] 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 tested user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and kernel-space support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
+   .. [#verl_compat-past-60] verl is only supported on ROCm 6.2.0.
+   .. [#stanford-megatron-lm_compat-past-60] Stanford Megatron-LM is only supported on ROCm 6.3.0.
+   .. [#dgl_compat-past-60] DGL is only supported on ROCm 6.4.0.
+   .. [#megablocks_compat-past-60] Megablocks is only supported on ROCm 6.3.0.
+   .. [#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.
+   .. [#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.
    

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:
 

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
 ================================================================================

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/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - 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/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - 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/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - 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/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - 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/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - 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/tensorflow_rocm-2.16.2-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - 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

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"]},
@@ -135,6 +137,9 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.4", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.5", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.6", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.7", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/pytorch-training", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-history", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.4", "os": ["linux"]},

docs/data/how-to/rocm-for-ai/inference/sglang-distributed-benchmark-models.yaml

@@ -0,0 +1,32 @@
+dockers:
+  - pull_tag: lmsysorg/sglang:v0.5.2rc1-rocm700-mi30x
+    docker_hub_url: https://hub.docker.com/layers/lmsysorg/sglang/v0.5.2rc1-rocm700-mi30x/images/sha256-10c4ee502ddba44dd8c13325e6e03868bfe7f43d23d0a44780a8ee8b393f4729
+    components:
+      ROCm: 7.0.0
+      SGLang: v0.5.2rc1
+      pytorch-triton-rocm: 3.4.0+rocm7.0.0.gitf9e5bf54
+model_groups:
+  - group: Dense models
+    tag: dense-models
+    models:
+      - model: Llama 3.1 8B Instruct
+        model_repo: Llama-3.1-8B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct
+      - model: Llama 3.1 405B FP8 KV
+        model_repo: Llama-3.1-405B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+      - model: Llama 3.3 70B FP8 KV
+        model_repo: amd-Llama-3.3-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.3-70B-Instruct-FP8-KV
+      - model: Qwen3 32B
+        model_repo: Qwen3-32B
+        url: https://huggingface.co/Qwen/Qwen3-32B
+  - group: Small experts models
+    tag: small-experts-models
+    models:
+      - model: DeepSeek V3
+        model_repo: DeepSeek-V3
+        url: https://huggingface.co/deepseek-ai/DeepSeek-V3
+      - model: Mixtral 8x7B v0.1
+        model_repo: Mixtral-8x7B-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x7B-v0.1

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

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:

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

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

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

@@ -0,0 +1,162 @@
+dockers:
+  - pull_tag: rocm/pytorch-training:v25.7
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.7/images/sha256-cc6fd840ab89cb81d926fc29eca6d075aee9875a55a522675a4b9231c9a0a712
+    components:
+      ROCm: 6.4.2
+      PyTorch: 2.8.0a0+gitd06a406
+      Python: 3.10.18
+      Transformer Engine: 2.2.0.dev0+94e53dd8
+      Flash Attention: 3.0.0.post1
+      hipBLASLt: 1.1.0-4b9a52edfc
+      Triton: 3.3.0
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 4 Scout 17B-16E
+      mad_tag: pyt_train_llama-4-scout-17b-16e
+      model_repo: Llama-4-17B_16E
+      url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.3 70B
+      mad_tag: pyt_train_llama-3.3-70b
+      model_repo: Llama-3.3-70B
+      url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 3.2 1B
+      mad_tag: pyt_train_llama-3.2-1b
+      model_repo: Llama-3.2-1B
+      url: https://huggingface.co/meta-llama/Llama-3.2-1B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 3B
+      mad_tag: pyt_train_llama-3.2-3b
+      model_repo: Llama-3.2-3B
+      url: https://huggingface.co/meta-llama/Llama-3.2-3B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 Vision 11B
+      mad_tag: pyt_train_llama-3.2-vision-11b
+      model_repo: Llama-3.2-Vision-11B
+      url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.2 Vision 90B
+      mad_tag: pyt_train_llama-3.2-vision-90b
+      model_repo: Llama-3.2-Vision-90B
+      url: https://huggingface.co/meta-llama/Llama-3.2-90B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.1 8B
+      mad_tag: pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+      training_modes: [pretrain, finetune_fw, finetune_lora, HF_pretrain]
+    - model: Llama 3.1 70B
+      mad_tag: pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+      precision: BF16
+      training_modes: [pretrain, finetune_fw, finetune_lora]
+    - model: Llama 3.1 405B
+      mad_tag: pyt_train_llama-3.1-405b
+      model_repo: Llama-3.1-405B
+      url: https://huggingface.co/meta-llama/Llama-3.1-405B
+      precision: BF16
+      training_modes: [finetune_qlora]
+    - model: Llama 3 8B
+      mad_tag: pyt_train_llama-3-8b
+      model_repo: Llama-3-8B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3 70B
+      mad_tag: pyt_train_llama-3-70b
+      model_repo: Llama-3-70B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-70B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 7B
+      mad_tag: pyt_train_llama-2-7b
+      model_repo: Llama-2-7B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 2 13B
+      mad_tag: pyt_train_llama-2-13b
+      model_repo: Llama-2-13B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 70B
+      mad_tag: pyt_train_llama-2-70b
+      model_repo: Llama-2-70B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_lora, finetune_qlora]
+  - group: OpenAI
+    tag: openai
+    models:
+    - model: GPT OSS 20B
+      mad_tag: pyt_train_gpt_oss_20b
+      model_repo: GPT-OSS-20B
+      url: https://huggingface.co/openai/gpt-oss-20b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+    - model: GPT OSS 120B
+      mad_tag: pyt_train_gpt_oss_120b
+      model_repo: GPT-OSS-120B
+      url: https://huggingface.co/openai/gpt-oss-120b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+  - group: Qwen
+    tag: qwen
+    models:
+    - model: Qwen 3 8B
+      mad_tag: pyt_train_qwen3-8b
+      model_repo: Qwen3-8B
+      url: https://huggingface.co/Qwen/Qwen3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 3 32B
+      mad_tag: pyt_train_qwen3-32b
+      model_repo: Qwen3-32
+      url: https://huggingface.co/Qwen/Qwen3-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 32B
+      mad_tag: pyt_train_qwen2.5-32b
+      model_repo: Qwen2.5-32B
+      url: https://huggingface.co/Qwen/Qwen2.5-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 72B
+      mad_tag: pyt_train_qwen2.5-72b
+      model_repo: Qwen2.5-72B
+      url: https://huggingface.co/Qwen/Qwen2.5-72B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2 1.5B
+      mad_tag: pyt_train_qwen2-1.5b
+      model_repo: Qwen2-1.5B
+      url: https://huggingface.co/Qwen/Qwen2-1.5B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 2 7B
+      mad_tag: pyt_train_qwen2-7b
+      model_repo: Qwen2-7B
+      url: https://huggingface.co/Qwen/Qwen2-7B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+  - group: Flux
+    tag: flux
+    models:
+    - model: FLUX.1-dev
+      mad_tag: pyt_train_flux
+      model_repo: Flux
+      url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+      precision: BF16
+      training_modes: [pretrain]

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:

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

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

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

@@ -1,14 +1,13 @@
 dockers:
-  - pull_tag: rocm/pytorch-training:v25.7
-    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.7/images/sha256-cc6fd840ab89cb81d926fc29eca6d075aee9875a55a522675a4b9231c9a0a712
+  - pull_tag: rocm/pytorch-training:v25.8
+    docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-training/v25.8/images/sha256-5082ae01d73fec6972b0d84e5dad78c0926820dcf3c19f301d6c8eb892e573c5
     components:
-      ROCm: 6.4.2
+      ROCm: 6.4.3
       PyTorch: 2.8.0a0+gitd06a406
       Python: 3.10.18
-      Transformer Engine: 2.2.0.dev0+94e53dd8
+      Transformer Engine: 2.2.0.dev0+a1e66aae
       Flash Attention: 3.0.0.post1
-      hipBLASLt: 1.1.0-4b9a52edfc
-      Triton: 3.3.0
+      hipBLASLt: 1.1.0-d1b517fc7a
 model_groups:
   - group: Meta Llama
     tag: llama
@@ -151,6 +150,15 @@ model_groups:
       url: https://huggingface.co/Qwen/Qwen2-7B
       precision: BF16
       training_modes: [finetune_fw, finetune_lora]
+  - group: Stable Diffusion
+    tag: sd
+    models:
+    - model: Stable Diffusion XL
+      mad_tag: pyt_huggingface_stable_diffusion_xl_2k_lora_finetuning
+      model_repo: SDXL
+      url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+      precision: BF16
+      training_modes: [finetune_lora]
   - group: Flux
     tag: flux
     models:
@@ -160,3 +168,11 @@ model_groups:
       url: https://huggingface.co/black-forest-labs/FLUX.1-dev
       precision: BF16
       training_modes: [pretrain]
+  - group: NCF
+    tag: ncf
+    models:
+    - model: NCF
+      mad_tag: pyt_ncf_training
+      model_repo:
+      url: https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Recommendation/NCF
+      precision: FP32

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

@@ -0,0 +1,257 @@
+.. meta::
+   :description: SGLang multi-node disaggregated distributed inference using Mooncake
+   :keywords: model, sglang, mooncake, disagg, disaggregated, distributed, multi-node, docker
+
+******************************************
+SGLang distributed inference with Mooncake
+******************************************
+
+As LLM inference increasingly demands handling massive models and dynamic workloads, efficient
+distributed inference becomes essential. Traditional co-located architectures face bottlenecks due
+to tightly coupled memory and compute resources, which limits scalability and flexibility.
+Disaggregated inference refers to the process of splitting the inference of LLMs into distinct
+phases. This architecture, facilitated by libraries like Mooncake, uses high-bandwidth
+RDMA to transfer the Key-Value (KV) cache between prefill and decode nodes.
+This allows for independent resource scaling and optimization, resulting in
+improved efficiency and throughput.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-distributed-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+
+   `SGLang <https://docs.sglang.ai>`__ is a high-performance inference and
+   serving engine for large language models (LLMs) and vision models. The
+   ROCm-enabled `SGLang base Docker image <{{ docker.docker_hub_url }}>`__
+   bundles SGLang with PyTorch, which is optimized for AMD Instinct MI300X series
+   accelerators. It includes the following software components:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+The following guides on setting up and running SGLang and Mooncake for disaggregated
+distributed inference on a Slurm cluster using AMD Instinct MI300X series accelerators backed by
+Mellanox CX-7 NICs.
+
+Prerequisites
+=============
+
+Before starting, ensure you have:
+
+* A Slurm cluster with at least three nodes: one for the proxy, one for prefill (``xP``), and one for decode (``yD``).
+
+  ``Nodes -> xP + yD + 1``
+
+* A Dockerized environment with SGLang, Mooncake, etcd, and NIC drivers built in. See :ref:`sglang-disagg-inf-build-docker-image` for instructions.
+
+* A shared filesystem for storing models, scripts, and logs (cluster-specific).
+
+Supported models
+================
+
+The following models are supported for SGLang disaggregated prefill/decode
+inference. Some instructions, commands, and recommendations in this
+documentation might vary by selected model.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-distributed-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 type</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.model_repo | lower }}" 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.model_repo | lower }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.model_repo }}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`__ to learn more about this model.
+         Some models require access authorization prior to use through an external license agreement with a third party.
+
+      {% endfor %}
+   {% endfor %}
+
+.. _sglang-disagg-inf-build-docker-image:
+
+Build the Docker image
+----------------------
+
+Get the Dockerfile located in
+`<https://github.com/ROCm/MAD/blob/develop/docker/sglang_dissag_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
+drivers.
+
+.. code-block:: shell
+
+   git clone https://github.com/ROCm/MAD.git
+   cd MAD/docker
+   docker build \
+       -t sglang_disagg_pd_image \
+       -f sglang_disagg_inference.ubuntu.amd.Dockerfile .
+
+Benchmarking
+============
+
+The `<https://github.com/ROCm/MAD/tree/develop/scripts/sglang_dissag>`__
+repository contains scripts to launch SGLang inference with prefill/decode
+disaggregation via Mooncake for supported models.
+
+* `scripts/sglang_dissag/run_xPyD_models.slurm <https://github.com/ROCm/MAD/blob/develop/scripts/sglang_disagg/run_xPyD_models.slurm>`__
+  -- the main Slurm batch script to launch Docker containers on all nodes using ``sbatch`` or ``salloc``.
+
+* `scripts/sglang_dissag/sglang_disagg_server.sh <https://github.com/ROCm/MAD/blob/develop/scripts/sglang_disagg/sglang_disagg_server.sh>`__
+  -- the entrypoint script that runs inside each container to start the correct service -- proxy, prefill, or decode.
+
+* `scripts/sglang_dissag/benchmark_xPyD.sh <https://github.com/ROCm/MAD/blob/develop/scripts/sglang_disagg/benchmark_xPyD.sh>`__
+  -- the benchmark script to run the GSM8K accuracy benchmark and the SGLang benchmarking tool for performance measurement.
+
+* `scripts/sglang_dissag/benchmark_parser.py <https://github.com/ROCm/MAD/blob/develop/scripts/sglang_disagg/benchmark_parser.py>`__
+  -- the log parser script to be run on the concurrency benchmark log file to generate tabulated data.
+
+Launch the service
+------------------
+
+The service is deployed using a Slurm batch script that orchestrates the containers across the
+allocated nodes.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-distributed-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.model_repo }}
+
+      .. code-block:: shell
+
+         # Clone the MAD repo if you haven't already and
+         # navigate to the scripts directory
+         git clone https://github.com/ROCm/MAD.git
+         cd MAD/scripts/sglang_disagg/
+
+         # Slurm sbatch run command
+         export DOCKER_IMAGE_NAME=sglang_disagg_pd_image
+         export xP=<num_prefill_nodes>
+         export yD=<num_decode_nodes>
+         export MODEL_NAME={{ model.model_repo }}
+         # num_nodes = xP + yD + 1
+         sbatch -N <num_nodes> -n <num_nodes> --nodelist=<Nodes> run_xPyD_models.slurm
+
+      {% endfor %}
+   {% endfor %}
+
+Post-run logs and testing
+-------------------------
+
+Logs are stored in your shared filesystem in the directory specified by the ``LOG_PATH`` variable in the Slurm script.
+A new directory named after the Slurm job ID is created for each run.
+
+Inside that directory, you can access various logs:
+
+* ``pd_sglang_bench_serving.sh_NODE<...>.log`` -- the main log for each server node.
+
+* ``etcd_NODE<...>.log`` -- logs for etcd services.
+
+* ``prefill_NODE<...>.log`` -- logs for the prefill services.
+
+* ``decode_NODE<...>.log`` -- logs for the decode services.
+
+Use the benchmark parser script for concurrency logs to tabulate different data.
+
+.. code-block:: shell
+
+   python3 benchmark_parser.py <log_path/benchmark_XXX_CONCURRENCY.log>
+
+To verify the service is responsive, you can try sending a ``curl`` request to test the launched
+server from the Docker container on the proxy node. For example:
+
+.. code-block:: shell
+
+   curl -X POST http://127.0.0.1:30000/generate \
+       -H "Content-Type: application/json" \
+       -d '{ "text": "Let me tell you a story ", "sampling_params": { "temperature": 0.3 } }'
+
+Known issues
+============
+
+When running larger models, such as DeepSeek-V3 and Llama-3.1-405B-Instruct-FP8-KV, at
+higher concurrency levels (512+), the following error might occur:
+
+.. code-block:: shell-session
+
+   <TransferEncodingError: 400, message:
+    Not enough data to satisfy transfer length header.
+
+   The above exception was the direct cause of the following exception:
+
+   Traceback (most recent call last):
+   ...
+
+This leads to dropping requests and lower throughput.
+
+Further reading
+===============
+
+- To learn about Mooncake, see `Welcome to Mooncake <https://kvcache-ai.github.io/Mooncake/>`__.
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/sgl-project/sglang/tree/main/benchmark/blog_v0_2>`__.
+
+- See the base upstream Docker image on `Docker Hub <https://hub.docker.com/layers/lmsysorg/sglang/v0.5.2rc1-rocm700-mi30x/images/sha256-10c4ee502ddba44dd8c13325e6e03868bfe7f43d23d0a44780a8ee8b393f4729>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__.
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.
+
+- To learn how to run community models from Hugging Face on AMD GPUs, see
+  :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.
+
+- To learn how to fine-tune LLMs and optimize inference, see
+  :doc:`Fine-tuning LLMs and inference optimization </how-to/rocm-for-ai/fine-tuning/fine-tuning-and-inference>`.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`previous-versions/sglang-history` to find documentation for previous releases
+of SGLang inference performance testing.

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

@@ -3,7 +3,7 @@
    :keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
 
 ******************************************
-Training a model with JAX MaxText for ROCm
+Training a model with JAX MaxText on ROCm
 ******************************************
 
 MaxText is a high-performance, open-source framework built on the Google JAX
@@ -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.
@@ -406,8 +396,6 @@ benchmark results:
 Further reading
 ===============
 
-- See the ROCm/maxtext benchmarking README at `<https://github.com/ROCm/maxtext/blob/main/benchmarks/gpu-rocm/readme.md>`__.
-
 - To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
 
 - To learn more about system settings and management practices to configure your system for

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

@@ -5,15 +5,13 @@
    :keywords: ROCm, AI, LLM, train, Megatron-LM, megatron, Llama, tutorial, docker, torch
 
 ******************************************
-Training a model with Megatron-LM for ROCm
+Training a model with Megatron-LM on ROCm
 ******************************************
 
 .. caution::
 
-   The ROCm Megatron-LM framework now has limited support with this Docker
-   environment; it now focuses on Primus with Megatron-Core. See :doc:`primus-megatron`.
-
-   To learn how to migrate your existing workloads to Primus with Megatron-Core,
+   Primus with Megatron supersedes this ROCm Megatron-LM training workflow.
+   To learn how to migrate workloads from Megatron-LM to Primus with Megatron,
    see :doc:`previous-versions/megatron-lm-primus-migration-guide`.
 
 The `Megatron-LM framework for ROCm <https://github.com/ROCm/Megatron-LM>`_ is
@@ -807,9 +805,16 @@ Single node training
       AC=none \
       SEQ_LEN=4096 \
       PAD_LEN=4096 \
-      TRAIN_ITERS=50 \
+      TRAIN_ITERS=20 \
       bash examples/deepseek_v2/train_deepseekv2.sh
 
+   .. note::
+
+      Note that DeepSeek-V2-Lite is experiencing instability due to GPU memory access fault
+      for large iterations.
+      For stability, it's recommended to use Primus for this workload.
+      See :doc:`primus-megatron`.
+
 .. container:: model-doc pyt_megatron_lm_train_mixtral-8x7b
 
    To run training on a single node for Mixtral 8x7B (MoE with expert parallel),

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

@@ -3,7 +3,7 @@
    :keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
 
 ******************************************
-Training MPT-30B with LLM Foundry and ROCm
+Training MPT-30B with LLM Foundry on ROCm
 ******************************************
 
 MPT-30B is a 30-billion parameter decoder-style transformer-based model from

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

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
 ==================

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.

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

@@ -4,7 +4,7 @@
 PyTorch training performance testing version history
 ****************************************************
 
-This table lists previous versions of the ROCm Megatron-LM training Docker image for
+This table lists previous versions of the ROCm PyTorch training Docker image for
 inference performance testing. For detailed information about available models
 for benchmarking, see the version-specific documentation. You can find tagged
 previous releases of the ``ROCm/pytorch-training`` Docker image on `Docker Hub <https://hub.docker.com/r/rocm/pytorch-training/tags>`_.
@@ -16,12 +16,21 @@ previous releases of the ``ROCm/pytorch-training`` Docker image on `Docker Hub <
      - Components
      - Resources
 
+   * - v25.8 (latest)
+     - 
+       * ROCm 6.4.3
+       * PyTorch 2.8.0a0+gitd06a406
+     - 
+       * :doc:`Primus PyTorch Training documentation <../primus-pytorch>`
+       * :doc:`PyTorch training (legacy) documentation <../pytorch-training>`
+       * `Docker Hub <https://hub.docker.com/r/rocm/pytorch-training/tags>`__
+
    * - v25.7
      - 
        * ROCm 6.4.2
        * PyTorch 2.8.0a0+gitd06a406
      - 
-       * :doc:`Documentation <../pytorch-training>`
+       * :doc:`Documentation <pytorch-training-v25.7>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-training/v25.7/images/sha256-cc6fd840ab89cb81d926fc29eca6d075aee9875a55a522675a4b9231c9a0a712>`__
 
    * - v25.6

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

@@ -0,0 +1,567 @@
+:orphan:
+
+.. meta::
+   :description: How to train a model using PyTorch for ROCm.
+   :keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
+
+**************************************
+Training a model with PyTorch for ROCm
+**************************************
+
+.. caution::
+
+   This documentation does not reflect the latest version of ROCm vLLM
+   performance benchmark documentation. See :doc:`../pytorch-training` for the latest version.
+
+PyTorch is an open-source machine learning framework that is widely used for
+model training with GPU-optimized components for transformer-based models.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.7-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+   The `PyTorch for ROCm training Docker <{{ docker.docker_hub_url }}>`__
+   (``{{ docker.pull_tag }}``) image provides a prebuilt optimized environment for fine-tuning and pretraining a
+   model on AMD Instinct MI325X and MI300X accelerators. It includes the following software components to accelerate
+   training workloads:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+.. _amd-pytorch-training-model-support-v257:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X accelerators.
+Some instructions, commands, and training recommendations in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.7-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-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>
+
+
+   .. _amd-pytorch-training-supported-training-modes-v257:
+
+   The following table lists supported training modes per model.
+
+   .. dropdown:: Supported training modes
+
+      .. list-table::
+         :header-rows: 1
+
+         * - Model
+           - Supported training modes
+
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+         * - {{ model.model }}
+           - ``{{ model.training_modes | join('``, ``') }}``
+
+         {% endfor %}
+      {% endfor %}
+
+      .. note::
+
+         Some model and fine-tuning combinations are not listed. This is
+         because the `upstream torchtune repository <https://github.com/pytorch/torchtune>`__
+         doesn't provide default YAML configurations for them.
+         For advanced usage, you can create a custom configuration to enable
+         unlisted fine-tuning methods by using an existing file in the
+         ``/workspace/torchtune/recipes/configs`` directory as a template.
+
+.. _amd-pytorch-training-performance-measurements-v257:
+
+Performance measurements
+========================
+
+To evaluate performance, the
+`Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
+page provides reference throughput and latency measurements for training
+popular AI models.
+
+.. note::
+
+   The performance data presented in
+   `Performance results with AMD ROCm software <https://www.amd.com/en/developer/resources/rocm-hub/dev-ai/performance-results.html#tabs-a8deaeb413-item-21cea50186-tab>`_
+   should not be interpreted as the peak performance achievable by AMD
+   Instinct MI325X and MI300X accelerators or ROCm software.
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+This Docker image is optimized for specific model configurations outlined
+below. Performance can vary for other training workloads, as AMD
+doesn’t test configurations and run conditions outside those described.
+
+Run training
+============
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.7-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+
+   Once the setup is complete, choose between two options to start benchmarking training:
+
+   .. tab-set::
+
+      .. tab-item:: MAD-integrated benchmarking
+
+         1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+            directory and install the required packages on the host machine.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD
+               pip install -r requirements.txt
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            2. For example, use this command to run the performance benchmark test on the {{ model.model }} model
+               using one node with the {{ model.precision }} data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{ model.mad_tag }} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+               MAD launches a Docker container with the name
+               ``container_ci-{{ model.mad_tag }}``. The latency and throughput reports of the
+               model are collected in ``~/MAD/perf.csv``.
+
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Standalone benchmarking
+
+         .. rubric:: Download the Docker image and required packages
+
+         1. Use the following command to pull the Docker image from Docker Hub.
+
+            .. code-block:: shell
+
+               docker pull {{ unified_docker.pull_tag }}
+
+         2. Run the Docker container.
+
+            .. code-block:: shell
+
+               docker run -it \
+                   --device /dev/dri \
+                   --device /dev/kfd \
+                   --network host \
+                   --ipc host \
+                   --group-add video \
+                   --cap-add SYS_PTRACE \
+                   --security-opt seccomp=unconfined \
+                   --privileged \
+                   -v $HOME:$HOME \
+                   -v $HOME/.ssh:/root/.ssh \
+                   --shm-size 64G \
+                   --name training_env \
+                   {{ unified_docker.pull_tag }}
+
+            Use these commands if you exit the ``training_env`` container and need to return to it.
+
+            .. code-block:: shell
+
+               docker start training_env
+               docker exec -it training_env bash
+
+         3. In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
+            repository and navigate to the benchmark scripts directory
+            ``/workspace/MAD/scripts/pytorch_train``.
+
+            .. code-block:: shell
+
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/pytorch_train
+
+         .. rubric:: Prepare training datasets and dependencies
+
+         1. The following benchmarking examples require downloading models and datasets
+            from Hugging Face. To ensure successful access to gated repos, set your
+            ``HF_TOKEN``.
+
+            .. code-block:: shell
+
+               export HF_TOKEN=$your_personal_hugging_face_access_token
+
+         2. Run the setup script to install libraries and datasets needed for benchmarking.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_setup.sh
+
+            .. container:: model-doc pyt_train_llama-3.1-8b
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 8B:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``accelerate``
+                    - `Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
+
+            .. container:: model-doc pyt_train_llama-3.1-70b
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for Llama 3.1 70B:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
+
+                  * - ``torchdata``
+                    - `TorchData <https://pytorch.org/data/beta/index.html>`_
+
+                  * - ``tomli``
+                    - `Tomli <https://pypi.org/project/tomli/>`_
+
+                  * - ``tiktoken``
+                    - `tiktoken <https://github.com/openai/tiktoken>`_
+
+                  * - ``blobfile``
+                    - `blobfile <https://pypi.org/project/blobfile/>`_
+
+                  * - ``tabulate``
+                    - `tabulate <https://pypi.org/project/tabulate/>`_
+
+                  * - ``wandb``
+                    - `Weights & Biases <https://github.com/wandb/wandb>`_
+
+                  * - ``sentencepiece``
+                    - `SentencePiece <https://github.com/google/sentencepiece>`_ 0.2.0
+
+                  * - ``tensorboard``
+                    - `TensorBoard <https://www.tensorflow.org/tensorboard>`_ 2.18.0
+
+            .. container:: model-doc pyt_train_flux
+
+               ``pytorch_benchmark_setup.sh`` installs the following libraries for FLUX:
+
+               .. list-table::
+                  :header-rows: 1
+
+                  * - Library
+                    - Reference
+
+                  * - ``accelerate``
+                    - `Hugging Face Accelerate <https://huggingface.co/docs/accelerate/en/index>`_
+
+                  * - ``datasets``
+                    - `Hugging Face Datasets <https://huggingface.co/docs/datasets/v3.2.0/en/index>`_ 3.2.0
+
+                  * - ``sentencepiece``
+                    - `SentencePiece <https://github.com/google/sentencepiece>`_ 0.2.0
+
+                  * - ``tensorboard``
+                    - `TensorBoard <https://www.tensorflow.org/tensorboard>`_ 2.18.0
+
+                  * - ``csvkit``
+                    - `csvkit <https://csvkit.readthedocs.io/en/latest/>`_ 2.0.1
+
+                  * - ``deepspeed``
+                    - `DeepSpeed <https://github.com/deepspeedai/DeepSpeed>`_ 0.16.2
+
+                  * - ``diffusers``
+                    - `Hugging Face Diffusers <https://huggingface.co/docs/diffusers/en/index>`_ 0.31.0
+
+                  * - ``GitPython``
+                    - `GitPython <https://github.com/gitpython-developers/GitPython>`_ 3.1.44
+
+                  * - ``opencv-python-headless``
+                    - `opencv-python-headless <https://pypi.org/project/opencv-python-headless/>`_ 4.10.0.84
+
+                  * - ``peft``
+                    - `PEFT <https://huggingface.co/docs/peft/en/index>`_ 0.14.0
+
+                  * - ``protobuf``
+                    - `Protocol Buffers <https://github.com/protocolbuffers/protobuf>`_ 5.29.2
+
+                  * - ``pytest``
+                    - `PyTest <https://docs.pytest.org/en/stable/>`_ 8.3.4
+
+                  * - ``python-dotenv``
+                    - `python-dotenv <https://pypi.org/project/python-dotenv/>`_ 1.0.1
+
+                  * - ``seaborn``
+                    - `Seaborn <https://seaborn.pydata.org/>`_ 0.13.2
+
+                  * - ``transformers``
+                    - `Transformers <https://huggingface.co/docs/transformers/en/index>`_ 4.47.0
+
+            ``pytorch_benchmark_setup.sh`` downloads the following datasets from Hugging Face:
+
+            * `bghira/pseudo-camera-10k <https://huggingface.co/datasets/bghira/pseudo-camera-10k>`_
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+         {% set training_modes = model.training_modes %}
+         {% set training_mode_descs = {
+            "pretrain": "Benchmark pre-training.",
+            "HF_pretrain": "Llama 3.1 8B pre-training with FP8 precision."
+         } %}
+         {% set available_modes = training_modes | select("in", ["pretrain", "HF_pretrain"]) | list %}
+         {% if available_modes %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Pre-training
+
+            To start the pre-training benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t {% if available_modes | length == 1 %}{{ available_modes[0] }}{% else %}$training_mode{% endif %} \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+            {% if model.mad_tag == "pyt_train_flux" %}
+            .. container:: model-doc {{ model.mad_tag }}
+
+               .. note::
+
+                  Currently, FLUX models are not supported out-of-the-box on {{ unified_docker.pull_tag }}.
+                  To use FLUX, refer to the previous version of the ``pytorch-training`` Docker: :doc:`pytorch-training-v25.6`
+
+                  Occasionally, downloading the Flux dataset might fail. In the event of this
+                  error, manually download it from Hugging Face at
+                  `black-forest-labs/FLUX.1-dev <https://huggingface.co/black-forest-labs/FLUX.1-dev>`_
+                  and save it to `/workspace/FluxBenchmark`. This ensures that the test script can access
+                  the required dataset.
+            {% endif %}
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if model.mad_tag == "pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+         {% endif %}
+
+         {% set training_mode_descs = {
+            "finetune_fw": "Full weight fine-tuning (BF16 and FP8 supported).",
+            "finetune_lora": "LoRA fine-tuning (BF16 supported).",
+            "finetune_qlora": "QLoRA fine-tuning (BF16 supported).",
+            "HF_finetune_lora": "LoRA fine-tuning with Hugging Face PEFT.",
+         } %}
+         {% set available_modes = training_modes | select("in", ["finetune_fw", "finetune_lora", "finetune_qlora", "HF_finetune_lora"]) | list %}
+         {% if available_modes %}
+         .. container:: model-doc {{ model.mad_tag }}
+
+            .. rubric:: Fine-tuning
+
+            To start the fine-tuning benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+            See :ref:`supported training modes <amd-pytorch-training-supported-training-modes-v257>`.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t $training_mode \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if "finetune_fw" in available_modes %} or ``FP8``{% endif %}
+                 - All models support BF16.{% if "finetune_fw" in available_modes %} FP8 is only available for full weight fine-tuning.{% endif %}
+
+               * - ``$sequence_length``
+                 - Between 2048 and 16384.
+                 - Sequence length for the language model.
+
+            {% if model.mad_tag in ["pyt_train_llama3.2-vision-11b", "pyt_train_llama-3.2-vision-90b"] %}
+            .. note::
+
+               For LoRA and QLoRA support with vision models (Llama 3.2 11B and 90B),
+               use the following torchtune commit for compatibility:
+
+               .. code-block:: shell
+
+                  git checkout 48192e23188b1fc524dd6d127725ceb2348e7f0e
+
+            {% elif model.mad_tag in ["pyt_train_llama-2-7b", "pyt_train_llama-2-13b", "pyt_train_llama-2-70b"] %}
+            .. note::
+
+               You might encounter the following error with Llama 2: ``ValueError: seq_len (16384) of
+               input tensor should be smaller than max_seq_len (4096)``.
+               This error indicates that an input sequence is longer than the model's maximum context window.
+
+               Ensure your tokenized input does not exceed the model's ``max_seq_len`` (4096
+               tokens in this case). You can resolve this by truncating the input or splitting
+               it into smaller chunks before passing it to the model.
+
+               Note on reproducibility: The results in this guide are based on
+               commit ``b4c98ac`` from the upstream
+               `<https://github.com/pytorch/torchtune>`__ repository. For the
+               latest updates, you can use the main branch.
+
+            {% endif %}
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+
+            .. rubric:: Benchmarking examples
+
+            For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.
+
+Multi-node training
+-------------------
+
+Pre-training
+~~~~~~~~~~~~
+
+Multi-node training with torchtitan is supported. The provided SLURM script is pre-configured for Llama 3 70B.
+
+To launch the training job on a SLURM cluster for Llama 3 70B, run the following commands from the MAD repository.
+
+.. code-block:: shell
+
+   # In the MAD repository
+   cd scripts/pytorch_train
+   sbatch run_slurm_train.sh
+
+Fine-tuning
+~~~~~~~~~~~
+
+Multi-node training with torchtune is supported. The provided SLURM script is pre-configured for Llama 3.3 70B.
+
+To launch the training job on a SLURM cluster for Llama 3.3 70B, run the following commands from the MAD repository.
+
+.. code-block:: shell
+
+   huggingface-cli login # Get access to HF Llama model space
+   huggingface-cli download meta-llama/Llama-3.3-70B-Instruct --local-dir ./models/Llama-3.3-70B-Instruct # Download the Llama 3.3 model locally
+   # In the MAD repository
+   cd scripts/pytorch_train
+   sbatch Torchtune_Multinode.sh
+
+.. note::
+
+   Information regarding benchmark setup:
+
+   * By default, Llama 3.3 70B is fine-tuned using ``alpaca_dataset``.
+   * You can adjust the torchtune `YAML configuration file
+     <https://github.com/pytorch/torchtune/blob/main/recipes/configs/llama3_3/70B_full_multinode.yaml>`__
+     if you're using a different model.
+   * The number of nodes and other parameters can be tuned in the SLURM script ``Torchtune_Multinode.sh``.
+   * Set the ``mounting_paths`` inside the SLURM script.
+
+Once the run is finished, you can find the log files in the ``result_torchtune/`` directory.
+
+Further reading
+===============
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series 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
+=================
+
+See :doc:`pytorch-training-history` to find documentation for previous releases
+of the ``ROCm/pytorch-training`` Docker image.

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

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

@@ -0,0 +1,305 @@
+.. meta::
+   :description: How to train a model using PyTorch for ROCm.
+   :keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
+
+****************************************
+Training a model with Primus and PyTorch
+****************************************
+
+`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 now supports the PyTorch torchtitan backend.
+
+.. note::
+
+   Primus with the PyTorch torchtitan backend is intended to supersede the :doc:`ROCm PyTorch training <pytorch-training>` workflow.
+   See :doc:`pytorch-training` to see steps to run workloads without Primus.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
+
+   {% set dockers = data.dockers %}
+   {% set docker = dockers[0] %}
+   For ease of use, AMD provides a ready-to-use Docker image -- ``{{
+   docker.pull_tag }}`` -- for MI300X series accelerators containing essential
+   components for Primus and PyTorch training with
+   Primus Turbo optimizations.
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+.. _amd-primus-pytorch-model-support-v258:
+
+Supported models
+================
+
+The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X accelerators.
+Some instructions, commands, and training recommendations in this documentation might
+vary by model -- select one to get started.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0" style="display: none;">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+.. seealso::
+
+   For additional workloads, including Llama 3.3, Llama 3.2, Llama 2, GPT OSS, Qwen, and Flux models,
+   see the documentation :doc:`pytorch-training` (without Primus)
+
+.. _amd-primus-pytorch-performance-measurements-v258:
+
+System validation
+=================
+
+Before running AI workloads, it's important to validate that your AMD hardware is configured
+correctly and performing optimally.
+
+If you have already validated your system settings, including aspects like NUMA auto-balancing, you
+can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
+optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+before starting training.
+
+To test for optimal performance, consult the recommended :ref:`System health benchmarks
+<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
+system's configuration.
+
+This Docker image is optimized for specific model configurations outlined
+below. Performance can vary for other training workloads, as AMD
+doesn’t test configurations and run conditions outside those described.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
+
+   {% set unified_docker = data.dockers[0] %}
+
+   Pull the Docker image
+   =====================
+
+   Use the following command to pull the `Docker image <{{ unified_docker.docker_hub_url }}>`_ from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ unified_docker.pull_tag }}
+
+   Run training
+   ============
+
+   {% set model_groups = data.model_groups %}
+
+   Once the setup is complete, choose between the following two workflows to start benchmarking training.
+   For fine-tuning workloads and multi-node training examples, see :doc:`pytorch-training` (without Primus).
+
+   .. tab-set::
+
+      .. tab-item:: MAD-integrated benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available model.
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
+            2. For example, use this command to run the performance benchmark test on the {{ model.model }} model
+               using one node with the {{ model.precision }} data type on the host machine.
+
+               .. code-block:: shell
+
+                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
+                  madengine run \
+                      --tags {{ model.mad_tag }} \
+                      --keep-model-dir \
+                      --live-output \
+                      --timeout 28800
+
+               MAD launches a Docker container with the name
+               ``container_ci-{{ model.mad_tag }}``. The latency and throughput reports of the
+               model are collected in ``~/MAD/perf.csv``.
+
+      {% endfor %}
+   {% endfor %}
+
+      .. tab-item:: Standalone benchmarking
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following run commands are tailored to {{ model.model }}.
+            See :ref:`amd-primus-pytorch-model-support-v258` to switch to another available model.
+
+            .. rubric:: Download the Docker image and required packages
+
+            1. Use the following command to pull the Docker image from Docker Hub.
+
+               .. code-block:: shell
+
+                  docker pull {{ unified_docker.pull_tag }}
+
+            2. Run the Docker container.
+
+               .. code-block:: shell
+
+                  docker run -it \
+                      --device /dev/dri \
+                      --device /dev/kfd \
+                      --network host \
+                      --ipc host \
+                      --group-add video \
+                      --cap-add SYS_PTRACE \
+                      --security-opt seccomp=unconfined \
+                      --privileged \
+                      -v $HOME:$HOME \
+                      -v $HOME/.ssh:/root/.ssh \
+                      --shm-size 64G \
+                      --name training_env \
+                      {{ unified_docker.pull_tag }}
+
+               Use these commands if you exit the ``training_env`` container and need to return to it.
+
+               .. code-block:: shell
+
+                  docker start training_env
+                  docker exec -it training_env bash
+
+            3. In the Docker container, clone the `<https://github.com/ROCm/MAD>`__
+               repository and navigate to the benchmark scripts directory
+               ``/workspace/MAD/scripts/pytorch_train``.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD/scripts/pytorch_train
+
+            .. rubric:: Prepare training datasets and dependencies
+
+            1. The following benchmarking examples require downloading models and datasets
+               from Hugging Face. To ensure successful access to gated repos, set your
+               ``HF_TOKEN``.
+
+               .. code-block:: shell
+
+                  export HF_TOKEN=$your_personal_hugging_face_access_token
+
+            2. Run the setup script to install libraries and datasets needed for benchmarking.
+
+               .. code-block:: shell
+
+                  ./pytorch_benchmark_setup.sh
+
+            .. rubric:: Pretraining
+
+            To start the pretraining benchmark, use the following command with the
+            appropriate options. See the following list of options and their descriptions.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -t pretrain \
+                   -m {{ model.model_repo }} \
+                   -p $datatype \
+                   -s $sequence_length
+
+
+            .. list-table::
+               :header-rows: 1
+
+               * - Name
+                 - Options
+                 - Description
+
+               {% for mode in available_modes %}
+               * - {% if loop.first %}``$training_mode``{% endif %}
+                 - ``{{ mode }}``
+                 - {{ training_mode_descs[mode] }}
+               {% endfor %}
+
+               * - ``$datatype``
+                 - ``BF16``{% if model.mad_tag == "primus_pyt_train_llama-3.1-8b" %} or ``FP8``{% endif %}
+                 - Currently, only Llama 3.1 8B supports FP8 precision.
+
+               * - ``$sequence_length``
+                 - Sequence length for the language model.
+                 - Between 2048 and 8192. 8192 by default.
+
+            .. rubric:: Benchmarking examples
+
+            Use the following command to run train {{ model.model }} with BF16 precision using Primus torchtitan.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -m {{ model.model_repo }}
+
+            To train {{ model.model }} with FP8 precision, use the following command.
+
+            .. code-block:: shell
+
+               ./pytorch_benchmark_report.sh -m {{ model.model_repo }} -p FP8
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- For an introduction to Primus, see `Primus: A Lightweight, Unified Training
+  Framework for Large Models on AMD GPUs <https://rocm.blogs.amd.com/software-tools-optimization/primus/README.html>`__.
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  AMD Instinct MI300X series 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
+=================
+
+See :doc:`previous-versions/pytorch-training-history` to find documentation for previous releases
+of the ``ROCm/pytorch-training`` Docker image.

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

@@ -1,11 +1,18 @@
+:orphan:
+
 .. meta::
    :description: How to train a model using PyTorch for ROCm.
    :keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
 
 **************************************
-Training a model with PyTorch for ROCm
+Training a model with PyTorch on ROCm
 **************************************
 
+.. note::
+
+   Primus with the PyTorch torchtitan backend is intended to supersede the :doc:`ROCm PyTorch training <pytorch-training>` workflow.
+   See :doc:`primus-pytorch` for details.
+
 PyTorch is an open-source machine learning framework that is widely used for
 model training with GPU-optimized components for transformer-based models.
 
@@ -49,7 +56,7 @@ vary by model -- select one to get started.
             <div class="col-2 me-1 px-2 model-param-head">Model</div>
             <div class="row col-10 pe-0">
       {% for model_group in model_groups %}
-               <div class="col-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
       {% endfor %}
             </div>
          </div>
@@ -87,9 +94,11 @@ vary by model -- select one to get started.
       {% for model_group in model_groups %}
          {% set models = model_group.models %}
          {% for model in models %}
+         {% if model.training_modes %}
          * - {{ model.model }}
            - ``{{ model.training_modes | join('``, ``') }}``
 
+         {% endif %}
          {% endfor %}
       {% endfor %}
 
@@ -152,20 +161,23 @@ Run training
 
       .. tab-item:: MAD-integrated benchmarking
 
-         1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
-            directory and install the required packages on the host machine.
-
-            .. code-block:: shell
-
-               git clone https://github.com/ROCm/MAD
-               cd MAD
-               pip install -r requirements.txt
-
    {% for model_group in model_groups %}
       {% for model in model_group.models %}
 
          .. container:: model-doc {{ model.mad_tag }}
 
+            The following run command is tailored to {{ model.model }}.
+            See :ref:`amd-pytorch-training-model-support` to switch to another available model.
+
+            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
+               directory and install the required packages on the host machine.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD
+                  pip install -r requirements.txt
+
             2. For example, use this command to run the performance benchmark test on the {{ model.model }} model
                using one node with the {{ model.precision }} data type on the host machine.
 
@@ -187,6 +199,17 @@ Run training
 
       .. tab-item:: Standalone benchmarking
 
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+         .. container:: model-doc {{ model.mad_tag }}
+
+            The following commands are tailored to {{ model.model }}.
+            See :ref:`amd-pytorch-training-model-support` to switch to another available model.
+
+      {% endfor %}
+   {% endfor %}
+
          .. rubric:: Download the Docker image and required packages
 
          1. Use the following command to pull the Docker image from Docker Hub.
@@ -388,7 +411,7 @@ Run training
                .. note::
 
                   Currently, FLUX models are not supported out-of-the-box on {{ unified_docker.pull_tag }}.
-                  To use FLUX, refer to the previous version of the ``pytorch-training`` Docker: :doc:`previous-versions/pytorch-training-v25.6`
+                  To use FLUX, refer to ``rocm/pytorch-training`` Docker: :doc:`previous-versions/pytorch-training-v25.6`
 
                   Occasionally, downloading the Flux dataset might fail. In the event of this
                   error, manually download it from Hugging Face at

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 |

docs/sphinx/_toc.yml.in

@@ -67,9 +67,9 @@ subtrees:
         subtrees:
         - entries:
           - file: how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
-            title: Train a model with Primus and Megatron-Core
-          - file: how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
-            title: Train a model with PyTorch
+            title: Train a model with Primus and Megatron-LM
+          - file: how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
+            title: Train a model with Primus and PyTorch
           - file: how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
             title: Train a model with JAX MaxText
           - file: how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry
@@ -106,6 +106,8 @@ subtrees:
             title: PyTorch inference performance testing
           - file: how-to/rocm-for-ai/inference/benchmark-docker/sglang.rst
             title: SGLang inference performance testing
+          - file: how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst
+            title: SGLang distributed inference with Mooncake
           - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
             title: Deploy your model
 

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>