Update README.md removing reference to instructions that were moved

Followup to the change in https://github.com/ROCm/ROCm/pull/4907/files - the instructions are no longer below. (Could also move the previous paragraph into this section.)
[Ex CI] reduce pipeline size (#5140 )
2026-01-11 23:58:09 -05:00 · 2025-08-01 15:06:51 -07:00 · 2025-08-01 11:54:59 -04:00 · 2025-08-01 11:17:34 -04:00 · 2025-07-31 13:30:39 -04:00 · 2025-07-31 13:00:31 -04:00
52 changed files with 2197 additions and 986 deletions
--- a/.azuredevops/ci-builds/aomp-mainline.yml
+++ b/.azuredevops/ci-builds/aomp-mainline.yml
@@ -1,42 +0,0 @@
-variables:
- group: common
- template: /.azuredevops/variables-global.yml
-
-resources:
-  repositories:
-  - repository: aomp_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/aomp
-    ref: amd-mainline
-  - repository: aomp-extras_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/aomp-extras
-    ref: amd-mainline
-  - repository: flang_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/flang
-    ref: amd-mainline
-  - repository: llvm-project_repo
-    type: github
-    endpoint: ROCm
-    name: ROCm/llvm-project
-    ref: amd-mainline
-  pipelines:
-  - pipeline: rocr-runtime_pipeline
-    source: \ROCR-Runtime
-    trigger:
-      branches:
-        include:
-        - amd-mainline
-# this job will only be triggered after successful build sequence of llvm-project and ROCR-Runtime
-
-trigger: none
-pr: none
-
-jobs:
-  - template: ${{ variables.CI_COMPONENT_PATH }}/aomp.yml
-    parameters:
-      checkoutRepo: aomp_repo
--- a/.azuredevops/components/AMDMIGraphX.yml
+++ b/.azuredevops/components/AMDMIGraphX.yml
@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: AMDMIGraphX
 - name: checkoutRepo
  type: string
  default: 'self'
 - name: checkoutRef
  type: string
  default: ''
+# monorepo related parameters
+# - name: sparseCheckoutDir
+#   type: string
+#   default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -93,7 +112,11 @@ parameters:

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: AMDMIGraphX_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
    variables:
    - group: common
    - template: /.azuredevops/variables-global.yml
@@ -121,6 +144,8 @@ jobs:
        dependencyList: ${{ parameters.rocmDependencies }}
        gpuTarget: ${{ job.target }}
        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
      parameters:
        extraBuildFlags: >-
@@ -146,12 +171,12 @@ jobs:
        gpuTarget: ${{ job.target }}

 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: AMDMIGraphX_test_${{ job.target }}
-    dependsOn: AMDMIGraphX_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
    condition:
      and(succeeded(),
        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
        eq(${{ parameters.aggregatePipeline }}, False)
      )
    variables:
@@ -183,6 +208,8 @@ jobs:
        checkoutRef: ${{ parameters.checkoutRef }}
        dependencyList: ${{ parameters.rocmTestDependencies }}
        gpuTarget: ${{ job.target }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
    - task: CMake@1
      displayName: MIGraphXTest CMake Flags
      inputs:
@@ -199,7 +226,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
      parameters:
-        componentName: AMDMIGraphX
+        componentName: ${{ parameters.componentName }}
        testExecutable: make
        testParameters: -j$(nproc) check
        testPublishResults: false
--- a/.azuredevops/components/MIOpen.yml
+++ b/.azuredevops/components/MIOpen.yml
@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: MIOpen
 - name: checkoutRepo
  type: string
  default: 'self'
 - name: checkoutRef
  type: string
  default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -74,10 +93,31 @@ parameters:
        target: gfx942
      - gfx90a:
        target: gfx90a
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - MIVisionX:
+      name: MIVisionX
+      checkoutRepo: mivisionx_repo
+      sparseCheckoutDir: ''
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - MIOpen_build
+    - AMDMIGraphX:
+      name: AMDMIGraphX
+      checkoutRepo: amdmigraphx_repo
+      sparseCheckoutDir: ''
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - MIOpen_build

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: MIOpen_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
    variables:
    - group: common
    - template: /.azuredevops/variables-global.yml
@@ -95,6 +135,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/miopen-get-ck-build.yml
      parameters:
        gpuTarget: ${{ job.target }}
@@ -104,11 +145,13 @@ jobs:
        dependencyList: ${{ parameters.rocmDependencies }}
        gpuTarget: ${{ job.target }}
        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
    - task: Bash@3
      displayName: Build and install other dependencies
      inputs:
        targetType: inline
-        workingDirectory: $(Build.SourcesDirectory)
+        workingDirectory: $(Agent.BuildDirectory)/s
        script: |
          sed -i '/composable_kernel/d' requirements.txt
          mkdir -p $(Agent.BuildDirectory)/miopen-deps
@@ -130,8 +173,10 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
      parameters:
        gpuTarget: ${{ job.target }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
      parameters:
+        componentName: ${{ parameters.componentName }}
        gpuTarget: ${{ job.target }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -143,9 +188,9 @@ jobs:
          - miopen-deps

 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: MIOpen_test_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
    timeoutInMinutes: 180
-    dependsOn: MIOpen_build_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
    condition:
      and(succeeded(),
        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -169,6 +214,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/miopen-get-ck-build.yml
      parameters:
@@ -178,11 +224,13 @@ jobs:
        checkoutRef: ${{ parameters.checkoutRef }}
        dependencyList: ${{ parameters.rocmTestDependencies }}
        gpuTarget: ${{ job.target }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
    - task: Bash@3
      displayName: Build and install other dependencies
      inputs:
        targetType: inline
-        workingDirectory: $(Build.SourcesDirectory)
+        workingDirectory: $(Agent.BuildDirectory)/s
        script: |
          sed -i '/composable_kernel/d' requirements.txt
          mkdir -p $(Agent.BuildDirectory)/miopen-deps
@@ -193,7 +241,7 @@ jobs:
      displayName: 'MIOpen Test CMake Flags'
      inputs:
        cmakeArgs: >-
-          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Build.SourcesDirectory)/bin;$(Agent.BuildDirectory)/miopen-deps
+          -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm;$(Agent.BuildDirectory)/s/bin;$(Agent.BuildDirectory)/miopen-deps
          -DCMAKE_INSTALL_PREFIX=$(Agent.BuildDirectory)/rocm
          -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
          -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
@@ -203,19 +251,19 @@ jobs:
          -DBUILD_DEV=OFF
          -DMIOPEN_USE_MLIR=ON
          -DMIOPEN_GPU_SYNC=OFF
-          ..
+          $(Agent.BuildDirectory)/s
    - task: Bash@3
      displayName: 'MIOpen Test Build'
      inputs:
        targetType: inline
+        workingDirectory: build
        script: |
          cmake --build . --target tests -- -j$(nproc)
-        workingDirectory: $(Build.SourcesDirectory)/build
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
      parameters:
-        componentName: MIOpen
-        testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex "test_rnn_seq_api|GPU_Conv2dTuningAsm_FP32"'
+        componentName: ${{ parameters.componentName }}
+        testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex "test_rnn_seq_api|GPU_Conv2dTuningAsm_FP32|GPU_Conv2dTuningAsmBwdWrw_FP32"'
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
@@ -224,3 +272,15 @@ jobs:
        gpuTarget: ${{ job.target }}
        extraCopyDirectories:
          - miopen-deps
+
+# - ${{ if parameters.triggerDownstreamJobs }}:
+#   - ${{ each component in parameters.downstreamComponentMatrix }}:
+#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+#         parameters:
+#           checkoutRepo: ${{ component.checkoutRepo }}
+#           # sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+#           buildDependsOn: ${{ component.buildDependsOn }}
+#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+#           triggerDownstreamJobs: true
+#           unifiedBuild: ${{ parameters.unifiedBuild }}
--- a/.azuredevops/components/MIVisionX.yml
+++ b/.azuredevops/components/MIVisionX.yml
@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: MIVisionX
 - name: checkoutRepo
  type: string
  default: 'self'
 - name: checkoutRef
  type: string
  default: ''
+# monorepo related parameters
+# - name: sparseCheckoutDir
+#   type: string
+#   default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -60,6 +79,7 @@ parameters:
 - name: rocmTestDependencies
  type: object
  default:
+    - aomp
    - clr
    - half
    - hipBLAS-common
@@ -88,7 +108,11 @@ parameters:

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: MIVisionX_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
    variables:
    - group: common
    - template: /.azuredevops/variables-global.yml
@@ -110,6 +134,8 @@ jobs:
        dependencyList: ${{ parameters.rocmDependencies }}
        gpuTarget: ${{ job.target }}
        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
      parameters:
        extraBuildFlags: >-
@@ -131,12 +157,12 @@ jobs:
    #     gpuTarget: ${{ job.target }}

 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: MIVisionX_test_${{ job.target }}
-    dependsOn: MIVisionX_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
    condition:
      and(succeeded(),
        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
        eq(${{ parameters.aggregatePipeline }}, False)
      )
    variables:
@@ -161,6 +187,8 @@ jobs:
        checkoutRef: ${{ parameters.checkoutRef }}
        dependencyList: ${{ parameters.rocmTestDependencies }}
        gpuTarget: ${{ job.target }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
    - task: Bash@3
      displayName: Build MIVisionX tests
      inputs:
@@ -174,7 +202,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
      parameters:
-        componentName: MIVisionX
+        componentName: ${{ parameters.componentName }}
        testDir: 'mivisionx-tests'
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
      parameters:
--- a/.azuredevops/components/ROCR-Runtime.yml
+++ b/.azuredevops/components/ROCR-Runtime.yml
@@ -28,8 +28,8 @@ parameters:
 - name: rocmTestDependencies
  type: object
  default:
+    - amdsmi
    - llvm-project
-    - rocm_smi_lib
    - rocprofiler-register

 - name: jobMatrix
@@ -111,14 +111,6 @@ jobs:
      parameters:
        aptPackages: ${{ parameters.aptPackages }}
        packageManager: ${{ job.packageManager }}
-    - task: Bash@3
-      displayName: Install libhwloc5
-      inputs:
-        targetType: 'inline'
-        script: |
-          wget http://ftp.us.debian.org/debian/pool/main/h/hwloc/libhwloc5_1.11.12-3_amd64.deb
-          wget http://ftp.us.debian.org/debian/pool/main/h/hwloc/libhwloc-dev_1.11.12-3_amd64.deb
-          sudo apt install -y --allow-downgrades ./libhwloc5_1.11.12-3_amd64.deb ./libhwloc-dev_1.11.12-3_amd64.deb
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
      parameters:
@@ -161,6 +153,10 @@ jobs:
        targetType: 'inline'
        workingDirectory: $(Build.SourcesDirectory)/rocrtst/suites/test_common
        script: |
+          echo $(Build.SourcesDirectory)/rocrtst/thirdparty/lib | sudo tee -a /etc/ld.so.conf.d/rocm-ci.conf
+          sudo cat /etc/ld.so.conf.d/rocm-ci.conf
+          sudo ldconfig -v
+          ldconfig -p
          if [ -e /opt/rh/gcc-toolset-14/enable ]; then
            source /opt/rh/gcc-toolset-14/enable
          fi
--- a/.azuredevops/components/hipBLAS.yml
+++ b/.azuredevops/components/hipBLAS.yml
@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipBLAS
 - name: checkoutRepo
  type: string
  default: 'self'
 - name: checkoutRef
  type: string
  default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -69,10 +88,30 @@ parameters:
        target: gfx942
      - gfx90a:
        target: gfx90a
+# MIOpen depends on both rocRAND and hipBLAS
+# for a unified build, hipBLAS will be the one to call MIOpen
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - MIOpen:
+      name: MIOpen
+      sparseCheckoutDir: projects/miopen
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - hipBLAS_build
+      unifiedBuild:
+        downstreamAggregateNames: hipBLAS+rocRAND
+        buildDependsOn:
+          - hipBLAS_build
+          - rocRAND_build

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipBLAS_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
    variables:
    - group: common
    - template: /.azuredevops/variables-global.yml
@@ -88,6 +127,7 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aocl.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
      parameters:
@@ -95,6 +135,8 @@ jobs:
        dependencyList: ${{ parameters.rocmDependencies }}
        gpuTarget: ${{ job.target }}
        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
      parameters:
        extraBuildFlags: >-
@@ -109,9 +151,12 @@ jobs:
          -GNinja
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
      parameters:
+        componentName: ${{ parameters.componentName }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
        gpuTarget: ${{ job.target }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
      parameters:
+        componentName: ${{ parameters.componentName }}
        gpuTarget: ${{ job.target }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -121,46 +166,67 @@ jobs:
        installAOCL: true
        gpuTarget: ${{ job.target }}

- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipBLAS_test_${{ job.target }}
-    dependsOn: hipBLAS_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipBLAS
-        testExecutable: $(Agent.BuildDirectory)/rocm/bin/hipblas-test
-        testParameters: '--yaml hipblas_smoke.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        pipModules: ${{ parameters.pipModules }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testExecutable: $(Agent.BuildDirectory)/rocm/bin/hipblas-test
+          testParameters: '--yaml hipblas_smoke.yaml --gtest_output=xml:./test_output.xml --gtest_color=yes'
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          environment: test
+          gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}
+          ${{ if parameters.unifiedBuild }}:
+            buildDependsOn: ${{ component.unifiedBuild.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ component.unifiedBuild.downstreamAggregateNames }}
+          ${{ else }}:
+            buildDependsOn: ${{ component.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
--- a/.azuredevops/components/hipFFT.yml
+++ b/.azuredevops/components/hipFFT.yml
@@ -80,11 +80,11 @@ parameters:

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: ${{ parameters.componentName }}_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
    ${{ if parameters.buildDependsOn }}:
      dependsOn:
        - ${{ each build in parameters.buildDependsOn }}:
-          - ${{ build }}_${{ job.target }} # todo: add OS
+          - ${{ build }}_ubuntu2204_${{ job.target }}
    variables:
    - group: common
    - template: /.azuredevops/variables-global.yml
@@ -141,12 +141,12 @@ jobs:
    #     gpuTarget: ${{ job.target }}

 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ${{ parameters.componentName }}_test_${{ job.target }}
-    dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
    condition:
      and(succeeded(),
        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
        eq(${{ parameters.aggregatePipeline }}, False)
      )
    variables:
--- a/.azuredevops/components/hipRAND.yml
+++ b/.azuredevops/components/hipRAND.yml
@@ -72,15 +72,15 @@ parameters:
    testJobs:
      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
-# - name: downstreamComponentMatrix
-#   type: object
-#   default:
-#     - rocFFT:
-#       name: rocFFT
-#       sparseCheckoutDir: projects/rocfft
-#       skipUnifiedBuild: 'false'
-#       buildDependsOn:
-#         - hipRAND_build
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - rocFFT:
+      name: rocFFT
+      sparseCheckoutDir: projects/rocfft
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - hipRAND_build

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
@@ -206,14 +206,14 @@ jobs:
          environment: test
          gpuTarget: ${{ job.target }}

-# - ${{ if parameters.triggerDownstreamJobs }}:
-#   - ${{ each component in parameters.downstreamComponentMatrix }}:
-#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
-#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
-#         parameters:
-#           checkoutRepo: ${{ parameters.checkoutRepo }}
-#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
-#           buildDependsOn: ${{ component.buildDependsOn }}
-#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
-#           triggerDownstreamJobs: true
-#           unifiedBuild: ${{ parameters.unifiedBuild }}
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}
--- a/.azuredevops/components/hipSOLVER.yml
+++ b/.azuredevops/components/hipSOLVER.yml
@@ -1,10 +1,29 @@
 parameters:
+- name: componentName
+  type: string
+  default: hipSOLVER
 - name: checkoutRepo
  type: string
  default: 'self'
 - name: checkoutRef
  type: string
  default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -66,7 +85,11 @@ parameters:

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: hipSOLVER_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_ubuntu2204_${{ job.target }}
    variables:
    - group: common
    - template: /.azuredevops/variables-global.yml
@@ -81,18 +104,21 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
      parameters:
        checkoutRepo: ${{ parameters.checkoutRepo }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
      parameters:
        checkoutRef: ${{ parameters.checkoutRef }}
        dependencyList: ${{ parameters.rocmDependencies }}
        gpuTarget: ${{ job.target }}
        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
  # build external gtest and lapack
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
      parameters:
        componentName: external
-        cmakeBuildDir: '$(Build.SourcesDirectory)/deps/build'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/deps'
+        cmakeBuildDir: '$(Agent.BuildDirectory)/s/deps/build'
+        cmakeSourceDir: '$(Agent.BuildDirectory)/s/deps'
        installDir: '$(Pipeline.Workspace)/deps-install'
        extraBuildFlags: >-
          -DBUILD_BOOST=OFF
@@ -111,8 +137,10 @@ jobs:
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
      parameters:
        gpuTarget: ${{ job.target }}
+        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
      parameters:
+        componentName: ${{ parameters.componentName }}
        gpuTarget: ${{ job.target }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -122,44 +150,49 @@ jobs:
    #     extraCopyDirectories:
    #       - deps-install

- ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: hipSOLVER_test_${{ job.target }}
-    dependsOn: hipSOLVER_build_${{ job.target }}
-    condition:
-      and(succeeded(),
-        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
-        eq(${{ parameters.aggregatePipeline }}, False)
-      )
-    variables:
-    - group: common
-    - template: /.azuredevops/variables-global.yml
-    pool: ${{ job.target }}_test_pool
-    workspace:
-      clean: all
-    steps:
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
-      parameters:
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
-      parameters:
-        checkoutRef: ${{ parameters.checkoutRef }}
-        dependencyList: ${{ parameters.rocmTestDependencies }}
-        gpuTarget: ${{ job.target }}
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
-      parameters:
-        componentName: hipSOLVER
-        testDir: '$(Agent.BuildDirectory)/rocm/bin'
-        testExecutable: './hipsolver-test'
-        testParameters: '--gtest_filter="*checkin*" --gtest_output=xml:./test_output.xml --gtest_color=yes'
-    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-      parameters:
-        aptPackages: ${{ parameters.aptPackages }}
-        environment: test
-        gpuTarget: ${{ job.target }}
+- ${{ if eq(parameters.unifiedBuild, False) }}:
+  - ${{ each job in parameters.jobMatrix.testJobs }}:
+    - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
+      dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
+      condition:
+        and(succeeded(),
+          eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
+          not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
+          eq(${{ parameters.aggregatePipeline }}, False)
+        )
+      variables:
+      - group: common
+      - template: /.azuredevops/variables-global.yml
+      pool: ${{ job.target }}_test_pool
+      workspace:
+        clean: all
+      steps:
+      - checkout: none
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+        parameters:
+          preTargetFilter: ${{ parameters.componentName }}
+          gpuTarget: ${{ job.target }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+        parameters:
+          checkoutRef: ${{ parameters.checkoutRef }}
+          dependencyList: ${{ parameters.rocmTestDependencies }}
+          gpuTarget: ${{ job.target }}
+          ${{ if parameters.triggerDownstreamJobs }}:
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
+        parameters:
+          componentName: ${{ parameters.componentName }}
+          testDir: '$(Agent.BuildDirectory)/rocm/bin'
+          testExecutable: './hipsolver-test'
+          testParameters: '--gtest_filter="*checkin*" --gtest_output=xml:./test_output.xml --gtest_color=yes'
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          environment: test
+          gpuTarget: ${{ job.target }}
--- a/.azuredevops/components/rocBLAS.yml
+++ b/.azuredevops/components/rocBLAS.yml
@@ -104,17 +104,17 @@ parameters:
        - rocBLAS_build
    # rocSOLVER depends on both rocBLAS and rocPRIM
    # for a unified build, rocBLAS will be the one to call rocSOLVER
-    # - rocSOLVER:
-    #   name: rocSOLVER
-    #   sparseCheckoutDir: projects/rocsolver
-    #   skipUnifiedBuild: 'false'
-    #   buildDependsOn:
-    #     - rocBLAS_build
-    #   unifiedBuild:
-    #     downstreamAggregateNames: rocBLAS+rocPRIM
-    #     buildDependsOn:
-    #       - rocBLAS_build
-    #       - rocPRIM_build
+    - rocSOLVER:
+      name: rocSOLVER
+      sparseCheckoutDir: projects/rocsolver
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocBLAS_build
+      unifiedBuild:
+        downstreamAggregateNames: rocBLAS+rocPRIM
+        buildDependsOn:
+          - rocBLAS_build
+          - rocPRIM_build

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
--- a/.azuredevops/components/rocFFT.yml
+++ b/.azuredevops/components/rocFFT.yml
@@ -78,19 +78,19 @@ parameters:
        target: gfx942
      - gfx90a:
        target: gfx90a
-# - name: downstreamComponentMatrix
-#   type: object
-#   default:
-#     - hipFFT:
-#       name: hipFFT
-#       sparseCheckoutDir: projects/hipfft
-#       skipUnifiedBuild: 'false'
-#       buildDependsOn:
-#         - rocFFT_build
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - hipFFT:
+      name: hipFFT
+      sparseCheckoutDir: projects/hipfft
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocFFT_build

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: ${{ parameters.componentName }}_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
    ${{ if parameters.buildDependsOn }}:
      dependsOn:
        - ${{ each build in parameters.buildDependsOn }}:
@@ -151,12 +151,12 @@ jobs:
          - HIP_ROCCLR_HOME:::/home/user/workspace/rocm

 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: ${{ parameters.componentName }}_test_${{ job.target }}
-    dependsOn: ${{ parameters.componentName }}_build_${{ job.target }}
+  - job: ${{ parameters.componentName }}_test_ubuntu2204_${{ job.target }}
+    dependsOn: ${{ parameters.componentName }}_build_ubuntu2204_${{ job.target }}
    condition:
      and(succeeded(),
        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
-        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), variables['Build.DefinitionName'])),
+        not(containsValue(split(variables['DISABLED_${{ upper(job.target) }}_TESTS'], ','), '${{ parameters.componentName }}')),
        eq(${{ parameters.aggregatePipeline }}, False)
      )
    variables:
@@ -196,14 +196,14 @@ jobs:
        environment: test
        gpuTarget: ${{ job.target }}

-# - ${{ if parameters.triggerDownstreamJobs }}:
-#   - ${{ each component in parameters.downstreamComponentMatrix }}:
-#     - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
-#       - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
-#         parameters:
-#           checkoutRepo: ${{ parameters.checkoutRepo }}
-#           sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
-#           buildDependsOn: ${{ component.buildDependsOn }}
-#           downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
-#           triggerDownstreamJobs: true
-#           unifiedBuild: ${{ parameters.unifiedBuild }}
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          buildDependsOn: ${{ component.buildDependsOn }}
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}
--- a/.azuredevops/components/rocPRIM.yml
+++ b/.azuredevops/components/rocPRIM.yml
@@ -91,12 +91,12 @@ parameters:
        - rocPRIM_build
    # rocSOLVER depends on both rocBLAS and rocPRIM
    # for a unified build, rocBLAS will be the one to call rocSOLVER
-    # - rocSOLVER:
-    #   name: rocSOLVER
-    #   sparseCheckoutDir: projects/rocsolver
-    #   skipUnifiedBuild: 'true'
-    #   buildDependsOn:
-    #     - rocPRIM_build
+    - rocSOLVER:
+      name: rocSOLVER
+      sparseCheckoutDir: projects/rocsolver
+      skipUnifiedBuild: 'true'
+      buildDependsOn:
+        - rocPRIM_build

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
--- a/.azuredevops/components/rocRAND.yml
+++ b/.azuredevops/components/rocRAND.yml
@@ -79,6 +79,12 @@ parameters:
      skipUnifiedBuild: 'false'
      buildDependsOn:
        - rocRAND_build
+    - MIOpen:
+      name: MIOpen
+      sparseCheckoutDir: projects/miopen
+      skipUnifiedBuild: 'true'
+      buildDependsOn:
+        - rocRAND_build

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
--- a/.azuredevops/components/rocSOLVER.yml
+++ b/.azuredevops/components/rocSOLVER.yml
@@ -83,6 +83,28 @@ parameters:
    testJobs:
      - { os: ubuntu2204, packageManager: apt, target: gfx942 }
      - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+- name: downstreamComponentMatrix
+  type: object
+  default:
+    - hipBLAS:
+      name: hipBLAS
+      sparseCheckoutDir: projects/hipblas
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocSOLVER_build
+    # hipSOLVER depends on both rocSOLVER and rocSPARSE
+    # for a unified build, rocSOLVER will be the one to call hipSOLVER
+    - hipSOLVER:
+      name: hipSOLVER
+      sparseCheckoutDir: projects/hipsolver
+      skipUnifiedBuild: 'false'
+      buildDependsOn:
+        - rocSOLVER_build
+      unifiedBuild:
+        downstreamAggregateNames: rocSOLVER+rocSPARSE
+        buildDependsOn:
+          - rocSOLVER_build
+          - rocSPARSE_build

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
@@ -228,3 +250,19 @@ jobs:
          aptPackages: ${{ parameters.aptPackages }}
          environment: test
          gpuTarget: ${{ job.target }}
+
+- ${{ if parameters.triggerDownstreamJobs }}:
+  - ${{ each component in parameters.downstreamComponentMatrix }}:
+    - ${{ if not(and(parameters.unifiedBuild, eq(component.skipUnifiedBuild, 'true'))) }}:
+      - template: /.azuredevops/components/${{ component.name }}.yml@pipelines_repo
+        parameters:
+          checkoutRepo: ${{ parameters.checkoutRepo }}
+          sparseCheckoutDir: ${{ component.sparseCheckoutDir }}
+          triggerDownstreamJobs: true
+          unifiedBuild: ${{ parameters.unifiedBuild }}
+          ${{ if parameters.unifiedBuild }}:
+            buildDependsOn: ${{ component.unifiedBuild.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ component.unifiedBuild.downstreamAggregateNames }}
+          ${{ else }}:
+            buildDependsOn: ${{ component.buildDependsOn }}
+            downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}+${{ parameters.componentName }}
--- a/.azuredevops/components/rocm-libraries.yml
+++ b/.azuredevops/components/rocm-libraries.yml
@@ -0,0 +1,163 @@
+parameters:
+- name: componentName
+  type: string
+  default: rocm_libraries
+- name: checkoutRepo
+  type: string
+  default: 'self'
+- name: checkoutRef
+  type: string
+  default: ''
+# monorepo related parameters
+- name: sparseCheckoutDir
+  type: string
+  default: ''
+- name: triggerDownstreamJobs
+  type: boolean
+  default: false
+- name: downstreamAggregateNames
+  type: string
+  default: ''
+- name: buildDependsOn
+  type: object
+  default: null
+- name: unifiedBuild
+  type: boolean
+  default: false
+# set to true if doing full build of ROCm stack
+# and dependencies are pulled from same pipeline
+- name: aggregatePipeline
+  type: boolean
+  default: false
+- name: aptPackages
+  type: object
+  default:
+    - ccache
+    - gfortran
+    - git
+    - libdrm-dev
+    - libmsgpack-dev
+    - libnuma-dev
+    - ninja-build
+    - python3-pip
+    - python3-venv
+- name: pipModules
+  type: object
+  default:
+    - joblib
+    - "packaging>=22.0"
+    - --upgrade
+- name: rocmDependencies
+  type: object
+  default:
+    - aomp
+    - clr
+    - llvm-project
+    - rocminfo
+    - rocm-cmake
+    - rocm_smi_lib
+    - rocprofiler-register
+    - ROCR-Runtime
+    - roctracer
+- name: rocmTestDependencies
+  type: object
+  default:
+    - aomp
+    - clr
+    - llvm-project
+    - rocminfo
+    - rocm_smi_lib
+    - rocprofiler-register
+    - ROCR-Runtime
+    - roctracer
+
+- name: jobMatrix
+  type: object
+  default:
+    buildJobs:
+      - { pool: rocm-ci_ultra_build_pool, os: ubuntu2204, packageManager: apt, target: gfx942 }
+
+jobs:
+- ${{ each job in parameters.jobMatrix.buildJobs }}:
+  - job: ${{ parameters.componentName }}_build_${{ job.os }}_${{ job.target }}
+    timeoutInMinutes: 300
+    ${{ if parameters.buildDependsOn }}:
+      dependsOn:
+        - ${{ each build in parameters.buildDependsOn }}:
+          - ${{ build }}_${{ job.os }}
+    variables:
+    - group: common
+    - template: /.azuredevops/variables-global.yml
+    - name: DAY_STRING
+      value: $[format('{0:ddMMyyyy}', pipeline.startTime)]
+    pool: ${{ job.pool }}
+    ${{ if eq(job.os, 'almalinux8') }}:
+      container:
+        image: rocmexternalcicd.azurecr.io/manylinux228:latest
+        endpoint: ContainerService3
+    workspace:
+      clean: all
+    steps:
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
+      parameters:
+        aptPackages: ${{ parameters.aptPackages }}
+        pipModules: ${{ parameters.pipModules }}
+        packageManager: ${{ job.packageManager }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-cmake-latest.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
+      parameters:
+        checkoutRepo: ${{ parameters.checkoutRepo }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-vendor.yml
+      parameters:
+        dependencyList:
+          - gtest
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
+      parameters:
+        checkoutRef: ${{ parameters.checkoutRef }}
+        dependencyList: ${{ parameters.rocmDependencies }}
+        os: ${{ job.os }}
+        gpuTarget: ${{ job.target }}
+        aggregatePipeline: ${{ parameters.aggregatePipeline }}
+        ${{ if parameters.triggerDownstreamJobs }}:
+          downstreamAggregateNames: ${{ parameters.downstreamAggregateNames }}
+    - script: |
+        mkdir -p $(CCACHE_DIR)
+        echo "##vso[task.prependpath]/usr/lib/ccache"
+      displayName: Update path for ccache
+    - task: Cache@2
+      displayName: Ccache caching
+      inputs:
+        key: rocm-libraries | ${{ job.os }} | ${{ job.target }} | $(DAY_STRING) | $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
+        path: $(CCACHE_DIR)
+        restoreKeys: |
+          rocm-libraries | ${{ job.os }} | ${{ job.target }} | $(DAY_STRING)
+          rocm-libraries | ${{ job.os }} | ${{ job.target }}
+          rocm-libraries | ${{ job.os }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
+      parameters:
+        os: ${{ job.os }}
+        extraBuildFlags: >-
+          -DROCM_LIBRARIES_SUPERBUILD=ON
+          -GNinja
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+        gpuTarget: ${{ job.target }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        componentName: ${{ parameters.componentName }}
+        os: ${{ job.os }}
+        gpuTarget: ${{ job.target }}
+    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.os, 'ubuntu2204') }}:
+      - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+        parameters:
+          aptPackages: ${{ parameters.aptPackages }}
+          pipModules: ${{ parameters.pipModules }}
+          gpuTarget: ${{ job.target }}
+          extraPaths: /home/user/workspace/rocm/llvm/bin:/home/user/workspace/rocm/bin
+          installLatestCMake: true
+          extraCopyDirectories:
+            - deps
--- a/.azuredevops/components/rocprofiler-compute.yml
+++ b/.azuredevops/components/rocprofiler-compute.yml
@@ -65,43 +65,19 @@ parameters:
  type: object
  default:
    buildJobs:
-      - gfx942-staging:
-        name: gfx942_staging
+      - gfx942:
        target: gfx942
-        dependencySource: staging
-      - gfx942-mainline:
-        name: gfx942_mainline
-        target: gfx942
-        dependencySource: mainline
-      - gfx90a-staging:
-        name: gfx90a_staging
+      - gfx90a:
        target: gfx90a
-        dependencySource: staging
-      - gfx90a-mainline:
-        name: gfx90a_mainline
-        target: gfx90a
-        dependencySource: mainline
    testJobs:
-      - gfx942-staging:
-        name: gfx942_staging
+      - gfx942:
        target: gfx942
-        dependencySource: staging
-      - gfx942-mainline:
-        name: gfx942_mainline
-        target: gfx942
-        dependencySource: mainline
-      - gfx90a-staging:
-        name: gfx90a_staging
+      - gfx90a:
        target: gfx90a
-        dependencySource: staging
-      - gfx90a-mainline:
-        name: gfx90a_mainline
-        target: gfx90a
-        dependencySource: mainline

 jobs:
 - ${{ each job in parameters.jobMatrix.buildJobs }}:
-  - job: rocprofiler_compute_build_${{ job.name }}
+  - job: rocprofiler_compute_build_${{ job.target }}
    variables:
    - group: common
    - template: /.azuredevops/variables-global.yml
@@ -124,11 +100,9 @@ jobs:
          -GNinja
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
      parameters:
-        artifactName: ${{ job.dependencySource }}
        gpuTarget: ${{ job.target }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
      parameters:
-        artifactName: ${{ job.dependencySource }}
        gpuTarget: ${{ job.target }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
    # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
@@ -138,9 +112,9 @@ jobs:
    #     gpuTarget: ${{ job.target }}

 - ${{ each job in parameters.jobMatrix.testJobs }}:
-  - job: rocprofiler_compute_test_${{ job.name }}
+  - job: rocprofiler_compute_test_${{ job.target }}
    timeoutInMinutes: 120
-    dependsOn: rocprofiler_compute_build_${{ job.name }}
+    dependsOn: rocprofiler_compute_build_${{ job.target }}
    condition:
      and(succeeded(),
        eq(variables['ENABLE_${{ upper(job.target) }}_TESTS'], 'true'),
@@ -166,14 +140,12 @@ jobs:
        checkoutRepo: ${{ parameters.checkoutRepo }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
      parameters:
-        postTargetFilter: ${{ job.dependencySource }}
        gpuTarget: ${{ job.target }}
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
      parameters:
        checkoutRef: ${{ parameters.checkoutRef }}
        dependencyList: ${{ parameters.rocmTestDependencies }}
-        dependencySource: ${{ job.dependencySource }}
        gpuTarget: ${{ job.target }}
    - task: Bash@3
      displayName: Add en_US.UTF-8 locale
--- a/.azuredevops/components/rocprofiler-systems.yml
+++ b/.azuredevops/components/rocprofiler-systems.yml
@@ -37,6 +37,7 @@ parameters:
    - libpfm4-dev
    - libtool
    - libopenmpi-dev
+    - libsqlite3-dev
    - m4
    - ninja-build
    - openmpi-bin
--- a/.azuredevops/dependencies/boost.yml
+++ b/.azuredevops/dependencies/boost.yml
@@ -40,7 +40,6 @@ jobs:
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
    parameters:
      dependencyList: ${{ parameters.rocmDependencies }}
-      dependencySource: staging
  - task: Bash@3
    displayName: Add ROCm binaries to PATH
    inputs:
--- a/.azuredevops/nightly/pytorch.yml
+++ b/.azuredevops/nightly/pytorch.yml
@@ -219,7 +219,6 @@ jobs:
  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
    parameters:
      dependencyList: ${{ parameters.rocmDependencies }}
-      dependencySource: staging
      gpuTarget: $(JOB_GPU_TARGET)
      setupHIPLibrarySymlinks: true
  - task: Bash@3
@@ -406,7 +405,6 @@ jobs:
    parameters:
      dependencyList: ${{ parameters.rocmTestDependencies }}
      gpuTarget: $(JOB_GPU_TARGET)
-      dependencySource: staging
 # get sources to run test scripts
  - task: Bash@3
    displayName: git clone upstream pytorch
--- a/.azuredevops/nightly/rocm-nightly.yml
+++ b/.azuredevops/nightly/rocm-nightly.yml
@@ -3,21 +3,21 @@ parameters:
 - name: jobList
  type: object
  default:
-    - { os: ubuntu2204, target: gfx942, source: staging }
-    - { os: ubuntu2204, target: gfx90a, source: staging }
-    - { os: ubuntu2204, target: gfx1201, source: staging }
-    - { os: ubuntu2204, target: gfx1100, source: staging }
-    - { os: ubuntu2204, target: gfx1030, source: staging }
-    - { os: ubuntu2404, target: gfx942, source: staging }
-    - { os: ubuntu2404, target: gfx90a, source: staging }
-    - { os: ubuntu2404, target: gfx1201, source: staging }
-    - { os: ubuntu2404, target: gfx1100, source: staging }
-    - { os: ubuntu2404, target: gfx1030, source: staging }
-    - { os: almalinux8, target: gfx942, source: staging }
-    - { os: almalinux8, target: gfx90a, source: staging }
-    - { os: almalinux8, target: gfx1201, source: staging }
-    - { os: almalinux8, target: gfx1100, source: staging }
-    - { os: almalinux8, target: gfx1030, source: staging }
+    - { os: ubuntu2204, packageManager: apt, target: gfx942 }
+    - { os: ubuntu2204, packageManager: apt, target: gfx90a }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1201 }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1100 }
+    - { os: ubuntu2204, packageManager: apt, target: gfx1030 }
+    - { os: ubuntu2404, packageManager: apt, target: gfx942 }
+    - { os: ubuntu2404, packageManager: apt, target: gfx90a }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1201 }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1100 }
+    - { os: ubuntu2404, packageManager: apt, target: gfx1030 }
+    - { os: almalinux8, packageManager: dnf, target: gfx942 }
+    - { os: almalinux8, packageManager: dnf, target: gfx90a }
+    - { os: almalinux8, packageManager: dnf, target: gfx1201 }
+    - { os: almalinux8, packageManager: dnf, target: gfx1100 }
+    - { os: almalinux8, packageManager: dnf, target: gfx1030 }
 - name: rocmDependencies
  type: object
  default:
@@ -92,7 +92,8 @@ schedules:

 jobs:
 - ${{ each job in parameters.jobList }}:
-  - job: rocm_nightly_${{ job.os }}_${{ job.target }}_${{ job.source }}
+  - job: nightly_${{ job.os }}_${{ job.target }}
+    timeoutInMinutes: 90
    variables:
    - group: common
    - template: /.azuredevops/variables-global.yml
@@ -115,7 +116,6 @@ jobs:
      displayName: System disk space before ROCm
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
      parameters:
-        dependencySource: ${{ job.source }}
        dependencyList: ${{ parameters.rocmDependencies }}
        os: ${{ job.os }}
        gpuTarget: ${{ job.target }}
@@ -131,7 +131,7 @@ jobs:
        includeRootFolder: false
        archiveType: tar
        tarCompression: gz
-        archiveFile: $(Build.ArtifactStagingDirectory)/$(Build.DefinitionName)_$(Build.BuildNumber)_ubuntu2204_${{ job.target }}.tar.gz
+        archiveFile: $(Build.ArtifactStagingDirectory)/$(Build.DefinitionName)_$(Build.BuildNumber)_${{ job.os }}_${{ job.target }}.tar.gz
    - script: du -sh $(Build.ArtifactStagingDirectory)
      displayName: Compressed ROCm size
    - task: PublishPipelineArtifact@1
@@ -144,5 +144,95 @@ jobs:
      inputs:
        workingDirectory: $(Pipeline.Workspace)
        targetType: inline
-        script: echo "$(Build.DefinitionName)_$(Build.BuildNumber)_ubuntu2204_${{ job.target }}.tar.gz" >> pipelineArtifacts.txt
+        script: echo "$(Build.DefinitionName)_$(Build.BuildNumber)_${{ job.os }}_${{ job.target }}.tar.gz" >> pipelineArtifacts.txt
    - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
+    - ${{ if eq(job.packageManager, 'apt') }}:
+      - task: Bash@3
+        displayName: Create Dockerfile
+        inputs:
+          workingDirectory: $(Agent.BuildDirectory)
+          targetType: inline
+          script: |
+            cat <<'EOF' > Dockerfile
+              ${{ iif(eq(job.os, 'ubuntu2204'), 'FROM ubuntu:22.04', '') }}
+              ${{ iif(eq(job.os, 'ubuntu2404'), 'FROM ubuntu:24.04', '') }}
+
+              WORKDIR /root
+              RUN mkdir rocm
+
+              RUN apt update \
+                && apt upgrade -y \
+                && apt install -y cmake curl git gcc g++ gpg lsb-release lsof ninja-build pkg-config python3 python3-pip wget zip libdrm-dev libelf-dev libgtest-dev libhsakmt-dev libhwloc-dev libnuma-dev libstdc++-12-dev libtbb-dev jq \
+                && apt clean all
+
+              RUN PACKAGE_NAME=$(curl -s https://repo.radeon.com/rocm/apt/latest/pool/main/h/hsa-amd-aqlprofile/ | grep -oP "href=\"\K[^\"]*$(lsb_release -rs)[^\"]*\.deb") \
+                && wget -nv --retry-connrefused https://repo.radeon.com/rocm/apt/latest/pool/main/h/hsa-amd-aqlprofile/$PACKAGE_NAME \
+                && mkdir hsa-amd-aqlprofile \
+                && dpkg-deb -R $PACKAGE_NAME hsa-amd-aqlprofile \
+                && cp -R hsa-amd-aqlprofile/opt/rocm-*/* rocm
+
+              RUN ARTIFACT_URL="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis/build/builds/$(Build.BuildId)/artifacts?artifactName=nightly${{ job.os }}${{ job.target }}&api-version=7.1" \
+                && DOWNLOAD_URL=$(curl -s $ARTIFACT_URL | jq ".resource.downloadUrl" | tr -d '"') \
+                && wget -nv --retry-connrefused $DOWNLOAD_URL -O nightly.zip \
+                && unzip nightly.zip \
+                && tar -xf nightly${{ job.os }}${{ job.target }}/rocm-nightly*${{ job.os }}*${{ job.target }}*.tar.gz -C rocm
+
+              RUN echo /root/rocm/lib | tee /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/llvm/lib | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/lib64 | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/llvm/lib64 | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN ldconfig -v
+              ENV PATH="$PATH:/root/rocm/bin"
+              ENTRYPOINT ["/bin/bash"]
+            EOF
+            cat Dockerfile
+    - ${{ elseif eq(job.packageManager, 'dnf') }}:
+      - task: Bash@3
+        displayName: Create Dockerfile
+        inputs:
+          workingDirectory: $(Agent.BuildDirectory)
+          targetType: inline
+          script: |
+            cat <<'EOF' > Dockerfile
+              ${{ iif(eq(job.os, 'almalinux8'), 'FROM almalinux:8', '') }}
+
+              WORKDIR /root
+              RUN mkdir rocm
+
+              RUN dnf install -y cmake curl git gcc gcc-c++ gnupg2 redhat-lsb-core lsof pkgconf python3 python3-pip wget zip libdrm-devel elfutils-libelf-devel numactl-devel libstdc++-devel tbb-devel jq \
+                && dnf clean all
+
+              RUN PACKAGE_NAME=$(curl -s https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/ | grep -oP "hsa-amd-aqlprofile-[^\"]+\.rpm" | head -n1) \
+                && wget -nv --retry-connrefused https://repo.radeon.com/rocm/rhel8/$(REPO_RADEON_VERSION)/main/$PACKAGE_NAME \
+                && mkdir hsa-amd-aqlprofile \
+                && dnf -y install rpm-build cpio \
+                && rpm2cpio $PACKAGE_NAME | (cd hsa-amd-aqlprofile && cpio -idmv) \
+                && cp -R hsa-amd-aqlprofile/opt/rocm-*/* rocm
+
+              RUN ARTIFACT_URL="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis/build/builds/$(Build.BuildId)/artifacts?artifactName=nightly${{ job.os }}${{ job.target }}&api-version=7.1" \
+                && DOWNLOAD_URL=$(curl -s $ARTIFACT_URL | jq ".resource.downloadUrl" | tr -d '"') \
+                && wget -nv --retry-connrefused $DOWNLOAD_URL -O nightly.zip \
+                && UNZIP_DISABLE_ZIPBOMB_DETECTION=TRUE unzip nightly.zip \
+                && tar -xf nightly${{ job.os }}${{ job.target }}/rocm-nightly*${{ job.os }}*${{ job.target }}*.tar.gz -C rocm
+
+              RUN echo /root/rocm/lib | tee /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/llvm/lib | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/lib64 | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN echo /root/rocm/llvm/lib64 | tee -a /etc/ld.so.conf.d/rocm-ci.conf
+              RUN ldconfig -v
+              ENV PATH="$PATH:/root/rocm/bin"
+              ENTRYPOINT ["/bin/bash"]
+            EOF
+            cat Dockerfile
+    - task: Docker@2
+      displayName: Build and upload Docker image
+      inputs:
+        containerRegistry: ContainerService3
+        repository: 'nightly-${{ job.os }}-${{ job.target }}'
+        Dockerfile: '$(Agent.BuildDirectory)/Dockerfile'
+        buildContext: '$(Agent.BuildDirectory)'
+    - task: Bash@3
+      displayName: '!! Docker Run Command !!'
+      inputs:
+        targetType: inline
+        script: echo "docker run -it --network=host --device=/dev/kfd --device=/dev/dri --security-opt seccomp=unconfined rocmexternalcicd.azurecr.io/nightly-${{ job.os }}-${{ job.target }}:$(Build.BuildId)" | tr '[:upper:]' '[:lower:]'
--- a/.azuredevops/templates/steps/dependencies-rocm.yml
+++ b/.azuredevops/templates/steps/dependencies-rocm.yml
@@ -3,13 +3,6 @@ parameters:
 - name: checkoutRef
  type: string
  default: ''
- name: dependencySource # optional, overrides checkoutRef
-  type: string
-  default: null
-  values:
-    - null # empty strings aren't allowed as values, use null instead
-    - staging
-    - mainline
 - name: dependencyList
  type: object
  default: []
@@ -38,309 +31,240 @@ parameters:
  type: object
  default:
    AMDMIGraphX:
-      pipelineId: $(AMDMIGRAPHX_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: master
+      pipelineId: 113
+      developBranch: develop
      hasGpuTarget: true
    amdsmi:
-      pipelineId: $(AMDSMI_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 99
+      developBranch: amd-staging
      hasGpuTarget: false
    aomp-extras:
-      pipelineId: $(AOMP_EXTRAS_PIPELINE_ID)
-      stagingBranch: aomp-dev
-      mainlineBranch: aomp-dev
+      pipelineId: 111
+      developBranch: aomp-dev
      hasGpuTarget: false
    aomp:
-      pipelineId: $(AOMP_PIPELINE_ID)
-      stagingBranch: aomp-dev
-      mainlineBranch: amd-mainline
+      pipelineId: 115
+      developBranch: aomp-dev
      hasGpuTarget: false
    clr:
-      pipelineId: $(CLR_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 145
+      developBranch: amd-staging
      hasGpuTarget: false
    composable_kernel:
-      pipelineId: $(COMPOSABLE_KERNEL_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 86
+      developBranch: develop
      hasGpuTarget: true
    half:
-      pipelineId: $(HALF_PIPELINE_ID)
-      stagingBranch: rocm
-      mainlineBranch: rocm
+      pipelineId: 101
+      developBranch: rocm
      hasGpuTarget: false
    HIP:
-      pipelineId: $(HIP_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 93
+      developBranch: amd-staging
      hasGpuTarget: false
    hip-tests:
-      pipelineId: $(HIP_TESTS_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 233
+      developBranch: amd-staging
      hasGpuTarget: false
    hipBLAS:
-      pipelineId: $(HIPBLAS_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 317
+      developBranch: develop
      hasGpuTarget: true
    hipBLASLt:
-      pipelineId: $(HIPBLASLT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 301
+      developBranch: develop
      hasGpuTarget: true
    hipBLAS-common:
-      pipelineId: $(HIPBLAS_COMMON_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 300
+      developBranch: develop
      hasGpuTarget: false
    hipCUB:
-      pipelineId: $(HIPCUB_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 277
+      developBranch: develop
      hasGpuTarget: true
    hipFFT:
-      pipelineId: $(HIPFFT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 283
+      developBranch: develop
      hasGpuTarget: true
    hipfort:
-      pipelineId: $(HIPFORT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 102
+      developBranch: develop
      hasGpuTarget: false
    HIPIFY:
-      pipelineId: $(HIPIFY_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 92
+      developBranch: amd-staging
      hasGpuTarget: false
    hipRAND:
-      pipelineId: $(HIPRAND_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 275
+      developBranch: develop
      hasGpuTarget: true
    hipSOLVER:
-      pipelineId: $(HIPSOLVER_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 84
+      developBranch: develop
      hasGpuTarget: true
    hipSPARSE:
-      pipelineId: $(HIPSPARSE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 315
+      developBranch: develop
      hasGpuTarget: true
    hipSPARSELt:
-      pipelineId: $(HIPSPARSELT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 309
+      developBranch: develop
      hasGpuTarget: true
    hipTensor:
-      pipelineId: $(HIPTENSOR_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 105
+      developBranch: develop
      hasGpuTarget: true
    llvm-project:
-      pipelineId: $(LLVM_PROJECT_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 2
+      developBranch: amd-staging
      hasGpuTarget: false
    MIOpen:
-      pipelineId: $(MIOpen_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: amd-master
+      pipelineId: 320
+      developBranch: develop
      hasGpuTarget: true
    MIVisionX:
-      pipelineId: $(MIVISIONX_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: master
-      hasGpuTarget: true
-    omnitrace: # deprecated
-      pipelineId: $(OMNITRACE_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 80
+      developBranch: develop
      hasGpuTarget: true
    rccl:
-      pipelineId: $(RCCL_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 107
+      developBranch: develop
      hasGpuTarget: true
    rdc:
-      pipelineId: $(RDC_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 100
+      developBranch: amd-staging
      hasGpuTarget: false
    rocAL:
-      pipelineId: $(ROCAL_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 151
+      developBranch: develop
      hasGpuTarget: true
    rocALUTION:
-      pipelineId: $(ROCALUTION_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 89
+      developBranch: develop
      hasGpuTarget: true
    rocBLAS:
-      pipelineId: $(ROCBLAS_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 302
+      developBranch: develop
      hasGpuTarget: true
    ROCdbgapi:
-      pipelineId: $(ROCDBGAPI_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 135
+      developBranch: amd-staging
      hasGpuTarget: false
    rocDecode:
-      pipelineId: $(ROCDECODE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 79
+      developBranch: develop
      hasGpuTarget: false
    rocFFT:
-      pipelineId: $(ROCFFT_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 282
+      developBranch: develop
      hasGpuTarget: true
    ROCgdb:
-      pipelineId: $(ROCGDB_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline-rocgdb-15
+      pipelineId: 134
+      developBranch: amd-staging
      hasGpuTarget: false
    rocJPEG:
-      pipelineId: $(ROCJPEG_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 262
+      developBranch: develop
      hasGpuTarget: false
    rocm-cmake:
-      pipelineId: $(ROCM_CMAKE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 6
+      developBranch: develop
      hasGpuTarget: false
    rocm-core:
-      pipelineId: $(ROCM_CORE_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: amd-master
+      pipelineId: 103
+      developBranch: master
      hasGpuTarget: false
    rocm-examples:
-      pipelineId: $(ROCM_EXAMPLES_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 216
+      developBranch: amd-staging
      hasGpuTarget: true
    rocminfo:
-      pipelineId: $(ROCMINFO_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 91
+      developBranch: amd-staging
      hasGpuTarget: false
    rocMLIR:
-      pipelineId: $(ROCMLIR_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 229
+      developBranch: develop
      hasGpuTarget: false
    ROCmValidationSuite:
-      pipelineId: $(ROCMVALIDATIONSUITE_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: master
+      pipelineId: 106
+      developBranch: master
      hasGpuTarget: true
    rocm_bandwidth_test:
-      pipelineId: $(ROCM_BANDWIDTH_TEST_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: master
+      pipelineId: 88
+      developBranch: master
      hasGpuTarget: false
    rocm_smi_lib:
-      pipelineId: $(ROCM_SMI_LIB_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 96
+      developBranch: amd-staging
      hasGpuTarget: false
    rocPRIM:
-      pipelineId: $(ROCPRIM_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 273
+      developBranch: develop
      hasGpuTarget: true
    rocprofiler:
-      pipelineId: $(ROCPROFILER_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-master
+      pipelineId: 143
+      developBranch: amd-staging
      hasGpuTarget: true
    rocprofiler-compute:
-      pipelineId: $(ROCPROFILER_COMPUTE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: amd-mainline
+      pipelineId: 257
+      developBranch: develop
      hasGpuTarget: true
    rocprofiler-register:
-      pipelineId: $(ROCPROFILER_REGISTER_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 1
+      developBranch: amd-staging
      hasGpuTarget: false
    rocprofiler-sdk:
-      pipelineId: $(ROCPROFILER_SDK_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 246
+      developBranch: amd-staging
      hasGpuTarget: true
    rocprofiler-systems:
-      pipelineId: $(ROCPROFILER_SYSTEMS_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 255
+      developBranch: amd-staging
      hasGpuTarget: true
    rocPyDecode:
-      pipelineId: $(ROCPYDECODE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 239
+      developBranch: develop
      hasGpuTarget: true
    ROCR-Runtime:
-      pipelineId: $(ROCR_RUNTIME_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 10
+      developBranch: amd-staging
      hasGpuTarget: false
    rocRAND:
-      pipelineId: $(ROCRAND_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 274
+      developBranch: develop
      hasGpuTarget: true
    rocr_debug_agent:
-      pipelineId: $(ROCR_DEBUG_AGENT_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 136
+      developBranch: amd-staging
      hasGpuTarget: false
    rocSOLVER:
-      pipelineId: $(ROCSOLVER_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 81
+      developBranch: develop
      hasGpuTarget: true
    rocSPARSE:
-      pipelineId: $(ROCSPARSE_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 314
+      developBranch: develop
      hasGpuTarget: true
-    ROCT-Thunk-Interface: # deprecated
-      pipelineId: $(ROCT_THUNK_INTERFACE_PIPELINE_ID)
-      stagingBranch: master
-      mainlineBranch: master
-      hasGpuTarget: false
    rocThrust:
-      pipelineId: $(ROCTHRUST_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      pipelineId: 276
+      developBranch: develop
      hasGpuTarget: true
    roctracer:
-      pipelineId: $(ROCTRACER_PIPELINE_ID)
-      stagingBranch: amd-staging
-      mainlineBranch: amd-mainline
+      pipelineId: 141
+      developBranch: amd-staging
      hasGpuTarget: true
    rocWMMA:
-      pipelineId: $(ROCWMMA_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 109
+      developBranch: develop
      hasGpuTarget: true
    rpp:
-      pipelineId: $(RPP_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 78
+      developBranch: develop
      hasGpuTarget: true
    TransferBench:
-      pipelineId: $(TRANSFERBENCH_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: mainline
+      pipelineId: 265
+      developBranch: develop
      hasGpuTarget: true

 steps:
@@ -356,72 +280,30 @@ steps:
      parameters:
        componentName: ${{ split(dependency, ':')[0] }}
        pipelineId: ${{ parameters.componentVarList[split(dependency, ':')[0]].pipelineId }}
+        branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].developBranch }}
        aggregatePipeline: ${{ parameters.aggregatePipeline }}
        extractAndDeleteFiles: false
-        ${{ if parameters.componentVarList[split(dependency, ':')[0]].hasGpuTarget }}:
-          fileFilter: "${{ split(dependency, ':')[1] }}*_${{ parameters.os }}_${{ parameters.gpuTarget }}"
-        # dependencySource = staging
-        ${{ if eq(parameters.dependencySource, 'staging')}}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
-        # dependencySource = mainline
-        ${{ elseif eq(parameters.dependencySource, 'mainline')}}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].mainlineBranch }}
-        # checkoutRef = staging
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].stagingBranch) }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
-        # checkoutRef = mainline
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].mainlineBranch) }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].mainlineBranch }}
-        # SourceBranchName = staging
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].stagingBranch) }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
-        # SourceBranchName = mainline
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].mainlineBranch) }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].mainlineBranch }}
-        # default = staging
-        ${{ else }}:
-          branchName: ${{ parameters.componentVarList[split(dependency, ':')[0]].stagingBranch }}
 # no colon (:) found in this item in the list
  - ${{ elseif containsValue(split(parameters.downstreamAggregateNames, '+'), dependency) }}:
    - template: local-artifact-download.yml
      parameters:
-        ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
-          gpuTarget: ${{ parameters.gpuTarget }}
+        buildType: current
        preTargetFilter: ${{ dependency }}
        os: ${{ parameters.os }}
-        buildType: current
+        ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
+          gpuTarget: ${{ parameters.gpuTarget }}
  - ${{ else }}:
    - template: artifact-download.yml
      parameters:
        componentName: ${{ dependency }}
        pipelineId: ${{ parameters.componentVarList[dependency].pipelineId }}
+        branchName: ${{ parameters.componentVarList[dependency].developBranch }}
        aggregatePipeline: ${{ parameters.aggregatePipeline }}
        extractAndDeleteFiles: false
        ${{ if parameters.componentVarList[dependency].hasGpuTarget }}:
          fileFilter: ${{ parameters.os }}_${{ parameters.gpuTarget }}
        ${{ else }}:
          fileFilter: ${{ parameters.os }}
-        # dependencySource = staging
-        ${{ if eq(parameters.dependencySource, 'staging')}}:
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
-        # dependencySource = mainline
-        ${{ elseif eq(parameters.dependencySource, 'mainline')}}:
-          branchName: ${{ parameters.componentVarList[dependency].mainlineBranch }}
-        # checkoutRef = staging
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].stagingBranch) }}:
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
-        # checkoutRef = mainline
-        ${{ elseif eq(parameters.checkoutRef, parameters.componentVarList[variables['Build.DefinitionName']].mainlineBranch) }}:
-          branchName: ${{ parameters.componentVarList[dependency].mainlineBranch }}
-        # SourceBranchName = staging
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].stagingBranch) }}:
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
-        # SourceBranchName = mainline
-        ${{ elseif eq(variables['Build.SourceBranchName'], parameters.componentVarlist[variables['Build.DefinitionName']].mainlineBranch) }}:
-          branchName: ${{ parameters.componentVarList[dependency].mainlineBranch }}
-        # default = staging
-        ${{ else }}:
-          branchName: ${{ parameters.componentVarList[dependency].stagingBranch }}
 - task: ExtractFiles@1
  displayName: Extract ROCm artifacts
  inputs:
--- a/.azuredevops/templates/steps/miopen-get-ck-build.yml
+++ b/.azuredevops/templates/steps/miopen-get-ck-build.yml
@@ -13,7 +13,7 @@ steps:
    CC: $(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
  inputs:
    targetType: inline
-    workingDirectory: $(Build.SourcesDirectory)
+    workingDirectory: $(Agent.BuildDirectory)/s
    script: |
      AZ_API="https://dev.azure.com/ROCm-CI/ROCm-CI/_apis"
      GH_API="https://api.github.com/repos/ROCm"
--- a/.azuredevops/variables-global.yml
+++ b/.azuredevops/variables-global.yml
@@ -23,145 +23,25 @@ variables:
  value: rocm-ci_high_build_pool
 - name: ULTRA_BUILD_POOL
  value: rocm-ci_ultra_build_pool
- name: ON_PREM_BUILD_POOL
-  value: rocm-ci_build_pool
- name: LARGE_DISK_BUILD_POOL
-  value: rocm-ci_larger_base_disk_pool
 - name: GFX942_TEST_POOL
  value: gfx942_test_pool
 - name: GFX90A_TEST_POOL
  value: gfx90a_test_pool
 - name: LATEST_RELEASE_VERSION
-  value: 6.4.1
+  value: 6.4.2
 - name: REPO_RADEON_VERSION
-  value: 6.4.1
+  value: 6.4.2
 - name: NEXT_RELEASE_VERSION
  value: 7.0.0
 - name: LATEST_RELEASE_TAG
-  value: rocm-6.4.1
+  value: rocm-6.4.2
 - name: DOCKER_SKIP_GFX
  value: gfx90a
- name: AMDMIGRAPHX_PIPELINE_ID
-  value: 113
- name: AMDSMI_PIPELINE_ID
-  value: 99
- name: AOMP_EXTRAS_PIPELINE_ID
-  value: 111
- name: AOMP_PIPELINE_ID
-  value: 115
- name: CLR_PIPELINE_ID
-  value: 145
 - name: COMPOSABLE_KERNEL_PIPELINE_ID
  value: 86
- name: FLANG_LEGACY_PIPELINE_ID
-  value: 77
- name: HALF_PIPELINE_ID
-  value: 101
 - name: HALF560_PIPELINE_ID
  value: 68
 - name: HALF560_BUILD_ID
  value: 621
 - name: HIP_PIPELINE_ID
  value: 93
- name: HIP_TESTS_PIPELINE_ID
-  value: 233
- name: HIPBLAS_COMMON_PIPELINE_ID
-  value: 300
- name: HIPBLAS_PIPELINE_ID
-  value: 87
- name: HIPBLASLT_PIPELINE_ID
-  value: 301
- name: HIPCUB_PIPELINE_ID
-  value: 277
- name: HIPFFT_PIPELINE_ID
-  value: 121
- name: HIPFORT_PIPELINE_ID
-  value: 102
- name: HIPIFY_PIPELINE_ID
-  value: 92
- name: HIPRAND_PIPELINE_ID
-  value: 275
- name: HIPSOLVER_PIPELINE_ID
-  value: 84
- name: HIPSPARSE_PIPELINE_ID
-  value: 83
- name: HIPSPARSELT_PIPELINE_ID
-  value: 309
- name: HIPTENSOR_PIPELINE_ID
-  value: 105
- name: LLVM_PROJECT_PIPELINE_ID
-  value: 2
- name: MIOPEN_PIPELINE_ID
-  value: 108
- name: MIVISIONX_PIPELINE_ID
-  value: 80
- name: RCCL_PIPELINE_ID
-  value: 107
- name: RDC_PIPELINE_ID
-  value: 100
- name: ROCAL_PIPELINE_ID
-  value: 151
- name: ROCALUTION_PIPELINE_ID
-  value: 89
- name: ROCBLAS_PIPELINE_ID
-  value: 302
- name: ROCDBGAPI_PIPELINE_ID
-  value: 135
- name: ROCDECODE_PIPELINE_ID
-  value: 79
- name: ROCFFT_PIPELINE_ID
-  value: 120
- name: ROCGDB_PIPELINE_ID
-  value: 134
- name: ROCJPEG_PIPELINE_ID
-  value: 262
- name: ROCM_BANDWIDTH_TEST_PIPELINE_ID
-  value: 88
- name: ROCM_CMAKE_PIPELINE_ID
-  value: 6
- name: ROCM_CORE_PIPELINE_ID
-  value: 103
- name: ROCM_EXAMPLES_PIPELINE_ID
-  value: 216
- name: ROCM_SMI_LIB_PIPELINE_ID
-  value: 96
- name: ROCMINFO_PIPELINE_ID
-  value: 91
- name: ROCMLIR_PIPELINE_ID
-  value: 229
- name: ROCMVALIDATIONSUITE_PIPELINE_ID
-  value: 106
- name: ROCPRIM_PIPELINE_ID
-  value: 273
- name: ROCPROFILER_COMPUTE_PIPELINE_ID
-  value: 257
- name: ROCPROFILER_REGISTER_PIPELINE_ID
-  value: 1
- name: ROCPROFILER_SDK_PIPELINE_ID
-  value: 246
- name: ROCPROFILER_SYSTEMS_PIPELINE_ID
-  value: 255
- name: ROCPROFILER_PIPELINE_ID
-  value: 143
- name: ROCPYDECODE_PIPELINE_ID
-  value: 239
- name: ROCR_DEBUG_AGENT_PIPELINE_ID
-  value: 136
- name: ROCR_RUNTIME_PIPELINE_ID
-  value: 10
- name: ROCRAND_PIPELINE_ID
-  value: 274
- name: ROCSOLVER_PIPELINE_ID
-  value: 81
- name: ROCSPARSE_PIPELINE_ID
-  value: 314
- name: ROCTHRUST_PIPELINE_ID
-  value: 276
- name: ROCTRACER_PIPELINE_ID
-  value: 141
- name: ROCWMMA_PIPELINE_ID
-  value: 109
- name: RPP_PIPELINE_ID
-  value: 78
- name: TRANSFERBENCH_PIPELINE_ID
-  value: 265
--- a/.wordlist.txt
+++ b/.wordlist.txt
@@ -45,6 +45,7 @@ Bootloader
 CAS
 CCD
 CDNA
+CGUI
 CHTML
 CIFAR
 CLI
@@ -115,6 +116,7 @@ DevCap
 DirectX
 Dockerfile
 Doxygen
+dropless
 ELMo
 ENDPGM
 EPYC
@@ -176,6 +178,7 @@ HBM
 HCA
 HGX
 HIPCC
+hipDataType
 HIPExtension
 HIPIFY
 HIPification
@@ -270,6 +273,7 @@ Makefiles
 Matplotlib
 Matrox
 MaxText
+Megablocks
 Megatrends
 Megatron
 Mellanox
@@ -279,6 +283,7 @@ Miniconda
 MirroredStrategy
 Mixtral
 MosaicML
+MoEs
 Mpops
 Multicore
 Multithreaded
@@ -408,6 +413,7 @@ SDMA
 SDPA
 SDRAM
 SENDMSG
+SGLang
 SGPR
 SGPRs
 SHA
@@ -452,6 +458,8 @@ TPS
 TPU
 TPUs
 TSME
+Taichi
+Taichi's
 Tagram
 TensileLite
 TensorBoard
@@ -863,6 +871,7 @@ seealso
 sendmsg
 seqs
 serializers
+sglang
 shader
 sharding
 sigmoid
--- a/README.md
+++ b/README.md
@@ -23,9 +23,6 @@ source software compilers, debuggers, and libraries. ROCm is fully integrated in
 > A new open source build platform for ROCm is under development at
 > https://github.com/ROCm/TheRock, featuring a unified CMake build with bundled
 > dependencies, Windows support, and more.
->
-> The instructions below describe the prior process for building from source
-> which will be replaced once TheRock is mature enough.

 ## Getting and Building ROCm from Source

--- a/default.xml
+++ b/default.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.4.1"
+    <default revision="refs/tags/rocm-6.4.2"
     remote="rocm-org"
     sync-c="true"
     sync-j="4" />
--- a/docs/compatibility/compatibility-matrix-historical-6.0.csv
+++ b/docs/compatibility/compatibility-matrix-historical-6.0.csv
@@ -30,9 +30,11 @@ ROCm Version,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,
      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"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>`,"2.18.1, 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>`,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
-      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,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>`,2.4.0,2.4.0,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:`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,0.3.0.post0,N/A,N/A,N/A,N/A,N/A,N/A
+      :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,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,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,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,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,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
      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.2,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
 ,,,,,,,,,,,,,,,,,
      ,,,,,,,,,,,,,,,,,
--- a/docs/compatibility/compatibility-matrix.rst
+++ b/docs/compatibility/compatibility-matrix.rst
@@ -56,7 +56,7 @@ compatibility and system requirements.
      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"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"
      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.4.35,0.4.35,0.4.31  
      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`,N/A,N/A,85f95ae
-      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`,2.4.0,2.4.0,N/A
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`,N/A,N/A,0.7.0
      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.2,1.2,1.17.3
      ,,,
      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
@@ -241,6 +241,8 @@ Expand for full historical view of:
   .. [#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.
+   .. [#dgl_compat] DGL is only supported on ROCm 6.4.0.
+   .. [#taichi_compat] Taichi is only supported on ROCm 6.3.2.
   .. [#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>`_.
   .. [#ROCT-rocr-past-60] Starting from ROCm 6.3.0, the ROCT Thunk Interface is included as part of the ROCr runtime package.
   
--- a/docs/compatibility/ml-compatibility/dgl-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/dgl-compatibility.rst
@@ -42,16 +42,16 @@ GAT, GCN and GraphSage. Using these we can support a variety of use-cases such a
 - 1D (Temporal) and 2D (Image) Classification
 - Drug Discovery

-Refer to :doc:`ROCm DGL blog posts <https://rocm.blogs.amd.com/blog/tag/dgl.html>` 
-for examples and best practices to optimize your training workflows on AMD GPUs. 
+Multiple use cases of DGL have been tested and verified.
+However, a recommended example follows a drug discovery pipeline using the ``SE3Transformer``.
+Refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`_, 
+where you can search for DGL examples and best practices to optimize your training workflows on AMD GPUs. 

 Coverage includes:

 - Single-GPU training/inference
 - Multi-GPU training

-Benchmarking details are included in the :doc:`Benchmarks` section.
-

 .. _dgl-docker-compat:

@@ -252,4 +252,4 @@ Unsupported functions
 * ``gather_mm_idx_b``
 * ``pgexplainer``
 * ``sample_labors_prob``
-* ``sample_labors_noprob``
+* ``sample_labors_noprob``
--- a/docs/compatibility/ml-compatibility/jax-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/jax-compatibility.rst
@@ -97,7 +97,7 @@ Docker image compatibility
 AMD validates and publishes ready-made `ROCm JAX Docker images <https://hub.docker.com/r/rocm/jax>`_
 with ROCm backends on Docker Hub. The following Docker image tags and
 associated inventories represent the latest JAX version from the official Docker Hub and are validated for
-`ROCm 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`_. Click the |docker-icon|
+`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
@@ -110,7 +110,7 @@ icon to view the image on Docker Hub.

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.1-jax0.4.35-py3.12/images/sha256-7a0745a2a2758bdf86397750bac00e9086cbf67d170cfdbb08af73f7c7d18a6a"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
+           <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
@@ -118,7 +118,7 @@ icon to view the image on Docker Hub.

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/jax/rocm6.4.1-jax0.4.35-py3.10/images/sha256-5f9e8d6e6e69fdc9a1a3f2ba3b1234c3f46c53b7468538c07fd18b00899da54f"><i class="fab fa-docker fa-lg"></i> rocm/jax</a>
+           <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
--- a/docs/compatibility/ml-compatibility/megablocks-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/megablocks-compatibility.rst
@@ -0,0 +1,93 @@
+:orphan:
+
+.. meta::
+    :description: Megablocks compatibility
+    :keywords: GPU, megablocks, compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+Megablocks compatibility
+********************************************************************************
+
+Megablocks is a light-weight library for mixture-of-experts (MoE) training. 
+The core of the system is efficient "dropless-MoE" and standard MoE layers. 
+Megablocks is integrated with `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`_, 
+where data and pipeline parallel training of MoEs is supported.
+
+* ROCm support for Megablocks is hosted in the official `https://github.com/ROCm/megablocks <https://github.com/ROCm/megablocks>`_ repository. 
+* Due to independent compatibility considerations, this location differs from the `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`_ upstream repository. 
+* Use the prebuilt :ref:`Docker image <megablocks-docker-compat>` with ROCm, PyTorch, and Megablocks preinstalled. 
+* See the :doc:`ROCm Megablocks installation guide <rocm-install-on-linux:install/3rd-party/megablocks-install>` to install and get started.
+
+.. note::
+
+  Megablocks is supported on ROCm 6.3.0.
+
+Supported devices
+================================================================================
+
+- **Officially Supported**: AMD Instinct MI300X
+- **Partially Supported** (functionality or performance limitations): AMD Instinct MI250X, MI210X
+
+Supported models and features
+================================================================================
+
+This section summarizes the Megablocks features supported by ROCm.
+
+* Distributed Pre-training
+* Activation Checkpointing and Recomputation
+* Distributed Optimizer
+* Mixture-of-Experts
+* dropless-Mixture-of-Experts
+
+
+.. _megablocks-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+The `ROCm Megablocks blog posts <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`_ 
+guide how to leverage the ROCm platform for pre-training using the Megablocks framework. 
+It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
+
+* Single-GPU pre-training
+* Multi-GPU pre-training
+
+
+.. _megablocks-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `ROCm Megablocks images <https://hub.docker.com/r/rocm/megablocks/tags>`_
+with ROCm and Pytorch backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest Megatron-LM version from the official Docker Hub.
+The Docker images have been validated for `ROCm 6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Megablocks
+      - PyTorch
+      - Ubuntu
+      - Python
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/megablocks/megablocks-0.7.0_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-372ff89b96599019b8f5f9db469c84add2529b713456781fa62eb9a148659ab4"><i class="fab fa-docker fa-lg"></i> rocm/megablocks</a>
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `0.7.0 <https://github.com/databricks/megablocks/releases/tag/v0.7.0>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+
+
--- a/docs/compatibility/ml-compatibility/pytorch-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/pytorch-compatibility.rst
@@ -95,7 +95,7 @@ Docker image compatibility

 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 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__.
+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
@@ -112,127 +112,118 @@ Click |docker-icon| to view the image on Docker Hub.
      - MAGMA
      - UCX
      - OMPI
-      - OFED

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.6.0/images/sha256-c76af9bfb1c25b0f40d4c29e8652105c57250bf018d23ff595b06bd79666fdd7"><i class="fab fa-docker fa-lg"></i></a>
+           <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
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `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>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `2.18.0 <https://github.com/tensorflow/tensorboard/tree/2.18.0>`__
      - `master <https://bitbucket.org/icl/magma/src/master/>`__
-      - `1.16.0 <https://github.com/openucx/ucx/tree/v1.16.0>`__
+      - `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>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.6.0/images/sha256-f9d226135d51831c810dcb1251636ec61f85c65fcdda03e188c053a5d4f6585b"><i class="fab fa-docker fa-lg"></i></a>
+           <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
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `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>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `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>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.5.1/images/sha256-3490e74d4f43dcdb3351dd334108d1ccd47e5a687c0523a2424ac1bcdd3dd6dd"><i class="fab fa-docker fa-lg"></i></a>
+           <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
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `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>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `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/v1.10.0>`__
      - `4.1.6-7ubuntu2 <https://github.com/open-mpi/ompi/tree/v4.1.6>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.5.1/images/sha256-26c5dfffb4a54625884abca83166940f17dd27bc75f1b24f6e80fbcb7d4e9afb"><i class="fab fa-docker fa-lg"></i></a>
+           <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
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `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>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `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>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.4.1/images/sha256-f378a24561fa6efc178b6dc93fc7d82e5b93653ecd59c89d4476674d29e1284d"><i class="fab fa-docker fa-lg"></i></a>
+           <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
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `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>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `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>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.4.1/images/sha256-2308dbd0e650b7bf8d548575cbb6e2bdc021f9386384ce570da16d58ee684d22"><i class="fab fa-docker fa-lg"></i></a>
+           <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
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `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>`__
-      - `2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13.0>`__
+      - `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>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu24.04_py3.12_pytorch_release_2.3.0/images/sha256-eefd2ab019728f91f94c5e6a9463cb0ea900b3011458d18fe5d88e50c0b57d86"><i class="fab fa-docker fa-lg"></i></a>
+           <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
-      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `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>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/pytorch/rocm6.4.1_ubuntu22.04_py3.10_pytorch_release_2.3.0/images/sha256-473643226ab0e93a04720b256ed772619878abf9c42b9f84828cefed522696fd"><i class="fab fa-docker fa-lg"></i></a>
-
-      - `2.3.0 <https://github.com/ROCm/pytorch/tree/release/2.3>`__
-      - 22.04
-      - `3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
-      - `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/>`__
-      - `1.12.1~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>`__
-      - `5.3-1.0.5.0 <https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz>`__

 Key ROCm libraries for PyTorch
 ================================================================================
--- a/docs/compatibility/ml-compatibility/taichi-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/taichi-compatibility.rst
@@ -0,0 +1,76 @@
+:orphan:
+
+.. meta::
+    :description: Taichi compatibility
+    :keywords: GPU, Taichi compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+Taichi compatibility
+*******************************************************************************
+
+`Taichi <https://www.taichi-lang.org/>`_ is an open-source, imperative, and parallel 
+programming language designed for high-performance numerical computation. 
+Embedded in Python, it leverages just-in-time (JIT) compilation frameworks such as LLVM to accelerate 
+compute-intensive Python code by compiling it to native GPU or CPU instructions.
+
+Taichi is widely used across various domains, including real-time physical simulation, 
+numerical computing, augmented reality, artificial intelligence, computer vision, robotics, 
+visual effects in film and gaming, and general-purpose computing.
+
+* ROCm support for Taichi is hosted in the official `https://github.com/ROCm/taichi <https://github.com/ROCm/taichi>`_ repository.
+* Due to independent compatibility considerations, this location differs from the `https://github.com/taichi-dev <https://github.com/taichi-dev>`_ upstream repository.
+* Use the prebuilt :ref:`Docker image <taichi-docker-compat>` with ROCm, PyTorch, and Taichi preinstalled.
+* See the :doc:`ROCm Taichi installation guide <rocm-install-on-linux:install/3rd-party/taichi-install>` to install and get started.
+
+.. note::
+
+	Taichi is supported on ROCm 6.3.2.
+
+Supported devices and features
+===============================================================================
+There is support through the ROCm software stack for all Taichi GPU features on AMD Instinct MI250X and MI210X series GPUs with the exception of Taichi’s GPU rendering system, CGUI.
+AMD Instinct MI300X series GPUs will be supported by November.
+
+.. _taichi-recommendations:
+
+Use cases and recommendations
+================================================================================
+To fully leverage Taichi's performance capabilities in compute-intensive tasks, it is best to adhere to specific coding patterns and utilize Taichi decorators. 
+A collection of example use cases is available in the `https://github.com/ROCm/taichi_examples <https://github.com/ROCm/taichi_examples>`_ repository, 
+providing practical insights and foundational knowledge for working with the Taichi programming language. 
+You can also refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`_ to search for Taichi examples and best practices to optimize your workflows on AMD GPUs.
+
+.. _taichi-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes ready-made `ROCm Taichi Docker images <https://hub.docker.com/r/rocm/taichi/tags>`_
+with ROCm backends on Docker Hub. The following Docker image tags and associated inventories 
+represent the latest Taichi version from the official Docker Hub.
+The Docker images have been validated for `ROCm 6.3.2 <https://rocm.docs.amd.com/en/docs-6.3.2/about/release-notes.html>`_. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Taichi
+      - Ubuntu
+      - Python
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/taichi/taichi-1.8.0b1_rocm6.3.2_ubuntu22.04_py3.10.12/images/sha256-e016964a751e6a92199032d23e70fa3a564fff8555afe85cd718f8aa63f11fc6"><i class="fab fa-docker fa-lg"></i> rocm/taichi</a>
+      - `6.3.2 <https://repo.radeon.com/rocm/apt/6.3.2/>`_
+      - `1.8.0b1 <https://github.com/taichi-dev/taichi>`_
+      - 22.04
+      - `3.10.12 <https://www.python.org/downloads/release/python-31012/>`_
--- a/docs/compatibility/ml-compatibility/tensorflow-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/tensorflow-compatibility.rst
@@ -56,7 +56,7 @@ Docker image compatibility
 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 6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__. Click
+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
@@ -65,128 +65,61 @@ the |docker-icon| icon to view the image on Docker Hub.
    * - Docker image
      - TensorFlow
      - Ubuntu
-      - Dev
      - Python
      - TensorBoard

    * - .. raw:: html

-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4-py3.12-tf2.18-dev/images/sha256-fa9cf5fa6c6079a7118727531ccd0056c6e3224a42c3d6e78a49e7781daafff4"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <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-6.4.1/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
+      - `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 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `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/rocm6.4.1-py3.12-tf2.18-runtime/images/sha256-d14d8c4989e7c9a60f4e72461b9e349de72347c6162dcd6897e6f4f80ffbb440"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <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-6.4.1/tensorflow_rocm-2.18.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 24.04
-      - `Python 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `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/rocm6.4.1-py3.10-tf2.18-dev/images/sha256-081e5bd6615a5dc17247ebd2ccc26895c3feeff086720400fa39b477e60a77c0"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <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 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - dev
-      - 22.04
-      - `Python 3.10.17 <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/rocm6.4.1-py3.10-tf2.18-runtime/images/sha256-bf369637378264f4af6ddad5ca8b8611d3e372ffbea9ab7a06f1e122f0a0867b"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.18.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 22.04
-      - `Python 3.10.17 <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/rocm6.4.1-py3.12-tf2.17-dev/images/sha256-5a502008c50d0b6508e6027f911bdff070a7493700ae064bed74e1d22b91ed50"><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/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
+      - `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 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `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/rocm6.4.1-py3.12-tf2.17-runtime/images/sha256-1ee5dfffceb71ac66617ada33de3a10de0cb74199cc4b82441192e5e92fa2ddf"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <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 2.18.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 24.04
-      - `Python 3.12.10 <https://www.python.org/downloads/release/python-3124/>`__
-      - `TensorBoard 2.17.1 <https://github.com/tensorflow/tensorboard/tree/2.17.1>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.17-dev/images/sha256-109218ad92bfae83bbd2710475f7502166e1ed54ca0b9748a9cbc3f5a1d75af1"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.17.1-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
+      - `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 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `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/rocm6.4.1-py3.10-tf2.17-runtime/images/sha256-5d78bd5918d394f92263daa2990e88d695d27200dd90ed83ec64d20c7661c9c1"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <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 2.17.1 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.17.1-cp310-cp310-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 22.04
-      - `Python 3.10.17 <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/rocm6.4.1-py3.12-tf2.16-dev/images/sha256-b09b1ad921c09c687b7c916141051e9fcf15539a5686e5aa67c689195a522719"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - dev
+      - `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 3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - `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/rocm6.4.1-py3.12-tf2.16-runtime/images/sha256-20dbd824e85558abfe33fc9283cc547d88cde3c623fe95322743a5082f883a64"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
+           <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-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 24.04
-      - `Python 3.12.10 <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/rocm6.4.1-py3.10-tf2.16-dev/images/sha256-36c4fa047c86e2470ac473ec1429aea6d4b8934b90ffeb34d1afab40e7e5b377"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-dev/images/sha256-36c4fa047c86e2470ac473ec1429aea6d4b8934b90ffeb34d1afab40e7e5b377>`__
-      - dev
+      - `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 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
-      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__
-
-    * - .. raw:: html
-
-           <a href="https://hub.docker.com/layers/rocm/tensorflow/rocm6.4.1-py3.10-tf2.16-runtime/images/sha256-a94150ffb81365234ebfa34e764db5474bc6ab7d141b56495eac349778dafcf3"><i class="fab fa-docker fa-lg"></i> rocm/tensorflow</a>
-
-      - `tensorflow-rocm 2.16.2 <https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4.1/tensorflow_rocm-2.16.2-cp312-cp312-manylinux_2_28_x86_64.whl>`__
-      - runtime
-      - 22.04
-      - `Python 3.10.17 <https://www.python.org/downloads/release/python-31017/>`__
+      - `Python 3.10 <https://www.python.org/downloads/release/python-31017/>`__
      - `TensorBoard 2.16.2 <https://github.com/tensorflow/tensorboard/tree/2.16.2>`__


--- a/docs/compatibility/ml-compatibility/verl-compatibility.rst
+++ b/docs/compatibility/ml-compatibility/verl-compatibility.rst
@@ -16,56 +16,25 @@ verl offers a scalable, open-source fine-tuning solution optimized for AMD Insti
 * See the `verl documentation <https://verl.readthedocs.io/en/latest/>`_ for more information about verl. 
 * The official verl GitHub repository is `https://github.com/volcengine/verl <https://github.com/volcengine/verl>`_.
 * Use the AMD-validated :ref:`Docker images <verl-docker-compat>` with ROCm and verl preinstalled. 
-* See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>` to get started.
+* See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>` to install and get started.

 .. note::

 	verl is supported on ROCm 6.2.0.

-
 .. _verl-recommendations:

 Use cases and recommendations
 ================================================================================

-The benefits of verl in large-scale reinforcement leaning from human feedback (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`_ blog.
-
-.. _verl-docker-compat:
-
-Docker image compatibility
-================================================================================
-
-.. |docker-icon| raw:: html
-
-   <i class="fab fa-docker"></i>
-
-AMD validates and publishes ready-made `ROCm verl Docker images <https://hub.docker.com/r/rocm/verl>`_
-with ROCm backends on Docker Hub. The following Docker image tags and associated inventories represent the latest verl version from the official Docker Hub. The Docker images have been validated for `ROCm 6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`_. 
-
-.. list-table:: 
-    :header-rows: 1
-
-    *   - Docker image
-        - verl
-        - Linux
-        - Pytorch
-        - Python
-        - vllm
-
-    *   - .. raw:: html
-
-            <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
-        - `0.3.0post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`_
-        - Ubuntu 20.04
-        - `2.5.0 <https://download.pytorch.org/whl/cu118/torch-2.5.0%2Bcu118-cp39-cp39-linux_x86_64.whl#sha256=1ee24b267418c37b297529ede875b961e382c1c365482f4142af2398b92ed127>`_
-        - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`_
-        - `0.6.4 <https://github.com/vllm-project/vllm/releases/tag/v0.6.4>`_
+The benefits of verl in large-scale reinforcement learning from human feedback (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`_ blog.

+.. _verl-supported_features:

 Supported features
 ===============================================================================

-The following table shows verl and ROCm support for GPU-accelerated modules.
+The following table shows verl on ROCm support for GPU-accelerated modules.

 .. list-table::
    :header-rows: 1
@@ -77,9 +46,41 @@ The following table shows verl and ROCm support for GPU-accelerated modules.
    * - ``FSDP``
      - Training engine
      - 0.3.0.post0
-      - 6.2
+      - 6.2.0
    * - ``vllm``
      - Inference engine
      - 0.3.0.post0
-      - 6.2
-  
+      - 6.2.0
+
+.. _verl-docker-compat:
+
+Docker image compatibility
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes ready-made `ROCm verl Docker images <https://hub.docker.com/r/rocm/verl/tags>`_
+with ROCm backends on Docker Hub. The following Docker image tags and associated inventories represent the available verl versions from the official Docker Hub. 
+
+.. list-table:: 
+    :header-rows: 1
+
+    *   - Docker image
+        - ROCm
+        - verl
+        - Ubuntu
+        - Pytorch
+        - Python
+        - vllm
+
+    *   - .. raw:: html
+
+            <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+        - `6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`_
+        - `0.3.0post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`_
+        - 20.04
+        - `2.5.0 <https://github.com/ROCm/pytorch/tree/release/2.5>`_
+        - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`_
+        - `0.6.3 <https://github.com/vllm-project/vllm/releases/tag/v0.6.3>`_
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -96,6 +96,11 @@ article_pages = [
    {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
    {"file": "compatibility/ml-compatibility/tensorflow-compatibility", "os": ["linux"]},
    {"file": "compatibility/ml-compatibility/jax-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/verl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/stanford-megatron-lm-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/dgl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/megablocks-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/taichi-compatibility", "os": ["linux"]},
    {"file": "how-to/deep-learning-rocm", "os": ["linux"]},

    {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},
--- a/docs/data/how-to/rocm-for-ai/inference/pytorch-inference-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/pytorch-inference-benchmark-models.yaml
@@ -1,6 +1,6 @@
 pytorch_inference_benchmark:
  unified_docker:
-    latest: &rocm-pytorch-docker-latest
+    latest:
      pull_tag: rocm/pytorch:latest
      docker_hub_url:
      rocm_version:
@@ -39,3 +39,11 @@ pytorch_inference_benchmark:
        model_repo: Wan-AI/Wan2.1-T2V-14B
        url: https://huggingface.co/Wan-AI/Wan2.1-T2V-14B
        precision: bfloat16
+    - group: Janus-Pro
+      tag: janus-pro
+      models:
+      - model: Janus Pro 7B
+        mad_tag: pyt_janus_pro_inference
+        model_repo: deepseek-ai/Janus-Pro-7B
+        url: https://huggingface.co/deepseek-ai/Janus-Pro-7B
+        precision: bfloat16
--- a/docs/data/how-to/rocm-for-ai/inference/sglang-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/sglang-benchmark-models.yaml
@@ -0,0 +1,17 @@
+sglang_benchmark:
+  unified_docker:
+    latest:
+      pull_tag: lmsysorg/sglang:v0.4.5-rocm630
+      docker_hub_url: https://hub.docker.com/layers/lmsysorg/sglang/v0.4.5-rocm630/images/sha256-63d2cb760a237125daf6612464cfe2f395c0784e21e8b0ea37d551cd10d3c951
+      rocm_version: 6.3.0
+      sglang_version: 0.4.5 (0.4.5-rocm)
+      pytorch_version: 2.6.0a0+git8d4926e
+  model_groups:
+    - group: DeepSeek
+      tag: deepseek
+      models:
+      - model: DeepSeek-R1-Distill-Qwen-32B
+        mad_tag: pyt_sglang_deepseek-r1-distill-qwen-32b
+        model_repo: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+        url: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+        precision: bfloat16
--- a/docs/data/rocm-software-stack-6_4_0.jpg
+++ b/docs/data/rocm-software-stack-6_4_0.jpg
--- a/docs/how-to/deep-learning-rocm.rst
+++ b/docs/how-to/deep-learning-rocm.rst
@@ -20,6 +20,8 @@ features for these ROCm-enabled deep learning frameworks.
 * :doc:`verl compatibility <../compatibility/ml-compatibility/verl-compatibility>`
 * :doc:`Stanford Megatron-LM compatibility <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
 * :doc:`DGL compatibility <../compatibility/ml-compatibility/dgl-compatibility>`
+* :doc:`Megablocks compatibility <../compatibility/ml-compatibility/megablocks-compatibility>`
+* :doc:`Taichi compatibility <../compatibility/ml-compatibility/taichi-compatibility>`

 This chart steps through typical installation workflows for installing deep learning frameworks for ROCm.

@@ -35,6 +37,8 @@ See the installation instructions to get started.
 * :doc:`verl for ROCm <rocm-install-on-linux:install/3rd-party/verl-install>`
 * :doc:`Stanford Megatron-LM for ROCm <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
 * :doc:`DGL for ROCm <rocm-install-on-linux:install/3rd-party/dgl-install>`
+* :doc:`Megablocks for ROCm <rocm-install-on-linux:install/3rd-party/megablocks-install>`
+* :doc:`Taichi for ROCm <rocm-install-on-linux:install/3rd-party/taichi-install>`

 .. note::

--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/sglang-history.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/sglang-history.rst
@@ -0,0 +1,25 @@
+:orphan:
+
+****************************************************
+SGLang inference performance testing version history
+****************************************************
+
+This table lists previous versions of the ROCm SGLang inference performance
+testing environment. For detailed information about available models for
+benchmarking, see the version-specific documentation.
+
+.. list-table::
+   :header-rows: 1
+
+   * - Docker image tag
+     - Components
+     - Resources
+
+   * - ``lmsysorg/sglang:v0.4.5-rocm630``
+     - 
+       * ROCm 6.3.0
+       * SGLang 0.4.5
+       * PyTorch 2.6.0
+     - 
+       * :doc:`Documentation <../sglang>`
+       * `Docker Hub <https://hub.docker.com/layers/lmsysorg/sglang/v0.4.5-rocm630/images/sha256-63d2cb760a237125daf6612464cfe2f395c0784e21e8b0ea37d551cd10d3c951>`__
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference.rst
@@ -103,7 +103,7 @@ PyTorch inference performance testing

         The Chai-1 benchmark uses a specifically selected Docker image using ROCm 6.2.3 and PyTorch 2.3.0 to address an accuracy issue.

-   .. container:: model-doc pyt_clip_inference pyt_mochi_video_inference pyt_wan2.1_inference
+   .. container:: model-doc pyt_clip_inference pyt_mochi_video_inference pyt_wan2.1_inference pyt_janus_pro_inference

      Use the following command to pull the `ROCm PyTorch Docker image <https://hub.docker.com/layers/rocm/pytorch/latest/images/sha256-05b55983e5154f46e7441897d0908d79877370adca4d1fff4899d9539d6c4969>`__ from Docker Hub.

@@ -140,22 +140,27 @@ PyTorch inference performance testing
      .. code-block:: shell

         export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-         python3 tools/run_models.py --tags {{model.mad_tag}} --keep-model-dir --live-output --timeout 28800
+         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 ``perf.csv``.
+      model are collected in ``perf_{{model.mad_tag}}.csv``.

+      {% if model.mad_tag != "pyt_janus_pro_inference" %}
      .. note::

         For improved performance, consider enabling TunableOp. By default,
         ``{{model.mad_tag}}`` runs with TunableOp disabled (see
         `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To enable
-         it, edit the default run behavior in the ``tools/run_models.py``-- update the model's
-         run ``args`` by changing ``--tunableop off`` to ``--tunableop on``.
+         it, include the ``--tunableop on`` argument in your run.

         Enabling TunableOp triggers a two-pass run -- a warm-up followed by the performance-collection run.
         Although this might increase the initial training time, it can result in a performance gain.
+      {% endif %}

      {% endfor %}
   {% endfor %}
@@ -163,8 +168,10 @@ PyTorch inference performance testing
 Further reading
 ===============

+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
 - To learn more about system settings and management practices to configure your system for
-  MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
+  AMD Instinct MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.

 - For application performance optimization strategies for HPC and AI workloads,
  including inference with vLLM, see :doc:`../../inference-optimization/workload`.
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/sglang.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/sglang.rst
@@ -0,0 +1,280 @@
+.. meta::
+   :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and SGLang
+   :keywords: model, MAD, automation, dashboarding, validate
+
+************************************
+SGLang inference performance testing
+************************************
+
+.. _sglang-benchmark-unified-docker:
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-benchmark-models.yaml
+
+   {% set unified_docker = data.sglang_benchmark.unified_docker.latest %}
+
+   `SGLang <https://docs.sglang.ai>`__ is a high-performance inference and
+   serving engine for large language models (LLMs) and vision models. The
+   ROCm-enabled `SGLang Docker image <{{ unified_docker.docker_hub_url }}>`__
+   bundles SGLang with PyTorch, optimized for AMD Instinct MI300X series
+   accelerators. It includes the following software components:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      * - `ROCm <https://github.com/ROCm/ROCm>`__
+        - {{ unified_docker.rocm_version }}
+
+      * - `SGLang <https://docs.sglang.ai/index.html>`__
+        - {{ unified_docker.sglang_version }} 
+
+      * - `PyTorch <https://github.com/pytorch/pytorch>`__
+        - {{ unified_docker.pytorch_version }} 
+
+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.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-benchmark-models.yaml
+
+   {% set unified_docker = data.sglang_benchmark.unified_docker.latest %}
+   {% set model_groups = data.sglang_benchmark.model_groups %}
+
+   Pull the Docker image
+   =====================
+
+   Download the `SGLang Docker image <{{ unified_docker.docker_hub_url }}>`__.
+   Use the following command to pull the Docker image from Docker Hub.
+
+   .. code-block:: shell
+
+      docker pull {{ unified_docker.pull_tag }}
+
+   Benchmarking
+   ============
+
+   Once the setup is complete, choose one of the following methods to benchmark inference performance with
+   `DeepSeek-R1-Distill-Qwen-32B <https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B>`__.
+
+   .. _sglang-benchmark-mad:
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{model.mad_tag}}
+
+      .. 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
+
+            2. Use this command to run the performance benchmark test on the `{{model.model}} <{{ model.url }}>`_ model
+               using one GPU 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 the following path: ``~/MAD/perf_DeepSeek-R1-Distill-Qwen-32B.csv``.
+
+            Although the DeepSeek-R1-Distill-Qwen-32B is preconfigured
+            to collect latency and throughput performance data, you can also change the benchmarking
+            parameters. See the standalone benchmarking tab for more information.
+
+         .. tab-item:: Standalone benchmarking
+
+            .. rubric:: Download the Docker image and required scripts
+
+            1. Run the SGLang benchmark script independently by starting the
+               `Docker container <{{ unified_docker.docker_hub_url }}>`__
+               as shown in the following snippet.
+
+               .. code-block:: shell
+
+                  docker pull {{ unified_docker.pull_tag }}
+                  docker run -it \
+                      --device=/dev/kfd \
+                      --device=/dev/dri \
+                      --group-add video \
+                      --shm-size 16G \
+                      --security-opt seccomp=unconfined \
+                      --security-opt apparmor=unconfined \
+                      --cap-add=SYS_PTRACE \
+                      -v $(pwd):/workspace \
+                      --env HUGGINGFACE_HUB_CACHE=/workspace \
+                      --name test \
+                      {{ unified_docker.pull_tag }}
+
+            2. In the Docker container, clone the ROCm MAD repository and navigate to the
+               benchmark scripts directory at ``~/MAD/scripts/sglang``.
+
+               .. code-block:: shell
+
+                  git clone https://github.com/ROCm/MAD
+                  cd MAD/scripts/sglang
+
+            3. To start the benchmark, use the following command with the appropriate options.
+
+               .. dropdown:: Benchmark options
+                  :open:
+
+                  .. list-table::
+                     :header-rows: 1
+                     :align: center
+
+                     * - Name
+                       - Options
+                       - Description
+
+                     * - ``$test_option``
+                       - latency
+                       - Measure decoding token latency
+
+                     * -
+                       - throughput
+                       - Measure token generation throughput
+
+                     * -
+                       - all
+                       - Measure both throughput and latency
+
+                     * - ``$num_gpu``
+                       - 8
+                       - Number of GPUs
+
+                     * - ``$datatype``
+                       - ``bfloat16``
+                       - Data type
+
+                     * - ``$dataset``
+                       - random
+                       - Dataset
+
+                  The input sequence length, output sequence length, and tensor parallel (TP) are
+                  already configured. You don't need to specify them with this script.
+
+               Command:
+
+               .. code-block:: shell
+
+                  ./sglang_benchmark_report.sh -s $test_option -m {{model.model_repo}} -g $num_gpu -d $datatype [-a $dataset]
+
+            .. note::
+
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
+
+               .. code-block:: shell-session
+
+                  OSError: You are trying to access a gated repo.
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
+
+            .. rubric:: Benchmarking examples
+
+            Here are some examples of running the benchmark with various options:
+
+            * Latency benchmark
+
+              Use this command to benchmark the latency of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block:: shell
+
+                 ./sglang_benchmark_report.sh \
+                     -s latency \
+                     -m {{model.model_repo}} \
+                     -g 8 \
+                     -d {{model.precision}}
+
+              Find the latency report at ``./reports_{{model.precision}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_latency_report.csv``.
+
+            * Throughput benchmark
+
+              Use this command to benchmark the throughput of the {{model.model}} model on eight GPUs with ``{{model.precision}}`` precision.
+
+              .. code-block:: shell
+
+                 ./sglang_benchmark_report.sh \
+                     -s throughput \
+                     -m {{model.model_repo}} \
+                     -g 8 \
+                     -d {{model.precision}} \
+                     -a random
+
+              Find the throughput report at ``./reports_{{model.precision}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_throughput_report.csv``.
+
+            .. raw:: html
+
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
+
+            .. note::
+
+               Throughput is calculated as:
+
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
+
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
+
+Further reading
+===============
+
+- 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>`__.
+
+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__.
+
+- 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.
--- a/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
+++ b/docs/how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
@@ -202,7 +202,7 @@ system's configuration.
               .. code-block:: shell

                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-                  python3 tools/run_models.py \
+                  madengine run \
                      --tags {{model.mad_tag}} \
                      --keep-model-dir \
                      --live-output \
@@ -226,12 +226,12 @@ system's configuration.

               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled
               (see
-               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To
-               enable it, edit the default run behavior in the ``models.json``
-               configuration before running inference -- update the model's run
-               ``args`` by changing ``--tunableop off`` to ``--tunableop on``.
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__).
+               To enable it, include the ``--tunableop on`` argument in your
+               run.

-               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the performance-collection run.
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed
+               by the performance-collection run.

            {% endif %}

@@ -419,8 +419,10 @@ Further reading
 - To learn more about the options for latency and throughput benchmark scripts,
  see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.

+- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
+
 - To learn more about system settings and management practices to configure your system for
-  MI300X series accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
+  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 application performance optimization strategies for HPC and AI workloads,
  including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.
--- a/docs/how-to/rocm-for-ai/inference/index.rst
+++ b/docs/how-to/rocm-for-ai/inference/index.rst
@@ -24,4 +24,6 @@ training, fine-tuning, and inference. It leverages popular machine learning fram

 - :doc:`PyTorch inference performance testing <benchmark-docker/pytorch-inference>`

+- :doc:`SGLang inference performance testing <benchmark-docker/sglang>`
+
 - :doc:`Deploying your model <deploy-your-model>`
--- a/docs/how-to/rocm-for-ai/install.rst
+++ b/docs/how-to/rocm-for-ai/install.rst
@@ -24,12 +24,13 @@ If you’re new to ROCm, refer to the :doc:`ROCm quick start install guide for L
 If you’re using a Radeon GPU for graphics-accelerated applications, refer to the
 `Radeon installation instructions <https://rocm.docs.amd.com/projects/radeon/en/docs-6.1.3/docs/install/native_linux/install-radeon.html>`_.

-ROCm supports multiple :doc:`installation methods <rocm-install-on-linux:install/install-overview>`:
+You can install ROCm on :ref:`compatible systems <rocm-install-on-linux:reference/system-requirements>` via your Linux
+distribution's package manager. See the following documentation resources to get started:
+
+* :doc:`ROCm installation overview <rocm-install-on-linux:install/install-overview>`

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

-* :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/install-methods/amdgpu-installer-index>`
-
 * :ref:`Multi-version installation <rocm-install-on-linux:installation-types>`

 .. grid:: 1
@@ -59,6 +60,12 @@ images with the framework pre-installed.

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

+* :doc:`verl for ROCm <rocm-install-on-linux:install/3rd-party/verl-install>`
+
+* :doc:`Stanford Megatron-LM for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`
+
+* :doc:`DGL for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`
+
 Next steps
 ==========

--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry.rst
@@ -73,7 +73,11 @@ document are not validated.

      .. code-block:: shell

-         python3 tools/run_models.py --tags pyt_mpt30b_training --keep-model-dir --live-output --clean-docker-cache
+         madengine run \
+             --tags pyt_mpt30b_training \
+             --keep-model-dir \
+             --live-output \
+             --clean-docker-cache

      .. tip::

@@ -90,7 +94,7 @@ document are not validated.

         For improved performance (training throughput), consider enabling TunableOp.
         By default, ``pyt_mpt30b_training`` runs with TunableOp disabled. To enable it,
-         run ``tools/run_models.py`` with the ``--tunableop on`` argument or edit the
+         run ``madengine run`` with the ``--tunableop on`` argument or edit the
         ``models.json`` configuration before running training.

         Although this might increase the initial training time, it can result in a performance gain.
@@ -172,4 +176,13 @@ Key performance metrics include:

    Overall training loss. A decreasing trend indicates the model is learning effectively.

+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>`_.
--- a/docs/how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
+++ b/docs/how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
@@ -142,7 +142,11 @@ The following models are pre-optimized for performance on the AMD Instinct MI325
            .. code-block:: shell

               export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-               python3 tools/run_models.py --tags {{ model.mad_tag }} --keep-model-dir --live-output --timeout 28800
+               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 }}``, for example. The latency and throughput reports of the
@@ -427,6 +431,17 @@ The following models are pre-optimized for performance on the AMD Instinct MI325

               For examples of benchmarking commands, see `<https://github.com/ROCm/MAD/tree/develop/benchmark/pytorch_train#benchmarking-examples>`__.

+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
 =================

--- a/docs/reference/precision-support.rst
+++ b/docs/reference/precision-support.rst
@@ -55,7 +55,7 @@ The floating-point types supported by ROCm are listed in the following table.

 .. list-table::
    :header-rows: 1
-    :widths: 15,15,70
+    :widths: 15,25,60

    *
      - Type name
@@ -63,18 +63,19 @@ The floating-point types supported by ROCm are listed in the following table.
      - Description
    *
      - float8 (E4M3)
-      - ``__hip_fp8_e4m3_fnuz``
-      - An 8-bit floating-point number that mostly follows IEEE-754 conventions
-        and **S1E4M3** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_,
-        with expanded range and no infinity or signed zero. NaN is represented
-        as negative zero.
+      - | ``__hip_fp8_e4m3_fnuz``,
+        | ``__hip_fp8_e4m3``
+      - An 8-bit floating-point number with **S1E4M3** bit layout, as described in :doc:`low precision floating point types page <hip:reference/low_fp_types>`.
+        The FNUZ variant has expanded range with no infinity or signed zero (NaN represented as negative zero),
+        while the OCP variant follows the Open Compute Project specification.
    *
      - float8 (E5M2)
-      - ``__hip_fp8_e5m2_fnuz``
-      - An 8-bit floating-point number mostly following IEEE-754 conventions and
-        **S1E5M2** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_,
-        with expanded range and no infinity or signed zero. NaN is represented
-        as negative zero.
+      - | ``__hip_fp8_e5m2_fnuz``,
+        | ``__hip_fp8_e5m2``
+      - An 8-bit floating-point number with **S1E5M2** bit layout, as described in :doc:`low precision floating point types page <hip:reference/low_fp_types>`.
+        The FNUZ variant has expanded range with no infinity or signed zero (NaN represented as negative zero),
+        while the OCP variant follows the Open Compute Project specification.
+
    *
      - float16
      - ``half``
@@ -107,9 +108,8 @@ The floating-point types supported by ROCm are listed in the following table.
  * The float8 and tensorfloat32 types are internal types used in calculations
    in Matrix Cores and can be stored in any type of the same size.

-  * The encodings for FP8 (E5M2) and FP8 (E4M3) that the
-    MI300 series natively supports differ from the FP8 (E5M2) and FP8 (E4M3)
-    encodings used in NVIDIA H100
+  * CNDA3 natively supports FP8 FNUZ (E4M3 and E5M2), which differs from the customised
+    FP8 format used in NVIDIA's H100
    (`FP8 Formats for Deep Learning <https://arxiv.org/abs/2209.05433>`_).

  * In some AMD documents and articles, float8 (E5M2) is referred to as bfloat8.
@@ -128,7 +128,7 @@ pages.
    :header-rows: 1

    *
-      -  Icon
+      - Icon
      - Definition

    *
@@ -163,12 +163,137 @@ pages.
  * Any type can be emulated by software, but this page does not cover such
    cases.

-Data type support by Hardware Architecture
+Data type support by hardware architecture
 ==========================================

-The MI200 series GPUs, which include MI210, MI250, and MI250X, are based on the
-CDNA2 architecture. The MI300 series GPUs, consisting of MI300A, MI300X, and
-MI325X, are based on the CDNA3 architecture.
+AMD's GPU lineup spans multiple architecture generations:
+
+* CDNA1 architecture: includes models such as MI100
+* CDNA2 architecture: includes models such as MI210, MI250, and MI250X
+* CDNA3 architecture: includes models such as MI300A, MI300X, and MI325X
+* RDNA3 architecture: includes models such as RX 7900XT and RX 7900XTX
+* RDNA4 architecture: includes models such as RX 9070 and RX 9070XT
+
+HIP C++ type implementation support
+-----------------------------------
+
+The HIP C++ types available on different hardware platforms are listed in the
+following table.
+
+.. list-table::
+    :header-rows: 1
+
+    *
+      - HIP C++ Type
+      - CDNA1
+      - CDNA2
+      - CDNA3
+      - RDNA3
+      - RDNA4
+
+    *
+      - ``int8_t``, ``uint8_t``
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+
+    *
+      - ``int16_t``, ``uint16_t``
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+
+    *
+      - ``int32_t``, ``uint32_t``
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+
+    *
+      - ``int64_t``, ``uint64_t``
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+
+    *
+      - ``__hip_fp8_e4m3_fnuz``
+      - ❌
+      - ❌
+      - ✅
+      - ❌
+      - ❌
+
+    *
+      - ``__hip_fp8_e5m2_fnuz``
+      - ❌
+      - ❌
+      - ✅
+      - ❌
+      - ❌
+
+    *
+      - ``__hip_fp8_e4m3``
+      - ❌
+      - ❌
+      - ❌
+      - ❌
+      - ✅
+
+    *
+      - ``__hip_fp8_e5m2``
+      - ❌
+      - ❌
+      - ❌
+      - ❌
+      - ✅
+
+    *
+      - ``half``
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+
+    *
+      - ``bfloat16``
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+
+    *
+      - ``float``
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+
+    *
+      - ``double``
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+      - ✅
+
+.. note::
+
+  Library support for specific data types is contingent upon hardware support.
+  Even if a ROCm library indicates support for a particular data type, that type
+  will only be fully functional if the underlying hardware architecture (as shown
+  in the table above) also supports it. For example, fp8 types are only available
+  on architectures shown with a checkmark in the relevant rows.

 Compute units support
 ---------------------
@@ -190,19 +315,33 @@ The following table lists data type support for compute units.
        - int32
        - int64
      *
-        - MI100
+        - CDNA1
        - ✅
        - ✅
        - ✅
        - ✅
      *
-        - MI200 series
+        - CDNA2
        - ✅
        - ✅
        - ✅
        - ✅
      *
-        - MI300 series
+        - CDNA3
+        - ✅
+        - ✅
+        - ✅
+        - ✅
+
+      *
+        - RDNA3
+        - ✅
+        - ✅
+        - ✅
+        - ✅
+
+      *
+        - RDNA4
        - ✅
        - ✅
        - ✅
@@ -224,7 +363,7 @@ The following table lists data type support for compute units.
        - float32
        - float64
      *
-        - MI100
+        - CDNA1
        - ❌
        - ❌
        - ✅
@@ -233,7 +372,7 @@ The following table lists data type support for compute units.
        - ✅
        - ✅
      *
-        - MI200 series
+        - CDNA2
        - ❌
        - ❌
        - ✅
@@ -242,7 +381,27 @@ The following table lists data type support for compute units.
        - ✅
        - ✅
      *
-        - MI300 series
+        - CDNA3
+        - ❌
+        - ❌
+        - ✅
+        - ✅
+        - ❌
+        - ✅
+        - ✅
+
+      *
+        - RDNA3
+        - ❌
+        - ❌
+        - ✅
+        - ✅
+        - ❌
+        - ✅
+        - ✅
+
+      *
+        - RDNA4
        - ❌
        - ❌
        - ✅
@@ -271,19 +430,33 @@ The following table lists data type support for AMD GPU matrix cores.
        - int32
        - int64
      *
-        - MI100
+        - CDNA1
        - ✅
        - ❌
        - ❌
        - ❌
      *
-        - MI200 series
+        - CDNA2
        - ✅
        - ❌
        - ❌
        - ❌
      *
-        - MI300 series
+        - CDNA3
+        - ✅
+        - ❌
+        - ❌
+        - ❌
+
+      *
+        - RDNA3
+        - ✅
+        - ❌
+        - ❌
+        - ❌
+
+      *
+        - RDNA4
        - ✅
        - ❌
        - ❌
@@ -305,7 +478,7 @@ The following table lists data type support for AMD GPU matrix cores.
        - float32
        - float64
      *
-        - MI100
+        - CDNA1
        - ❌
        - ❌
        - ✅
@@ -314,7 +487,7 @@ The following table lists data type support for AMD GPU matrix cores.
        - ✅
        - ❌
      *
-        - MI200 series
+        - CDNA2
        - ❌
        - ❌
        - ✅
@@ -323,7 +496,7 @@ The following table lists data type support for AMD GPU matrix cores.
        - ✅
        - ✅
      *
-        - MI300 series
+        - CDNA3
        - ✅
        - ✅
        - ✅
@@ -332,6 +505,26 @@ The following table lists data type support for AMD GPU matrix cores.
        - ✅
        - ✅

+      *
+        - RDNA3
+        - ❌
+        - ❌
+        - ✅
+        - ✅
+        - ❌
+        - ❌
+        - ❌
+
+      *
+        - RDNA4
+        - ✅
+        - ✅
+        - ✅
+        - ✅
+        - ❌
+        - ❌
+        - ❌
+
 Atomic operations support
 -------------------------

@@ -357,19 +550,33 @@ page.
        - int32
        - int64
      *
-        - MI100
+        - CDNA1
        - ❌
        - ❌
        - ✅
        - ✅
      *
-        - MI200 series
+        - CDNA2
        - ❌
        - ❌
        - ✅
        - ✅
      *
-        - MI300 series
+        - CDNA3
+        - ❌
+        - ❌
+        - ✅
+        - ✅
+
+      *
+        - RDNA3
+        - ❌
+        - ❌
+        - ✅
+        - ✅
+
+      *
+        - RDNA4
        - ❌
        - ❌
        - ✅
@@ -391,7 +598,7 @@ page.
        - float32
        - float64
      *
-        - MI100
+        - CDNA1
        - ❌
        - ❌
        - ✅
@@ -400,7 +607,7 @@ page.
        - ✅
        - ❌
      *
-        - MI200 series
+        - CDNA2
        - ❌
        - ❌
        - ✅
@@ -409,7 +616,7 @@ page.
        - ✅
        - ✅
      *
-        - MI300 series
+        - CDNA3
        - ❌
        - ❌
        - ✅
@@ -418,6 +625,26 @@ page.
        - ✅
        - ✅

+      *
+        - RDNA3
+        - ❌
+        - ❌
+        - ❌
+        - ❌
+        - ❌
+        - ✅
+        - ❌
+
+      *
+        - RDNA4
+        - ❌
+        - ❌
+        - ✅
+        - ✅
+        - ❌
+        - ✅
+        - ❌
+
 .. note::

  You can emulate atomic operations using software for cases that are not
@@ -452,36 +679,98 @@ detailed description.
        - int16
        - int32
        - int64
+
      *
-        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - :doc:`Composable Kernel <composable_kernel:reference/Composable_Kernel_supported_scalar_types>`
        - ✅/✅
        - ❌/❌
+        - ✅/✅
        - ❌/❌
-        - ❌/❌
-      *
-        - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
-        - NA/✅
-        - NA/✅
-        - NA/✅
-        - NA/✅
-      *
-        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
-        - NA/✅
-        - NA/✅
-        - NA/✅
-        - NA/✅
-      *
-        -  :doc:`rocPRIM <rocprim:reference/data-type-support>`
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
-        - ✅/✅
+
      *
        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
        - ✅/✅
        - ✅/✅
        - ✅/✅
        - ✅/✅
+
+      *
+        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
+        - NA/✅
+        - NA/✅
+        - NA/✅
+        - NA/✅
+
+      *
+        - :doc:`hipSOLVER <hipsolver:reference/precision>`
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+
+      *
+        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - ✅/✅
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+
+      *
+        - :doc:`hipTensor <hiptensor:api-reference/api-reference>`
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+
+      *
+        - :doc:`MIGraphX <amdmigraphx:reference/cpp>`
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`MIOpen <miopen:reference/datatypes>`
+        - ⚠️/⚠️
+        - ❌/❌
+        - ⚠️/⚠️
+        - ❌/❌
+
+      *
+        - :doc:`RCCL <rccl:api-reference/library-specification>`
+        - ✅/✅
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`rocFFT <rocfft:reference/api>`
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+
+      *
+        -  :doc:`rocPRIM <rocprim:reference/data-type-support>`
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
+        - NA/✅
+        - NA/✅
+        - NA/✅
+        - NA/✅
+
+      *
+        - :doc:`rocSOLVER <rocsolver:reference/precision>`
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+
      *
        - :doc:`rocThrust <rocthrust:data-type-support>`
        - ✅/✅
@@ -489,6 +778,14 @@ detailed description.
        - ✅/✅
        - ✅/✅

+      *
+        - :doc:`rocWMMA <rocwmma:api-reference/api-reference-guide>`
+        - ✅/✅
+        - ❌/❌
+        - ❌/✅
+        - ❌/❌
+
+
  .. tab-item:: Floating-point types
    :sync: floating-point-type

@@ -504,42 +801,17 @@ detailed description.
        - tensorfloat32
        - float32
        - float64
+
      *
-        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
-        - ❌/❌
-        - ❌/❌
+        - :doc:`Composable Kernel <composable_kernel:reference/Composable_Kernel_supported_scalar_types>`
        - ✅/✅
        - ✅/✅
-        - ❌/❌
-        - ❌/❌
-        - ❌/❌
-      *
-        - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/✅
-      *
-        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/❌
-        - NA/❌
-        - NA/✅
-        - NA/✅
-      *
-        - :doc:`rocPRIM <rocprim:reference/data-type-support>`
-        - ❌/❌
-        - ❌/❌
        - ✅/✅
        - ✅/✅
        - ❌/❌
        - ✅/✅
        - ✅/✅
+
      *
        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
        - ❌/❌
@@ -549,6 +821,117 @@ detailed description.
        - ❌/❌
        - ✅/✅
        - ✅/✅
+
+      *
+        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/✅
+
+      *
+        - :doc:`hipSOLVER <hipsolver:reference/precision>`
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+
+      *
+        - :doc:`hipTensor <hiptensor:api-reference/api-reference>`
+        - ❌/❌
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`MIGraphX <amdmigraphx:reference/cpp>`
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`MIOpen <miopen:reference/datatypes>`
+        - ⚠️/⚠️
+        - ⚠️/⚠️
+        - ✅/✅
+        - ⚠️/⚠️
+        - ❌/❌
+        - ✅/✅
+        - ⚠️/⚠️
+
+      *
+        - :doc:`RCCL <rccl:api-reference/library-specification>`
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`rocFFT <rocfft:reference/api>`
+        - ❌/❌
+        - ❌/❌
+        - ✅/✅
+        - ❌/❌
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`rocPRIM <rocprim:reference/data-type-support>`
+        - ❌/❌
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+
+      *
+        - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/✅
+
+      *
+        - :doc:`rocSOLVER <rocsolver:reference/precision>`
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ❌/❌
+        - ✅/✅
+        - ✅/✅
+
      *
        - :doc:`rocThrust <rocthrust:data-type-support>`
        - ❌/❌
@@ -559,62 +942,123 @@ detailed description.
        - ✅/✅
        - ✅/✅

+      *
+        - :doc:`rocWMMA <rocwmma:api-reference/api-reference-guide>`
+        - ✅/❌
+        - ✅/❌
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+        - ✅/✅
+
 .. note::
-   
+
  As random number generation libraries, rocRAND and hipRAND only specify output
  data types for the random values they generate, with no need for input data
  types.

-Libraries internal calculations type support
--------------------------------------------
+hipDataType enumeration
+-----------------------

-The following tables list ROCm library support for specific internal data types.
-Refer to the corresponding library data type support page for a detailed
-description.
+The ``hipDataType`` enumeration defines data precision types and is primarily
+used when the data reference itself does not include type information, such as
+in ``void*`` pointers. This enumeration is mainly utilized in BLAS libraries.
+The HIP type equivalents of the ``hipDataType`` enumeration are listed in the
+following table with descriptions and values.

-.. tab-set::
+.. list-table::
+    :header-rows: 1
+    :widths: 25,25,10,40

-  .. tab-item:: Integral types
-    :sync: integral-type
+    *
+      - hipDataType
+      - HIP type
+      - Value
+      - Description

-    .. list-table::
-      :header-rows: 1
+    *
+      - ``HIP_R_8I``
+      - ``int8_t``
+      - 3
+      - 8-bit real signed integer.

-      *
-        - Library internal data type name
-        - int8
-        - int16
-        - int32
-        - int64
-      *
-        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
-        - ❌
-        - ❌
-        - ✅
-        - ❌
+    *
+      - ``HIP_R_8U``
+      - ``uint8_t``
+      - 8
+      - 8-bit real unsigned integer.

+    *
+      - ``HIP_R_16I``
+      - ``int16_t``
+      - 20
+      - 16-bit real signed integer.

-  .. tab-item:: Floating-point types
-    :sync: floating-point-type
+    *
+      - ``HIP_R_16U``
+      - ``uint16_t``
+      - 22
+      - 16-bit real unsigned integer.

-    .. list-table::
-      :header-rows: 1
+    *
+      - ``HIP_R_32I``
+      - ``int32_t``
+      - 10
+      - 32-bit real signed integer.

-      *
-        - Library internal data type name
-        - float8 (E4M3)
-        - float8 (E5M2)
-        - float16
-        - bfloat16
-        - tensorfloat32
-        - float32
-        - float64
-      *
-        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
-        - ❌
-        - ❌
-        - ❌
-        - ❌
-        - ❌
-        - ✅
-        - ❌
+    *
+      - ``HIP_R_32U``
+      - ``uint32_t``
+      - 12
+      - 32-bit real unsigned integer.
+
+    *
+      - ``HIP_R_32F``
+      - ``float``
+      - 0
+      - 32-bit real single precision floating-point.
+
+    *
+      - ``HIP_R_64F``
+      - ``double``
+      - 1
+      - 64-bit real double precision floating-point.
+
+    *
+      - ``HIP_R_16F``
+      - ``half``
+      - 2
+      - 16-bit real half precision floating-point.
+
+    *
+      - ``HIP_R_16BF``
+      - ``bfloat16``
+      - 14
+      - 16-bit real bfloat16 precision floating-point.
+
+    *
+      - ``HIP_R_8F_E4M3``
+      - ``__hip_fp8_e4m3``
+      - 28
+      - 8-bit real float8 precision floating-point (OCP version).
+
+    *
+      - ``HIP_R_8F_E5M2``
+      - ``__hip_fp8_e5m2``
+      - 29
+      - 8-bit real bfloat8 precision floating-point (OCP version).
+
+    *
+      - ``HIP_R_8F_E4M3_FNUZ``
+      - ``__hip_fp8_e4m3_fnuz``
+      - 1000
+      - 8-bit real float8 precision floating-point (FNUZ version).
+
+    *
+      - ``HIP_R_8F_E5M2_FNUZ``
+      - ``__hip_fp8_e5m2_fnuz``
+      - 1001
+      - 8-bit real bfloat8 precision floating-point (FNUZ version).
+
+The full list of the ``hipDataType`` enumeration listed in `library_types.h <https://github.com/ROCm/hip/blob/amd-staging/include/hip/library_types.h>`_ .
--- a/docs/sphinx/_toc.yml.in
+++ b/docs/sphinx/_toc.yml.in
@@ -19,9 +19,9 @@ subtrees:

 - caption: Install
  entries:
-  - url: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/
+  - url: https://rocm.docs.amd.com/projects/install-on-linux/en/${branch}/
    title: ROCm on Linux
-  - url: https://rocm.docs.amd.com/projects/install-on-windows/en/${branch}/
+  - url: https://rocm.docs.amd.com/projects/install-on-windows/en/latest/
    title: HIP SDK on Windows
  - url: https://rocm.docs.amd.com/projects/radeon/en/latest/index.html
    title: ROCm on Radeon GPUs
@@ -82,6 +82,8 @@ subtrees:
            title: vLLM inference performance testing
          - file: how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference.rst
            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/deploy-your-model.rst
            title: Deploy your model

--- a/tools/autotag/components.xml
+++ b/tools/autotag/components.xml
@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <manifest>
    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
-    <default revision="refs/tags/rocm-6.4.1"
+    <default revision="refs/tags/rocm-6.4.2"
     remote="rocm-org"
     sync-c="true"
     sync-j="4" />
--- a/tools/rocm-build/rocm-6.4.2.xml
+++ b/tools/rocm-build/rocm-6.4.2.xml
@@ -0,0 +1,79 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest>
+    <remote name="rocm-org" fetch="https://github.com/ROCm/" />
+    <default revision="refs/tags/rocm-6.4.2"
+     remote="rocm-org"
+     sync-c="true"
+     sync-j="4" />
+<!--list of projects for ROCm-->
+    <project name="ROCm" revision="roc-6.4.x" />
+    <project name="ROCK-Kernel-Driver" />
+    <project name="ROCR-Runtime" />
+    <project name="amdsmi" />
+    <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="MIOpen" />
+    <project groups="mathlibs" name="MIVisionX" />
+    <project groups="mathlibs" name="ROCmValidationSuite" />
+    <project groups="mathlibs" name="Tensile" />
+    <project groups="mathlibs" name="composable_kernel" />
+    <project groups="mathlibs" name="hipBLAS-common" />
+    <project groups="mathlibs" name="hipBLAS" />
+    <project groups="mathlibs" name="hipBLASLt" />
+    <project groups="mathlibs" name="hipCUB" />
+    <project groups="mathlibs" name="hipFFT" />
+    <project groups="mathlibs" name="hipRAND" />
+    <project groups="mathlibs" name="hipSOLVER" />
+    <project groups="mathlibs" name="hipSPARSE" />
+    <project groups="mathlibs" name="hipSPARSELt" />
+    <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="rocBLAS" />
+    <project groups="mathlibs" name="rocDecode" />
+    <project groups="mathlibs" name="rocJPEG" />
+    <project groups="mathlibs" name="rocPyDecode" />
+    <project groups="mathlibs" name="rocFFT" />
+    <project groups="mathlibs" name="rocPRIM" />
+    <project groups="mathlibs" name="rocRAND" />
+    <project groups="mathlibs" name="rocSHMEM" />
+    <project groups="mathlibs" name="rocSOLVER" />
+    <project groups="mathlibs" name="rocSPARSE" />
+    <project groups="mathlibs" name="rocThrust" />
+    <project groups="mathlibs" name="rocWMMA" />
+    <project groups="mathlibs" name="rocm-cmake" />
+    <project groups="mathlibs" name="rpp" />
+    <project groups="mathlibs" name="TransferBench" />
+<!-- Projects for OpenMP-Extras -->
+    <project name="aomp" path="openmp-extras/aomp" />
+    <project name="aomp-extras" path="openmp-extras/aomp-extras" />
+    <project name="flang" path="openmp-extras/flang" />
+</manifest>
Author	SHA1	Message	Date
Dominic Widdows	a38b09844f	Update README.md removing reference to instructions that were moved Followup to the change in https://github.com/ROCm/ROCm/pull/4907/files - the instructions are no longer below. (Could also move the previous paragraph into this section.)	2025-08-01 15:06:51 -07:00
Daniel Su	885ab8438a	[Ex CI] reduce pipeline size (#5140 ) * new fft miopen pipeline ids * remove all references to mainline builds	2025-08-01 11:54:59 -04:00
anisha-amd	3837fe8440	Updates to the compatibility matrix with DGL fix (#5143 )	2025-08-01 11:17:34 -04:00
anisha-amd	98530811b4	Update megablocks-compatibility.rst (#5136 )	2025-07-31 13:30:39 -04:00
anisha-amd	266387d816	Docs: Adding frameworks compatibility for Megablocks and Taichi (#5133 )	2025-07-31 13:00:31 -04:00
Daniel Su	2e93925311	[Ex CI] disable rocSPARSE to hipSOLVER downstream path (#5134 )	2025-07-31 12:42:04 -04:00
Daniel Su	88c2a2877b	[Ex CI] enable hipSOLVER monorepo builds (#5119 ) For ROCm/rocm-libraries#942 Enables hipSOLVER monorepo builds. Enables downstream paths: rocSOLVER -> hipSOLVER rocSPARSE -> hipSOLVER Sample runs: hipSOLVER: https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=40959&view=results rocSOLVER: https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=40948&view=results rocSPARSE: https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=40949&view=results	2025-07-31 10:31:55 -04:00
Daniel Su	85e0580b28	[Ex CI] enable FFT downstream jobs (#5126 ) Monorepo support for FFTs was already implemented and trigger files already exist, so just need to enable their downstream jobs. Enables downstream path: hipRAND -> rocFFT -> hipFFT Sample runs: hipRAND: https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=41270&view=results rocFFT: https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=41268&view=results hipFFT: https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=41269&view=results	2025-07-31 10:31:35 -04:00
Peter Park	b61d6a021e	Update PyT and TF Docker images in compatibility pages for 6.4.2 (#5129 )	2025-07-31 09:55:46 -04:00
Istvan Kiss	fb30dafa29	Update precision support page part I. (#5127 )	2025-07-31 15:22:19 +02:00
Joseph Macaranas	b2012cb0b9	External CI: rocm-libraries superbuild component yaml (#5125 ) - Subset of the hipblaslt component yaml, deleting extra gpu targets and the testing component. - Sparse checkout details removed. - Basic build flags from top-level invocation added.	2025-07-30 17:50:46 -04:00
Daniel Su	45cf2b9a80	[Ex CI] rocprof-systems: add libsqlite3-dev (#5124 ) Fixes rocprofiler-systems builds following ROCm/rocprofiler-systems@26ae543 Sample build: https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=41257&view=results	2025-07-30 16:05:26 -04:00
Daniel Su	bee363995b	[Ex CI] revert miopen-get-ck script change (#5123 )	2025-07-30 12:03:51 -07:00
Daniel Su	3a031fad3a	[Ex CI] disable MIOpen downstream jobs (#5122 )	2025-07-30 13:12:11 -04:00
Daniel Su	46f6c4ff9a	[Ex CI] enable MIOpen monorepo (#5117 ) * init * fix source dir * miopen specify test build dir * fix test build dir * revert change * fix test build again * move to ultra temporarily * miopen-get-ck, working dir * exclude flaky test * move back to high * Add MIVisionX and AMDMIGraphX downstream jobs to MIOpen * comment sparsecheckoutdir * quote component names * fix artifact name * miopen ck script exit on fail * add downstream checkout repos * mivisionx, add aomp	2025-07-30 09:53:52 -07:00
Pratik Basyal	f632f2879f	ROCm Software Stack image for 6.4.0 updated (#5112 )	2025-07-28 14:51:19 -04:00
yugang-amd	cc5bc5a882	Add SGLang inference benchmark doc w/ initial support for DeepSeek-R1-Distill-Qwen-32B (#4870 )	2025-07-25 12:42:40 -04:00
Daniel Su	2c9c3d0ba1	[Ex CI] switch hipBLAS/SPARSE pipeline IDs to monorepo (#5098 )	2025-07-24 16:53:29 -04:00
Peter Park	14249f24d8	Use `madengine` instead of tools/run_models.py in docs (#5095 )	2025-07-24 15:38:12 -04:00
Daniel Su	0e8045cca7	[Ex CI] enable hipBLAS monorepo (#5090 )	2025-07-24 12:37:34 -04:00
Daniel Su	541fe92947	[Ex CI] update to 6.4.2 (#5087 )	2025-07-23 14:10:40 -04:00
Daniel Su	628d5f8a19	[Ex CI] create Docker images for nightly builds (#5005 )	2025-07-23 12:16:11 -04:00
Peter Park	984a91f008	Add DeepSeek Janus Pro 7B to PyTorch inference benchmark doc (#5071 ) --------- Co-authored-by: yugang-amd <yugang.wang@amd.com>	2025-07-22 16:26:06 -04:00
amd-hsivasun	ae2cc6ab38	[EX CI] ROCR-Runtime: migrate from rocm-smi to amd-smi (#5088 ) * Update ROCR-Runtime.yml Migrate from rocmsmi to amdsmi * Update ROCR-Runtime.yml Removed libhwloc.so.5 install * Update ROCR-Runtime.yml Link to hwloc.so.5 * Update ROCR-Runtime.yml Added link in the rocrtst step * Update ROCR-Runtime.yml	2025-07-22 14:17:53 -04:00
Peter Park	15ee605d18	Fix branches for install docs in _toc.yml.in (#5083 )	2025-07-22 11:03:40 -04:00
anisha-amd	ae54add299	Sphinx warning for ROCm fixed (#5077 ) (#5082 ) * Sphinx warning for DGL fixed * Update dgl-compatibility.rst removed benchmark line and updated link --------- Co-authored-by: Pratik Basyal <prbasyal@amd.com>	2025-07-22 10:51:15 -04:00
Peter Park	2269e9d25d	Remove broken link to deprecated AMDGPU installer documentation (#5078 ) * remove link to deprecated AMDGPU installation method * add deep learning frameworks	2025-07-21 19:36:20 -04:00
alexxu-amd	1b0b9f5a67	update xml for 6.4.2 (#5075 )	2025-07-21 17:22:12 -04:00