Replace "-" on precision support page

Bumps [rocm-docs-core](https://github.com/ROCm/rocm-docs-core) from 1.17.0 to 1.17.1.
- [Release notes](https://github.com/ROCm/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/ROCm/rocm-docs-core/compare/v1.17.0...v1.17.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.azuredevops/components/AMDMIGraphX.yml

@@ -146,6 +146,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/HIP.yml

@@ -41,7 +41,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -85,18 +86,19 @@ jobs:
     parameters:
       artifactName: amd
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      environment: amd
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     environment: amd
 
 # HIP with Nvidia backend
 - job: hip_clr_combined_nvidia
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -139,8 +141,8 @@ jobs:
     parameters:
       artifactName: nvidia
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      environment: nvidia
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     environment: nvidia

.azuredevops/components/MIOpen.yml

@@ -141,6 +141,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -196,7 +199,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:
       componentName: MIOpen
-      testParameters: '-VV --output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex test_rnn_seq_api'
+      testParameters: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml --exclude-regex test_rnn_seq_api'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/MIVisionX.yml

@@ -70,7 +70,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -107,11 +108,11 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      gpuTarget: $(JOB_GPU_TARGET)
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
 
 - job: MIVisionX_testing
   dependsOn: MIVisionX
@@ -127,6 +128,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/ROCR-Runtime.yml

@@ -32,7 +32,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -56,9 +57,9 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
 
 - job: ROCR_Runtime_testing
   dependsOn: ROCR_Runtime
@@ -74,6 +75,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/ROCdbgapi.yml

@@ -24,7 +24,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -48,6 +49,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/ROCmValidationSuite.yml

@@ -60,7 +60,8 @@ jobs:
     value: $(Agent.BuildDirectory)/rocm
   - name: HIP_INC_DIR
     value: $(Agent.BuildDirectory)/rocm
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -97,14 +98,14 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      extraEnvVars:
-        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
-        - ROCM_PATH:::/home/user/workspace/rocm
-        - HIP_INC_DIR:::/home/user/workspace/rocm
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     extraEnvVars:
+  #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+  #       - ROCM_PATH:::/home/user/workspace/rocm
+  #       - HIP_INC_DIR:::/home/user/workspace/rocm
 
 - job: ROCmValidationSuite_testing
   dependsOn: ROCmValidationSuite
@@ -120,6 +121,11 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+        TEST_CONF_DIR: MI300X
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
+        TEST_CONF_DIR: MI210
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -138,7 +144,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:
       componentName: ROCmValidationSuite
-      testExecutable: $(Agent.BuildDirectory)/rocm/bin/rvs -c $(Agent.BuildDirectory)/rocm/share/rocm-validation-suite/conf/MI300X/gst_single.conf
+      testExecutable: $(Agent.BuildDirectory)/rocm/bin/rvs -c $(Agent.BuildDirectory)/rocm/share/rocm-validation-suite/conf/$(TEST_CONF_DIR)/gst_single.conf
       testParameters: ''
       testDir: $(Agent.BuildDirectory)
       testPublishResults: false

.azuredevops/components/Tensile.yml

@@ -35,7 +35,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -83,10 +84,10 @@ jobs:
           echo $(basename "$whlFile") >> pipelineArtifacts.txt
         fi
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
 
 - job: Tensile_testing
   timeoutInMinutes: 90
@@ -103,6 +104,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/TransferBench.yml

@@ -35,7 +35,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -71,10 +72,10 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      gpuTarget: $(JOB_GPU_TARGET)
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
 
 - job: TransferBench_testing
   dependsOn: TransferBench
@@ -90,6 +91,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/amdsmi.yml

@@ -18,7 +18,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -36,9 +37,9 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
 
 - job: amdsmi_testing
   dependsOn: amdsmi
@@ -54,6 +55,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/aomp-extras.yml

@@ -23,7 +23,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -51,6 +52,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/aomp.yml

@@ -456,6 +456,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/composable_kernel.yml

@@ -119,6 +119,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/half.yml

@@ -25,7 +25,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -59,7 +60,7 @@ jobs:
         ./bin/test
       workingDirectory: $(Build.SourcesDirectory)/test
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      environment: combined
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     environment: combined

.azuredevops/components/hip-tests.yml

@@ -108,6 +108,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipBLAS-common.yml

@@ -29,7 +29,8 @@ jobs:
   - name: ROCM_PATH
     value: $(Agent.BuildDirectory)/rocm
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -53,8 +54,8 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      extraEnvVars:
-        - ROCM_PATH:::/home/user/workspace/rocm
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     extraEnvVars:
+  #       - ROCM_PATH:::/home/user/workspace/rocm

.azuredevops/components/hipBLAS.yml

@@ -120,6 +120,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipBLASLt.yml

@@ -158,6 +158,7 @@ jobs:
         - deps
 
 - job: hipBLASLt_testing
+  timeoutInMinutes: 120
   dependsOn: hipBLASLt
   condition: and(succeeded(), eq(variables.ENABLE_GFX942_TESTS, 'true'), not(containsValue(split(variables.DISABLED_GFX942_TESTS, ','), variables['Build.DefinitionName'])))
   variables:
@@ -171,6 +172,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipCUB.yml

@@ -93,6 +93,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipFFT.yml

@@ -47,7 +47,8 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -91,10 +92,10 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      gpuTarget: $(JOB_GPU_TARGET)
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
 
 - job: hipFFT_testing
   dependsOn: hipFFT
@@ -110,6 +111,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipRAND.yml

@@ -38,7 +38,8 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -78,12 +79,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      extraEnvVars:
-        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     extraEnvVars:
+  #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
 - job: hipRAND_testing
   dependsOn: hipRAND
@@ -99,6 +100,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipSOLVER.yml

@@ -50,7 +50,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -99,12 +100,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      extraCopyDirectories:
-        - deps-install
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     extraCopyDirectories:
+  #       - deps-install
 
 - job: hipSOLVER_testing
   dependsOn: hipSOLVER
@@ -120,6 +121,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipSPARSE.yml

@@ -45,7 +45,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -94,11 +95,11 @@ jobs:
       artifactName: testMatrices
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      environment: test
-      gpuTarget: $(JOB_GPU_TARGET)
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     environment: test
+  #     gpuTarget: $(JOB_GPU_TARGET)
 
 - job: hipSPARSE_testing
   dependsOn: hipSPARSE
@@ -114,6 +115,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/hipSPARSELt.yml

@@ -105,6 +105,7 @@ jobs:
         -DCMAKE_BUILD_TYPE=Release
         -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang++
         -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/amdclang
+        -DCMAKE_Fortran_COMPILER=f95
         -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
         -DTensile_LOGIC=
         -DTensile_CPU_THREADS=

.azuredevops/components/hipTensor.yml

@@ -94,6 +94,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -113,7 +116,7 @@ jobs:
     parameters:
       componentName: hipTensor
       testDir: '$(Agent.BuildDirectory)/rocm/bin/hiptensor'
-      testParameters: '-E ".*-extended" -VV --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+      testParameters: '-E ".*-extended" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     parameters:
       aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/hipfort.yml

@@ -110,6 +110,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/llvm-project.yml

@@ -29,7 +29,7 @@ jobs:
     value: '$(Build.BinariesDirectory)/amdgcn/bitcode'
   - name: HIP_PATH
     value: '$(Agent.BuildDirectory)/rocm'
-  pool: ${{ variables.MEDIUM_BUILD_POOL }}
+  pool: ${{ variables.ULTRA_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -51,7 +51,7 @@ jobs:
       extraBuildFlags: >-
         -DCMAKE_PREFIX_PATH="$(Build.BinariesDirectory)/llvm;$(Build.BinariesDirectory)"
         -DCMAKE_BUILD_TYPE=Release
-        -DLLVM_ENABLE_PROJECTS=clang;lld;clang-tools-extra;mlir
+        -DLLVM_ENABLE_PROJECTS=clang;lld;clang-tools-extra;mlir;flang
         -DLLVM_ENABLE_RUNTIMES=compiler-rt;libunwind;libcxx;libcxxabi
         -DCLANG_ENABLE_AMDCLANG=ON
         -DLLVM_TARGETS_TO_BUILD=AMDGPU;X86
@@ -85,7 +85,7 @@ jobs:
       componentName: check-llvm
       testDir: 'llvm/build'
       testExecutable: './bin/llvm-lit'
-      testParameters: '-q --xunit-xml-output=llvm_test_output.xml ./test'
+      testParameters: '-q --xunit-xml-output=llvm_test_output.xml --filter-out="live-debug-values-spill-tracking" ./test'
       testOutputFile: llvm_test_output.xml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:

.azuredevops/components/rccl.yml

@@ -123,6 +123,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rdc.yml

@@ -134,6 +134,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocAL.yml

@@ -66,7 +66,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -157,14 +158,14 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      registerJPEGPackages: true
-      gpuTarget: $(JOB_GPU_TARGET)
-      extraCopyDirectories:
-        - /opt/libjpeg-turbo
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     registerJPEGPackages: true
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     extraCopyDirectories:
+  #       - /opt/libjpeg-turbo
 
 - job: rocAL_testing
   dependsOn: rocAL
@@ -186,6 +187,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - task: Bash@3
     displayName: 'Register libjpeg-turbo packages'

.azuredevops/components/rocALUTION.yml

@@ -53,7 +53,8 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -94,12 +95,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      extraEnvVars:
-        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     extraEnvVars:
+  #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
 - job: rocALUTION_testing
   dependsOn: rocALUTION
@@ -115,6 +116,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocBLAS.yml

@@ -144,6 +144,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocDecode.yml

@@ -45,7 +45,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool:
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -71,10 +72,10 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     registerROCmPackages: true
 
 - job: rocDecode_testing
   dependsOn: rocDecode
@@ -92,6 +93,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocFFT.yml

@@ -112,6 +112,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocJPEG.yml

@@ -40,7 +40,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -74,11 +75,11 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      registerROCmPackages: true
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     registerROCmPackages: true
 
 - job: rocJPEG_testing
   dependsOn: rocJPEG
@@ -96,6 +97,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocMLIR.yml

@@ -9,21 +9,25 @@ parameters:
   type: object
   default:
     - cmake
-    - ninja-build
     - git
-    - python3-pip
     - libdrm-dev
     - libstdc++-12-dev
+    - ninja-build
+    - python3-pip
 - name: pipModules
   type: object
   default:
+    - hip-python --extra-index-url https://test.pypi.org/simple
+    - ml_dtypes
+    - numpy
     - tomli
+    - scipy
 - name: rocmDependencies
   type: object
   default:
+    - clr
     - llvm-project
     - rocm-cmake
-    - clr
     - rocminfo
     - rocprofiler-register
     - ROCR-Runtime
@@ -56,6 +60,7 @@ jobs:
         -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
         -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
         -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+        -DROCM_PATH=$(Agent.BuildDirectory)/rocm
         -DBUILD_FAT_LIBROCKCOMPILER=1
         -GNinja
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
@@ -81,6 +86,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -111,6 +119,7 @@ jobs:
         -DCMAKE_CXX_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang++
         -DCMAKE_C_COMPILER=$(Agent.BuildDirectory)/rocm/llvm/bin/clang
         -DCMAKE_PREFIX_PATH=$(Agent.BuildDirectory)/rocm
+        -DROCM_PATH=$(Agent.BuildDirectory)/rocm
         -DAMDGPU_TARGETS=$(JOB_GPU_TARGET)
         -DROCM_TEST_CHIPSET=$(JOB_GPU_TARGET)
         -GNinja

.azuredevops/components/rocPRIM.yml

@@ -92,6 +92,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocPyDecode.yml

@@ -22,26 +22,28 @@ parameters:
 - name: pipModules
   type: object
   default:
+    - hip-python --extra-index-url https://test.pypi.org/simple
     - numpy
     - pybind11
 - name: rocmDependencies
   type: object
   default:
-    - rocm-cmake
-    - llvm-project
-    - ROCR-Runtime
     - clr
-    - rocminfo
-    - rocm-core
-    - rocprofiler-register
+    - llvm-project
     - rocDecode
+    - rocm-cmake
+    - rocm-core
+    - rocminfo
+    - ROCR-Runtime
+    - rocprofiler-register
 
 jobs:
 - job: rocPyDecode
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -55,11 +57,6 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-  - task: Bash@3
-    displayName: 'pip install hip-python'
-    inputs:
-      targetType: inline
-      script: pip install -i https://test.pypi.org/simple hip-python
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
     parameters:
@@ -141,12 +138,12 @@ jobs:
           echo $(basename "$whlFile") >> pipelineArtifacts.txt
         fi
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      optSymLink: true
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     optSymLink: true
 
 - job: rocPyDecode_testing
   dependsOn: rocPyDecode
@@ -164,6 +161,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - task: Bash@3
     displayName: Ensure pybind11-dev is not installed
@@ -180,11 +180,6 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
-  - task: Bash@3
-    displayName: 'pip install hip-python'
-    inputs:
-      targetType: inline
-      script: pip install -i https://test.pypi.org/simple hip-python
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
   - task: DownloadPipelineArtifact@2
     displayName: 'Download Pipeline Wheel Files'

.azuredevops/components/rocRAND.yml

@@ -38,7 +38,8 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -75,12 +76,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      extraEnvVars:
-        - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     extraEnvVars:
+  #       - HIP_ROCCLR_HOME:::/home/user/workspace/rocm
 
 - job: rocRAND_testing
   dependsOn: rocRAND
@@ -96,6 +97,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocSOLVER.yml

@@ -130,6 +130,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocSPARSE.yml

@@ -125,6 +125,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocThrust.yml

@@ -97,6 +97,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocWMMA.yml

@@ -98,7 +98,7 @@ jobs:
       gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rocWMMA_testing
-  timeoutInMinutes: 90
+  timeoutInMinutes: 120
   dependsOn: rocWMMA
   condition: and(succeeded(), eq(variables.ENABLE_GFX942_TESTS, 'true'), not(containsValue(split(variables.DISABLED_GFX942_TESTS, ','), variables['Build.DefinitionName'])))
   variables:
@@ -112,6 +112,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocm-cmake.yml

@@ -8,7 +8,6 @@ parameters:
 - name: aptPackages
   type: object
   default:
-    - cmake
     - doxygen
     - doxygen-doc
     - ninja-build
@@ -18,14 +17,17 @@ parameters:
   type: object
   default:
     - cget
+    - cmake==3.20.5
     - ninja
+    - rocm-docs-core
 
 jobs:
 - job: rocm_cmake
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -33,26 +35,34 @@ jobs:
     parameters:
       aptPackages: ${{ parameters.aptPackages }}
       pipModules: ${{ parameters.pipModules }}
+  - task: Bash@3
+    displayName: Add CMake to PATH
+    inputs:
+      targetType: inline
+      script: echo "##vso[task.prependpath]$(python3 -m site --user-base)/bin"
   - 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/build-cmake.yml
-# extra steps for ctest suite
-  - script: |
-      python -m pip install -r $(Build.SourcesDirectory)/docs/requirements.txt
-      python -m pip install -r $(Build.SourcesDirectory)/test/docsphinx/docs/.sphinx/requirements.txt
-      git config --global user.email "you@example.com"
-      git config --global user.name "Your Name"
-    displayName: "ctest setup"
+  - task: Bash@3
+    displayName: CTest setup
+    inputs:
+      targetType: inline
+      script: |
+        python -m pip install -r $(Build.SourcesDirectory)/docs/requirements.txt
+        python -m pip install -r $(Build.SourcesDirectory)/test/docsphinx/docs/.sphinx/requirements.txt
+        git config --global user.email "you@example.com"
+        git config --global user.name "Your Name"
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:
       componentName: rocm-cmake
+      testParameters: '-E "pass-version-parent" --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      environment: combined
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     environment: combined

.azuredevops/components/rocm-core.yml

@@ -16,7 +16,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -40,6 +41,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}

.azuredevops/components/rocm-examples.yml

@@ -135,6 +135,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocm_bandwidth_test.yml

@@ -40,7 +40,8 @@ jobs:
     value: $(Agent.BuildDirectory)/rocm
   - name: ROCR_LIB_DIR
     value: $(Agent.BuildDirectory)/rocm
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -66,13 +67,13 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      extraEnvVars:
-        - ROCR_INC_DIR:::/home/user/workspace/rocm
-        - ROCR_LIB_DIR:::/home/user/workspace/rocm
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     extraEnvVars:
+  #       - ROCR_INC_DIR:::/home/user/workspace/rocm
+  #       - ROCR_LIB_DIR:::/home/user/workspace/rocm
 
 - job: rocm_bandwidth_test_testing
   dependsOn: rocm_bandwidth_test
@@ -88,6 +89,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocm_smi_lib.yml

@@ -18,7 +18,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -37,9 +38,9 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
 
 - job: rocm_smi_lib_testing
   dependsOn: rocm_smi_lib
@@ -55,7 +56,13 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   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
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/gpu-diagnostics.yml

.azuredevops/components/rocminfo.yml

@@ -28,7 +28,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -53,10 +54,10 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      registerROCmPackages: true
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     registerROCmPackages: true
 
 - job: rocminfo_testing
   dependsOn: rocminfo
@@ -72,6 +73,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocprofiler-compute.yml

@@ -52,7 +52,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -84,11 +85,11 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      gpuTarget: $(JOB_GPU_TARGET)
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rocprofiler_compute_testing
   timeoutInMinutes: 120
@@ -107,6 +108,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:
@@ -157,7 +161,7 @@ jobs:
     parameters:
       componentName: rocprofiler-compute
       testDir: $(Build.BinariesDirectory)/libexec/rocprofiler-compute
-      testExecutable: ROCPROFCOMPUTE_ARCH_OVERRIDE="MI300X" ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
+      testExecutable: ROCM_PATH=$(Agent.BuildDirectory)/rocm ctest
   - task: Bash@3
     displayName: Remove ROCm binaries from PATH
     condition: always()

.azuredevops/components/rocprofiler-register.yml

@@ -16,7 +16,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -44,7 +45,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      environment: combined
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     environment: combined

.azuredevops/components/rocprofiler-sdk.yml

@@ -50,7 +50,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -98,12 +99,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      registerROCmPackages: true
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     registerROCmPackages: true
 
 - job: rocprofiler_sdk_testing
   dependsOn: rocprofiler_sdk
@@ -119,6 +120,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocprofiler-systems.yml

@@ -158,6 +158,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocprofiler.yml

@@ -114,6 +114,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rocr_debug_agent.yml

@@ -40,7 +40,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   steps:
@@ -66,9 +67,9 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
 
 - job: rocr_debug_agent_testing
   dependsOn: rocr_debug_agent
@@ -84,6 +85,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/roctracer.yml

@@ -43,7 +43,8 @@ jobs:
   - template: /.azuredevops/variables-global.yml
   - name: HIP_ROCCLR_HOME
     value: $(Build.BinariesDirectory)/rocm
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -84,12 +85,12 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      gpuTarget: $(JOB_GPU_TARGET)
-      registerROCmPackages: true
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
+  #     registerROCmPackages: true
 
 - job: roctracer_testing
   dependsOn: roctracer
@@ -105,6 +106,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/components/rpp.yml

@@ -50,7 +50,8 @@ jobs:
   variables:
   - group: common
   - template: /.azuredevops/variables-global.yml
-  pool: ${{ variables.LOW_BUILD_POOL }}
+  pool: 
+    vmImage: ${{ variables.BASE_BUILD_POOL }}
   workspace:
     clean: all
   strategy:
@@ -91,11 +92,11 @@ jobs:
     parameters:
       gpuTarget: $(JOB_GPU_TARGET)
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
-  - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
-    parameters:
-      aptPackages: ${{ parameters.aptPackages }}
-      pipModules: ${{ parameters.pipModules }}
-      gpuTarget: $(JOB_GPU_TARGET)
+  # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
+  #   parameters:
+  #     aptPackages: ${{ parameters.aptPackages }}
+  #     pipModules: ${{ parameters.pipModules }}
+  #     gpuTarget: $(JOB_GPU_TARGET)
 
 - job: rpp_testing
   dependsOn: rpp
@@ -113,6 +114,9 @@ jobs:
       gfx942:
         JOB_GPU_TARGET: gfx942
         JOB_TEST_POOL: ${{ variables.GFX942_TEST_POOL }}
+      gfx90a:
+        JOB_GPU_TARGET: gfx90a
+        JOB_TEST_POOL: ${{ variables.GFX90A_TEST_POOL }}
   steps:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-other.yml
     parameters:

.azuredevops/templates/steps/build-cmake.yml

@@ -32,6 +32,9 @@ parameters:
 - name: installEnabled
   type: boolean
   default: true
+- name: printDiskSpace
+  type: boolean
+  default: true
 
 steps:
 # create workingDirectory if it does not exist and change into it
@@ -44,8 +47,9 @@ steps:
       cmakeArgs: -DCMAKE_INSTALL_PREFIX=${{ parameters.installDir }} ${{ parameters.extraBuildFlags }} ${{ parameters.cmakeSourceDir }}
     ${{ else }}:
       cmakeArgs: ${{ parameters.extraBuildFlags }} ..
-- script: df -h
-  displayName: Disk space before build
+- ${{ if parameters.printDiskSpace }}:
+  - script: df -h
+    displayName: Disk space before build
 # equivalent to running make $cmakeTargetDir from $cmakeBuildDir
 # i.e., cd $cmakeBuildDir; make $cmakeTargetDir
 - task: CMake@1
@@ -57,8 +61,9 @@ steps:
     ${{ else }}:
       cmakeArgs: '--build ${{ parameters.cmakeTargetDir }} --target ${{ parameters.customBuildTarget }} ${{ parameters.multithreadFlag }}'
     retryCountOnTaskFailure: 10
-- script: df -h
-  displayName: Disk space after build
+- ${{ if parameters.printDiskSpace }}:
+  - script: df -h
+    displayName: Disk space after build
 # equivalent to running make $cmakeTarget from $cmakeBuildDir
 # e.g., make install
 - ${{ if eq(parameters.installEnabled, true) }}:

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

@@ -34,7 +34,12 @@ steps:
   displayName: 'sudo apt-get update'
   inputs:
     targetType: inline
-    script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update
+    script: |
+      echo "deb http://archive.ubuntu.com/ubuntu/ jammy main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
+      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
+      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-backports main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
+      echo "deb http://archive.ubuntu.com/ubuntu/ jammy-security main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/default.list
+      sudo DEBIAN_FRONTEND=noninteractive apt-get --yes update
 - task: Bash@3
   displayName: 'sudo apt-get upgrade'
   inputs:
@@ -50,7 +55,7 @@ steps:
     displayName: 'sudo apt-get install ...'
     inputs:
       targetType: inline
-      script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes install ${{ join(' ', parameters.aptPackages) }}
+      script: sudo DEBIAN_FRONTEND=noninteractive apt-get --yes --fix-missing install ${{ join(' ', parameters.aptPackages) }}
 - ${{ if gt(length(parameters.pipModules), 0) }}:
   - task: Bash@3
     displayName: 'pip install  ...'

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

@@ -222,13 +222,13 @@ parameters:
       hasGpuTarget: false
     rocm-examples:
       pipelineId: $(ROCM_EXAMPLES_PIPELINE_ID)
-      stagingBranch: develop
-      mainlineBranch: develop
+      stagingBranch: amd-staging
+      mainlineBranch: amd-mainline
       hasGpuTarget: true
     rocminfo:
       pipelineId: $(ROCMINFO_PIPELINE_ID)
       stagingBranch: amd-staging
-      mainlineBranch: amd-master
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocMLIR:
       pipelineId: $(ROCMLIR_PIPELINE_ID)
@@ -288,7 +288,7 @@ parameters:
     ROCR-Runtime:
       pipelineId: $(ROCR_RUNTIME_PIPELINE_ID)
       stagingBranch: amd-staging
-      mainlineBranch: amd-master
+      mainlineBranch: amd-mainline
       hasGpuTarget: false
     rocRAND:
       pipelineId: $(ROCRAND_PIPELINE_ID)

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

@@ -107,7 +107,7 @@ steps:
 # dynamically write to a Dockerfile
 # first is to do base setup of users, groups
   - task: Bash@3
-    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: Create start of Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
@@ -126,7 +126,7 @@ steps:
 # for test jobs, setup GPU-related users and group
   - ${{ if eq(parameters.environment, 'test') }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: GPU setup of Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -137,7 +137,7 @@ steps:
 # now install a common set of packages through apt
   - ${{ if gt(length(parameters.baseAptPackages), 0) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Base Apt Packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -146,7 +146,7 @@ steps:
 # iterate through possible apt repos that might need to be added to the docker container
   - ${{ if eq(parameters.registerROCmPackages, true) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Register ROCm packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -160,7 +160,7 @@ steps:
           echo "RUN DEBIAN_FRONTEND=noninteractive apt-get --yes update" >> Dockerfile
   - ${{ if eq(parameters.registerCUDAPackages, true) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Register CUDA packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -172,7 +172,7 @@ steps:
           echo 'RUN DEBIAN_FRONTEND=noninteractive apt-get --yes update' >> Dockerfile
   - ${{ if eq(parameters.registerJPEGPackages, true) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Register libjpeg-turbo packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -185,7 +185,7 @@ steps:
 # install AOCL to docker container, if needed
   - ${{ if eq(parameters.installAOCL, true) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: aocl install to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -197,7 +197,7 @@ steps:
 # since apt repo list is updated, install the extra apt packages
   - ${{ if gt(length(parameters.aptPackages), 0) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Extra Apt Packages to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -206,7 +206,7 @@ steps:
 # install latest cmake to docker container, if needed
   - ${{ if eq(parameters.installLatestCMake, true) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: latest cmake install to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -216,7 +216,7 @@ steps:
             echo "RUN pip install cmake --upgrade" >> Dockerfile
 # setup workspace where binaries, sources, and dependencies from the job will be copied to
   - task: Bash@3
-    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: Workspace setup of Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
@@ -228,7 +228,7 @@ steps:
 # pip install is done here as non-root
   - ${{ if gt(length(parameters.pipModules), 0) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Extra Python Modules to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -236,7 +236,7 @@ steps:
         script: echo "RUN pip install -v ${{ join(' ', parameters.pipModules) }}" >> Dockerfile
 # copy common directories
   - task: Bash@3
-    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: Copy base directories to Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
@@ -254,7 +254,7 @@ steps:
 # copy extra directories, if applicable to the job
   - ${{ each extraCopyDirectory in parameters.extraCopyDirectories }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Copy ${{ extraCopyDirectory }} to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -265,7 +265,7 @@ steps:
           fi
 # setup ldconfig
   - task: Bash@3
-    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: ldconfig to Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
@@ -279,7 +279,7 @@ steps:
 # create /opt/rocm symbolic link, if needed
   - ${{ if eq(parameters.optSymLink, true) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: /opt/rocm symbolic link to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -290,7 +290,7 @@ steps:
 # set environment variables needed for some python-based components
   - ${{ if eq(parameters.pythonEnvVars, true) }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: python environment variables
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -303,7 +303,7 @@ steps:
 # add to PATH environment variable
   - ${{ if ne(parameters.extraPaths, '') }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Add to PATH in Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
@@ -313,21 +313,21 @@ steps:
 # use ::: as delimiter to allow for colons to be in the environment variable values
   - ${{ each extraEnvVar in parameters.extraEnvVars }}:
     - task: Bash@3
-      condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+      condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
       displayName: Set ${{ extraEnvVar }} to Dockerfile
       inputs:
         workingDirectory: $(Pipeline.Workspace)
         targetType: inline
         script: echo "ENV ${{ split(extraEnvVar, ':::')[0] }}='${{ split(extraEnvVar, ':::')[1] }}'" >> Dockerfile
   - task: Bash@3
-    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: Print Dockerfile
     inputs:
       workingDirectory: $(Pipeline.Workspace)
       targetType: inline
       script: cat Dockerfile
   - task: Docker@2
-    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
     inputs:
       containerRegistry: 'ContainerService'
       ${{ if ne(parameters.gpuTarget, '') }}:
@@ -337,7 +337,7 @@ steps:
       Dockerfile: '$(Pipeline.Workspace)/Dockerfile'
       buildContext: '$(Pipeline.Workspace)'
   - task: Bash@3
-    condition: or(failed(), ${{ eq(parameters.forceDockerCreation, true) }})
+    condition: or(and(failed(), not(contains(variables['DOCKER_SKIP_GFX'], variables['JOB_GPU_TARGET']))), ${{ eq(parameters.forceDockerCreation, true) }})
     displayName: "!! Docker Image URL !!"
     inputs:
       workingDirectory: $(Pipeline.Workspace)

.azuredevops/templates/steps/manifest.yml

@@ -77,11 +77,11 @@ steps:
 
       dependencies_rows=$(cat $manifest_json | \
         jq -r '
-          .dependencies[] | 
-          "<tr><td>" + .buildNumber + "</td>" + 
-          "<td><a href=\"https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=" + .buildId + "\">" + .buildId + "</a></td>" + 
-          "<td><a href=\"" + .repoUrl + "\">" + .repoName + "</a></td>" + 
-          "<td><a href=\"" + .repoUrl + "/tree/" + .repoRef + "\">" + .repoRef + "</a></td>" + 
+          .dependencies[] |
+          "<tr><td>" + .buildNumber + "</td>" +
+          "<td><a href=\"https://dev.azure.com/ROCm-CI/ROCm-CI/_build/results?buildId=" + .buildId + "\">" + .buildId + "</a></td>" +
+          "<td><a href=\"" + .repoUrl + "\">" + .repoName + "</a></td>" +
+          "<td><a href=\"" + .repoUrl + "/tree/" + .repoRef + "\">" + .repoRef + "</a></td>" +
           "<td><a href=\"" + .repoUrl + "/commit/" + .repoVersion + "\">" + .repoVersion + "</a></td></tr>"
         ')
       dependencies_rows=$(echo $dependencies_rows)
@@ -130,6 +130,11 @@ steps:
       </html>
       EOF
 
+      sed -i -e 's|</tr> <tr>|</tr>\n<tr>|g' \
+        -e 's|</td><td>|</td>\n  <td>|g' \
+        -e 's|<tr><td>|<tr>\n  <td>|g' \
+        -e 's|</td></tr>|</td>\n</tr>|g' $manifest_html
+
       cat $manifest_html
 - task: PublishHtmlReport@1
   displayName: Publish manifest.html

.azuredevops/templates/steps/test.yml

@@ -10,7 +10,7 @@ parameters:
   default: 'ctest'
 - name: testParameters
   type: string
-  default: '-VV --output-on-failure --force-new-ctest-process --output-junit test_output.xml'
+  default: '--output-on-failure --force-new-ctest-process --output-junit test_output.xml'
 - name: testOutputFile
   type: string
   default: test_output.xml
@@ -33,7 +33,6 @@ parameters:
     - aomp
     - HIPIFY
     - MIVisionX
-    - rocm-cmake
     - rocm_smi_lib
     - rocprofiler-sdk
     - roctracer

.azuredevops/variables-global.yml

@@ -27,14 +27,18 @@ variables:
   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: 6.3.3
+  value: 6.3.4
 - name: REPO_RADEON_VERSION
-  value: 6.3.3
+  value: 6.3.4
 - name: NEXT_RELEASE_VERSION
   value: 6.4.0
 - name: LATEST_RELEASE_TAG
-  value: rocm-6.3.3
+  value: rocm-6.3.4
+- name: DOCKER_SKIP_GFX
+  value: gfx90a
 - name: AMDMIGRAPHX_GFX942_TEST_PIPELINE_ID
   value: 197
 - name: AMDMIGRAPHX_PIPELINE_ID

.gitignore

@@ -11,6 +11,7 @@ _toc.yml
 docBin/
 _doxygen/
 _readthedocs/
+__pycache__/
 
 # avoid duplicating contributing.md due to conf.py
 docs/CHANGELOG.md

.wordlist.txt

@@ -481,6 +481,7 @@ ZenDNN
 accuracies
 activations
 addr
+ai
 alloc
 allocatable
 allocator
@@ -546,6 +547,7 @@ cTDP
 dataset
 datasets
 dataspace
+datatemplate
 datatype
 datatypes
 dbgapi
@@ -574,6 +576,7 @@ el
 embeddings
 enablement
 encodings
+endfor
 endpgm
 enqueue
 env
@@ -694,6 +697,7 @@ pageable
 pallas
 parallelization
 parallelizing
+param
 parameterization
 passthrough
 perfcounter
@@ -811,6 +815,7 @@ supercomputing
 symlink
 symlinks
 sys
+tabindex
 td
 tensorfloat
 th
@@ -856,6 +861,7 @@ vectorizes
 virtualize
 virtualized
 vjxb
+vllm
 voxel
 walkthrough
 walkthroughs

CONTRIBUTING.md

@@ -66,11 +66,10 @@ project-specific steps. Refer to each repository's PR process for any additional
   during our release cycle, as coordinated by the maintainer
 * We'll inform you once your change is committed
 
-:::{important}
-By creating a PR, you agree to allow your contribution to be licensed under the
-terms of the LICENSE.txt file in the corresponding repository. Different repositories may use different
-licenses.
-:::
+> [!IMPORTANT]
+> By creating a PR, you agree to allow your contribution to be licensed under the
+> terms of the LICENSE.txt file in the corresponding repository. Different repositories may use different
+> licenses.
 
 You can look up each license on the [ROCm licensing](https://rocm.docs.amd.com/en/latest/about/license.html) page.
 

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

@@ -4,6 +4,8 @@
    :description: JAX compatibility
    :keywords: GPU, JAX compatibility
 
+.. version-set:: rocm_version latest
+
 *******************************************************************************
 JAX compatibility
 *******************************************************************************
@@ -119,7 +121,8 @@ Critical ROCm libraries for JAX
 
 The functionality of JAX with ROCm is determined by its underlying library
 dependencies. These critical ROCm components affect the capabilities,
-performance, and feature set available to developers.
+performance, and feature set available to developers. The versions described
+are available in ROCm :version:`rocm_version`.
 
 .. list-table::
     :header-rows: 1
@@ -129,7 +132,7 @@ performance, and feature set available to developers.
       - Purpose
       - Used in
     * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - 2.3.0
+      - :version-ref:`hipBLAS rocm_version`
       - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
         matrix and vector operations.
       - Matrix multiplication in ``jax.numpy.matmul``, ``jax.lax.dot`` and
@@ -138,7 +141,7 @@ performance, and feature set available to developers.
         ``jax.numpy.einsum`` with matrix-multiplication patterns algebra
         operations.
     * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - 0.10.0
+      - :version-ref:`hipBLASLt rocm_version`
       - hipBLASLt is an extension of hipBLAS, providing additional
         features like epilogues fused into the matrix multiplication kernel or
         use of integer tensor cores.
@@ -147,7 +150,7 @@ performance, and feature set available to developers.
         operations, mixed-precision support, and hardware-specific
         optimizations.
     * - `hipCUB <https://github.com/ROCm/hipCUB>`_
-      - 3.3.0
+      - :version-ref:`hipCUB rocm_version`
       - Provides a C++ template library for parallel algorithms for reduction,
         scan, sort and select.
       - Reduction functions (``jax.numpy.sum``, ``jax.numpy.mean``,
@@ -155,23 +158,23 @@ performance, and feature set available to developers.
         (``jax.numpy.cumsum``, ``jax.numpy.cumprod``) and sorting
         (``jax.numpy.sort``, ``jax.numpy.argsort``).
     * - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - 1.0.17
+      - :version-ref:`hipFFT rocm_version`
       - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
       - Used in functions like ``jax.numpy.fft``.
     * - `hipRAND <https://github.com/ROCm/hipRAND>`_
-      - 2.11.0
+      - :version-ref:`hipRAND rocm_version`
       - Provides fast random number generation for GPUs.
       - The ``jax.random.uniform``, ``jax.random.normal``,
         ``jax.random.randint`` and ``jax.random.split``.
     * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - 2.3.0
+      - :version-ref:`hipSOLVER rocm_version`
       - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
         singular value decompositions (SVD).
       - Solving linear systems (``jax.numpy.linalg.solve``), matrix
         factorizations, SVD (``jax.numpy.linalg.svd``) and eigenvalue problems
         (``jax.numpy.linalg.eig``).
     * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - 3.1.2
+      - :version-ref:`hipSPARSE rocm_version`
       - Accelerates operations on sparse matrices, such as sparse matrix-vector
         or matrix-matrix products.
       - Sparse matrix multiplication (``jax.numpy.matmul``), sparse
@@ -179,28 +182,28 @@ performance, and feature set available to developers.
         (``jax.experimental.sparse.dot``), sparse linear system solvers and
         sparse data handling.
     * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
-      - 0.2.2
+      - :version-ref:`hipSPARSELt rocm_version`
       - Accelerates operations on sparse matrices, such as sparse matrix-vector
         or matrix-matrix products.
       - Sparse matrix multiplication (``jax.numpy.matmul``), sparse
         matrix-vector and matrix-matrix products
         (``jax.experimental.sparse.dot``) and sparse linear system solvers.
     * - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - 3.3.0
+      - :version-ref:`MIOpen rocm_version`
       - Optimized for deep learning primitives such as convolutions, pooling,
         normalization, and activation functions.
       - Speeds up convolutional neural networks (CNNs), recurrent neural
         networks (RNNs), and other layers. Used in operations like
         ``jax.nn.conv``, ``jax.nn.relu``, and ``jax.nn.batch_norm``.
     * - `RCCL <https://github.com/ROCm/rccl>`_
-      - 2.21.5
+      - :version-ref:`RCCL rocm_version`
       - Optimized for multi-GPU communication for operations like  all-reduce,
         broadcast, and scatter.
       - Distribute computations across multiple GPU with ``pmap`` and
         ``jax.distributed``. XLA automatically uses rccl when executing
         operations across multiple GPUs on AMD hardware.
     * - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - 3.3.0
+      - :version-ref:`rocThrust rocm_version`
       - Provides a C++ template library for parallel algorithms like sorting,
         reduction, and scanning.
       - Reduction operations like ``jax.numpy.sum``, ``jax.pmap`` for

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

@@ -4,6 +4,8 @@
     :description: PyTorch compatibility
     :keywords: GPU, PyTorch compatibility
 
+.. version-set:: rocm_version latest
+
 ********************************************************************************
 PyTorch compatibility
 ********************************************************************************
@@ -200,7 +202,8 @@ Critical ROCm libraries for PyTorch
 
 The functionality of PyTorch with ROCm is determined by its underlying library
 dependencies. These critical ROCm components affect the capabilities,
-performance, and feature set available to developers.
+performance, and feature set available to developers. The versions described
+are available in ROCm :version:`rocm_version`.
 
 .. list-table::
     :header-rows: 1
@@ -210,28 +213,28 @@ performance, and feature set available to developers.
       - Purpose
       - Used in
     * - `Composable Kernel <https://github.com/ROCm/composable_kernel>`_
-      - 1.1.0
+      - :version-ref:`"Composable Kernel" rocm_version`
       - Enables faster execution of core operations like matrix multiplication
         (GEMM), convolutions and transformations.
       - Speeds up ``torch.permute``, ``torch.view``, ``torch.matmul``,
         ``torch.mm``, ``torch.bmm``, ``torch.nn.Conv2d``, ``torch.nn.Conv3d``
         and ``torch.nn.MultiheadAttention``.
     * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - 2.3.0
+      - :version-ref:`hipBLAS rocm_version`
       - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
         matrix and vector operations.
       - Supports operations like matrix multiplication, matrix-vector products,
         and tensor contractions. Utilized in both dense and batched linear
         algebra operations.
     * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - 0.10.0
+      - :version-ref:`hipBLASLt rocm_version`
       - hipBLASLt is an extension of the hipBLAS library, providing additional
         features like epilogues fused into the matrix multiplication kernel or
         use of integer tensor cores.
       - It accelerates operations like ``torch.matmul``, ``torch.mm``, and the
         matrix multiplications used in convolutional and linear layers.
     * - `hipCUB <https://github.com/ROCm/hipCUB>`_
-      - 3.3.0
+      - :version-ref:`hipCUB rocm_version`
       - Provides a C++ template library for parallel algorithms for reduction,
         scan, sort and select.
       - Supports operations like ``torch.sum``, ``torch.cumsum``, ``torch.sort``
@@ -239,93 +242,93 @@ performance, and feature set available to developers.
         irregular shapes often involve scanning, sorting, and filtering, which
         hipCUB handles efficiently.
     * - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - 1.0.17
+      - :version-ref:`hipFFT rocm_version`
       - Provides GPU-accelerated Fast Fourier Transform (FFT) operations.
       - Used in functions like the ``torch.fft`` module.
     * - `hipRAND <https://github.com/ROCm/hipRAND>`_
-      - 2.11.0
+      - :version-ref:`hipRAND rocm_version`
       - Provides fast random number generation for GPUs.
       - The ``torch.rand``, ``torch.randn`` and stochastic layers like
         ``torch.nn.Dropout``.
     * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - 2.3.0
+      - :version-ref:`hipSOLVER rocm_version`
       - Provides GPU-accelerated solvers for linear systems, eigenvalues, and
         singular value decompositions (SVD).
       - Supports functions like ``torch.linalg.solve``,
         ``torch.linalg.eig``, and ``torch.linalg.svd``.
     * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - 3.1.2
+      - :version-ref:`hipSPARSE rocm_version`
       - Accelerates operations on sparse matrices, such as sparse matrix-vector
         or matrix-matrix products.
       - Sparse tensor operations ``torch.sparse``.
     * - `hipSPARSELt <https://github.com/ROCm/hipSPARSELt>`_
-      - 0.2.2
+      - :version-ref:`hipSPARSELt rocm_version`
       - Accelerates operations on sparse matrices, such as sparse matrix-vector
         or matrix-matrix products.
       - Sparse tensor operations ``torch.sparse``.
     * - `hipTensor <https://github.com/ROCm/hipTensor>`_
-      - 1.4.0
+      - :version-ref:`hipTensor rocm_version`
       - Optimizes for high-performance tensor operations, such as contractions.
       - Accelerates tensor algebra, especially in deep learning and scientific
         computing.
     * - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - 3.3.0
+      - :version-ref:`MIOpen rocm_version`
       - Optimizes deep learning primitives such as convolutions, pooling,
         normalization, and activation functions.
       - Speeds up convolutional neural networks (CNNs), recurrent neural
         networks (RNNs), and other layers. Used in operations like
         ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
     * - `MIGraphX <https://github.com/ROCm/AMDMIGraphX>`_
-      - 2.11.0
+      - :version-ref:`MIGraphX rocm_version`
       - Adds graph-level optimizations, ONNX models and mixed precision support
         and enable Ahead-of-Time (AOT) Compilation.
       - Speeds up inference models and executes ONNX models for
         compatibility with other frameworks.
         ``torch.nn.Conv2d``, ``torch.nn.ReLU``, and ``torch.nn.LSTM``.
     * - `MIVisionX <https://github.com/ROCm/MIVisionX>`_
-      - 3.1.0
+      - :version-ref:`MIVisionX rocm_version`
       - Optimizes acceleration for computer vision and AI workloads like
         preprocessing, augmentation, and inferencing.
       - Faster data preprocessing and augmentation pipelines for datasets like
         ImageNet or COCO and easy to integrate into PyTorch's ``torch.utils.data``
         and ``torchvision`` workflows.
     * - `rocAL <https://github.com/ROCm/rocAL>`_
-      - 2.1.0
+      - :version-ref:`rocAL rocm_version`
       - Accelerates the data pipeline by offloading intensive preprocessing and
         augmentation tasks. rocAL is part of MIVisionX.
       - Easy to integrate into PyTorch's ``torch.utils.data`` and
         ``torchvision`` data load workloads.
     * - `RCCL <https://github.com/ROCm/rccl>`_
-      - 2.21.5
+      - :version-ref:`RCCL rocm_version`
       - Optimizes for multi-GPU communication for operations like AllReduce and
         Broadcast.
       - Distributed data parallel training (``torch.nn.parallel.DistributedDataParallel``).
         Handles communication in multi-GPU setups.
     * - `rocDecode <https://github.com/ROCm/rocDecode>`_
-      - 0.8.0
+      - :version-ref:`rocDecode rocm_version`
       - Provides hardware-accelerated data decoding capabilities, particularly
         for image, video, and other dataset formats.
       - Can be integrated in ``torch.utils.data``, ``torchvision.transforms``
         and ``torch.distributed``.
     * - `rocJPEG <https://github.com/ROCm/rocJPEG>`_
-      - 0.6.0
+      - :version-ref:`rocJPEG rocm_version`
       - Provides hardware-accelerated JPEG image decoding and encoding.
       - GPU accelerated ``torchvision.io.decode_jpeg`` and
         ``torchvision.io.encode_jpeg`` and can be integrated in
         ``torch.utils.data`` and ``torchvision``.
     * - `RPP <https://github.com/ROCm/RPP>`_
-      - 1.9.1
+      - :version-ref:`RPP rocm_version`
       - Speeds up data augmentation, transformation, and other preprocessing steps.
       - Easy to integrate into PyTorch's ``torch.utils.data`` and
         ``torchvision`` data load workloads.
     * - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - 3.3.0
+      - :version-ref:`rocThrust rocm_version`
       - Provides a C++ template library for parallel algorithms like sorting,
         reduction, and scanning.
       - Utilized in backend operations for tensor computations requiring
         parallel processing.
     * - `rocWMMA <https://github.com/ROCm/rocWMMA>`_
-      - 1.6.0
+      - :version-ref:`rocWMMA rocm_version`
       - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
         multiplication (GEMM) and accumulation operations with mixed precision
         support.

docs/compatibility/ml-compatibility/tensorflow-compatibility.rst

@@ -4,6 +4,8 @@
     :description: TensorFlow compatibility
     :keywords: GPU, TensorFlow compatibility
 
+.. version-set:: rocm_version latest
+
 *******************************************************************************
 TensorFlow compatibility
 *******************************************************************************
@@ -117,7 +119,8 @@ Critical ROCm libraries for TensorFlow
 TensorFlow depends on multiple components and the supported features of those
 components can affect the TensorFlow ROCm supported feature set. The versions
 in the following table refer to the first TensorFlow version where the ROCm
-library was introduced as a dependency.
+library was introduced as a dependency. The versions described
+are available in ROCm :version:`rocm_version`.
 
 .. list-table::
     :widths: 25, 10, 35, 30
@@ -128,43 +131,43 @@ library was introduced as a dependency.
       - Purpose
       - Used in
     * - `hipBLAS <https://github.com/ROCm/hipBLAS>`_
-      - 2.3.0
+      - :version-ref:`hipBLAS rocm_version`
       - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
         matrix and vector operations.
       - Accelerates operations like ``tf.matmul``, ``tf.linalg.matmul``, and
         other matrix multiplications commonly used in neural network layers.
     * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`_
-      - 0.10.0
+      - :version-ref:`hipBLASLt rocm_version`
       - Extends hipBLAS with additional optimizations like fused kernels and
         integer tensor cores.
       - Optimizes matrix multiplications and linear algebra operations used in
         layers like dense, convolutional, and RNNs in TensorFlow.
     * - `hipCUB <https://github.com/ROCm/hipCUB>`_
-      - 3.3.0
+      - :version-ref:`hipCUB rocm_version`
       - Provides a C++ template library for parallel algorithms for reduction,
         scan, sort and select.
       - Supports operations like ``tf.reduce_sum``, ``tf.cumsum``, ``tf.sort``
         and other tensor operations in TensorFlow, especially those involving
         scanning, sorting, and filtering.
     * - `hipFFT <https://github.com/ROCm/hipFFT>`_
-      - 1.0.17
+      - :version-ref:`hipFFT rocm_version`
       - Accelerates Fast Fourier Transforms (FFT) for signal processing tasks.
       - Used for operations like signal processing, image filtering, and
         certain types of neural networks requiring FFT-based transformations.
     * - `hipSOLVER <https://github.com/ROCm/hipSOLVER>`_
-      - 2.3.0
+      - :version-ref:`hipSOLVER rocm_version`
       - Provides GPU-accelerated direct linear solvers for dense and sparse
         systems.
       - Optimizes linear algebra functions such as solving systems of linear
         equations, often used in optimization and training tasks.
     * - `hipSPARSE <https://github.com/ROCm/hipSPARSE>`_
-      - 3.1.2
+      - :version-ref:`hipSPARSE rocm_version`
       - Optimizes sparse matrix operations for efficient computations on sparse
         data.
       - Accelerates sparse matrix operations in models with sparse weight
         matrices or activations, commonly used in neural networks.
     * - `MIOpen <https://github.com/ROCm/MIOpen>`_
-      - 3.3.0
+      - :version-ref:`MIOpen rocm_version`
       - Provides optimized deep learning primitives such as convolutions,
         pooling,
         normalization, and activation functions.
@@ -172,13 +175,13 @@ library was introduced as a dependency.
         in TensorFlow for layers like ``tf.nn.conv2d``, ``tf.nn.relu``, and
         ``tf.nn.lstm_cell``.
     * - `RCCL <https://github.com/ROCm/rccl>`_
-      - 2.21.5
+      - :version-ref:`RCCL rocm_version`
       - Optimizes for multi-GPU communication for operations like AllReduce and
         Broadcast.
       - Distributed data parallel training (``tf.distribute.MirroredStrategy``).
         Handles communication in multi-GPU setups.
     * - `rocThrust <https://github.com/ROCm/rocThrust>`_
-      - 3.3.0
+      - :version-ref:`rocThrust rocm_version`
       - Provides a C++ template library for parallel algorithms like sorting,
         reduction, and scanning.
       - Reduction operations like ``tf.reduce_sum``, ``tf.cumsum`` for computing

docs/conceptual/gpu-arch.md

@@ -32,7 +32,7 @@ architecture.
 
 * [AMD Instinct™ MI250 microarchitecture](./gpu-arch/mi250.md)
 * [AMD Instinct MI200/CDNA2 ISA](https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf)
-* [White paper](https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf)
+* [White paper](https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna2-white-paper.pdf)
 * [Performance counters](./gpu-arch/mi300-mi200-performance-counters.rst)
 
 :::
@@ -45,7 +45,7 @@ architecture.
 
 * [AMD Instinct™ MI100 microarchitecture](./gpu-arch/mi100.md)
 * [AMD Instinct MI100/CDNA1 ISA](https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf)
-* [White paper](https://www.amd.com/system/files/documents/amd-cdna-whitepaper.pdf)
+* [White paper](https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna-white-paper.pdf)
 
 :::
 
@@ -55,7 +55,6 @@ architecture.
 * [AMD RDNA3 ISA](https://www.amd.com/system/files/TechDocs/rdna3-shader-instruction-set-architecture-feb-2023_0.pdf)
 * [AMD RDNA2 ISA](https://www.amd.com/system/files/TechDocs/rdna2-shader-instruction-set-architecture.pdf)
 * [AMD RDNA ISA](https://www.amd.com/system/files/TechDocs/rdna-shader-instruction-set-architecture.pdf)
-* [AMD RDNA Architecture White Paper](https://www.amd.com/system/files/documents/rdna-whitepaper.pdf)
 
 :::
 

docs/conf.py

@@ -6,6 +6,8 @@
 
 import os
 import shutil
+import sys
+from pathlib import Path
 
 shutil.copy2("../RELEASE.md", "./about/release-notes.md")
 
@@ -50,8 +52,8 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/training/index", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/train-a-model", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/prerequisite-system-validation", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/training/train-a-model/benchmark-docker/megatron-lm", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/training/train-a-model/benchmark-docker/pytorch-training", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/megatron-lm", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/training/benchmark-docker/pytorch-training", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/scale-model-training", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/fine-tuning/index", "os": ["linux"]},
@@ -66,7 +68,7 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/inference/llm-inference-frameworks", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/vllm-benchmark", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/deploy-your-model", "os": ["linux"]},
-    
+
     {"file": "how-to/rocm-for-ai/inference-optimization/index", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference-optimization/model-quantization", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries", "os": ["linux"]},
@@ -89,11 +91,16 @@ article_pages = [
 
 external_toc_path = "./sphinx/_toc.yml"
 
-extensions = ["rocm_docs", "sphinx_reredirects", "sphinx_sitemap"]
+# Add the _extensions directory to Python's search path
+sys.path.append(str(Path(__file__).parent / 'extension'))
+
+extensions = ["rocm_docs", "sphinx_reredirects", "sphinx_sitemap", "sphinxcontrib.datatemplates", "version-ref"]
+
+compatibility_matrix_file = str(Path(__file__).parent / 'compatibility/compatibility-matrix-historical-6.0.csv')
 
 external_projects_current_project = "rocm"
 
-# Uncomment if facing rate limit exceed issue with local build 
+# Uncomment if facing rate limit exceed issue with local build
 # external_projects_remote_repository = ""
 
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "https://rocm-stg.amd.com/")
@@ -104,8 +111,9 @@ if os.environ.get("READTHEDOCS", "") == "True":
 html_theme = "rocm_docs_theme"
 html_theme_options = {"flavor": "rocm-docs-home"}
 
-html_static_path = ["sphinx/static/css"]
-html_css_files = ["rocm_custom.css", "rocm_rn.css"]
+html_static_path = ["sphinx/static/css", "extension/how-to/rocm-for-ai/inference"]
+html_css_files = ["rocm_custom.css", "rocm_rn.css", "vllm-benchmark.css"]
+html_js_files = ["vllm-benchmark.js"]
 
 html_title = "ROCm Documentation"
 

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

@@ -0,0 +1,153 @@
+vllm_benchmark:
+  unified_docker:
+    latest:
+      pull_tag: rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6/images/sha256-9a12ef62bbbeb5a4c30a01f702c8e025061f575aa129f291a49fbd02d6b4d6c9
+      rocm_version: 6.3.1
+      vllm_version: 0.6.6
+      pytorch_version: 2.7.0 (2.7.0a0+git3a58512)
+  model_groups:
+    - group: Llama
+      tag: llama
+      models:
+      - model: Llama 3.1 8B
+        mad_tag: pyt_vllm_llama-3.1-8b
+        model_repo: meta-llama/Llama-3.1-8B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: float16
+      - model: Llama 3.1 70B
+        mad_tag: pyt_vllm_llama-3.1-70b
+        model_repo: meta-llama/Llama-3.1-70B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+        precision: float16
+      - model: Llama 3.1 405B
+        mad_tag: pyt_vllm_llama-3.1-405b
+        model_repo: meta-llama/Llama-3.1-405B-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct
+        precision: float16
+      - model: Llama 3.2 11B Vision
+        mad_tag: pyt_vllm_llama-3.2-11b-vision-instruct
+        model_repo: meta-llama/Llama-3.2-11B-Vision-Instruct
+        url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct
+        precision: float16
+      - model: Llama 2 7B
+        mad_tag: pyt_vllm_llama-2-7b
+        model_repo: meta-llama/Llama-2-7b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
+        precision: float16
+      - model: Llama 2 70B
+        mad_tag: pyt_vllm_llama-2-70b
+        model_repo: meta-llama/Llama-2-70b-chat-hf
+        url: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+        precision: float16
+      - model: Llama 3.1 70B FP8
+        mad_tag: pyt_vllm_llama-3.1-70b_fp8
+        model_repo: amd/Llama-3.1-70B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV
+        precision: float8
+      - model: Llama 3.1 405B FP8
+        mad_tag: pyt_vllm_llama-3.1-405b_fp8
+        model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
+        url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
+        precision: float8
+    - group: Mistral
+      tag: mistral
+      models:
+      - model: Mixtral MoE 8x7B
+        mad_tag: pyt_vllm_mixtral-8x7b
+        model_repo: mistralai/Mixtral-8x7B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+        precision: float16
+      - model: Mixtral MoE 8x22B
+        mad_tag: pyt_vllm_mixtral-8x22b
+        model_repo: mistralai/Mixtral-8x22B-Instruct-v0.1
+        url: https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1
+        precision: float16
+      - model: Mistral 7B
+        mad_tag: pyt_vllm_mistral-7b
+        model_repo: mistralai/Mistral-7B-Instruct-v0.3
+        url: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
+        precision: float16
+      - model: Mixtral MoE 8x7B FP8
+        mad_tag: pyt_vllm_mixtral-8x7b_fp8
+        model_repo: amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV
+        precision: float8
+      - model: Mixtral MoE 8x22B FP8
+        mad_tag: pyt_vllm_mixtral-8x22b_fp8
+        model_repo: amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV
+        precision: float8
+      - model: Mistral 7B FP8
+        mad_tag: pyt_vllm_mistral-7b_fp8
+        model_repo: amd/Mistral-7B-v0.1-FP8-KV
+        url: https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV
+        precision: float8
+    - group: Qwen
+      tag: qwen
+      models:
+      - model: Qwen2 7B
+        mad_tag: pyt_vllm_qwen2-7b
+        model_repo: Qwen/Qwen2-7B-Instruct
+        url: https://huggingface.co/Qwen/Qwen2-7B-Instruct
+        precision: float16
+      - model: Qwen2 72B
+        mad_tag: pyt_vllm_qwen2-72b
+        model_repo: Qwen/Qwen2-72B-Instruct
+        url: https://huggingface.co/Qwen/Qwen2-72B-Instruct
+        precision: float16
+    - group: JAIS
+      tag: jais
+      models:
+      - model: JAIS 13B
+        mad_tag: pyt_vllm_jais-13b
+        model_repo: core42/jais-13b-chat
+        url: https://huggingface.co/core42/jais-13b-chat
+        precision: float16
+      - model: JAIS 30B
+        mad_tag: pyt_vllm_jais-30b
+        model_repo: core42/jais-30b-chat-v3
+        url: https://huggingface.co/core42/jais-30b-chat-v3
+        precision: float16
+    - group: DBRX
+      tag: dbrx
+      models:
+      - model: DBRX Instruct
+        mad_tag: pyt_vllm_dbrx-instruct
+        model_repo: databricks/dbrx-instruct
+        url: https://huggingface.co/databricks/dbrx-instruct
+        precision: float16
+      - model: DBRX Instruct FP8
+        mad_tag: pyt_vllm_dbrx_fp8
+        model_repo: amd/dbrx-instruct-FP8-KV
+        url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
+        precision: float8
+    - group: Gemma
+      tag: gemma
+      models:
+      - model: Gemma 2 27B
+        mad_tag: pyt_vllm_gemma-2-27b
+        model_repo: google/gemma-2-27b
+        url: https://huggingface.co/google/gemma-2-27b
+        precision: float16
+    - group: Cohere
+      tag: cohere
+      models:
+      - model: C4AI Command R+ 08-2024
+        mad_tag: pyt_vllm_c4ai-command-r-plus-08-2024
+        model_repo: CohereForAI/c4ai-command-r-plus-08-2024
+        url: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024
+        precision: float16
+      - model: C4AI Command R+ 08-2024 FP8
+        mad_tag: pyt_vllm_command-r-plus_fp8
+        model_repo: amd/c4ai-command-r-plus-FP8-KV
+        url: https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV
+        precision: float8
+    - group: DeepSeek
+      tag: deepseek
+      models:
+      - model: DeepSeek MoE 16B
+        mad_tag: pyt_vllm_deepseek-moe-16b-chat
+        model_repo: deepseek-ai/deepseek-moe-16b-chat
+        url: https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat
+        precision: float16

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

@@ -0,0 +1,212 @@
+function ready(proc) {
+  // Check if page is loaded. If so, init.
+  if (document.readyState !== "loading") {
+    proc();
+  } else {
+    // Otherwise, wait for DOMContentLoaded event.
+    document.addEventListener("DOMContentLoaded", proc);
+  }
+}
+
+ready(() => {
+  const ModelPicker = {
+    // Selector strings for DOM elements
+    SELECTORS: {
+      CONTAINER: "#vllm-benchmark-ud-params-picker",
+      MODEL_GROUP_BTN: 'div[data-param-k="model-group"][data-param-v]',
+      MODEL_PARAM_BTN: 'div[data-param-k="model"][data-param-v]',
+      MODEL_DOC: "div.model-doc",
+    },
+    CSS_CLASSES: {
+      HIDDEN: "hidden",
+    },
+    ATTRIBUTES: {
+      PARAM_KEY: "data-param-k", // URL search parameter key (i.e., "model")
+      PARAM_VALUE: "data-param-v", // URL search param value (e.g., "pyt_vllm_llama-3.1-8b", "pyt_vllm_llama-3.1-70b") -- these are MAD model tags
+      PARAM_GROUP: "data-param-group", // Model group (e.g., "llama", "mistral")
+      PARAM_STATE: "data-param-state", // Selection state
+    },
+
+    // Cache DOM elements
+    elements: {
+      container: null,
+      modelGroups: null,
+      modelParams: null,
+      modelDocs: null,
+    },
+
+    data: {
+      availableModels: new Set(),
+      modelsByGroup: new Map(),
+      modelToGroupMap: new Map(),
+      formattedModelClassMap: new Map(), //TODO
+    },
+
+    init() {
+      this.elements.container = document.querySelector(
+        this.SELECTORS.CONTAINER,
+      );
+      if (!this.elements.container) return;
+
+      this.cacheDOMElements();
+      if (!this.validateElements()) return;
+
+      this.buildModelData();
+      this.bindEvents();
+      this.initializeState();
+    },
+
+    cacheDOMElements() {
+      const { CONTAINER, MODEL_GROUP_BTN, MODEL_PARAM_BTN, MODEL_DOC } =
+        this.SELECTORS;
+      this.elements = {
+        container: document.querySelector(CONTAINER),
+        modelGroups: document.querySelectorAll(MODEL_GROUP_BTN),
+        modelParams: document.querySelectorAll(MODEL_PARAM_BTN),
+        modelDocs: document.querySelectorAll(MODEL_DOC),
+      };
+    },
+
+    validateElements() {
+      const { modelGroups, modelParams } = this.elements;
+      if (!modelGroups.length || !modelParams.length) {
+        console.warn("Model picker is missing required elements");
+        return false;
+      }
+      return true;
+    },
+
+    buildModelData() {
+      const { PARAM_VALUE, PARAM_GROUP } = this.ATTRIBUTES;
+
+      this.elements.modelParams.forEach((model) => {
+        const modelTag = model.getAttribute(PARAM_VALUE);
+        const groupTag = model.getAttribute(PARAM_GROUP);
+
+        if (!modelTag || !groupTag) return;
+
+        this.data.availableModels.add(modelTag);
+        this.data.modelToGroupMap.set(modelTag, groupTag);
+
+        // FIXME: this is because Sphinx auto-formats class names to use dashes
+        this.data.formattedModelClassMap.set(
+          modelTag,
+          modelTag.replace(/[^a-zA-Z0-9]/g, "-"),
+        );
+
+        if (!this.data.modelsByGroup.has(groupTag)) {
+          this.data.modelsByGroup.set(groupTag, []);
+        }
+        this.data.modelsByGroup.get(groupTag).push(modelTag);
+      });
+    },
+
+    // Event listeners for user interactions
+    bindEvents() {
+      const handleInteraction = (event) => {
+        const target = event.target.closest(`[${this.ATTRIBUTES.PARAM_KEY}]`);
+        if (!target) return;
+
+        const paramType = target.getAttribute(this.ATTRIBUTES.PARAM_KEY);
+        const paramValue = target.getAttribute(this.ATTRIBUTES.PARAM_VALUE);
+
+        if (paramType === "model") {
+          const groupTag = target.getAttribute(this.ATTRIBUTES.PARAM_GROUP);
+          if (groupTag) this.updateUI(paramValue, groupTag);
+        } else if (paramType === "model-group") {
+          const firstModelInGroup = this.data.modelsByGroup.get(paramValue)
+            ?.[0];
+          if (firstModelInGroup) this.updateUI(firstModelInGroup, paramValue);
+        }
+      };
+
+      this.elements.container.addEventListener("click", handleInteraction);
+      this.elements.container.addEventListener("keydown", (event) => {
+        if (event.key === "Enter" || event.key === " ") {
+          event.preventDefault();
+          handleInteraction(event);
+        }
+      });
+    },
+
+    // Update the page based on the selected model
+    updateUI(modelTag, groupTag) {
+      const validModel = this.setModelSearchParam(modelTag);
+
+      // Update model group buttons
+      this.elements.modelGroups.forEach((group) => {
+        const isSelected =
+          group.getAttribute(this.ATTRIBUTES.PARAM_VALUE) === groupTag;
+        group.setAttribute(
+          this.ATTRIBUTES.PARAM_STATE,
+          isSelected ? "selected" : "",
+        );
+        group.setAttribute("aria-selected", isSelected.toString());
+      });
+
+      // Update model buttons
+      this.elements.modelParams.forEach((model) => {
+        const isInSelectedGroup =
+          model.getAttribute(this.ATTRIBUTES.PARAM_GROUP) === groupTag;
+        const isSelectedModel =
+          model.getAttribute(this.ATTRIBUTES.PARAM_VALUE) === validModel;
+
+        model.classList.toggle(this.CSS_CLASSES.HIDDEN, !isInSelectedGroup);
+        model.setAttribute(
+          this.ATTRIBUTES.PARAM_STATE,
+          isSelectedModel ? "selected" : "",
+        );
+        model.setAttribute("aria-selected", isSelectedModel.toString());
+      });
+
+      // Update visibility of doc sections
+      const formattedClass = this.data.formattedModelClassMap.get(validModel);
+      if (formattedClass) {
+        this.elements.modelDocs.forEach((doc) => {
+          doc.classList.toggle(
+            this.CSS_CLASSES.HIDDEN,
+            !doc.classList.contains(formattedClass),
+          );
+        });
+      }
+    },
+
+    // Get the current model from the URL search parameters.
+    getModelSearchParam() {
+      return new URLSearchParams(location.search).get("model");
+    },
+
+    // Set the model in the URL search parameters, or fallback to the first available one.
+    setModelSearchParam(modelTag) {
+      const defaultModel = [...this.data.availableModels][0];
+      const model = this.data.availableModels.has(modelTag)
+        ? modelTag
+        : defaultModel;
+
+      const searchParams = new URLSearchParams(location.search);
+      searchParams.set("model", model);
+
+      history.replaceState(
+        {},
+        "",
+        `${location.pathname}?${searchParams.toString()}`,
+      );
+      return model;
+    },
+
+    // Initialize the UI state based on the current URL search parameter or default values.
+    initializeState() {
+      const currentModel = this.getModelSearchParam();
+      const validModel = this.setModelSearchParam(currentModel);
+
+      const initialGroup = this.data.modelToGroupMap.get(validModel) ??
+        [...this.data.modelsByGroup.keys()][0];
+
+      if (initialGroup) {
+        this.updateUI(validModel, initialGroup);
+      }
+    },
+  };
+
+  ModelPicker.init();
+});

docs/extension/version-ref.py

@@ -0,0 +1,266 @@
+from docutils import nodes
+from docutils.parsers.rst import Directive
+from sphinx.util import logging
+import csv
+from io import StringIO
+import re
+import shlex
+
+logger = logging.getLogger(__name__)
+
+class VersionReference(nodes.Inline, nodes.TextElement):
+    """Represents an inline version reference."""
+    pass
+
+class VersionSetDirective(Directive):
+    """Directive for setting version references within a page scope."""
+    required_arguments = 2  # name and value
+    optional_arguments = 0
+
+    def run(self):
+        env = self.state.document.settings.env
+        if not hasattr(env, 'doc_version_refs'):
+            env.doc_version_refs = {}
+        current_doc = env.docname
+        if current_doc not in env.doc_version_refs:
+            env.doc_version_refs[current_doc] = {}
+
+        name, value = self.arguments
+        if name.lower() == 'latest':
+            logger.warning('Cannot override the "latest" keyword with version-set')
+            return []
+
+        # Handle 'latest' value by getting the actual version
+        if value.lower() == 'latest':
+            data = getattr(env, 'compatibility_matrix', None)
+            if data:
+                latest_version = get_latest_rocm_version(data)
+                if latest_version:
+                    value = latest_version
+
+        env.doc_version_refs[current_doc][name] = value
+        return []
+
+def clean_library_name(name):
+    """Extract library name from RST formatting."""
+    # Handle :doc: format
+    doc_match = re.search(r':doc:`([^<]+)(?:\s+<[^>]+>)?`', name)
+    if doc_match:
+        return doc_match.group(1).strip()
+
+    # Handle other link formats
+    link_match = re.search(r'`([^<]+)(?:\s+<[^>]+>)?`_?', name)
+    if link_match:
+        return link_match.group(1).strip()
+
+    return name.strip()
+
+def get_latest_rocm_version(data):
+    """Get the latest ROCm version from the matrix headers."""
+    if not data or len(data) == 0:
+        return None
+
+    # Get all column names except 'ROCm Version'
+    columns = [col for col in data[0].keys() if col != 'ROCm Version']
+    # Return the first column name (assumed to be the latest version)
+    return columns[0] if columns else None
+
+def version_role(name, rawtext, text, lineno, inliner, options={}, content=[]):
+    """
+    Role function to print version value.
+    Usage: :version:`version_name`
+    """
+    try:
+        version_name = text.strip()
+        env = inliner.document.settings.env
+
+        if hasattr(env, 'doc_version_refs'):
+            current_doc = env.docname
+            if current_doc in env.doc_version_refs:
+                doc_refs = env.doc_version_refs[current_doc]
+                if version_name in doc_refs:
+                    version = doc_refs[version_name]
+                    node = nodes.Text(version)
+                    return [node], []
+
+        msg = inliner.reporter.warning(
+            f'No version defined for name {version_name}',
+            line=lineno
+        )
+        return [], [msg]
+
+    except Exception as e:
+        msg = inliner.reporter.error(
+            f'Error looking up version: {str(e)}',
+            line=lineno
+        )
+        prb = inliner.problematic(rawtext, rawtext, msg)
+        return [prb], [msg]
+
+def version_ref_role(name, rawtext, text, lineno, inliner, options={}, content=[]):
+    """
+    Role function for version references.
+    Usage: :version-ref:`library_name release`
+           :version-ref:`"library name" release`
+           :version-ref:`library_name latest`
+           :version-ref:`rocm latest`
+    """
+    try:
+        # Parse the text - handle both quoted and unquoted formats
+        if '"' in text:
+            parts = shlex.split(text)
+        else:
+            parts = text.split()
+
+        if len(parts) != 2:
+            msg = inliner.reporter.error(
+                'Version reference must be in format "library_name release" or "\\"library name\\" release"',
+                line=lineno
+            )
+            prb = inliner.problematic(rawtext, rawtext, msg)
+            return [prb], [msg]
+
+        library_name, release = parts
+        env = inliner.document.settings.env
+
+        # Check if release is a version reference in current document
+        if hasattr(env, 'doc_version_refs'):
+            current_doc = env.docname
+            if current_doc in env.doc_version_refs:
+                doc_refs = env.doc_version_refs[current_doc]
+                if release in doc_refs:
+                    release = doc_refs[release]
+
+        # Handle special case for "rocm latest"
+        if library_name.lower() == 'rocm' and release.lower() == 'latest':
+            data = getattr(env, 'compatibility_matrix', None)
+            if not data:
+                raise ValueError("Compatibility matrix not found in environment")
+
+            latest_version = get_latest_rocm_version(data)
+            if latest_version:
+                node = VersionReference()
+                node += nodes.Text(latest_version)
+                return [node], []
+            else:
+                msg = inliner.reporter.warning(
+                    'No ROCm versions found in compatibility matrix',
+                    line=lineno
+                )
+                return [], [msg]
+
+        version = lookup_version(inliner, library_name, release)
+
+        if version:
+            node = VersionReference()
+            node += nodes.Text(version)
+            return [node], []
+        else:
+            msg = inliner.reporter.warning(
+                f'No version found for library {library_name} in release {release}',
+                line=lineno
+            )
+            return [], [msg]
+
+    except Exception as e:
+        msg = inliner.reporter.error(
+            f'Error looking up version: {str(e)}',
+            line=lineno
+        )
+        prb = inliner.problematic(rawtext, rawtext, msg)
+        return [prb], [msg]
+
+def lookup_version(inliner, library_name, release):
+    """Look up the version in the compatibility matrix."""
+    env = inliner.document.settings.env
+    data = getattr(env, 'compatibility_matrix', None)
+
+    if not data:
+        raise ValueError("Compatibility matrix not found in environment")
+
+    # Handle the 'latest' keyword
+    if release.lower() == 'latest':
+        latest_version = get_latest_rocm_version(data)
+        if not latest_version:
+            return None
+        release = latest_version
+
+    # For ROCm, check if the version exists in column headers
+    if library_name.lower() == 'rocm':
+        columns = [col for col in data[0].keys() if col != 'ROCm Version']
+        if release in columns:
+            return release
+        return None
+
+    # Find the library version
+    for row in data:
+        row_lib_name = clean_library_name(row['ROCm Version'])
+        if row_lib_name == library_name:
+            # Get the version, removing any whitespace
+            version = row.get(release, '').strip()
+            if version:
+                return version
+
+    # If not found, try a case-insensitive search
+    for row in data:
+        row_lib_name = clean_library_name(row['ROCm Version'])
+        if row_lib_name.lower() == library_name.lower():
+            version = row.get(release, '').strip()
+            if version:
+                return version
+
+    return None
+
+def visit_version_reference(self, node):
+    self.body.append(f'<span class="version-reference">')
+
+def depart_version_reference(self, node):
+    self.body.append('</span>')
+
+def load_compatibility_matrix(app):
+    """Load the compatibility matrix content from CSV."""
+    if not app.config.compatibility_matrix_file:
+        logger.warning('No compatibility matrix file configured')
+        return
+
+    try:
+        with open(app.config.compatibility_matrix_file, 'r', encoding='utf-8') as f:
+            reader = csv.DictReader(f)
+            app.env.compatibility_matrix = list(reader)
+            logger.info('Successfully loaded compatibility matrix')
+
+            # Debug: print first few rows with their library names
+            for row in list(app.env.compatibility_matrix)[:5]:
+                if 'ROCm Version' in row:
+                    lib_name = clean_library_name(row['ROCm Version'])
+                    logger.debug(f"Loaded library: {lib_name}")
+
+    except Exception as e:
+        logger.error(f'Error loading compatibility matrix: {str(e)}')
+
+def purge_version_refs(app, env, docname):
+    """Remove version references for a document when it is purged"""
+    if hasattr(env, 'doc_version_refs'):
+        if docname in env.doc_version_refs:
+            del env.doc_version_refs[docname]
+
+def setup(app):
+    app.add_node(VersionReference,
+                 html=(visit_version_reference, depart_version_reference))
+    app.add_role('version-ref', version_ref_role)
+    app.add_role('version', version_role)
+    app.add_directive('version-set', VersionSetDirective)
+
+    # Add a config value for the compatibility matrix file path
+    app.add_config_value('compatibility_matrix_file', None, 'env')
+
+    # Connect to the builder-inited event to load the matrix
+    app.connect('builder-inited', load_compatibility_matrix)
+
+    # Connect to env-purge-doc event to clean up document-specific version refs
+    app.connect('env-purge-doc', purge_version_refs)
+
+    return {
+        'parallel_read_safe': True,
+        'parallel_write_safe': True,
+    }

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

@@ -9,422 +9,266 @@ LLM inference performance validation on AMD Instinct MI300X
 
 .. _vllm-benchmark-unified-docker:
 
-The `ROCm vLLM Docker <https://hub.docker.com/r/rocm/vllm/tags>`_ image offers
-a prebuilt, optimized environment for validating large language model (LLM)
-inference performance on the AMD Instinct™ MI300X accelerator. This ROCm vLLM
-Docker image integrates vLLM and PyTorch tailored specifically for the MI300X
-accelerator and includes the following components:
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
 
-* `ROCm 6.3.1 <https://github.com/ROCm/ROCm>`_
+   {% set unified_docker = data.vllm_benchmark.unified_docker.latest %}
+   {% set model_groups = data.vllm_benchmark.model_groups %}
 
-* `vLLM 0.6.6 <https://docs.vllm.ai/en/latest>`_
+   The `ROCm vLLM Docker <{{ unified_docker.docker_hub_url }}>`_ image offers
+   a prebuilt, optimized environment for validating large language model (LLM)
+   inference performance on the AMD Instinct™ MI300X accelerator. This ROCm vLLM
+   Docker image integrates vLLM and PyTorch tailored specifically for the MI300X
+   accelerator and includes the following components:
 
-* `PyTorch 2.7.0 (2.7.0a0+git3a58512) <https://github.com/pytorch/pytorch>`_
+   * `ROCm {{ unified_docker.rocm_version }} <https://github.com/ROCm/ROCm>`_
 
-With this Docker image, you can quickly validate the expected inference
-performance numbers for the MI300X accelerator. This topic also provides tips on
-optimizing performance with popular AI models. For more information, see the lists of
-:ref:`available models for MAD-integrated benchmarking <vllm-benchmark-mad-models>`
-and :ref:`standalone benchmarking <vllm-benchmark-standalone-options>`.
+   * `vLLM {{ unified_docker.vllm_version }} <https://docs.vllm.ai/en/latest>`_
 
-.. _vllm-benchmark-vllm:
+   * `PyTorch {{ unified_docker.pytorch_version }} <https://github.com/pytorch/pytorch>`_
 
-.. note::
+   With this Docker image, you can quickly validate the expected inference
+   performance numbers for the MI300X accelerator. This topic also provides tips on
+   optimizing performance with popular AI models.
 
-   vLLM is a toolkit and library for LLM inference and serving. AMD implements
-   high-performance custom kernels and modules in vLLM to enhance performance.
-   See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
-   more information.
+   .. _vllm-benchmark-available-models:
 
-Getting started
-===============
+   Available models
+   ================
 
-Use the following procedures to reproduce the benchmark results on an
-MI300X accelerator with the prebuilt vLLM Docker image.
+   .. raw:: html
 
-.. _vllm-benchmark-get-started:
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+        <div class="row">
+          <div class="col-2 me-2 model-param-head">Model</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+            <div class="col-3 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+   {% endfor %}
+          </div>
+        </div>
 
-1. Disable NUMA auto-balancing.
+        <div class="row mt-1">
+          <div class="col-2 me-2 model-param-head">Model variant</div>
+          <div class="row col-10">
+   {% for model_group in model_groups %}
+      {% set models = model_group.models %}
+      {% for model in models %}
+         {% if models|length % 3 == 0 %}
+            <div class="col-4 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% else %}
+            <div class="col-6 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+         {% endif %}
+      {% endfor %}
+   {% endfor %}
+          </div>
+        </div>
+      </div>
 
-   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
-   might hang until the periodic balancing is finalized. For more information,
-   see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
+   .. _vllm-benchmark-vllm:
 
-   .. code-block:: shell
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
 
-      # disable automatic NUMA balancing
-      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
-      # check if NUMA balancing is disabled (returns 0 if disabled)
-      cat /proc/sys/kernel/numa_balancing
-      0
+   .. container:: model-doc {{model.mad_tag}}
 
-2. Download the :ref:`ROCm vLLM Docker image <vllm-benchmark-unified-docker>`.
+      .. note::
 
-   Use the following command to pull the Docker image from Docker Hub.
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_ to learn more about your selected model.
+         Some models require access authorization prior to use via an external license agreement through a third party.
 
-   .. code-block:: shell
+      {% endfor %}
+   {% endfor %}
 
-      docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
 
-Once the setup is complete, choose between two options to reproduce the
-benchmark results:
+   .. note::
 
--  :ref:`MAD-integrated benchmarking <vllm-benchmark-mad>`
+      vLLM is a toolkit and library for LLM inference and serving. AMD implements
+      high-performance custom kernels and modules in vLLM to enhance performance.
+      See :ref:`fine-tuning-llms-vllm` and :ref:`mi300x-vllm-optimization` for
+      more information.
 
--  :ref:`Standalone benchmarking <vllm-benchmark-standalone>`
+   Getting started
+   ===============
 
-.. _vllm-benchmark-mad:
+   Use the following procedures to reproduce the benchmark results on an
+   MI300X accelerator with the prebuilt vLLM Docker image.
 
-MAD-integrated benchmarking
-===========================
+   .. _vllm-benchmark-get-started:
 
-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.
+   1. Disable NUMA auto-balancing.
 
-.. code-block:: shell
+      To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+      might hang until the periodic balancing is finalized. For more information,
+      see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
 
-   git clone https://github.com/ROCm/MAD
-   cd MAD
-   pip install -r requirements.txt
+      .. code-block:: shell
 
-Use this command to run a performance benchmark test of the Llama 3.1 8B model
-on one GPU with ``float16`` data type in the host machine.
+         # disable automatic NUMA balancing
+         sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+         # check if NUMA balancing is disabled (returns 0 if disabled)
+         cat /proc/sys/kernel/numa_balancing
+         0
 
-.. code-block:: shell
+   2. Download the `ROCm vLLM Docker image <{{ unified_docker.docker_hub_url }}>`_.
 
-   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-   python3 tools/run_models.py --tags pyt_vllm_llama-3.1-8b --keep-model-dir --live-output --timeout 28800
+      Use the following command to pull the Docker image from Docker Hub.
 
-ROCm MAD launches a Docker container with the name
-``container_ci-pyt_vllm_llama-3.1-8b``. The latency and throughput reports of the
-model are collected in the following path: ``~/MAD/reports_float16/``.
+      .. code-block:: shell
 
-Although the following models are preconfigured to collect latency and
-throughput performance data, you can also change the benchmarking parameters.
-Refer to the :ref:`Standalone benchmarking <vllm-benchmark-standalone>` section.
+         docker pull {{ unified_docker.pull_tag }}
 
-.. _vllm-benchmark-mad-models:
+   Benchmarking
+   ============
 
-Available models
-----------------
+   Once the setup is complete, choose between two options to reproduce the
+   benchmark results:
 
-.. list-table::
-   :header-rows: 1
-   :widths: 2, 3
+   .. _vllm-benchmark-mad:
 
-   * - Model name
-     - Tag
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
 
-   * - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
-     - ``pyt_vllm_llama-3.1-8b``
+   .. container:: model-doc {{model.mad_tag}}
 
-   * - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
-     - ``pyt_vllm_llama-3.1-70b``
+      .. tab-set::
 
-   * - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
-     - ``pyt_vllm_llama-3.1-405b``
+         .. tab-item:: MAD-integrated benchmarking
 
-   * - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
-     - ``pyt_vllm_llama-3.2-11b-vision-instruct``
+            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.
 
-   * - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
-     - ``pyt_vllm_llama-2-7b``
+            .. code-block:: shell
 
-   * - `Llama 2 70B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
-     - ``pyt_vllm_llama-2-70b``
+               git clone https://github.com/ROCm/MAD
+               cd MAD
+               pip install -r requirements.txt
 
-   * - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
-     - ``pyt_vllm_mixtral-8x7b``
+            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.
 
-   * - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
-     - ``pyt_vllm_mixtral-8x22b``
+            .. code-block:: shell
 
-   * - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
-     - ``pyt_vllm_mistral-7b``
+               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
 
-   * - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
-     - ``pyt_vllm_qwen2-7b``
+            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/reports_{{model.precision}}/``.
 
-   * - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
-     - ``pyt_vllm_qwen2-72b``
+            Although the :ref:`available models <vllm-benchmark-available-models>` are preconfigured
+            to collect latency and throughput performance data, you can also change the benchmarking
+            parameters. See the standalone benchmarking tab for more information.
 
-   * - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
-     - ``pyt_vllm_jais-13b``
+         .. tab-item:: Standalone benchmarking
 
-   * - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
-     - ``pyt_vllm_jais-30b``
+            Run the vLLM benchmark tool independently by starting the
+            `Docker container <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6/images/sha256-9a12ef62bbbeb5a4c30a01f702c8e025061f575aa129f291a49fbd02d6b4d6c9>`_
+            as shown in the following snippet.
 
-   * - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
-     - ``pyt_vllm_dbrx-instruct``
+            .. code-block::
 
-   * - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
-     - ``pyt_vllm_gemma-2-27b``
+               docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+               docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.6 rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
 
-   * - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
-     - ``pyt_vllm_c4ai-command-r-plus-08-2024``
+            In the Docker container, clone the ROCm MAD repository and navigate to the
+            benchmark scripts directory at ``~/MAD/scripts/vllm``.
 
-   * - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
-     - ``pyt_vllm_deepseek-moe-16b-chat``
+            .. code-block::
 
-   * - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
-     - ``pyt_vllm_llama-3.1-70b_fp8``
+               git clone https://github.com/ROCm/MAD
+               cd MAD/scripts/vllm
 
-   * - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
-     - ``pyt_vllm_llama-3.1-405b_fp8``
+            To start the benchmark, use the following command with the appropriate options.
 
-   * - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
-     - ``pyt_vllm_mixtral-8x7b_fp8``
+            .. code-block::
 
-   * - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
-     - ``pyt_vllm_mixtral-8x22b_fp8``
+               ./vllm_benchmark_report.sh -s $test_option -m {{model.model_repo}} -g $num_gpu -d {{model.precision}}
 
-   * - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
-     - ``pyt_vllm_mistral-7b_fp8``
+            .. list-table::
+               :header-rows: 1
+               :align: center
 
-   * - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
-     - ``pyt_vllm_dbrx_fp8``
+               * - Name
+                 - Options
+                 - Description
 
-   * - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
-     - ``pyt_vllm_command-r-plus_fp8``
+               * - ``$test_option``
+                 - latency
+                 - Measure decoding token latency
 
-.. _vllm-benchmark-standalone:
+               * -
+                 - throughput
+                 - Measure token generation throughput
 
-Standalone benchmarking
-=======================
+               * -
+                 - all
+                 - Measure both throughput and latency
 
-You can run the vLLM benchmark tool independently by starting the
-`Docker container <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6/images/sha256-9a12ef62bbbeb5a4c30a01f702c8e025061f575aa129f291a49fbd02d6b4d6c9>`_
-as shown in the following snippet.
+               * - ``$num_gpu``
+                 - 1 or 8
+                 - Number of GPUs
 
-.. code-block::
+               * - ``$datatype``
+                 - ``float16`` or ``float8``
+                 - Data type
 
-   docker pull rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
-   docker run -it --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 16G --security-opt seccomp=unconfined --security-opt apparmor=unconfined --cap-add=SYS_PTRACE -v $(pwd):/workspace --env HUGGINGFACE_HUB_CACHE=/workspace --name vllm_v0.6.6 rocm/vllm:rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6
+            .. note::
 
-In the Docker container, clone the ROCm MAD repository and navigate to the
-benchmark scripts directory at ``~/MAD/scripts/vllm``.
+               The input sequence length, output sequence length, and tensor parallel (TP) are
+               already configured. You don't need to specify them with this script.
 
-.. code-block::
+            .. note::
 
-   git clone https://github.com/ROCm/MAD
-   cd MAD/scripts/vllm
+               If you encounter the following error, pass your access-authorized Hugging
+               Face token to the gated models.
 
-Command
--------
+               .. code-block::
 
-To start the benchmark, use the following command with the appropriate options.
-See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
-options and their descriptions.
+                  OSError: You are trying to access a gated repo.
 
-.. code-block:: shell
+                  # pass your HF_TOKEN
+                  export HF_TOKEN=$your_personal_hf_token
 
-   ./vllm_benchmark_report.sh -s $test_option -m $model_repo -g $num_gpu -d $datatype
+            Here are some examples of running the benchmark with various options.
 
-See the :ref:`examples <vllm-benchmark-run-benchmark>` for more information.
+            * Latency benchmark
 
-.. note::
+              Use this command to benchmark the latency of the {{model.model}} model on eight GPUs with the ``{{model.precision}}`` data type.
 
-   The input sequence length, output sequence length, and tensor parallel (TP) are
-   already configured. You don't need to specify them with this script.
+              .. code-block::
 
-.. note::
+                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
 
-   If you encounter the following error, pass your access-authorized Hugging
-   Face token to the gated models.
+              Find the latency report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_latency_report.csv``.
 
-   .. code-block:: shell
+            * Throughput benchmark
 
-      OSError: You are trying to access a gated repo.
+              Use this command to throughput the latency of the {{model.model}} model on eight GPUs with the ``{{model.precision}}`` data type.
 
-      # pass your HF_TOKEN
-      export HF_TOKEN=$your_personal_hf_token
+              .. code-block:: shell
 
-.. _vllm-benchmark-standalone-options:
+                 ./vllm_benchmark_report.sh -s latency -m {{model.model_repo}} -g 8 -d {{model.precision}}
 
-Options and available models
-----------------------------
+              Find the throughput report at ``./reports_{{model.precision}}_vllm_rocm{{unified_docker.rocm_version}}/summary/{{model.model_repo.split('/', 1)[1] if '/' in model.model_repo else model.model_repo}}_throughput_report.csv``.
 
-.. list-table::
-   :header-rows: 1
-   :align: center
+            .. raw:: html
 
-   * - Name
-     - Options
-     - Description
+               <style>
+               mjx-container[jax="CHTML"][display="true"] {
+                  text-align: left;
+                  margin: 0;
+               }
+               </style>
 
-   * - ``$test_option``
-     - latency
-     - Measure decoding token latency
+            .. note::
 
-   * -
-     - throughput
-     - Measure token generation throughput
+               Throughput is calculated as:
 
-   * -
-     - all
-     - Measure both throughput and latency
+               - .. math:: throughput\_tot = requests \times (\mathsf{\text{input lengths}} + \mathsf{\text{output lengths}}) / elapsed\_time
 
-   * - ``$model_repo``
-     - ``meta-llama/Llama-3.1-8B-Instruct``
-     - `Llama 3.1 8B <https://huggingface.co/meta-llama/Llama-3.1-8B>`_
-
-   * - (``float16``)
-     - ``meta-llama/Llama-3.1-70B-Instruct``
-     - `Llama 3.1 70B <https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct>`_
-
-   * -
-     - ``meta-llama/Llama-3.1-405B-Instruct``
-     - `Llama 3.1 405B <https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct>`_
-
-   * -
-     - ``meta-llama/Llama-3.2-11B-Vision-Instruct``
-     - `Llama 3.2 11B Vision <https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct>`_
-
-   * -
-     - ``meta-llama/Llama-2-7b-chat-hf``
-     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-7b-chat-hf>`_
-
-   * -
-     - ``meta-llama/Llama-2-70b-chat-hf``
-     - `Llama 2 7B <https://huggingface.co/meta-llama/Llama-2-70b-chat-hf>`_
-
-   * -
-     - ``mistralai/Mixtral-8x7B-Instruct-v0.1``
-     - `Mixtral MoE 8x7B <https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1>`_
-
-   * -
-     - ``mistralai/Mixtral-8x22B-Instruct-v0.1``
-     - `Mixtral MoE 8x22B <https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1>`_
-
-   * -
-     - ``mistralai/Mistral-7B-Instruct-v0.3``
-     - `Mistral 7B <https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3>`_
-
-   * -
-     - ``Qwen/Qwen2-7B-Instruct``
-     - `Qwen2 7B <https://huggingface.co/Qwen/Qwen2-7B-Instruct>`_
-
-   * -
-     - ``Qwen/Qwen2-72B-Instruct``
-     - `Qwen2 72B <https://huggingface.co/Qwen/Qwen2-72B-Instruct>`_
-
-   * -
-     - ``core42/jais-13b-chat``
-     - `JAIS 13B <https://huggingface.co/core42/jais-13b-chat>`_
-
-   * -
-     - ``core42/jais-30b-chat-v3``
-     - `JAIS 30B <https://huggingface.co/core42/jais-30b-chat-v3>`_
-
-   * -
-     - ``databricks/dbrx-instruct``
-     - `DBRX Instruct <https://huggingface.co/databricks/dbrx-instruct>`_
-
-   * -
-     - ``google/gemma-2-27b``
-     - `Gemma 2 27B <https://huggingface.co/google/gemma-2-27b>`_
-
-   * -
-     - ``CohereForAI/c4ai-command-r-plus-08-2024``
-     - `C4AI Command R+ 08-2024 <https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024>`_
-
-   * -
-     - ``deepseek-ai/deepseek-moe-16b-chat``
-     - `DeepSeek MoE 16B <https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat>`_
-
-   * - ``$model_repo``
-     - ``amd/Llama-3.1-70B-Instruct-FP8-KV``
-     - `Llama 3.1 70B FP8 <https://huggingface.co/amd/Llama-3.1-70B-Instruct-FP8-KV>`_
-
-   * - (``float8``)
-     - ``amd/Llama-3.1-405B-Instruct-FP8-KV``
-     - `Llama 3.1 405B FP8 <https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV>`_
-
-   * -
-     - ``amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV``
-     - `Mixtral MoE 8x7B FP8 <https://huggingface.co/amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV>`_
-
-   * -
-     - ``amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV``
-     - `Mixtral MoE 8x22B FP8 <https://huggingface.co/amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV>`_
-
-   * -
-     - ``amd/Mistral-7B-v0.1-FP8-KV``
-     - `Mistral 7B FP8 <https://huggingface.co/amd/Mistral-7B-v0.1-FP8-KV>`_
-
-   * -
-     - ``amd/dbrx-instruct-FP8-KV``
-     - `DBRX Instruct FP8 <https://huggingface.co/amd/dbrx-instruct-FP8-KV>`_
-
-   * -
-     - ``amd/c4ai-command-r-plus-FP8-KV``
-     - `C4AI Command R+ 08-2024 FP8 <https://huggingface.co/amd/c4ai-command-r-plus-FP8-KV>`_
-
-   * - ``$num_gpu``
-     - 1 or 8
-     - Number of GPUs
-
-   * - ``$datatype``
-     - ``float16`` or ``float8``
-     - Data type
-
-.. _vllm-benchmark-run-benchmark:
-
-Running the benchmark on the MI300X accelerator
------------------------------------------------
-
-Here are some examples of running the benchmark with various options.
-See :ref:`Options <vllm-benchmark-standalone-options>` for the list of
-options and their descriptions.
-
-Example 1: latency benchmark
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- 
-Use this command to benchmark the latency of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
-
-.. code-block::
-
-   ./vllm_benchmark_report.sh -s latency -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
-   ./vllm_benchmark_report.sh -s latency -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
-
-Find the latency reports at:
-
-- ``./reports_float16/summary/Llama-3.1-70B-Instruct_latency_report.csv``
-
-- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_latency_report.csv``
-
-Example 2: throughput benchmark
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Use this command to benchmark the throughput of the Llama 3.1 70B model on eight GPUs with the ``float16`` and ``float8`` data types.
-
-.. code-block:: shell
-
-   ./vllm_benchmark_report.sh -s throughput -m meta-llama/Llama-3.1-70B-Instruct -g 8 -d float16
-   ./vllm_benchmark_report.sh -s throughput -m amd/Llama-3.1-70B-Instruct-FP8-KV -g 8 -d float8
-
-Find the throughput reports at:
-
-- ``./reports_float16/summary/Llama-3.1-70B-Instruct_throughput_report.csv``
-
-- ``./reports_float8/summary/Llama-3.1-70B-Instruct-FP8-KV_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
+               - .. math:: throughput\_gen = requests \times \mathsf{\text{output lengths}} / elapsed\_time
+      {% endfor %}
+   {% endfor %}
 
 Further reading
 ===============
@@ -446,33 +290,3 @@ Further reading
 
 - To learn how to fine-tune LLMs, see
   :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
-
-Previous versions
-=================
-
-This table lists previous versions of the ROCm vLLM Docker image for inference
-performance validation. For detailed information about available models for
-benchmarking, see the version-specific documentation.
-
-.. list-table::
-   :header-rows: 1
-   :stub-columns: 1
-
-   * - ROCm version
-     - vLLM version
-     - PyTorch version
-     - Resources
-
-   * - 6.2.1
-     - 0.6.4
-     - 2.5.0
-     - 
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4/images/sha256-ccbb74cc9e7adecb8f7bdab9555f7ac6fc73adb580836c2a35ca96ff471890d8>`_
-
-   * - 6.2.0
-     - 0.4.3
-     - 2.4.0
-     -
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.2.0/how-to/performance-validation/mi300x/vllm-benchmark.html>`_
-       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.2_mi300_ubuntu22.04_py3.9_vllm_7c5fd50/images/sha256-9e4dd4788a794c3d346d7d0ba452ae5e92d39b8dfac438b2af8efdc7f15d22c0>`_

docs/how-to/system-optimization/mi300x.rst

@@ -308,6 +308,24 @@ Otherwise, if the system has Intel host CPUs add this instead to
 
    intel_iommu=on iommu=pt
 
+``modprobe.blacklist=amdgpu``
+  For some system configurations, the ``amdgpu`` driver needs to be blocked during kernel initialization to avoid an issue where after boot, the GPUs are not listed when running the command ``rocm-smi`` or ``amd-smi``.
+
+  Alternatively, configuring the AMD recommended system optimized BIOS settings might remove the need for using this setting. Some manufacturers and users might not implement the recommended system optimized BIOS settings.
+
+If you experience the mentioned issue, then add this to ``GRUB_CMDLINE_LINUX``:
+
+.. code-block:: text
+
+  modprobe.blacklist=amdgpu
+
+After the change, the ``amdgpu`` module must be loaded to support the ROCm framework
+software tools and utilities. Run the following command to load the ``amdgpu`` module:
+
+.. code-block:: text
+
+  sudo modprobe amdgpu
+
 Update GRUB
 -----------
 

docs/reference/precision-support.rst

@@ -9,16 +9,14 @@
 Data types and precision support
 *************************************************************
 
-This topic lists the supported data types of AMD GPUs and ROCm libraries.
-Corresponding :doc:`HIP <hip:index>` data types are also noted. 
+This topic lists the data types support on AMD GPUs, ROCm libraries along
+with corresponding :doc:`HIP <hip:index>` data types.
 
 Integral types
-==========================================
+==============
 
 The signed and unsigned integral types supported by ROCm are listed in
-the following table, along with their corresponding HIP type and a short
-description.
-
+the following table.
 
 .. list-table::
     :header-rows: 1
@@ -48,10 +46,9 @@ description.
 .. _precision_support_floating_point_types:
 
 Floating-point types
-==========================================
+====================
 
-The floating-point types supported by ROCm are listed in the following
-table, along with their corresponding HIP type and a short description.
+The floating-point types supported by ROCm are listed in the following table.
 
 .. image:: ../data/about/compatibility/floating-point-data-types.png
     :alt: Supported floating-point types
@@ -66,18 +63,18 @@ table, along with their corresponding HIP type and a short description.
       - 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.
+        and **S1E4M3** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_,
+        with expanded range and no infinity or signed zero. NaN is represented
+        as negative zero.
     *
       - float8 (E5M2)
-      - ``-``
+      - ``__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.
+        **S1E5M2** bit layout, as described in `8-bit Numerical Formats for Deep Neural Networks <https://arxiv.org/abs/2206.02915>`_,
+        with expanded range and no infinity or signed zero. NaN is represented
+        as negative zero.
     *
       - float16
       - ``half``
@@ -90,7 +87,7 @@ table, along with their corresponding HIP type and a short description.
         format.
     *
       - tensorfloat32
-      - ``-``
+      - Not available
       - A floating-point number that occupies 32 bits or less of storage,
         providing improved range compared to half (16-bit) format, at
         (potentially) greater throughput than single-precision (32-bit) formats.
@@ -117,12 +114,15 @@ table, along with their corresponding HIP type and a short description.
 
   * In some AMD documents and articles, float8 (E5M2) is referred to as bfloat8.
 
-ROCm support icons
-==========================================
+  * The :doc:`low precision floating point types page <hip:reference/low_fp_types>`
+    describes how to use these types in HIP with examples.
 
-In the following sections, icons represent the level of support. These
-icons, described in the following table, are also used in the library data type
-support pages.
+Level of support definitions
+============================
+
+In the following sections, icons represent the level of support. These icons,
+described in the following table, are also used in the library data type support
+pages.
 
 .. list-table::
     :header-rows: 1
@@ -130,6 +130,11 @@ support pages.
     *
       -  Icon
       - Definition
+
+    *
+      - NA
+      - Not applicable
+
     *
       - ❌
       - Not supported
@@ -158,16 +163,15 @@ support pages.
   * Any type can be emulated by software, but this page does not cover such
     cases.
 
-Hardware data type support
+Data type support by Hardware Architecture
 ==========================================
 
-The following tables provide information about AMD Instinct accelerators support
-for various data types. The MI200 series GPUs, which include MI210, MI250, and
-MI250X, are based on the CDNA2 architecture. The MI300 series GPUs, consisting
-of MI300A, MI300X, and MI325X, are built on the CDNA3 architecture.
+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.
 
 Compute units support
--------------------------------------------------------------------------------
+---------------------
 
 The following table lists data type support for compute units.
 
@@ -248,7 +252,7 @@ The following table lists data type support for compute units.
         - ✅
 
 Matrix core support
--------------------------------------------------------------------------------
+-------------------
 
 The following table lists data type support for AMD GPU matrix cores.
 
@@ -329,7 +333,7 @@ The following table lists data type support for AMD GPU matrix cores.
         - ✅
 
 Atomic operations support
--------------------------------------------------------------------------------
+-------------------------
 
 The following table lists data type support for atomic operations.
 
@@ -416,14 +420,14 @@ The following table lists data type support for atomic operations.
   performance impact when they frequently access the same memory address.
 
 Data type support in ROCm libraries
-==========================================
+===================================
 
 ROCm library support for int8, float8 (E4M3), float8 (E5M2), int16, float16,
 bfloat16, int32, tensorfloat32, float32, int64, and float64 is listed in the
 following tables.
 
 Libraries input/output type support
--------------------------------------------------------------------------------
+-----------------------------------
 
 The following tables list ROCm library support for specific input and output
 data types. Refer to the corresponding library data type support page for a
@@ -444,37 +448,37 @@ detailed description.
         - int32
         - int64
       *
-        - hipSPARSELt (:doc:`details <hipsparselt:reference/data-type-support>`)
+        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
         - ✅/✅
         - ❌/❌
         - ❌/❌
         - ❌/❌
       *
-        - rocRAND (:doc:`details <rocrand:api-reference/data-type-support>`)
-        - -/✅
-        - -/✅
-        - -/✅
-        - -/✅
+        - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
+        - NA/✅
+        - NA/✅
+        - NA/✅
+        - NA/✅
       *
-        - hipRAND (:doc:`details <hiprand:api-reference/data-type-support>`)
-        - -/✅
-        - -/✅
-        - -/✅
-        - -/✅
+        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
+        - NA/✅
+        - NA/✅
+        - NA/✅
+        - NA/✅
       *
-        - rocPRIM (:doc:`details <rocprim:reference/data-type-support>`)
+        -  :doc:`rocPRIM <rocprim:reference/data-type-support>`
         - ✅/✅
         - ✅/✅
         - ✅/✅
         - ✅/✅
       *
-        - hipCUB (:doc:`details <hipcub:api-reference/data-type-support>`)
+        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
         - ✅/✅
         - ✅/✅
         - ✅/✅
         - ✅/✅
       *
-        - rocThrust (:doc:`details <rocthrust:data-type-support>`)
+        - :doc:`rocThrust <rocthrust:data-type-support>`
         - ✅/✅
         - ✅/✅
         - ✅/✅
@@ -496,7 +500,7 @@ detailed description.
         - float32
         - float64
       *
-        - hipSPARSELt (:doc:`details <hipsparselt:reference/data-type-support>`)
+        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
         - ❌/❌
         - ❌/❌
         - ✅/✅
@@ -505,25 +509,25 @@ detailed description.
         - ❌/❌
         - ❌/❌
       *
-        - rocRAND (:doc:`details <rocrand:api-reference/data-type-support>`)
-        - -/❌
-        - -/❌
-        - -/✅
-        - -/❌
-        - -/❌
-        - -/✅
-        - -/✅
+        - :doc:`rocRAND <rocrand:api-reference/data-type-support>`
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/✅
       *
-        - hipRAND (:doc:`details <hiprand:api-reference/data-type-support>`)
-        - -/❌
-        - -/❌
-        - -/✅
-        - -/❌
-        - -/❌
-        - -/✅
-        - -/✅
+        - :doc:`hipRAND <hiprand:api-reference/data-type-support>`
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/❌
+        - NA/❌
+        - NA/✅
+        - NA/✅
       *
-        - rocPRIM (:doc:`details <rocprim:reference/data-type-support>`)
+        - :doc:`rocPRIM <rocprim:reference/data-type-support>`
         - ❌/❌
         - ❌/❌
         - ✅/✅
@@ -532,7 +536,7 @@ detailed description.
         - ✅/✅
         - ✅/✅
       *
-        - hipCUB (:doc:`details <hipcub:api-reference/data-type-support>`)
+        - :doc:`hipCUB <hipcub:api-reference/data-type-support>`
         - ❌/❌
         - ❌/❌
         - ✅/✅
@@ -541,7 +545,7 @@ detailed description.
         - ✅/✅
         - ✅/✅
       *
-        - rocThrust (:doc:`details <rocthrust:data-type-support>`)
+        - :doc:`rocThrust <rocthrust:data-type-support>`
         - ❌/❌
         - ❌/❌
         - ⚠️/⚠️
@@ -550,9 +554,14 @@ detailed description.
         - ✅/✅
         - ✅/✅
 
+.. 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
--------------------------------------------------------------------------------
+--------------------------------------------
 
 The following tables list ROCm library support for specific internal data types.
 Refer to the corresponding library data type support page for a detailed
@@ -573,7 +582,7 @@ description.
         - int32
         - int64
       *
-        - hipSPARSELt (:doc:`details <hipsparselt:reference/data-type-support>`)
+        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
         - ❌
         - ❌
         - ✅
@@ -596,7 +605,7 @@ description.
         - float32
         - float64
       *
-        - hipSPARSELt (:doc:`details <hipsparselt:reference/data-type-support>`)
+        - :doc:`hipSPARSELt <hipsparselt:reference/data-type-support>`
         - ❌
         - ❌
         - ❌

docs/sphinx/_toc.yml.in

@@ -154,7 +154,7 @@ subtrees:
         - entries:
           - url: https://www.amd.com/system/files/TechDocs/instinct-mi200-cdna2-instruction-set-architecture.pdf
             title: AMD Instinct MI200/CDNA2 ISA
-          - url: https://www.amd.com/system/files/documents/amd-cdna2-white-paper.pdf
+          - url: https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna2-white-paper.pdf
             title: White paper
       - file: conceptual/gpu-arch/mi100.md
         title: MI100 microarchitecture
@@ -162,7 +162,7 @@ subtrees:
         - entries:
           - url: https://www.amd.com/system/files/TechDocs/instinct-mi100-cdna1-shader-instruction-set-architecture%C2%A0.pdf
             title: AMD Instinct MI100/CDNA1 ISA
-          - url: https://www.amd.com/system/files/documents/amd-cdna-whitepaper.pdf
+          - url: https://www.amd.com/content/dam/amd/en/documents/instinct-business-docs/white-papers/amd-cdna-white-paper.pdf
             title: White paper
   - file: conceptual/iommu.rst
     title: Input-Output Memory Management Unit (IOMMU)

docs/sphinx/requirements.in

@@ -1,3 +1,4 @@
-rocm-docs-core==1.17.0
+rocm-docs-core==1.17.1
 sphinx-reredirects
 sphinx-sitemap
+sphinxcontrib.datatemplates==0.11.0

docs/sphinx/requirements.txt

@@ -2,7 +2,7 @@
 # This file is autogenerated by pip-compile with Python 3.10
 # by the following command:
 #
-#    pip-compile requirements.in
+#    pip-compile docs/sphinx/requirements.in
 #
 accessible-pygments==0.0.5
     # via pydata-sphinx-theme
@@ -43,6 +43,8 @@ debugpy==1.8.12
     # via ipykernel
 decorator==5.1.1
     # via ipython
+defusedxml==0.7.1
+    # via sphinxcontrib-datatemplates
 deprecated==1.2.15
     # via pygithub
 docutils==0.21.2
@@ -175,6 +177,7 @@ pyyaml==6.0.2
     #   myst-parser
     #   rocm-docs-core
     #   sphinx-external-toc
+    #   sphinxcontrib-datatemplates
 pyzmq==26.2.0
     # via
     #   ipykernel
@@ -187,7 +190,7 @@ requests==2.32.3
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.17.0
+rocm-docs-core==1.17.1
     # via -r requirements.in
 rpds-py==0.22.3
     # via
@@ -215,6 +218,8 @@ sphinx==8.1.3
     #   sphinx-notfound-page
     #   sphinx-reredirects
     #   sphinx-sitemap
+    #   sphinxcontrib-datatemplates
+    #   sphinxcontrib-runcmd
 sphinx-book-theme==1.1.3
     # via rocm-docs-core
 sphinx-copybutton==0.5.2
@@ -231,6 +236,8 @@ sphinx-sitemap==2.6.0
     # via -r requirements.in
 sphinxcontrib-applehelp==2.0.0
     # via sphinx
+sphinxcontrib-datatemplates==0.11.0
+    # via -r requirements.in
 sphinxcontrib-devhelp==2.0.0
     # via sphinx
 sphinxcontrib-htmlhelp==2.1.0
@@ -239,6 +246,8 @@ sphinxcontrib-jsmath==1.0.1
     # via sphinx
 sphinxcontrib-qthelp==2.0.0
     # via sphinx
+sphinxcontrib-runcmd==0.2.0
+    # via sphinxcontrib-datatemplates
 sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
 sqlalchemy==2.0.37

docs/sphinx/static/css/vllm-benchmark.css

@@ -0,0 +1,102 @@
+/* ------------------ Compatibility options grid ------------------ */
+html {
+  --compat-border-radius: 2px;
+  --compat-accent-color: var(--pst-color-primary);
+  --compat-bg-color: var(--pst-color-on-background);
+  --compat-fg-color: var(--pst-color-primary-text);
+  --compat-head-color: var(--pst-color-surface);
+  --compat-param-hover-color: var(--pst-color-link-hover);
+  --compat-param-selected-color: var(--pst-color-primary);
+}
+
+html[data-theme="light"] {
+  --compat-border-color: var(--pst-gray-500);
+  --compat-param-disabled-color: var(--pst-gray-300);
+}
+
+html[data-theme="dark"] {
+  --compat-border-color: var(--pst-gray-600);
+  --compat-param-disabled-color: var(--pst-gray-600);
+}
+
+div#vllm-benchmark-ud-params-picker.container-fluid {
+  padding: 0 0 1rem 0;
+}
+
+div[data-param-k="model"] {
+  background-color: var(--compat-bg-color);
+  padding: 2px;
+  border: solid 1px var(--compat-border-color);
+  font-weight: 500;
+  cursor: pointer;
+}
+
+div[data-param-k="model"][data-param-state="selected"] {
+  background-color: var(--compat-param-selected-color);
+  color: var(--compat-fg-color);
+}
+
+div[data-param-k="model"][data-param-state="latest-version"] {
+  background-color: var(--compat-param-selected-color);
+  color: var(--compat-fg-color);
+}
+
+div[data-param-k="model"][data-param-state="disabled"] {
+  background-color: var(--compat-param-disabled-color);
+  text-decoration: line-through;
+  /* text-decoration-color: var(--pst-color-danger); */
+  cursor: auto;
+}
+
+div[data-param-k="model"]:not([data-param-state]):hover {
+  background-color: var(--compat-param-hover-color);
+}
+
+div[data-param-k="model-group"] {
+  background-color: var(--compat-bg-color);
+  padding: 2px;
+  border: solid 1px var(--compat-border-color);
+  font-weight: 500;
+  cursor: pointer;
+}
+
+div[data-param-k="model-group"][data-param-state="selected"] {
+  background-color: var(--compat-param-selected-color);
+  color: var(--compat-fg-color);
+}
+
+div[data-param-k="model-group"][data-param-state="latest-version"] {
+  background-color: var(--compat-param-selected-color);
+  color: var(--compat-fg-color);
+}
+
+div[data-param-k="model-group"][data-param-state="disabled"] {
+  background-color: var(--compat-param-disabled-color);
+  text-decoration: line-through;
+  /* text-decoration-color: var(--pst-color-danger); */
+  cursor: auto;
+}
+
+div[data-param-k="model-group"]:not([data-param-state]):hover {
+  background-color: var(--compat-param-hover-color);
+}
+
+.model-param-head {
+  background-color: var(--compat-head-color);
+  padding: 0.15rem 0.15rem 0.15rem 0.67rem;
+  /* margin: 2px; */
+  border-right: solid 2px var(--compat-accent-color);
+  font-weight: 600;
+}
+
+.model-param {
+  /* padding: 2px; */
+  /* margin: 0 2px 0 2px; */
+  /* margin: 2px; */
+  border: solid 1px var(--compat-border-color);
+  font-weight: 500;
+}
+
+.hidden {
+  display: none !important;
+}