External CI: Try defining rocBLAS version explicity for MIOpen build

* Add Qwen2 MoE 2.7B to vllm-benchmark-models.yaml

* Add QwQ-32B-Preview to vllm-benchmark-models.yaml

* add links to performance results

words

* change "performance validation" to "performance testing"

* remove "-Preview" from QwQ-32B

* move qwen2 MoE after qwen2

* add TunableOp section

* fix formatting

* add link to TunableOp doc

* add tunableop note

* fix vllm-benchmark template

* remove cmdline option for --tunableop on

* update docker details

* remove "training"

* remove qwen2

.azuredevops/components/MIOpen.yml

@@ -125,6 +125,9 @@ jobs:
           -DMIOPEN_ENABLE_AI_IMMED_MODE_FALLBACK=OFF
           -DCMAKE_BUILD_TYPE=Release
           -DBUILD_TESTING=ON
+          -Drocblas_VERSION_MAJOR=5
+          -Drocblas_VERSION_MINOR=0
+          -Drocblas_VERSION_PATCH=0
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
       parameters:

.azuredevops/components/rocJPEG.yml

@@ -89,6 +89,8 @@ jobs:
           -GNinja
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
+      parameters:
+        gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml
     # - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/docker-container.yml
     #   parameters:
@@ -122,6 +124,8 @@ jobs:
         registerROCmPackages: true
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/preamble.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/local-artifact-download.yml
+      parameters:
+        gpuTarget: ${{ job.target }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-aqlprofile.yml
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
@@ -147,4 +151,3 @@ jobs:
         environment: test
         gpuTarget: ${{ job.target }}
         registerROCmPackages: true
-        optSymLink: true

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

@@ -1,10 +1,10 @@
 vllm_benchmark:
   unified_docker:
     latest:
-      pull_tag: rocm/vllm:instinct_main
-      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.7.3_20250311/images/sha256-de0a2649b735f45b7ecab8813eb7b19778ae1f40591ca1196b07bc29c42ed4a3
+      pull_tag: rocm/vllm:rocm6.3.1_instinct_vllm0.8.3_20250410
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.8.3_20250410/images/sha256-a0b55c6c0f3fa5d437fb54a66e32a108306c36d4776e570dfd0ae902719bd190
       rocm_version: 6.3.1
-      vllm_version: 0.7.3
+      vllm_version: 0.8.3
       pytorch_version: 2.7.0 (dev nightly)
       hipblaslt_version: 0.13
   model_groups:
@@ -102,19 +102,12 @@ vllm_benchmark:
         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
+      - model: QwQ-32B
+        mad_tag: pyt_vllm_qwq-32b
+        model_repo: Qwen/QwQ-32B
+        url: https://huggingface.co/Qwen/QwQ-32B
         precision: float16
+        tunableop: true
     - group: DBRX
       tag: dbrx
       models:

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

@@ -92,6 +92,10 @@ PyTorch inference performance testing
 
             docker pull rocm/pytorch:rocm6.2.3_ubuntu22.04_py3.10_pytorch_release_2.3.0_triton_llvm_reg_issue
 
+         .. note::
+
+            The Chai-1 benchmark uses a specifically selected Docker image using ROCm 6.2.3 and PyTorch 2.3.0 to address an accuracy issue.
+
    .. container:: model-doc pyt_clip_inference
 
       2. Use the following command to pull the `ROCm PyTorch Docker image <https://hub.docker.com/layers/rocm/pytorch/rocm6.2.3_ubuntu22.04_py3.10_pytorch_release_2.3.0_triton_llvm_reg_issue/images/sha256-b736a4239ab38a9d0e448af6d4adca83b117debed00bfbe33846f99c4540f79b>`_ from Docker Hub.

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

@@ -34,7 +34,7 @@ vLLM inference performance testing
 
    .. _vllm-benchmark-available-models:
 
-   Available models
+   Supported models
    ================
 
    .. raw:: html
@@ -183,6 +183,25 @@ vLLM inference performance testing
             to collect latency and throughput performance data, you can also change the benchmarking
             parameters. See the standalone benchmarking tab for more information.
 
+            {% if model.tunableop %}
+
+            .. note::
+
+               For improved performance, consider enabling :ref:`PyTorch TunableOp <mi300x-tunableop>`.
+               TunableOp automatically explores different implementations and configurations of certain PyTorch
+               operators to find the fastest one for your hardware.
+
+               By default, ``{{model.mad_tag}}`` runs with TunableOp disabled
+               (see
+               `<https://github.com/ROCm/MAD/blob/develop/models.json>`__). To
+               enable it, edit the default run behavior in the ``models.json``
+               configuration before running inference -- update the model's run
+               ``args`` by changing ``--tunableop off`` to ``--tunableop on``.
+
+               Enabling TunableOp triggers a two-pass run -- a warm-up followed by the performance-collection run.
+
+            {% endif %}
+
          .. tab-item:: Standalone benchmarking
 
             Run the vLLM benchmark tool independently by starting the
@@ -331,11 +350,18 @@ for benchmarking, see the version-specific documentation.
      - PyTorch version
      - Resources
 
+   * - 6.3.1
+     - 0.7.3
+     - 2.7.0
+     - 
+       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.3/how-to/rocm-for-ai/inference/vllm-benchmark.html>`_
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.7.3_20250325/images/sha256-25245924f61750b19be6dcd8e787e46088a496c1fe17ee9b9e397f3d84d35640>`_
+
    * - 6.3.1
      - 0.6.6
      - 2.7.0
      - 
-       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.2/how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.html>`_
+       * `Documentation <https://rocm.docs.amd.com/en/docs-6.3.2/how-to/rocm-for-ai/inference/vllm-benchmark.html>`_
        * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_mi300_ubuntu22.04_py3.12_vllm_0.6.6/images/sha256-9a12ef62bbbeb5a4c30a01f702c8e025061f575aa129f291a49fbd02d6b4d6c9>`_
 
    * - 6.2.1