Add latest rocm/vllm Docker details in vLLM inference benchmark guide (#4824)

* update rocm/vllm Docker details to latest release

* Add previous vLLM version

* fix 'further reading' xrefs

* improve model grouping names

* fix links

* update model picker text

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

@@ -1,14 +1,14 @@
 vllm_benchmark:
   unified_docker:
     latest:
-      pull_tag: rocm/vllm:rocm6.3.1_instinct_vllm0.8.3_20250415
-      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.8.3_20250415/images/sha256-ad9062dea3483d59dedb17c67f7c49f30eebd6eb37c3fac0a171fb19696cc845
+      pull_tag: rocm/vllm:rocm6.3.1_vllm0.8.3_20250415
+      docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_vllm_0.8.5_20250513/images/sha256-5c8b4436dd0464119d9df2b44c745fadf81512f18ffb2f4b5dc235c71ebe26b4
       rocm_version: 6.3.1
-      vllm_version: 0.8.3
-      pytorch_version: 2.7.0 (dev nightly)
-      hipblaslt_version: 0.13
+      vllm_version: 0.8.5
+      pytorch_version: 2.7.0+gitf717b2a
+      hipblaslt_version: 0.15
   model_groups:
-    - group: Llama
+    - group: Meta Llama
       tag: llama
       models:
       - model: Llama 3.1 8B
@@ -56,7 +56,7 @@ vllm_benchmark:
         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
+    - group: Mistral AI
       tag: mistral
       models:
       - model: Mixtral MoE 8x7B
@@ -108,7 +108,7 @@ vllm_benchmark:
         url: https://huggingface.co/Qwen/QwQ-32B
         precision: float16
         tunableop: true
-    - group: DBRX
+    - group: Databricks DBRX
       tag: dbrx
       models:
       - model: DBRX Instruct
@@ -121,7 +121,7 @@ vllm_benchmark:
         model_repo: amd/dbrx-instruct-FP8-KV
         url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
         precision: float8
-    - group: Gemma
+    - group: Google Gemma
       tag: gemma
       models:
       - model: Gemma 2 27B

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

@@ -1,6 +1,6 @@
 megatron-lm_benchmark:
   model_groups:
-    - group: Llama
+    - group: Meta Llama
       tag: llama
       models:
       - model: Llama 3.3 70B
@@ -20,7 +20,7 @@ megatron-lm_benchmark:
         mad_tag: pyt_megatron_lm_train_deepseek-v3-proxy
       - model: DeepSeek-V2-Lite
         mad_tag: pyt_megatron_lm_train_deepseek-v2-lite-16b
-    - group: Mistral
+    - group: Mistral AI
       tag: mistral
       models:
       - model: Mixtral 8x7B

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

@@ -24,11 +24,15 @@ PyTorch inference performance testing
    Supported models
    ================
 
+   The following models are supported for inference performance benchmarking
+   with PyTorch and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started.
+
    .. raw:: html
 
       <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="col-2 me-2 model-param-head">Model group</div>
           <div class="row col-10">
    {% for model_group in model_groups %}
             <div class="col-6 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
@@ -37,7 +41,7 @@ PyTorch inference performance testing
         </div>
 
         <div class="row mt-1" style="display: none;">
-          <div class="col-2 me-2 model-param-head">Model variant</div>
+          <div class="col-2 me-2 model-param-head">Model</div>
           <div class="row col-10">
    {% for model_group in model_groups %}
       {% set models = model_group.models %}
@@ -162,11 +166,14 @@ Further reading
 - To learn more about system settings and management practices to configure your system for
   MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
 
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`../../inference-optimization/workload`.
+
 - To learn how to run LLM models from Hugging Face or your model, see
-  :doc:`Running models from Hugging Face <hugging-face-models>`.
+  :doc:`Running models from Hugging Face <../hugging-face-models>`.
 
 - To learn how to optimize inference on LLMs, see
-  :doc:`Inference optimization <../inference-optimization/index>`.
+  :doc:`Inference optimization <../../inference-optimization/index>`.
 
 - To learn how to fine-tune LLMs, see
-  :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
+  :doc:`Fine-tuning LLMs <../../fine-tuning/index>`.

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

@@ -37,11 +37,15 @@ vLLM inference performance testing
    Supported models
    ================
 
+   The following models are supported for inference performance benchmarking
+   with vLLM and ROCm. Some instructions, commands, and recommendations in this
+   documentation might vary by model -- select one to get started.
+
    .. raw:: html
 
       <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="col-2 me-2 model-param-head">Model group</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>
@@ -50,7 +54,7 @@ vLLM inference performance testing
         </div>
 
         <div class="row mt-1">
-          <div class="col-2 me-2 model-param-head">Model variant</div>
+          <div class="col-2 me-2 model-param-head">Model</div>
           <div class="row col-10">
    {% for model_group in model_groups %}
       {% set models = model_group.models %}
@@ -318,23 +322,23 @@ vLLM inference performance testing
 Further reading
 ===============
 
-- For application performance optimization strategies for HPC and AI workloads,
-  including inference with vLLM, see :doc:`../inference-optimization/workload`.
-
 - To learn more about the options for latency and throughput benchmark scripts,
   see `<https://github.com/ROCm/vllm/tree/main/benchmarks>`_.
 
 - To learn more about system settings and management practices to configure your system for
   MI300X accelerators, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_
 
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`../../inference-optimization/workload`.
+
 - To learn how to run LLM models from Hugging Face or your own model, see
-  :doc:`Running models from Hugging Face <hugging-face-models>`.
+  :doc:`Running models from Hugging Face <../hugging-face-models>`.
 
 - To learn how to optimize inference on LLMs, see
-  :doc:`Inference optimization <../inference-optimization/index>`.
+  :doc:`Inference optimization <../../inference-optimization/index>`.
 
 - To learn how to fine-tune LLMs, see
-  :doc:`Fine-tuning LLMs <../fine-tuning/index>`.
+  :doc:`Fine-tuning LLMs <../../fine-tuning/index>`.
 
 Previous versions
 =================
@@ -352,6 +356,13 @@ for benchmarking, see the version-specific documentation.
      - PyTorch version
      - Resources
 
+   * - 6.3.1
+     - 0.8.3
+     - 2.7.0
+     - 
+       * `Documentation <https://rocm.docs.amd.com/en/docs-6.4.0/how-to/rocm-for-ai/inference/vllm-benchmark.html>`_
+       * `Docker Hub <https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.8.3_20250415/images/sha256-ad9062dea3483d59dedb17c67f7c49f30eebd6eb37c3fac0a171fb19696cc845>`_
+
    * - 6.3.1
      - 0.7.3
      - 2.7.0