add qwen3 30b a3b to vllm-benchmark-models (#5280)

2026-04-05 03:01:17 -04:00 · 2025-09-09 17:41:11 -04:00
parent 3c37ae88f0
commit 05a66f75fe
1 changed files with 5 additions and 1 deletions
--- a/docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/inference/vllm-benchmark-models.yaml
@@ -78,7 +78,11 @@ vllm_benchmark:
        model_repo: Qwen/QwQ-32B
        url: https://huggingface.co/Qwen/QwQ-32B
        precision: float16
-        tunableop: true
+      - model: Qwen3 30B A3B
+        mad_tag: pyt_vllm_qwen3-30b-a3b
+        model_repo: Qwen/Qwen3-30B-A3B
+        url: https://huggingface.co/Qwen/Qwen3-30B-A3B
+        precision: float16
    - group: Microsoft Phi
      tag: phi
      models: