diff --git 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 index 714534ef1..a522e61a6 100644 --- 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: