model_name: "RedHatAI/Qwen3-30B-A3B-FP8-block"
accuracy_threshold: 0.85
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"
env:
  VLLM_USE_DEEP_GEMM: "1"
  VLLM_USE_DEEP_GEMM_MOE: "1"