vllm/tests/evals/gsm8k/configs/moe-refactor/Qwen3-30B-A3B-Fp8-AutoFp8-fi-cutlass.yaml

model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
accuracy_threshold: 0.88
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2"
env:
  VLLM_USE_FLASHINFER_MOE_FP8: "1"
  VLLM_FLASHINFER_MOE_BACKEND: "throughput"