| 1 | model_name: "nvidia/Qwen3-30B-A3B-NVFP4" |
| 2 | accuracy_threshold: 0.88 |
| 3 | num_questions: 1319 |
| 4 | num_fewshot: 5 |
| 5 | # 30B MoE + CuTeDSL/DeepEP JIT compile can exceed the 1200s default startup wait. |
| 6 | startup_max_wait_seconds: 2400 |
| 7 | server_args: "--enforce-eager --max-model-len 8192 --data-parallel-size 2 --enable-expert-parallel --all2all-backend deepep_low_latency --moe-backend=flashinfer_cutedsl" |