| 1 | model_name: "nvidia/Qwen3.5-397B-A17B-NVFP4" |
| 2 | accuracy_threshold: 0.88 |
| 3 | tolerance: 0.03 |
| 4 | num_questions: 1319 |
| 5 | num_fewshot: 5 |
| 6 | max_tokens: 12000 |
| 7 | server_args: >- |
| 8 | --max-model-len 16384 |
| 9 | --data-parallel-size 2 |
| 10 | --enable-expert-parallel |
| 11 | --max-num-seqs 256 |
| 12 | --spec-method mtp |
| 13 | --spec-tokens 3 |