| 1 | model_name: "deepseek-ai/DeepSeek-V4-Flash" |
| 2 | accuracy_threshold: 0.95 |
| 3 | num_questions: 1319 |
| 4 | num_fewshot: 5 |
| 5 | server_args: "--trust-remote-code --kv-cache-dtype fp8 --block-size 256 --enable-expert-parallel --tensor-parallel-size 2 --attention_config.indexer_kv_dtype=mxfp4 --moe-backend deep_gemm_mega_moe --tokenizer-mode deepseek_v4 --tool-call-parser deepseek_v4 --enable-auto-tool-choice --reasoning-parser deepseek_v4 --speculative_config.method=mtp --speculative_config.num_speculative_tokens=2" |