| 1 | model_name: "deepseek-ai/DeepSeek-V4-Flash-DSpark" |
| 2 | accuracy_threshold: 0.92 |
| 3 | # lower acceptance length since trimming drafts at higher concurrency reduces |
| 4 | # acceptance length, this is very loose lower bound for smoke testing |
| 5 | min_acceptance_length: 1.2 |
| 6 | num_questions: 1319 |
| 7 | num_fewshot: 5 |
| 8 | startup_max_wait_seconds: 1800 |
| 9 | server_args: >- |
| 10 | --tokenizer-mode deepseek_v4 |
| 11 | --trust-remote-code |
| 12 | --max-model-len 8192 |
| 13 | --tensor-parallel-size 4 |
| 14 | --enable-expert-parallel |
| 15 | --block-size 256 |
| 16 | --gpu-memory-utilization 0.5 |
| 17 | --kv-cache-dtype fp8 |
| 18 | --attention_config.indexer_kv_dtype=mxfp4 |
| 19 | --max-num-batched-tokens 16384 |
| 20 | --max-num-seqs 128 |
| 21 | --speculative-config '{"method":"dspark", |
| 22 | "model":"deepseek-ai/DeepSeek-V4-Flash-DSpark", |
| 23 | "attention_backend":"FLASH_ATTN","num_speculative_tokens":7, |
| 24 | "draft_sample_method":"probabilistic", |
| 25 | "enable_adaptive_verification":true}' |