yy-fighting
|
7d2ed7f05d
|
Add vLLM+MTP speculative decoding benchmark vs default on H200
- Experiment: experiments/dsv4_h200_vllm_mtp_vs_default/
- Use official DeepSeek-V4 recipe: --speculative-config '{method: mtp, num_speculative_tokens: 1}'
- Reuse default-side results from dsv4_h200_vllm_dspark_vs_default
- Add TTFT analysis for DSpark vs default trade-offs
|
2026-07-08 16:13:01 +00:00 |
|