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

..

20260708-142121

Add vLLM+MTP speculative decoding benchmark vs default on H200

2026-07-08 16:13:01 +00:00