Search
vLLM · benchflow-ai/skillsbench
1 skill found.
Category:
Skills
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Replay an LLM inference request trace (Mooncake / vLLM / SGLang hashids format) against a block-level KV prefix cache and compute hit statistics. | benchflow-ai/ | 1.8k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
