Author

Huang Cheng

h-index 0 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

CacheRoute: Planned Prefix-Affinity Routing for Large-Scale LLM Serving

When affinity recovers too little KV work, its residual load skew reduces or erases the improvement, so gating any deployment with a shadow replay rather than enabling affinity from workload statistics alone is recommended.

Huang Cheng · 1 citation