Author

Kaixin Zhang

1 paper indexed here

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.

Jul 2026

SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling

SMetric addresses session-centric scheduling with differential scheduling based on two indicators derived from the request itself, the session turn and the local KV\$ hit: it schedules first-turn requests for load balance, and sticks follow-ups to the instance with the highest local hit for high KV\$ reuse.

Jiahao Wang, Kai-Zhan Lin, Kaixin Zhang et al. · arXiv.org · 1 citation