Preprint
Aug 2026
Efficiency and Cost Alignment in Batched LLM Serving via Resource-Fair Scheduling
A mathematical scheduling model that connects within-batch resource fairness to system throughput and provides a bi-criterion scheduling policy, ISJL, which maintains high throughput while aligning max-driven batch cost with token-metered revenue.
Dayi Yao, Zijie Zhou
· 0 citations