JIEAS OPEN ACCESS

Journal of Industrial Engineering and Applied Science

ISSN:3005-608X (print) | ISSN:3005-6071 (online) | Publication Frequency: Bimonthly

OPEN ACCESS|Research Article||4 February 2026

KV Cache and Inference Scheduling: Energy Modeling for High-QPS Services

* Corresponding Author1: Wenwen Liu, E-Mail: liuwenwen.jessica@bytedance.com

t