LIU, Wenwen. KV Cache and Inference Scheduling: Energy Modeling for High-QPS Services. Journal of Industrial Engineering and Applied Science, London, U.K., v. 4, n. 1, p. 34–41, 2026. DOI: 10.70393/6a69656173.333930. Disponível em: https://www.suaspress.org/ojs/index.php/JIEAS/article/view/v4n1a05. Acesso em: 6 feb. 2026.