首页|期刊导航|高技术通讯(英文版)|Triage:optimizing LLM serving goodput in unified scheduling via feedback-driven batch shaping
Triage:optimizing LLM serving goodput in unified scheduling via feedback-driven batch shapingOA
Triage:optimizing LLM serving goodput in unified scheduling via feedback-driven batch shaping
吕存驰
large language model servingiteration-level schedulinggoodput-driven sched-uling
large language model servingiteration-level schedulinggoodput-driven sched-uling
《高技术通讯(英文版)》 2026 (2)
121-132,12
Supported by the National Natural Science Foundation of China Joint Fund Project(No.U24B6012)and the Innovation Project of the Institute of Computing Technology,Chinese Academy of Sciences(No.E461040).
评论