| 注册
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 shaping

吕存驰

高技术通讯(英文版)2026,Vol.32Issue(2):121-132,12.
高技术通讯(英文版)2026,Vol.32Issue(2):121-132,12.DOI:10.3772/j.issn.1006-6748.2026.02.002

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 shaping

吕存驰1

作者信息

  • 折叠

摘要

关键词

large language model serving/iteration-level scheduling/goodput-driven sched-uling

Key words

large language model serving/iteration-level scheduling/goodput-driven sched-uling

引用本文复制引用

吕存驰..Triage:optimizing LLM serving goodput in unified scheduling via feedback-driven batch shaping[J].高技术通讯(英文版),2026,32(2):121-132,12.

基金项目

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). (No.U24B6012)

高技术通讯(英文版)

1006-6748

访问量0
|
下载量0
段落导航相关论文