Staggered Batch Scheduling: Co-optimizing Time-to-First-Token and Throughput for High-Efficiency LLM Inference

Tian Jian(Unknown), Dou Shen, Zhiwen Xiao(Southwest Jiaotong University), Minghan Zhu, Yang Cao(Hefei University of Technology), Wei Wu(Wuxi People's Hospital), Wenbo Cui, Jianming Zhang, Yanpeng Wang(University of South China), Zhenyu Hou, Shuailong Li
arXiv (Cornell University)
December 18, 2025
Cited by 0


Related Papers