Skip to content

STAR: Decode-Phase Rescheduling for LLM Inference.

Zhibin Wang, Zetao Hong, Xue Li, Zibo Wang, Shipeng Li, Qingkai Meng, Qing Wang, Chengying Huan, Rong Gu, Sheng Zhong, Chen Tian

VenueAHPDC
Year2026
ProceedingsHPDC

Browse the full HPDC paper archive.