Cite
Notes
Only stored in your browser.
Attribution
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
arXiv 2024
from 1 papers
Hao Zhang
professor
Jianbo Hu
Junda Chen
Xin Jin
Xuanzhe Liu
Yibo Zhu
Yinmin Zhong