zhengzangw/Sequence-Scheduling
PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
Python
Stargazers
- akashicMargaSaarthi.Ai
- AlanSynn@gatech-sysml
- caliba
- ChaoGaoUCRUniversity of California Riverside
- chengyinieStony Brook University
- DamienLee2017
- DamilolaDami
- ericxian1997
- fabiohtoSão Paulo
- fly51flyPRIS
- hijkzzzNVIDIA
- JeffCarpenterCanada
- JonathanFlyiforcedabot.com
- Jun-jie-HuangThe Chinese University of Hong Kong
- kaiwang960112National University of Singapore
- leesh6796KAIST
- lessw2020Seattle, WA USA
- llx-08Beijing, China
- NeosKnight233
- nigelleejyl
- ningwanyiBeijing University of Posts and Telecommunications
- oujieww
- PDS99
- qzwengShanghai AI Lab
- RevliterNanjing University
- SushantDaga
- vishaal27University of Tübingen | University of Cambridge
- wilsonodpn
- wolegechuStepFUN
- XiaoxinHeNUS
- xuanhan863Los Angeles, USA
- Yanxing-ShiAMD.inc
- YixinSong-eSJTU
- zhengzangwNation University of Singapore
- zhixin612Tianjin University
- ZiruiOu