vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
PythonApache-2.0
Stargazers
- TheSeamau5Austin, TX
- merrymercyBay Arena, CA
- jlin816
- akrentselBerkeley
- eluzhnica
- franklsf95Berkeley, CA
- Giuseppe5Cologne
- scv119United States
- marcloveNew York, NY
- ysu1989
- rohan-paulBangalore
- LeoltySan Diego
- antferdomSeville, Spain
- the-crypt-keeper
- gustavecortalFrance
- huyangqiu
- CharewiczH
- SuhongMoon
- kssteven418Berkeley, United States
- vishjainSF, CA
- kallsymsBrooklyn, NY
- rishabh135Japan
- jauderho
- link2xt
- tqchen
- jianshen92
- kaiinuiTokyo, Japan
- sigma-andexPortugal
- VikParuchuriBrooklyn, NY
- golergka
- rizki96Jakarta, Indonesia
- xczas
- cadedanielSan Francisco
- zxybazhSeattle
- Kabilan108Philadelphia, PA
- Kaiyang-ChenSan Jose