vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
PythonApache-2.0
Stargazers
- PKUFlyingPigBeijing, China
- ZYHowellPittsburgh, PA
- lambda7xx
- caoshiyiBerkeley, CA
- 66RING
- fengyangyang98Beijing China
- ZiruiOu
- gaocegege
- VoVAllenEarth
- ryantdBeijing
- wildkid1024Haidian Beijing
- nikitavoloboev
- larme
- aarnphmtoronto, ca
- wolegechuBeijing
- hanzz2007china
- jaywonchungAnn Arbor, MI, USA
- beamiter
- MohamedAzyzChayeb
- BtlmdBeijing, China
- prnake
- Xiao9905Beijing, China
- pengwu22Mountain View
- BrightXiaoHanChina.
- WoosukKwonBerkeley, CA
- zhisbug
- BabyChouSrUniversity of California, Berkeley
- Matthieu-Tinycoaching
- zbruceli
- concretevitaminBerkeley, CA
- abacaj
- ZQ-Dev8California
- wxj77
- michaelzhiluo
- MichaelvllBerkeley, CA
- romilbhardwajBerkeley, CA