vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
PythonApache-2.0
Watchers
- AaronFriel@pulumi
- bradjonescaNew York
- cadedaniel@anyscale
- duanshuaiminzonli
- fadihaik
- gvspraveen
- JohnnyOpcodeToronto, Ontario, Canada
- kahkeng
- kakugawa
- lt1946
- michalwolsNew York
- Neustradamus
- okumura
- pcmoritzAnyscale
- photosbanIntel Corporation
- qiuxiafeiAlibaba Group
- QubitiumEarth/Epoch 3
- rebotnixrebotnix technologies
- rschumann
- slamj1SaasyCloud™.com
- theSymbeintEemerg RAM
- timothyklim
- tistergitshenzhen
- tmostak@heavyai
- trappedinspacetimeFor Personal Use
- tyyang
- wanghaipeng789
- wDevilTinkoff
- wideblueskyBaidu, Inc.
- windwang
- xinyu1607Heilongjiang University
- xorgnakDenver.
- xuchengbeijing
- zhouyuan@Intel-bigdata
- zhubao315MXds
- zqstarmoon