vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

97k stars25kforks2.9kissuespushed

vllm.ai ↗github.com/vllm-project/vllm ↗

Worth your time

Outside contributors get merged here, though some wait a while for a reply.

27 of 60outside PRs merged (45%)

checked