vllm-project/vllm

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

[view on github]last commit: Oct 20, 2026

stars

94,215

7d

+512

30d

+1,996

90d

+8,838

## star history

## found in

Awesome local LLM/Inference engines Awesome Open Source AI/⚡ 3. Inference Engines & Serving