vllm-project/vllm

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

Python80,711 stars17,102 forksApache-2.0

amdblackwellcudadeepseekdeepseek-v3gptgpt-ossinferencekimillamallmllm-servingmodel-servingmoeopenaipytorchqwenqwen3tputransformer

Rankings

Daily

#201

Weekly

#195

Monthly

#165

Total stars

Daily new stars

Get badge

This repository is tracked by Trending Repos. The badge upgrades automatically if it ever cracks the top 100.

Markdown

![Trending Repos](https://trending-repos.com/badge/vllm-project/vllm.svg)

HTML

<img src="https://trending-repos.com/badge/vllm-project/vllm.svg" alt="Trending Repos" />

Raw URL

https://trending-repos.com/badge/vllm-project/vllm.svg