V
vllm
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
★88.5kstars
Python
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A open-source Data & Infrastructure project, built with Python, focusing on amd and blackwell
Who made it?Maintained by vllm-project team, 88.5K⭐ on GitHub, #6 out of 3133 in Data & Infrastructure
Why does it exist?With the growing demand for amd and blackwell in Data & Infrastructure, vllm-project created vllm as a streamlined solution.
What can it do?Key use cases: cuda, deepseek, deepseek-v3
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/vllm-project/vllm | 官网 https://vllm.ai
🔗 github.com/vllm-project/vllm | 官网 https://vllm.ai
Topics
amdblackwellcudadeepseekdeepseek-v3gptgpt-ossinferencekimillamallmllm-servingmodel-servingmoeopenaipytorchqwenqwen3tputransformer