vllm-mlx

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

macos

View on GitHub Website

1.6k Stars

229 Forks

10 Watchers

Python Language

apache-2.0 License

100 SrcLog Score

Cost to Build

$520.2K

Market Value

$2.62M

How is this calculated?

Growth over time

5 data points · 2026-04-25 → 2026-10-02

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about vllm-mlx

Question copied to clipboard

What is the waybarrios/vllm-mlx GitHub project? Description: "High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone vllm-mlx

Clone via HTTPS

git clone https://github.com/waybarrios/vllm-mlx.git

Clone via SSH

[email protected]:waybarrios/vllm-mlx.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the vllm-mlx issue tracker:

Open GitHub Issues

Similar to vllm-mlx

node atom the-art-of-command-line netdata nylas-mail awesome-mac dotfiles awesome-macos-command-line nativefier ShadowsocksX-NG macOS-Security-and-Privacy-Guide brew iina open-source-mac-os-apps textmate alacritty Best-App electronic-wechat PowerShell flow Kap BoostNote-Legacy kivy browser-laptop awesome-macOS macdown xbmc Karabiner-Elements marktext m-cli