waybarrios/vllm-mlx

vllm-mlx

✅ Recently maintained

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.

1,645Stars
235Forks
+77-day stars

Python · Apache-2.0 · Last push 2026-10-26

Official repository & installation ↗

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-12-012026-11-03
View historical data
DateStars
2026-10-051,608
2026-10-061,610
2026-10-071,611
2026-10-081,614
2026-10-091,616
2026-10-101,616
2026-10-111,616
2026-10-121,617
2026-10-131,618
2026-10-141,622
2026-10-151,622
2026-10-161,623
2026-10-171,624
2026-10-181,624
2026-10-191,624
2026-10-201,627
2026-10-211,628
2026-10-221,632
2026-10-231,635
2026-10-241,637
2026-10-251,637
2026-10-261,637
2026-10-271,639
2026-10-281,641
2026-10-291,641
2026-10-301,643
2026-10-311,644
2026-11-011,644
2026-11-021,644
2026-11-031,645

Get the project

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

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.