raullenchai/Rapid-MLX

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

语言：Python · GitHub 星标：4,108 · Fork：438

话题：anthropic-api · apple-silicon · claude-code · coding-agents · continuous-batching · inference-server · llm-inference · llm-server

在 GitHub 上查看原仓库