Perfup

Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

raullenchai Updated
Rapid-MLX. Local LLM server for Apple Silicon, built for coding agents. Up to 4× faster than Apple's MLX. 1.5× on a typical task — same model, same weights. bre

File contents

raullenchai/rapid-mlx commit e0c9b95ab9

Frequently asked questions

npx get-skill add raullenchai/perfup