jundot/omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

★ 23.4k · 2.1k forks · Python

Add it to your README

Charts use snapshots recorded by Repostream, starting at the first observation. README images are cached for 6 to 12 hours. Limited history is shown as collecting, never estimated.

Star history chart

[![Star history](https://repostream.com/chart/jundot/omlx.svg)](https://repostream.com/repo/jundot/omlx)

Trending rank badge

[![Trending on Repostream](https://repostream.com/badge/jundot/omlx.svg)](https://repostream.com/repo/jundot/omlx)

Want to see what is gaining stars fastest right now? Open the live leaderboard.