pmerolla / fomoeView on GitHub
Fast Opportunistic Mixture-Of-Experts. From-scratch C/HIP MoE inference with multi-tier caching and cache-aware routing. First ever example of running Qwen3.5-397B at 5–9 tok/s on a $2,100 desktop.
28Mar 31, 2026Updated 3 months ago

Alternatives and similar repositories for fomoe

Users that are interested in fomoe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?