Repository Issues

kyegomez/Latent-MoE

Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch. A single-file, dependency-light layer you can drop in place of a standard MoE FFN.

View on GitHub
Stars
 (4 stars)
Forks
 (0 forks)
Indexed issues
 (0 indexed issues)
open beginner issues
 (0 open beginner issues)
Latest indexed
Jul 22, 2026
Last GitHub push
Jul 21, 2026
License
Apache License 2.0
Contributing guide
No contributing guide
Code of conduct
No code of conduct
Dominant language
Python
PR merge metrics
 (PR metrics pending)
Beginner labels
No beginner labels indexed

Issues

0 open indexed issues

RSSAtom

No open indexed issues found for this repository.