KY
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.
Growth
- Last 24 hours
- +0
- stars
- Last 7 days
- +2
- stars
- Last 30 days
- +5
- stars
- Total stars
- 23
- 18 a month ago
- Forks
- 1
- 0 contributors
Star history
Last 12 weeks · weekly cumulative stars · computed from public GitHub star events
Rank in its topics
| Topic | Today | This week | This month |
|---|---|---|---|
| Python | – | – | – |
| LLM | – | – | – |
| Machine learning | – | – | – |
README
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.
Upstar hasn’t fetched this README yet. Read it on GitHub.