thu-ml/
[ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.
by TSAIL group Python Other licence 13 forks Created Dec 2024 View on GitHub
- Stars
- 123
- <1% of thu-ml's stars
- Rank
- #413,082
- of 852,180 repos, top 49%
- In Python
- #82,015
- of 173,254 repos, top 48%
Among 852,180 repos
100–160 stars: 155,671 repos, including ReMoE
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #410,466
- Next milestone
- +33 stars to reach the top 40%
- Popular
- One of 490,958 repos with 100+ stars
- Yearly average
- 64 stars a year since Dec 2024