ByteDance-Seed/
Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
by ByteDance-Seed Python Apache-2.0 licence 11 forks Created Feb 2025 View on GitHub
- Stars
- 172
- 1% of ByteDance-Seed's stars
- Rank
- #313,981
- of 852,180 repos, top 37%
- In Python
- #61,392
- of 173,254 repos, top 36%
Among 852,180 repos
160–250 stars: 104,143 repos, including FlexPrefill
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 #312,478
- Next milestone
- +49 stars to reach the top 30%
- Popular
- One of 490,958 repos with 100+ stars
- Yearly average
- 99 stars a year since Feb 2025