deepseek-ai/
FlashMLA: Efficient Multi-head Latent Attention Kernels
by DeepSeek C++ MIT licence 1,274 forks Created Feb 2025 View on GitHub
- Stars
- 13,261
- 2% of deepseek-ai's stars
- Rank
- #4,052
- of 852,204 repos, top 0.5%
- Down 8 places this week
- In C++
- #200
- of 45,409 repos, top 0.4%
Among 852,204 repos
10k–16k stars: 2,596 repos, including FlashMLA
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
- +13 stars to reach #4,051
- Next milestone
- +24,879 stars to reach the top 0.1%
- Popular
- One of 5,759 repos with 10k+ stars
- Yearly average
- 7,691 stars a year since Feb 2025