SakanaAI/
Cuda kernels for leveraging LLM sparsity to improve throughput and decrease the memory requirements during inference and training.
by Sakana AI Cuda MIT licence 27 forks Created Mar 2026 View on GitHub
- Stars
- 263
- 1% of SakanaAI's stars
- Rank
- #220,815
- of 851,979 repos, top 26%
Among 851,979 repos
250–400 stars: 77,404 repos, including sparser-faster-llms
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 #220,054
- Next milestone
- +93 stars to reach the top 20%
- Popular
- One of 490,661 repos with 100+ stars