mit-han-lab/
[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
by MIT HAN Lab Python MIT licence 44 forks Created Oct 2024 View on GitHub
- Stars
- 545
- 1% of mit-han-lab's stars
- Rank
- #116,530
- of 851,984 repos, top 14%
- In Python
- #21,640
- of 173,300 repos, top 13%
Among 851,984 repos
400–630 stars: 51,570 repos, including duo-attention
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 #116,340
- Next milestone
- +222 stars to reach the top 10%
- Popular
- One of 490,652 repos with 100+ stars
- Yearly average
- 262 stars a year since Oct 2024