mit-han-lab/
[MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
by MIT HAN Lab C++ Apache-2.0 licence 74 forks Created May 2024 View on GitHub
- Stars
- 867
- 2% of mit-han-lab's stars
- Rank
- #75,924
- of 851,984 repos, top 9%
- In C++
- #3,966
- of 45,406 repos, top 9%
Among 851,984 repos
630–1k stars: 35,594 repos, including omniserve
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 #75,836
- Next milestone
- +6,353 stars to reach the top 1%
- Popular
- One of 490,652 repos with 100+ stars
- Yearly average
- 344 stars a year since May 2024