# thu-ml/spargeattn

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/thu-ml-spargeattn).**

1,005 stars · 95 forks · Cuda · Apache-2.0

## Links

- GitHub: https://github.com/thu-ml/SpargeAttn
- Homepage: https://arxiv.org/abs/2502.18137
- awesome-repositories: https://awesome-repositories.com/repository/thu-ml-spargeattn.md

## Description

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

## Tags

### Part of an Awesome List

- [Attention Optimization](https://awesome-repositories.com/f/awesome-lists/ai/attention-optimization.md) — Accurate sparse attention for general model inference.