thu-ml/SpargeAttn

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

↗ Open on GitHub

Stars

1,047

Forks

104

Language

Cuda

License

Apache-2.0

Last push

6 months ago

Cuda video-generation llm quantization attention vision-transformer sparse-attention vit ai-infra inference-acceleration mlsys sageattention

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.