thu-ml/SpargeAttn

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

Inference & local LLMCuda Apache-2.0 108created 2025-02-25

Stars

1,267

1-day growth

—

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

The chart appears after at least 2 days of data.

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

Top contributors

Not collected yet (contributors job).