Reading the repo
Opening the box…
Reading the repo
Opening the box…
Assembly instructions
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
Saved setup from 1 h ago
Will it work on macOS?
Choose one way. Most people should use the recommended one; the rest are other options.
pip install sageattention==2.2.0 --no-build-isolation
pip install sageattention==1.0.6
From the README, exactly as the maintainers wrote it.
No reports for macOS yet.
GitManual AI Agent reads the 4 key files and writes a step-by-step guide for macOS. Once written, it's saved for everyone.