thu-ml/SageAttention
[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.
[view on github]last commit: Jan 17, 2026
stars
3,427
7d
+11
30d
-
90d
-
## star history