efficient-attention

Here is 1 public repository matching this topic...

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.

cuda triton attention vit quantization video-generation mlsys inference-acceleration efficient-attention llm llm-infra video-generate

Updated Jan 17, 2026
Cuda

Add this topic to your repo

To associate your repository with the efficient-attention topic, visit your repo's landing page and select "manage topics."

Learn more