Skip to content

Latest commit

 

History

History
9 lines (6 loc) · 354 Bytes

README.md

File metadata and controls

9 lines (6 loc) · 354 Bytes

Native Sparse Attention PyTorch

Native Sparse Attention

PyTorch implementation of Native Sparse Attention.

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention.