SecondNatureComputing
/

flash-attn-4-sm120

flash-attention

Model card Files Files and versions

flash-attn-4-sm120 / build /torch-cuda /__pycache__ /interface.cpython-313.pyc

blake-snc's picture

Restructure: build/torch-cuda/ layout with relative imports for self-contained kernels.get_kernel() use

02fc236 verified 3 months ago

History Contribute Delete

81.2 kB

This file contains binary data. It cannot be displayed, but you can still download it.