Metadata-Version: 2.4
Name: sgl-fa4
Version: 4.0.5
Summary: Flash Attention CUTE (CUDA Template Engine) implementation
Author: Tri Dao
License: BSD 3-Clause License
Project-URL: Homepage, https://github.com/Dao-AILab/flash-attention
Project-URL: Repository, https://github.com/Dao-AILab/flash-attention
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: BSD License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: nvidia-cutlass-dsl==4.3.5
Requires-Dist: torch
Requires-Dist: einops
Requires-Dist: typing_extensions
Requires-Dist: apache-tvm-ffi<0.2,>=0.1.5
Requires-Dist: torch-c-dlpack-ext
Requires-Dist: quack-kernels==0.2.4
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: ruff; extra == "dev"
