flash-attn-4
Flash Attention CUTE (CUDA Template Engine) implementation
- Category
- Python packages
pip install flash-attn-4 Official docs outline
flash-attn-4.readthedocs.ioExtra Credit builds an outline of flash-attn-4's docs the first time your work uses it. Until then, start at the official documentation.
More in Python packages
All 9,553-
microsoft-agents-authentication-msal A msal-based authentication library for Microsoft Agents
-
mypy-boto3-qapps Type annotations for boto3 QApps 1.43.0 service generated with mypy-boto3-builder 8.12.0
-
pedalboard A Python library for adding effects to audio.
-
nvidia-cuda-tileiras TileIR Assembler Package
-
sudachidict-full Sudachi Dictionary for SudachiPy - Full Edition
-
microsoft-teams-apps The app package for a Microsoft Teams agent
-
pyandoc Python wrapper for Pandoc - the universal document converter
-
coveralls Show coverage stats online via coveralls.io
-
fickling A static analyzer and interpreter for Python pickle data
-
flash-linear-attention Fast linear attention models and layers
-
mgrs MGRS coordinate conversion for Python
-
habluetooth High availability Bluetooth