You can deploy this model and start earning money today!

niknah/
flash-attention-windows-wheel

Name: flash-attention-windows-wheel
Availability: InStock

Views

No views yet

To compile flash attention for windows...

Install visual studio build tools.
Start a new windows terminal. Click "+" -> "developer command prompt for VS"
set CUDA_HOME=%CUDA_PATH_V13_0% Or whatever your version of CUDA is.
Follow instructions in https://huggingface.co/lldacing/flash-attention-windows-wheel
Leave your computer on overnight to compile it. (Might run faster if you change MAX_JOBS= in the script)

After upgrading major things like CUDA, python, you will need to upgrade just about everything else. If you upgrade to something just released recently, you may need the git version.

I have included sageattention if you have problems installing it. (https://github.com/thu-ml/SageAttention/issues/242)

You may also need to install xformers from the latest...

pip uninstall xformers pip install -v --no-build-isolation -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers

niknah/flash-attention-windows-wheel

To compile flash attention for windows...

niknah/
flash-attention-windows-wheel