reproduce it under Windows

[pengjunxing]

Can anyone reproduce it under Windows? Can you share the environment configuration and each installation package version?

[siddagra]

Yeah I was able to get it to work in windows using wsl2

[siddagra]

You have to use WSL2 or Linux!!

First you have to make sure you install torch version that matches your nvcc version:

python3 -c 'import torch; print(torch.version.cuda)'
nvcc --version

You can match the versions by installing an older version of torch which uses a different cuda version:

pip3 install -U torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu<major_version><minor_version>

then clone causal conv 1d and pip install:

git clone https://github.com/Dao-AILab/causal-conv1d.git
cd causal_conv1d
git checkout v1.0.2  # this is the highest compatible version allowed by Mamba
CAUSAL_CONV1D_FORCE_BUILD=TRUE pip3 install .

then clone mamba and pip install:

https://github.com/state-spaces/mamba.git
cd mamba
pip3 install .

then clone mamba vision and remove the causal-conv1d and mamba-ssm requirements from requirements.txt as u already have them installed, otherwise it will try to install them again and fail. then pip install mamba vision:

https://github.com/NVlabs/MambaVision.git
**manually remove the causal-conv1d and mamba-ssm requirements from requirements.txt**
cd MambaVision
pip3 install .

[binhpt310]

which version of Python you use sir