Open Hakur0uken opened 7 months ago
The situation you encountered is the same as mine, it is missing the selective_scan_cuda library. I would like to know how to install this library.
CPU is not supported by the package selective_scan_cuda_oflex
or mamba_ssm
, so make sure you are using GPU.
To install selective_scan_cuda_oflex
, you can cd into that directory and pip install .
.
To install mamba_ssm
, you can refer to mamba
.
You can choose to install one of mamba_ssm
or selective_scan_cuda_oflex
, both works fine, with only speed difference.
I'm new to the field of deep learning. My model was trained using GPU, and I don't encounter any issues when using GPU for inference. However, when I try to deploy it on a CPU device, I encounter an error:RuntimeError: Expected u.is_cuda() to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.) Does this mean that I can only use GPU for inference?