Skip to content

AssertionError: Torch not compiled with CUDA enabled on Mac #1680

Description

@prashantSoni14

I'm using Mac and trying to run the this model using Pinokio but getting the error AssertionError: Torch not compiled with CUDA enabled

How I can change it so model will use only CPU or MPS.

Full error trace:

Traceback (most recent call last):
File "/Users/prashantsoni/pinokio/api/wan2gp.git/app/wgp.py", line 49, in
from shared.attention import get_attention_modes, get_supported_attention_modes
File "/Users/prashantsoni/pinokio/api/wan2gp.git/app/shared/attention.py", line 9, in
major, minor = torch.cuda.get_device_capability(None)
File "/Users/prashantsoni/pinokio/api/wan2gp.git/app/env/lib/python3.10/site-packages/torch/cuda/init.py", line 669, in get_device_capability
prop = get_device_properties(device)
File "/Users/prashantsoni/pinokio/api/wan2gp.git/app/env/lib/python3.10/site-packages/torch/cuda/init.py", line 686, in get_device_properties
_lazy_init() # will define _get_device_properties
File "/Users/prashantsoni/pinokio/api/wan2gp.git/app/env/lib/python3.10/site-packages/torch/cuda/init.py", line 471, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions