Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Detecting cuda but not using it. #412

Closed
2 of 9 tasks
tikendraw opened this issue Jan 20, 2024 · 5 comments
Closed
2 of 9 tasks

Detecting cuda but not using it. #412

tikendraw opened this issue Jan 20, 2024 · 5 comments

Comments

@tikendraw
Copy link

Describe the bug
Roop is detecting the GPU, but not using it.

Details
What OS are you using?

  • Linux
  • Linux in WSL
  • Windows
  • Mac

Are you using a GPU?

  • No. CPU FTW
  • NVIDIA
  • AMD
  • Intel
  • Mac

Which version of roop unleashed are you using?
jan 20, 2024 git pull

Screenshots
Screenshot from 2024-01-20 19-40-16

@C0untFloyd
Copy link
Owner

Your CUDA version is not suuported currently, please see #400

@C0untFloyd C0untFloyd closed this as not planned Won't fix, can't repro, duplicate, stale Jan 20, 2024
@tikendraw
Copy link
Author

Your CUDA version is not suuported currently, please see #400

Will converting this ONNX model to latest model work?

import onnx
from onnx import version_converter

model_path = Path("models")
dest_path = Path('converted_models')

for model_ in model_path.iterdir():
	if str(model_).endswith('onnx'):
		dest_path_model = dest_path/model_.name
		print(dest_path_model)

		model = onnx.load(model_)
		converted_model = version_converter.convert_version(model, 11)
		onnx.save(converted_model, dest_path_model)

@C0untFloyd
Copy link
Owner

I doubt it. The problem isn't the model but the runtime which isn't up to date.

@tikendraw
Copy link
Author

I doubt it. The problem isn't the model but the runtime which isn't up to date.

Somedev's roop is working on this same gpu. how?

@CPioGH2002
Copy link

I had a similar problem and fixed it by installing the not yet final release of ONNX runtime. It uses current CUDA versions, therefore enabling your GPU: #329 (comment)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants