-
Notifications
You must be signed in to change notification settings - Fork 216
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
model.to('xpu') does not terminate #614
Comments
Hi, I'm afraid the support for iGPU is in the roadmap of IPEX evolution, but so far this is not the case, so it's possible to get stability or performance issues. Please keep tuned for this support, thanks. |
Hi, this might because the official release doesn't include iGPU AOT, you can try the community version at least for MTL https://github.com/Nuullll/intel-extension-for-pytorch/releases |
Yeah, I communicated offline with the reporter that we could try source code build with AOT code "0x7d55". Of course the community version is worth to try. |
Describe the issue
When trying to upload a simple model to 'xpu' device, the script is taking a lot of time, and also doesn't finish.
Firstly tried with a resnet50, but after that with the simplest tensor (got the same problem):
and got the same issue:
The text was updated successfully, but these errors were encountered: