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.

Sign up for GitHub

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

Jump to bottom

Failed to run RealESRGAN_x4plus_fp16_t1024_torchscript.onnx model with dxdispatch tool #542

Open
mingmingtasd opened this issue Jan 4, 2024 · 2 comments
Open

Failed to run RealESRGAN_x4plus_fp16_t1024_torchscript.onnx model with dxdispatch tool #542

mingmingtasd opened this issue Jan 4, 2024 · 2 comments

Comments

@mingmingtasd
Copy link
Contributor

mingmingtasd commented Jan 4, 2024 •
edited

image

As the screenshot above, dxdispatch tool can't run RealESRGAN_x4plus_fp16_t1024_torchscript.onnx model. I have located the root cause is: IDMLBindingTable::BindTemporaryResource will fail and remove dml device, maybe because the temporary resource size is too big (6 GB).
The DirectML Debug Layer Tool will report:

image

@fdwr I reproduced this issue with dxdispatch tool, this should be a native issue.
@fdwr
Copy link
Contributor

fdwr commented Jan 12, 2024

And to clarify, this GPU had 8GB total, right?

@mingmingtasd
Copy link
Contributor Author

And to clarify, this GPU had 8GB total, right?

The GPU is NVIDIA GeForce GT 1030 with 17.9 GB total memory.

Edition Windows 11 Pro
Version 22H2
Installed on ‎3/‎6/‎2023
OS build 22621.3007
Experience Windows Feature Experience Pack 1000.22681.1000.0

image

Notice that creating the temporary committed resource can succeed, but binding it fails.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@fdwr @mingmingtasd