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鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

ONNX docs missing info about how to remove custom domains #128698

Open
Jerry-Master opened this issue Jun 14, 2024 · 0 comments
Open

ONNX docs missing info about how to remove custom domains #128698

Jerry-Master opened this issue Jun 14, 2024 · 0 comments
Labels
module: docs Related to our documentation, both in docs/ and docblocks module: onnx Related to torch.onnx triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module

Comments

@Jerry-Master
Copy link

Jerry-Master commented Jun 14, 2024

馃摎 The doc issue

In the docs about exporting to onnx here there is not a mention of how to remove the functions. The use of aten operators defined as functions creates a problem when converting to tensorrt. When visualizing with netron the functions are composed of simpler official ai.onnx operators which have support for tensorrt but not the custom exported aten operators. There should be a way to save the models without using functions and custom operators and just export the raw operators even if that means more repetitions, but it would make models exportable to tensorrt.

Suggest a potential alternative/fix

No response

cc @svekars @brycebortree

@malfet malfet added module: onnx Related to torch.onnx module: docs Related to our documentation, both in docs/ and docblocks triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module labels Jun 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
module: docs Related to our documentation, both in docs/ and docblocks module: onnx Related to torch.onnx triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Projects
None yet
Development

No branches or pull requests

2 participants