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

Add warnings for FP8 onnx #2531

Merged
merged 1 commit into from
Dec 7, 2023
Merged

Add warnings for FP8 onnx #2531

merged 1 commit into from
Dec 7, 2023

Conversation

umangyadav
Copy link
Member

@umangyadav umangyadav commented Dec 7, 2023

Need to put some warnings.

Can't find a better place other than parser to put these warnings. Ideally warnings should come from API side.

This would work for both C/C++ and Python.

But this wouldn't work if users were to create python or C program themselves. I assume it is not a usecase other than for testing purpose.

@umangyadav umangyadav requested a review from CharlieL7 December 7, 2023 14:47
@umangyadav umangyadav self-assigned this Dec 7, 2023
@umangyadav umangyadav added FP8 issues related to FP8 implemenation skip bot checks Skips the Performance and Accuracy CI tests simple small or simple changes labels Dec 7, 2023
@umangyadav
Copy link
Member Author

@pfultz2 can't find your username for some reason in reviewers list. Therefore pinging here manually.

@causten causten merged commit dfc18d6 into develop Dec 7, 2023
13 of 20 checks passed
@causten causten deleted the add_fp8_warnings branch December 7, 2023 16:32
@pfultz2
Copy link
Collaborator

pfultz2 commented Dec 7, 2023

You could put this warning in the compile step, that way it warns whether it was created manually, onnx or tensorflow.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
FP8 issues related to FP8 implemenation simple small or simple changes skip bot checks Skips the Performance and Accuracy CI tests
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants