Skip to content

Disable RMSNorm in onnx_backend_test.py and Topk(uint_64) #25056

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

Conversation

titaiwangms
Copy link
Contributor

Missing test failures from ONNX 1.18 integration.

  1. The RMSNorm test models is invalid in terms of ONNX spec (e.g. Model rms_normalization_2d_axis1_expanded failed to load:Node () Op (Range) [ShapeInferenceError] Input to 'Range' op should be scalars (Tensor with only one element and shape empty)).
    Screenshot 2025-06-13 120308

  2. TopK with uint64 is currently not supported.

@titaiwangms titaiwangms marked this pull request as ready for review June 13, 2025 23:25
@titaiwangms
Copy link
Contributor Author

@snnn @tianleiwu I think this should be able to skip the failing onnx backend tests that are added since ONNX==1.18.0 (I have not tested it on CI machine though.).

@titaiwangms titaiwangms merged commit ece0c1e into microsoft:main Jun 16, 2025
85 of 88 checks passed
titaiwangms added a commit that referenced this pull request Jun 16, 2025
misspelled in #25056 
topk with uint64 is currently not supported in ORT
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

Successfully merging this pull request may close these issues.

2 participants