Skip to content

Conversation

@chaya2350
Copy link

Description

This PR adds support for ONNX LpNormalization operator opset 22 on CPU execution provider.

Changes

  • Register LpNormalization kernel for opset 1-21 (versioned)
  • Add new LpNormalization kernel for opset 22
  • Support both float and double data types
  • Update kernel registry in CPU execution provider

Related Issue

Fixes #27160

Testing

  • Build completed successfully
  • All CPU provider tests passed
  • LpNormalization tests verified

- Register LpNormalization kernel for opset 1-21 (versioned)
- Add new LpNormalization kernel for opset 22
- Support both float and double data types
- Update kernel registry in CPU execution provider

Fixes: microsoft#27160
- Register LpNormalization kernel for opset 1-21 (versioned)
- Add new LpNormalization kernel for opset 22
- Support both float and double data types
- Update kernel registry in CPU execution provider

Fixes: microsoft#27160
@chaya2350
Copy link
Author

@titaiwangms Could you please review this PR? It fixes the issue you reported. Thanks! 🙂

The duplicate declarations were causing kernel registration conflicts.
Only keep the declarations in the correct section (lines 199-200).
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.

LpNormalization-22 is not registered

1 participant