Skip to content

[Feature Request] Consider support int4/uint4 for reshape op of default CPU EP #24285

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

Open
lisa0314 opened this issue Apr 3, 2025 · 0 comments
Labels
ep:WebNN WebNN execution provider feature request request for unsupported feature or enhancement

Comments

@lisa0314
Copy link

lisa0314 commented Apr 3, 2025

Describe the feature request

ONNX opset 21 added support for int4 and uint4 of reshape op. So I suppose default CPU EP should support int4 and uint4 data type for reshape op.

Describe scenario use case

For WebNN use case, we need to insert reshape before scale and zeroPoint for dequantizeLinear implementation since ONNX constrains scale and zeroPoint(if exits) must be 1D tensor for per-axis dequantizeLinear. In some scenarios, the data type of zero_point is int4 or uint4.

@lisa0314 lisa0314 added the feature request request for unsupported feature or enhancement label Apr 3, 2025
@github-actions github-actions bot added the ep:WebNN WebNN execution provider label Apr 3, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ep:WebNN WebNN execution provider feature request request for unsupported feature or enhancement
Projects
None yet
Development

No branches or pull requests

1 participant