Add Int4 and UInt4 support for Cast #24973
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
tianleiwu
reviewed
Jun 6, 2025
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
tianleiwu
reviewed
Jul 22, 2025
tianleiwu
reviewed
Jul 22, 2025
tianleiwu
approved these changes
Jul 22, 2025
sanketkaleoss
pushed a commit
to sanketkaleoss/onnxruntime
that referenced
this pull request
Aug 11, 2025
Add Int4 and UInt4 support for `Cast`. There were a few QNN pipelines [failing](https://aiinfra.visualstudio.com/PublicPackages/_build/results?buildId=841810&view=logs&j=9d976e38-31ec-50dd-b1f8-279fbf889fca&t=85ed5ad3-b72a-52c3-abe0-a87b66004fd0&l=1773) for this PR, which are fixed by this onnx PR [Update input and output tensors in pb files to match the model](onnx/onnx#7074). The problem is that onnxruntime, which uses onnx as a submodule in `cmake/external/onnx`, points to the latest release of onnx (1.18.0), but in order to have the pipeline run with my onnx fix, we would need to point to a newer version. Since we can't update the onnx submodule to point to a non-release commit, waiting for a new onnx release might take a long time, and creating a patch under [onnxruntime/cmake/patches/onnx](https://github.com/microsoft/onnxruntime/tree/main/cmake/patches/onnx) with the changes in my onnx PR is tricky because that fix changes some binary files, this PR skips the tests which are currently failing in the QNN pipelines.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add Int4 and UInt4 support for
Cast.There were a few QNN pipelines failing for this PR, which are fixed by this onnx PR Update input and output tensors in pb files to match the model. The problem is that onnxruntime, which uses onnx as a submodule in
cmake/external/onnx, points to the latest release of onnx (1.18.0), but in order to have the pipeline run with my onnx fix, we would need to point to a newer version.Since we can't update the onnx submodule to point to a non-release commit, waiting for a new onnx release might take a long time, and creating a patch under onnxruntime/cmake/patches/onnx with the changes in my onnx PR is tricky because that fix changes some binary files, this PR skips the tests which are currently failing in the QNN pipelines.