[QNN EP] Add support for GatherNd Op in QNN EP #25635
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
- Added new op builder for GatherNd Op - Added unit tests for GatherNd and QDQ tests - Disabled two tests in ORT test as QNN CPU does not support negative indices
Contributor
|
/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline |
|
Azure Pipelines successfully started running 5 pipeline(s). |
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for the GatherND operation in the QNN Execution Provider. The implementation handles quantized and non-quantized models, supports different index types, and includes proper shape handling and type casting.
Key changes:
- Added complete GatherND op builder implementation with index processing and casting
- Added comprehensive test coverage for both QDQ and non-QDQ GatherND scenarios
- Disabled specific CPU tests that use negative indices due to QNN CPU limitations
Reviewed Changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| gather_nd_op_builder.cc | Complete GatherND op builder implementation with index handling and type casting |
| gather_op_htp_test.cc | Added comprehensive test cases for GatherND including QDQ variants |
| gather_nd_op_test.cc | Disabled negative index tests for QNN CPU compatibility |
| op_builder_factory.h | Added function declaration for GatherND op builder |
| op_builder_factory.cc | Registered GatherND op builder in factory |
Comments suppressed due to low confidence (2)
onnxruntime/core/providers/qnn/builder/opbuilder/gather_nd_op_builder.cc:68
- The comment mentions converting int64 to uint32, but the function template converts to int32. The comment should be updated to reflect the actual conversion to int32.
}
onnxruntime/core/providers/qnn/builder/opbuilder/gather_nd_op_builder.cc:70
- The data_shape parameter is passed by non-const reference but is only read from. It should be passed by const reference for better API design.
Status GatherNDOpBuilder::ProcessInputs(QnnModelWrapper& qnn_model_wrapper,
onnxruntime/core/providers/qnn/builder/opbuilder/gather_nd_op_builder.cc
Show resolved
Hide resolved
onnxruntime/core/providers/qnn/builder/opbuilder/gather_nd_op_builder.cc
Show resolved
Hide resolved
sanketkaleoss
pushed a commit
to sanketkaleoss/onnxruntime
that referenced
this pull request
Aug 11, 2025
- Added new op builder for GatherNd Op - Added unit tests for GatherNd and QDQ tests - Disabled two tests in ORT test as QNN CPU does not support negative indices ### Description Adding support for GatherNd op in QNN EP ### Motivation and Context Currently GatherNd op is not supported in QNN EP and hence falls back to ORT CPU.
gedoensmax
pushed a commit
to gedoensmax/onnxruntime
that referenced
this pull request
Sep 2, 2025
- Added new op builder for GatherNd Op - Added unit tests for GatherNd and QDQ tests - Disabled two tests in ORT test as QNN CPU does not support negative indices ### Description Adding support for GatherNd op in QNN EP ### Motivation and Context Currently GatherNd op is not supported in QNN EP and hence falls back to ORT CPU.
qti-yuduo
pushed a commit
to CodeLinaro/onnxruntime
that referenced
this pull request
Sep 24, 2025
- pick microsoft#25584 - pick microsoft#25635 - pick microsoft#25673 - pick microsoft#25702 - pick microsoft#25738
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Description
Adding support for GatherNd op in QNN EP
Motivation and Context
Currently GatherNd op is not supported in QNN EP and hence falls back to ORT CPU.