[QNN-EP] Support non-last axis TopK. #24881
Open
+230
−44
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
QNN only accepts TopK on the last axis but ONNX/ORT's TopK has axis attribute. In TopK op builder, add Transpose around TopK to permute the axis to the last before and permute back after. Additionally, since TopK's second output is indices which may have INT64 dtype, add Cast to cast transformed INT32 back to INT64 if is graph output.
|
/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). |
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Outdated suggestions cannot be applied.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.
Description
In TopK op builder, add Transpose around TopK to permute the axis to the last before and permute back after.
Additionally, since TopK's second output is indices which may have INT64 dtype, add Cast to cast transformed INT32 back to INT64 if is graph output.
Motivation and Context
QNN only accepts TopK on the last axis but ONNX/ORT's TopK has axis attribute. Complement TopK op builder to avoid falling back to CPU for non-last axis TopK.