Qualcomm AI Engine Direct - Adding QNN backend support for reflection_pad1/2d core ATen ops#18963
Merged
abhinaykukkadapu merged 1 commit intopytorch:mainfrom Apr 20, 2026
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18963
Note: Links to docs will display an error until the docs builds have been completed. ⏳ 33 Pending, 1 Unrelated FailureAs of commit 8b7a7bd with merge base 401ea8e ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Contributor
Author
|
@pytorchbot label "release notes: qualcomm" |
abhinaykukkadapu
approved these changes
Apr 20, 2026
Contributor
|
Thanks for adding support. |
abhinaykukkadapu
approved these changes
Apr 20, 2026
…_pad1/2d core ATen ops
3c17a6f to
8b7a7bd
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Added support for the aten ops
reflection_pad1dandreflection_pad2d. Both ops use the QNNpadop usingmode=reflectwith a decomposition duringto_edgeand extra padding in the2dcase. Theop_padbuilder was extended to handle these ops.Note that we cannot currently support
reflection_pad3deasily, because the input rank forMIRROR_REFLECTis constrained to <5 for the QNN op. We can support it by decomposing the op into2dslices, but that seems complicated and bug-prone, so I just added implementation for the 1d and 2dreflection_padops for now.Test plan
Also ran the existing tests for the
padop to make sure nothing was broken with the existing implementation: