Update some remove ops passes to correctly set their modified bit #16065
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16065
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 New Failure, 1 Unrelated FailureAs of commit 4cdb90b with merge base 4014597 ( NEW FAILURE - The following job has failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
DrJessop
pushed a commit
to DrJessop/executorch
that referenced
this pull request
Dec 3, 2025
…torch#16065) Summary: Updated - RemoveNopSelectOpPass - RemovePermutesAroundElementwiseOps Differential Revision: D87895473
DrJessop
force-pushed
the
export-D87895473
branch
from
1544f43 to
be11b4f
Compare
added 6 commits
December 5, 2025 10:12
Summary: Updated - ReplaceAtenAvgPoolWithCadenceAvgPoolPass - ReplaceIm2RowWithViewPass - ReplaceEmptyTensorsWithFullPass (doesn't use new interface, just correctly only runs full export pass if necessary) - ReplaceWhereWithFullArgsWithWhereScalar - ReplaceMulTensorWithMulAndFullOpsPass - ReplaceAdaptiveAvgPoolWithAtenAvgPoolPass Reviewed By: hsharma35 Differential Revision: D87877176
…entations Summary: Updated - FuseCascadedViewOps - ReplaceAtenConvolutionWithCadenceConvolutionPass - ReplaceTransposedConvWithLinearPass - ReplaceNopTransposeOrPermuteWithViewPass - ReplaceLinearWithFullyConnectedOpPass to use the new efficient pass interface which also correctly sets the modified bit. Also fix the transposed_im2row since numerical validation was failing for tests that introduced those ops. Differential Revision: D87837579
…mostPass to correctly set modified bit Summary: As titled Differential Revision: D87880891
Summary: Updated - FuseMMWithAdd - FuseOpPairsAcrossBranchesPass - FuseQuantDequantToRequantizePass - FuseTransposeOrPermuteOpPairsPass - FuseFullThenReshapePass And modified tests for those passes to run numerical validation. Additionally, fixed a test which was providing wrong dtypes for requant Differential Revision: D87885581
…FuseMulTensorIntoDequantPass to use new pass interface Summary: Updates - FuseMulScalarIntoDequantPass - FuseMulTensorIntoDequantPass - FuseMulTensorIntoQuantPass Differential Revision: D87887841
…torch#16065) Summary: Updated - RemoveNopSelectOpPass - RemovePermutesAroundElementwiseOps Differential Revision: D87895473
DrJessop
force-pushed
the
export-D87895473
branch
from
be11b4f to
4cdb90b
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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:
Updated
Differential Revision: D87895473