Cleanup XNN delegate post removal of upsample decomposition #8910
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/8910
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit 0246ac2 with merge base a828307 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Summary: Following the removal of the decompositions for upsample_bilinear2d in PyTorch, we don't need to pattern match and recompose upsample_bilinear2d. This PR cleans up the convert_to_upsample_bilinear2d pass and associated logic. Differential Revision: D68374585
|
This pull request was exported from Phabricator. Differential Revision: D68374585 |
|
This pull request was exported from Phabricator. Differential Revision: D68374585 |
GregoryComer
force-pushed
the
export-D68374585
branch
from
2e5be22 to
84c76fc
Compare
|
Yeah if it is now impossible to ever get a decomposed op then this is a good BE work. Thanks @GregoryComer . |
digantdesai
approved these changes
Mar 4, 2025
|
nice dead code! |
mcr229
approved these changes
Mar 4, 2025
|
Thanks. With pytorch/pytorch#147153, we should never see a decomposed upsample unless it somehow gets manually added to the decomp table. It's core and is now never decomposed by default. |
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Outdated suggestions cannot be applied.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: Following the removal of the decompositions for upsample_bilinear2d in PyTorch, we don't need to pattern match and recompose upsample_bilinear2d. This PR cleans up the convert_to_upsample_bilinear2d pass and associated logic.
Differential Revision: D68374585