Update XNN delegate to handle non-decomposed upsample ops #7770
Conversation
This file contains 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/7770
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 4d85c0f with merge base fedb035 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D68374352 |
GregoryComer
changed the title
GregoryComer
added a commit
to GregoryComer/executorch
that referenced
this pull request
Jan 19, 2025
Summary: Pull Request resolved: pytorch#7770 Differential Revision: D68374352
GregoryComer
force-pushed
the
export-D68374352
branch
from
add1567 to
a6a3f93
Compare
|
This pull request was exported from Phabricator. Differential Revision: D68374352 |
GregoryComer
added a commit
to GregoryComer/executorch
that referenced
this pull request
Jan 19, 2025
Summary: I'm preparing to disable decomposition by default for core upsample ops in pytorch/pytorch#141791. This PR makes changes to ExecuTorch to handle non-decomposed upsample_bilinear2d. There are tests that expect the decomposition when not delegated, as well as a recomposition pass in the XNNPACK delegate which need updates to function. The changes in this PR are intended to work with both the decomposed and non-decomposed upsample ops. After the decomposition change lands in PyTorch, I will clean up the remaining ExecuTorch usages. Differential Revision: D68374352
GregoryComer
force-pushed
the
export-D68374352
branch
from
a6a3f93 to
cde514e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D68374352 |
Summary: I'm preparing to disable decomposition by default for core upsample ops in pytorch/pytorch#141791. This PR makes changes to ExecuTorch to handle non-decomposed upsample_bilinear2d. There are tests that expect the decomposition when not delegated, as well as a recomposition pass in the XNNPACK delegate which need updates to function. The changes in this PR are intended to work with both the decomposed and non-decomposed upsample ops. After the decomposition change lands in PyTorch, I will clean up the remaining ExecuTorch usages. Differential Revision: D68374352
GregoryComer
force-pushed
the
export-D68374352
branch
from
cde514e to
4d85c0f
Compare
|
This pull request was exported from Phabricator. Differential Revision: D68374352 |
digantdesai
approved these changes
Jan 21, 2025
YIWENX14
pushed a commit
that referenced
this pull request
Jan 28, 2025
Differential Revision: D68374352 Pull Request resolved: #7770
zonglinpeng
pushed a commit
to zonglinpeng/executorch
that referenced
this pull request
Jan 30, 2025
Differential Revision: D68374352 Pull Request resolved: pytorch#7770
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.
Differential Revision: D68374352
I'm preparing to disable decomposition by default for core upsample ops in pytorch/pytorch#141791. This PR makes changes to ExecuTorch to handle non-decomposed upsample_bilinear2d. There are tests that expect the decomposition when not delegated, as well as a recomposition pass in the XNNPACK delegate which need updates to function.
The changes in this PR are intended to work with both the decomposed and non-decomposed upsample ops. After the decomposition change lands in PyTorch, I will clean up the remaining ExecuTorch usages.