Move output tensor resize to before XNNPACK subgraph execution#17661
Merged
GregoryComer merged 1 commit intopytorch:mainfrom Apr 29, 2026
Merged
Move output tensor resize to before XNNPACK subgraph execution#17661GregoryComer merged 1 commit intopytorch:mainfrom
GregoryComer merged 1 commit intopytorch:mainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17661
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: ✅ You can merge normally! (2 Unrelated Failures)As of commit 3b7281d with merge base 321c029 ( BROKEN TRUNK - The following jobs 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
Contributor
|
@GregoryComer has exported this pull request. If you are a Meta employee, you can view the originating Diff in D94148443. |
GregoryComer
added a commit
to GregoryComer/executorch
that referenced
this pull request
Feb 24, 2026
…ch#17661) Summary: ET's XNNPACK delegate currently resizes output tensors after running the XNNPACK subgraph. This is normally fine, as the buffer is large enough. However, if there is a logic bug or corrupt model file, the current code doesn't catch if XNNPACK's output is larger than the planned buffer until after execution, where it may crash. To fix this, I've moved the resize up. This fails gracefully in the above case. Differential Revision: D94148443
GregoryComer
force-pushed
the
export-D94148443
branch
from
4782781 to
c8a2924
Compare
GregoryComer
added a commit
to GregoryComer/executorch
that referenced
this pull request
Feb 25, 2026
…ch#17661) Summary: ET's XNNPACK delegate currently resizes output tensors after running the XNNPACK subgraph. This is normally fine, as the buffer is large enough. However, if there is a logic bug or corrupt model file, the current code doesn't catch if XNNPACK's output is larger than the planned buffer until after execution, where it may crash. To fix this, I've moved the resize up. This fails gracefully in the above case. Differential Revision: D94148443
GregoryComer
force-pushed
the
export-D94148443
branch
from
c8a2924 to
45ee5c1
Compare
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
…ch#17661) Summary: ET's XNNPACK delegate currently resizes output tensors after running the XNNPACK subgraph. This is normally fine, as the buffer is large enough. However, if there is a logic bug or corrupt model file, the current code doesn't catch if XNNPACK's output is larger than the planned buffer until after execution, where it may crash. To fix this, I've moved the resize up. This fails gracefully in the above case. Differential Revision: D94148443
GregoryComer
force-pushed
the
export-D94148443
branch
from
45ee5c1 to
3b7281d
Compare
GregoryComer
added
the
release notes: none
lucylq
approved these changes
Apr 28, 2026
Contributor
|
@GregoryComer has imported this pull request. If you are a Meta employee, you can view this in D94148443. |
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
2 participants
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:
ET's XNNPACK delegate currently resizes output tensors after running the XNNPACK subgraph. This is normally fine, as the buffer is large enough. However, if there is a logic bug or corrupt model file, the current code doesn't catch if XNNPACK's output is larger than the planned buffer until after execution, where it may crash.
To fix this, I've moved the resize up. This fails gracefully in the above case.
Differential Revision: D94148443