Reapply "Add EXECUTORCH_THREADPOOL_SIZE options, default to u… (#14307)#14842
Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14842
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 1 PendingAs of commit 0cea48f with merge base 2672dd3 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
GregoryComer
force-pushed
the
reapply-thread-defaults
branch
2 times, most recently
from
7b16cb4 to
4db5e01
Compare
GregoryComer
force-pushed
the
reapply-thread-defaults
branch
from
4db5e01 to
0cea48f
Compare
GregoryComer
requested review from
kimishpatel,
kirklandsign,
larryliu0820 and
swolchok
as code owners
GregoryComer
added
the
release notes: api
Member
Author
|
Voxtral CI failure is due to running on a fork. Samsung failure is also pre-existing. |
kimishpatel
approved these changes
Oct 8, 2025
kimishpatel
left a comment
kimishpatel
left a comment
Contributor
There was a problem hiding this comment.
assuming this is reapply. stamping
Member
Author
Yeah, this is a direct re-apply of the previously landed PR. Thanks. |
jirioc
pushed a commit
to nxp-upstream/executorch
that referenced
this pull request
Dec 19, 2025
…ch#14307) (pytorch#14842) This reverts commit 750cba7. Re-applying the better threadpool size defaults from pytorch#14090 with the fix from pytorch#14838. This gives a 2-4x speedup for many models and platforms (I measured 4x speedup on M1 with MobileNet V3 + XNNPACK). On high core count server platforms (doing evals, for example), this can give a 100x speedup out of box.
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.
This reverts commit 750cba7.
Re-applying the better threadpool size defaults from #14090 with the fix from #14838. This gives a 2-4x speedup for many models and platforms (I measured 4x speedup on M1 with MobileNet V3 + XNNPACK). On high core count server platforms (doing evals, for example), this can give a 100x speedup out of box.