Relax XNN quantized conv1d test tolerances #15666
Merged
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/15666
Note: Links to docs will display an error until the docs builds have been completed. ⏳ 5 Pending, 1 Unrelated FailureAs of commit cca4dd3 with merge base 3405317 ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
GregoryComer
added
the
release notes: none
metascroy
approved these changes
Nov 7, 2025
GregoryComer
force-pushed
the
fix-xnn-conv1d-test
branch
from
61cd18b to
cca4dd3
Compare
GregoryComer
changed the title
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Outdated suggestions cannot be applied.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
The test_qs8_conv1d_batchnorm_seq test is periodically failing in CI due to being out of tolerance. From looking at the numbers, I believe this is due to an overly tight tolerance when quantizing. The error reported in https://github.com/pytorch/executorch/actions/runs/19147331216/job/54728231147#step:9:19945, for example, is 0.03, which seems large, but given that the output range is 6, that's roughly 1/200th. With 8-bit quant, that's not unreasonable. I've updated the tolerance in the test to reflect this.