Adjust tolerance for quantized XNN conv1d tests #8093
Conversation
< 10000 div class="pull-discussion-timeline js-pull-discussion-timeline js-quote-selection-container js-review-state-classes" data-quote-markdown=".js-comment-body" data-discussion-hovercards-enabled data-issue-and-pr-hovercards-enabled data-team-hovercards-enabled data-hpc >
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/8093
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: ⏳ No Failures, 1 PendingAs of commit 3ea5560 with merge base ce93291 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
digantdesai
reviewed
Jan 31, 2025
| tester.to_executorch().serialize().run_method_and_compare_outputs( | ||
| num_runs=10, atol=0.01, rtol=0.01 | ||
| ) | ||
| tester.to_executorch().serialize() |
There was a problem hiding this comment.
Might be ok but feels like sliding under the rug 😄
As an alternative, does it make sense to mark it as flaky (I know this is not the correct use of the flaky tag but..) so the unit-tests won't block CI and create a task to look into it?
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Outdated suggestions cannot be applied.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
Quantized conv1d tests are flaky due to tolerance being too low. This PR bumps the tolerance slightly. This should be safe, as the underlying kernels are believed to be correct and this issue has been observed for some time (not a recent regression in kernel accuracy).
Test plan
Ran tests locally for 1000 iterations and did not observe any failures.