Increase calibration samples and tolerance for flaky quantized op tests #7990
+27
−8
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/7990
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 2dbb0c5 with merge base 06ef713 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
YIWENX14
pushed a commit
that referenced
this pull request
Jan 28, 2025
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Outdated suggestions cannot be applied.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
Several tests, including test_add_qs8 and test_qs8_conv1d, are failing intermittently. This PR adds additional calibration samples to reduce dependence on the single input sample and adjusts test tolerance accordingly.
Note: We likely want to expose calibration_samples as a numeric option in the tester, in addition to the logic I added to pass in samples. If we can re-use generate_random_inputs, that would be ideal, though it requires a little refactoring to make it available from inside of a stage. We can take that as a follow-up.
Test plan
Re-ran the above failing tests 10k times (100 full runs with 100 iterations of run_method_and_compare_outputs).