Adjust atol/rtol for ring attention's quantized kv cache test #13909
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/13909
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 PendingAs of commit b9b28e0 with merge base cac1a71 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
kimishpatel
requested review from
jackzhxng and
metascroy
and removed request for
jackzhxng
kimishpatel
added
the
release notes: none
Summary: In another PR, #13722, for whatever reason, this test was failing. Adjusting the margin here since I have seen this fail before on trunk but somehow it got resolved. So there is some level of flakiness particularly around quantized kv cache + ring attention Test Plan: CI Reviewers: Subscribers: Tasks: Tags:
kimishpatel
force-pushed
the
fix_ring_attention_tests
branch
from
9192afd to
b9b28e0
Compare
jackzhxng
approved these changes
Sep 3, 2025
metascroy
approved these changes
Sep 3, 2025
metascroy
reviewed
Sep 3, 2025
| else: | ||
| # For quantized kv cache we need bigger margin | ||
| self.assertTrue( | ||
| torch.allclose(baseline_out, ring_out, rtol=1e-6, atol=1e-6), |
There was a problem hiding this comment.
Is baseline also quantized?
There was a problem hiding this comment.
yes. baseline is also quantized. I dont quite know why for the PR in summary it is failing but I had observed some flakiness in the past. So this is to just unblock myself. This is actually not reproducible either on my end
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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:
In another PR, #13722, for whatever reason, this test was failing. Adjusting the margin here since I have seen this fail before on trunk but somehow it got resolved. So there is some level of flakiness particularly around quantized kv cache
Test Plan:
CI
Reviewers:
Subscribers:
Tasks:
Tags:
Summary
[PLEASE REMOVE] See CONTRIBUTING.md's Pull Requests for ExecuTorch PR guidelines.
[PLEASE REMOVE] If this PR closes an issue, please add a
Fixes #<issue-id>line.[PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: " label. For a list of available release notes labels, check out CONTRIBUTING.md's Pull Requests.
Test plan
[PLEASE REMOVE] How did you test this PR? Please write down any manual commands you used and note down tests that you have written if applicable.