fix: enforce correct pass thresholds for deterministic and approximate tests (core_r0.17.0)#4314
Draft
ko3n1g wants to merge 2 commits intoNVIDIA:core_r0.17.0from
Draft
Conversation
…e tests Cherry-pick of 4e85d74 (common.py only) from main onto core_r0.17.0. - Deterministic tests and single-step evaluations now require all steps to pass (np.all), rather than a loose ratio-based threshold. - Approximate tests keep the ratio-based check but with a corrected formula: `>= 1 - (num_failing_steps_allowed / total_steps_evaluated)` instead of `>= (num_failing_steps_allowed / total_steps_evaluated)`. Signed-off-by: oliver könig <okoenig@nvidia.com> Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> Signed-off-by: oliver könig <okoenig@nvidia.com>
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
Contributor
Author
|
/ok to test |
Co-authored-by: Kunlun Li <kunlunl@cw-dfw-cs-001-login-02.cm.cluster>
Contributor
Author
|
/ok to test |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Cherry-picks from `main` onto `core_r0.17.0`:
`4e85d74` — Pass threshold fixes in `common.py`
Example — why the old formula was wrong:
```
Old (wrong): passes if mean(is_close) >= 1/100 = 0.01 → almost always passes
New (correct): passes if mean(is_close) >= 1 - 1/100 = 0.99 → requires 99/100 steps to pass
```
`76371d4` — Fix UT timeout
Restructures `test_attention_variant_dsa.py` to fix unit test timeouts.
Test plan
🤖 Generated with Claude Code