fix cuda ut fail caused by used instructions for base model#1994
Merged
Conversation
n1ck-guo
changed the title
Signed-off-by: n1ck-guo <heng.guo@intel.com>
n1ck-guo
force-pushed
the
hengguo/fix_release_ut
branch
from
c9f999f to
4dc74e2
Compare
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes CUDA unit test flakiness by changing the default generation sanity-check prompt from an instruction-following task to a completion-style prompt that is more reliable for base (non-instruction-tuned) models after quantization.
Changes:
- Updated
eval_generated_promptdefaults to use a completion-style prompt ("United States of"→ expects"America"). - Added an inline comment explaining why instruction-style prompts are avoided for base models in this check.
Contributor
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines could not run because the pipeline triggers exclude this branch/path. |
chensuyue
approved these changes
Jul 6, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Please briefly describe your main changes, the motivation.
Type of Change
Bug fix
Related Issues
Fixes or relates to #
Checklist Before Submitting
/azp run Unit-Test-CUDA-AutoRound.