make KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU #11308
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
KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU Signed-off-by: Matrix Yao <[email protected]>
|
@hlky , pls help review, thx |
hlky
approved these changes
Apr 14, 2025
There was a problem hiding this comment.
Thanks @yao-matrix. This pipeline is not commonly used and already requires high tolerance so no issue increasing it further. If in the future we find some larger difference in required tolerances like 1e-4 on one backend and 1e-3 on another, then we could consider something similar to the expected slice changes where the expected_max_diff is set per backend type.
|
sure, will co-work w/ you to make it once needed |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
loose
expected_max_difffrom5e-1to8e-1to make KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU.