skip invalid test case for helios pipeline#13218
Merged
yiyixuxu merged 4 commits intohuggingface:mainfrom Mar 18, 2026
Merged
Conversation
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
Contributor
Author
|
@DN6 pls help review, thx! |
Contributor
Author
|
@yiyixuxu Hi, can you help review? Thx! |
Collaborator
|
hey @kaixuanliu did I miss anything? |
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
Contributor
Author
|
@yiyixuxu Thx for the comment! Yes, I am afraid you are right. But for this pipeline, it has a lot of modules using mixed precision, such as: keep_in_fp32_module, FP32LayerNorm, L435-L437 and HeliosOutputNorm, hence I suggest to skip this test case like in WanVACE pipeline, and I have updated the skip reason. Do you think it is OK? |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In helios pipeline, the latents are always in FP32 format: L798, hence we should skip the test_save_load_float16 test case, rather than adjust the tolerance.