Skip to content

Fix: filter Cosmos3 warnings for auxiliary FP8 export scales - #15107

Open
yzhautouskay wants to merge 2 commits into
huggingface:mainfrom
yzhautouskay:yzhautouskay/cosmos3_fp8_warn_filter
Open

yzhautouskay wants to merge 2 commits into
huggingface:mainfrom
yzhautouskay:yzhautouskay/cosmos3_fp8_warn_filter

Conversation

@yzhautouskay

@yzhautouskay yzhautouskay commented Oct 22, 2026 •

Copy link
Copy Markdown
Contributor

What does this PR do?

Ignore the auxiliary input_scale and weight_scale keys exported for vLLM-Omni/SGLang when loading Cosmos3 in Diffusers. Preserve warnings for unrelated unexpected weights and add regression coverage

Before submitting

  • Did you use an AI agent (Claude Code, Codex, Cursor, etc.) to help with this PR? If so:
    • Did you read the Coding with AI agents guide?
    • Did you run the self-review skill on the diff?
    • Did you share the final self-review notes in the PR description or a comment?
  • Did you read the contributor guideline?
  • Did you read our philosophy doc? (important for complex PRs)
  • Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?
  • Are you the author (or part of the team) of the model/pipeline (only applicable for model/pipeline related PRs)?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@github-actions

Copy link
Copy Markdown
Contributor

Hi @yzhautouskay, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. Fixes #1234) to the PR description so the issue is linked. See the contribution guide for more details. If this PR intentionally does not fix a tracked issue, a maintainer can add the no-issue-needed label to silence this reminder.

Please note that PRs without a linked issue are likely to be automatically closed 10 days after this notice.

Once the PR links an issue (or gets the no-issue-needed label), you can ignore this message — it stays here as a comment, but it no longer applies.

@yiyixuxu yiyixuxu added the no-issue-needed for PRs that do not require link to an issue label Oct 27, 2026
@yiyixuxu

Copy link
Copy Markdown
Collaborator

@yzhautouskay
if you check this author box in our PR template, you won't get this bot message #15107 (comment)

Before submitting

  • ...
  • Are you the author (or part of the team) of the model/pipeline (only applicable for model/pipeline related PRs)?

@HuggingFaceDocBuilderDev

Copy link
Copy Markdown

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.


class TestCosmos3OmniTransformerModel(Cosmos3OmniTransformerTesterConfig, ModelTesterMixin):
@pytest.mark.parametrize("include_unexpected_weight", [False, True])
def test_load_ignores_export_scales(self, tmp_path, include_unexpected_weight):

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ohh i think we don't need the test this per model
cc @sayakpaul, do we want to add a generic test for this instead?

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

#15140

@yzhautouskay I think let's wait for #15140 so that you could rebase it in your PR and this PR will then just be about the src/diffusers/models/transformers/transformer_cosmos3.py change?

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

models no-issue-needed for PRs that do not require link to an issue size/S PR with diff < 50 LOC tests

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants