[Modular] Fix dtype assignment when type hint is AutoModel#13271
Open
[Modular] Fix dtype assignment when type hint is AutoModel#13271
Conversation
DN6
commented
Mar 16, 2026
|
|
||
| if self.type_hint is None: | ||
| try: | ||
| from diffusers import AutoModel |
Collaborator
Author
There was a problem hiding this comment.
Moved this up because now we need to import AutoModel regardless of whether type_hint is provided or not.
|
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. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Oversight on my part when adding #13168. We avoid passing
torch_dtypeto nonnn.Modulessuch as Processors and Tokenizers because these objects do not accept that anymore and instead store it in init_kwargs which then throw an error during serialization. However, I neglected the fact thatAutoModeldoes not subclassModelMixin, so iftype_hintis set to diffusersAutoModelthe check evaluates toTrueand we skip passingtorch_dtypeThis PR fixes the issue by checking whether
type_hintisAutoModelFixes # (issue)
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
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.