Skip to content

Conversation

@JingyaHuang
Copy link
Collaborator

What does this PR do?

TP size was not considered for diffusers before Flux, thus Optimum Neuron was unable to identify cached Flux artifacts, this PR would fix it.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you make sure to update the documentation with your changes?
  • Did you write any new necessary tests?

@HuggingFaceDocBuilderDev

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.

"timm >= 1.0.0",
"hf_transfer",
"torchcodec",
"torchcodec < 0.6.0",
Copy link
Collaborator

Choose a reason for hiding this comment

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

I think this conflicts with the changes in pr #935

Copy link
Collaborator

@dacorvo dacorvo left a comment

Choose a reason for hiding this comment

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

LGTM, thanks !

@dacorvo dacorvo merged commit 33d7f7d into main Aug 25, 2025
7 of 10 checks passed
@dacorvo dacorvo deleted the improve-flux-cache branch August 25, 2025 07:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants