Skip to content

Conversation

@a-r-r-o-w
Copy link
Contributor

Fixes #10566.

I overlooked this part during the integration. Since we're operating on the embedding dimension, there's no need to concatenate across the sequence dimension

@a-r-r-o-w a-r-r-o-w requested a review from yiyixuxu February 13, 2025 20:50
@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.

Copy link
Collaborator

@yiyixuxu yiyixuxu left a comment

Choose a reason for hiding this comment

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

thanks!

@yiyixuxu yiyixuxu merged commit ab42820 into main Feb 13, 2025
15 checks passed
@yiyixuxu yiyixuxu deleted the refactor/cogvideox-transformer-layernorm branch February 13, 2025 22:11
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.

Unnecessary operations in CogVideoXTransformer3DModel.forward()?

4 participants