Skip to content

feat: add pretrained orbax cache for fast WAN inference loads#406

Draft
csgoogle wants to merge 1 commit into
mainfrom
wan-orbax-checkpoint-cache
Draft

feat: add pretrained orbax cache for fast WAN inference loads#406
csgoogle wants to merge 1 commit into
mainfrom
wan-orbax-checkpoint-cache

Conversation

@csgoogle
Copy link
Copy Markdown
Collaborator

No description provided.

@github-actions
Copy link
Copy Markdown

Copy link
Copy Markdown
Collaborator

@Perseus14 Perseus14 left a comment

Choose a reason for hiding this comment

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

Can you also add this for the other WAN models?

Comment on lines +92 to +93
def _get_pretrained_orbax_dir(self) -> str:
return getattr(self.config, "pretrained_orbax_dir", "")
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.

Do we need this function? We could just directly use getattr(self.config, "pretrained_orbax_dir", "") as it is only needed in one place. Also should the default value be None instead of ""

Comment on lines +92 to +93
def _get_pretrained_orbax_dir(self) -> str:
return getattr(self.config, "pretrained_orbax_dir", "")
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.

Same as above

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.

2 participants