Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Generate: force caching on the main model, in assisted generation #24177

Merged
merged 1 commit into from
Jun 12, 2023

Conversation

gante
Copy link
Member

@gante gante commented Jun 11, 2023

What does this PR do?

Fixes #23686

Caching is a requirement in assisted generation -- we even check for it (here).

However, it was still possible for the main model to run without cache. This PR fixes it.

@gante gante requested a review from amyeroberts June 11, 2023 18:06
@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Jun 11, 2023

The documentation is not available anymore as the PR was closed or merged.

Copy link
Collaborator

@amyeroberts amyeroberts left a comment

Choose a reason for hiding this comment

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

Thanks for fixing!

@gante gante merged commit 9f81f4f into huggingface:main Jun 12, 2023
@gante gante deleted the 23686 branch June 12, 2023 13:10
novice03 pushed a commit to novice03/transformers that referenced this pull request Jun 23, 2023
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.

support for model.generate with assistant_model / model being load_in_8bit and PeftModel (LoRA)
3 participants