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.

Sign up for GitHub

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

Jump to bottom

repeats audio_features tensor, just like tokens tensor, by group size… #2389

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

repeats audio_features tensor, just like tokens tensor, by group size… #2389

wants to merge 1 commit into from

Conversation

Majdoddin
Copy link
Contributor

… for beam search or best-of-n sampling.

If run with batch of size 1, the current code does not raise an error, because of Pytorch's Broadcasting. But by bigger batch sizes it raises error.

@Majdoddin
repeats audio_features tensor, just like tokens tensor, by group size…
2aafd81 
… for beam search or best-of-n sampling, to avoid size mismatch error in attention by batch inference
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@Majdoddin