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

Check if kv_cache is tuple before calling split_kv_cache #697

Merged
merged 1 commit into from
Jan 17, 2025
Merged

Check if kv_cache is tuple before calling split_kv_cache #697

merged 1 commit into from
Jan 17, 2025

Conversation

kdamaszk
Copy link

@kdamaszk kdamaszk commented Jan 17, 2025 •
edited by github-actions bot
Loading

After last rebase mllama is broken. During the prompt kv_cache is a torch.Tensor([0]) instead of None like before. It is probably caused by new function bind_kv_cache that is called during preparation of inputs.
This fix is checking also if kv_cache is a tuple before calling split_kv_cache function.

@kdamaszk kdamaszk added the habana Issues or PRs submitted by Habana Labs label Jan 17, 2025
madamczykhabana
madamczykhabana approved these changes Jan 17, 2025
View reviewed changes
Copy link

@madamczykhabana madamczykhabana left a comment

Choose a reason for hiding this comment

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

lgtm

@kdamaszk kdamaszk merged commit a685225 into habana_main Jan 17, 2025
33 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@madamczykhabana madamczykhabana madamczykhabana approved these changes

@kzawora-intel kzawora-intel Awaiting requested review from kzawora-intel kzawora-intel is a code owner

@michalkuligowski michalkuligowski Awaiting requested review from michalkuligowski michalkuligowski is a code owner

@mgawarkiewicz mgawarkiewicz Awaiting requested review from mgawarkiewicz mgawarkiewicz is a code owner

@vivekgoe vivekgoe Awaiting requested review from vivekgoe vivekgoe is a code owner

@afierka-intel afierka-intel Awaiting requested review from afierka-intel afierka-intel is a code owner

Assignees
No one assigned
Labels
habana Issues or PRs submitted by Habana Labs
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@kdamaszk @madamczykhabana