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

Fix pipeline parallel inference past_key_value error in Baichuan #11318

Merged
merged 7 commits into from
Jun 17, 2024
Merged

Fix pipeline parallel inference past_key_value error in Baichuan #11318

merged 7 commits into from
Jun 17, 2024

Conversation

sgwhat
Copy link
Contributor

@sgwhat sgwhat commented Jun 14, 2024 •
edited
Loading

Description

This PR mainly supports past_key_values with tuple type in pipeline parallel inference.

1. Why the change?

Currently we only support past_key_values with DynamicCache.

2. User API changes

N/A

3. Summary of the change

  • Add dummy past_key_value for dummy layer.

4. How to test?

  • Local test
  • Unit test

@sgwhat sgwhat requested a review from plusbang June 14, 2024 06:50
plusbang
plusbang approved these changes Jun 14, 2024
View reviewed changes
Copy link
Contributor

@plusbang plusbang left a comment

Choose a reason for hiding this comment

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

Please also update verified model list in README.

@sgwhat sgwhat merged commit be00380 into intel-analytics:main Jun 17, 2024
30 of 31 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@plusbang plusbang plusbang approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@sgwhat @plusbang