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

[Model] Fix array out of bounds when rank > 2. #441

Merged
merged 2 commits into from
Jun 6, 2024
Merged

[Model] Fix array out of bounds when rank > 2. #441

merged 2 commits into from
Jun 6, 2024

Conversation

Duyi-Wang
Copy link
Contributor

No description provided.

@Duyi-Wang Duyi-Wang linked an issue Jun 6, 2024 that may be closed by this pull request
Crash when using CB mode with multi-rank #440
Closed
@Duyi-Wang Duyi-Wang added bug Something isn't working continuous batching continuous batching labels Jun 6, 2024
pujiang2018
pujiang2018 approved these changes Jun 6, 2024
View reviewed changes
Copy link
Contributor

@pujiang2018 pujiang2018 left a comment

Choose a reason for hiding this comment

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

Next version, we may not need FP32 for logits.

@Duyi-Wang
Copy link
Contributor Author

Duyi-Wang commented Jun 6, 2024 •
edited
Loading

Next version, we may not need FP32 for logits.

It can reduce communication overhead, but we still need to convert to FP32 when passed to Python for sampling....
We can do the convert and reorder at the same time.

@Duyi-Wang Duyi-Wang merged commit ba79f6f into intel:main Jun 6, 2024
1 check passed
@Duyi-Wang Duyi-Wang deleted the fix_multi_rank_cb_issue branch June 6, 2024 08:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@pujiang2018 pujiang2018 pujiang2018 approved these changes

Assignees
No one assigned
Labels
bug Something isn't working continuous batching continuous batching
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Crash when using CB mode with multi-rank
2 participants
@Duyi-Wang @pujiang2018