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

optimize qwen2 memory usage again #11520

Merged
merged 1 commit into from
Jul 5, 2024
Merged

optimize qwen2 memory usage again #11520

merged 1 commit into from
Jul 5, 2024

Conversation

MeouSker77
Copy link
Contributor

Description

attention_mask is not required when using sdp_causal and batch_size=1 or generating 2nd+ token, so don't generate it in these cases to save memory

@MeouSker77 MeouSker77 requested a review from rnwang04 July 5, 2024 08:54
@MeouSker77
Copy link
Contributor Author

PR validation: https://github.com/intel-analytics/ipex-llm-workflow/actions/runs/9805767952/job/27076276807

@MeouSker77 MeouSker77 merged commit 7cb09a8 into intel-analytics:main Jul 5, 2024
1 check passed
@MeouSker77 MeouSker77 deleted the optimize-qwen2-mem-again branch July 5, 2024 09:32
RyuKosei pushed a commit to RyuKosei/ipex-llm that referenced this pull request Jul 19, 2024
@MeouSker77
optimize qwen2 memory usage again (intel-analytics#11520)
e46396c
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@rnwang04 rnwang04 rnwang04 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
@MeouSker77 @rnwang04