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.

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

optimize lookahead init time #11769

Merged
merged 1 commit into from
Aug 12, 2024

Conversation

rnwang04
Copy link
Contributor

@rnwang04 rnwang04 commented Aug 12, 2024

Description

1. Why the change?

  • fix abnormal first token time of lookahead
  • update qwen2 exmaple to use fp16+int4

2. User API changes

No.

3. Summary of the change

  • fix abnormal first token time of lookahead
    4k baseline time: 5999.75
    lookahead time: 10181.13
    with this PR, lookahead time: 6056.97

4. How to test?

  • Unit test: Please manually trigger the PR Validation here by inputting the PR number (e.g., 1234). And paste your action link here once it has been successfully finished.

@rnwang04 rnwang04 requested a review from jason-dai August 12, 2024 09:05
Copy link
Contributor

@jason-dai jason-dai left a comment

Choose a reason for hiding this comment

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

LGTM

@rnwang04 rnwang04 merged commit 8db3405 into intel-analytics:main Aug 12, 2024
1 check passed
@rnwang04 rnwang04 deleted the optimize_lookahead_init branch August 12, 2024 09:19
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants