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

Remove experimental compilation flag for text-generation models #228

Merged
merged 1 commit into from
Sep 14, 2023

Conversation

dacorvo
Copy link
Collaborator

@dacorvo dacorvo commented Sep 14, 2023

Using the --enable-experimental-01 flag speeds up the compilation, but also increases inference latency by 25 to 35 %.

Using this flag speeds up the compilation, but also increases inference
latency by 25 to 35 %.
Copy link
Collaborator

@JingyaHuang JingyaHuang left a comment

Choose a reason for hiding this comment

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

I will remove it from the exporter as well, it looks very risky for the moment.

@dacorvo dacorvo merged commit d3a67fa into main Sep 14, 2023
7 of 13 checks passed
@dacorvo dacorvo deleted the remove_O1_flag branch September 14, 2023 09:22
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.

3 participants