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

feat(server): auto max_batch_total_tokens for flash att models #630

Merged
merged 19 commits into from
Jul 19, 2023

Conversation

OlivierDehaene
Copy link
Member

No description provided.

@OlivierDehaene OlivierDehaene merged commit fe80f53 into main Jul 19, 2023
5 checks passed
@OlivierDehaene OlivierDehaene deleted the feat/automatic_max branch July 19, 2023 07:31
@flozi00
Copy link
Contributor

flozi00 commented Jul 19, 2023

since this PR is merged I am running OOM all the time, even when the cli arg is set
using the docker container and 48GB GPU
7B model is the smallest i tested

@OlivierDehaene
Copy link
Member Author

Can you open a separate issue with the issue template?

@flozi00 flozi00 mentioned this pull request Jul 19, 2023
4 tasks
@flozi00
Copy link
Contributor

flozi00 commented Jul 19, 2023

found more details and opened issue

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