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

feat: Parallelise Model Loading #360

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

feat: Parallelise Model Loading #360

wants to merge 4 commits into from
+60 −18

Conversation

vovw
Copy link

@vovw vovw commented Oct 17, 2024 •
edited
Loading

test using

exo --preload-models llama-3.2-1b,llama-3.1-8b

@vovw vovw mentioned this pull request Oct 17, 2024
Open
@AlexCheema
Copy link
Contributor

Almost what I envisioned - only thing I would change is to preload after the preemptive download. We don't want to download all possible model shards, only the relevant one.

@vovw
Copy link
Author

vovw commented Oct 18, 2024

@AlexCheema I think I got it, can you review the changes ??

AlexCheema
AlexCheema requested changes Oct 18, 2024
View reviewed changes
exo/main.py Outdated Show resolved Hide resolved
@vovw
Copy link
Author

vovw commented Oct 19, 2024

tested on a m3 pro

@vovw vovw requested a review from AlexCheema October 19, 2024 23:08
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@AlexCheema AlexCheema Awaiting requested review from AlexCheema

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
@vovw @AlexCheema