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

minimum required Memory #169

Open
nfloquet opened this issue Jan 29, 2025 · 2 comments
Open

minimum required Memory #169

nfloquet opened this issue Jan 29, 2025 · 2 comments

Comments

@nfloquet
Copy link

Hello, i have two NVIDIA GeForce RTX 2080 with each 8192 Mb memory. Impossible to achieve any job for now ... because of "WARNING: ran out of memory, skipping batch" message. Do you think it would be possible and i missed something or my GPU are clearly not sufficient to run jobs on my local machine ? Can i use both GPUs for one same job ? how to proceed for this ?

Thanks !

@gcorso
Copy link
Collaborator

gcorso commented Jan 29, 2025

Hi @nfloquet, unfortunately 8GB is probably not enough to run any "medium scale" complex at this point and we have not yet implemented ways to shard predictions across multiple GPUs

@nfloquet
Copy link
Author

thanks gabriele for this quick answer, will use it only remotely then

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

No branches or pull requests

2 participants