Skip to content

CUDA acceleration doesn't seem to work #1445

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
Closed
megupta opened this issue May 14, 2023 · 1 comment
Closed

CUDA acceleration doesn't seem to work #1445

megupta opened this issue May 14, 2023 · 1 comment

Comments

@megupta
Copy link

megupta commented May 14, 2023 •
edited
Loading

I compiled the latest code in this repo with cuBLAS support as described in the README

It doesn't seem to be utilizing my 1070 although main is running in nvidia-smi

llama_model_load_internal: [cublas] offloading 0 layers to GPU
llama_model_load_internal: [cublas] total VRAM used: 0 MB

What am I missing here?
@FSSRepo
Copy link
Collaborator

FSSRepo commented May 14, 2023 •
edited
Loading

Add the option -ngl 10, for upload 10 layers to your gpu memory

@Bearsaerker Bearsaerker mentioned this issue Mar 12, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@Green-Sky @megupta @FSSRepo