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

How to use GPU? #99

Closed
SwayStar123 opened this issue Feb 24, 2024 · 1 comment · Fixed by #103
Closed

How to use GPU? #99

SwayStar123 opened this issue Feb 24, 2024 · 1 comment · Fixed by #103
Labels
📙 documentation ❓ question

Comments

@SwayStar123
Copy link

Even with
let model_params = LlamaModelParams::default().with_n_gpu_layers(10000);
Everything seems to run on the cpu, nothing gets run on the gpu. Do i need to do anything else to run the model on the gpu?
@MarcusDunn
Copy link
Contributor

MarcusDunn commented Feb 24, 2024 •
edited
Loading

Ensure that you've enabled the cublas feature. (I'm assuming you have a Nvidia GPU)

Other accelerators are unsupported at the moment, but should just take some build script adjustments to get working.

I'll add something to docs about available features.

@MarcusDunn MarcusDunn linked a pull request Feb 25, 2024 that will close this issue
added docs for cublas support #103
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
📙 documentation ❓ question
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

added docs for cublas support utilityai/llama-cpp-rs
2 participants
@SwayStar123 @MarcusDunn