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

python binding does not use explicitly requested NVIDIA GPU #2387

Open
cebtenzzre opened this issue May 29, 2024 · 0 comments
Open

python binding does not use explicitly requested NVIDIA GPU #2387

cebtenzzre opened this issue May 29, 2024 · 0 comments
Labels
backend gpt4all-backend issues python-bindings gpt4all-bindings Python specific issues

Comments

@cebtenzzre
Copy link
Member

gpu - NVIDIA GeForce RTX 3050 Laptop GPU
model - tinyllama-1.1b-chat-v1.0.Q8_0.gguf
os - Windows 11

When I use GPT4All UI, it uses the gpu while prompting.

But when I try to prompt in my notebook, it loads the model with above gpu set as device without any error.

GPT4All("path\\to\\tinyllama-1.1b-chat-v1.0.Q8_0.gguf", device='NVIDIA GeForce RTX 3050 Laptop GPU')

But, when I prompt, it doesn't use the gpu memory, only uses cpu (in task manager). How can I run gpu?

Originally posted by @soumenseth in #1843 (comment)

@cebtenzzre cebtenzzre added backend gpt4all-backend issues python-bindings gpt4all-bindings Python specific issues labels May 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
backend gpt4all-backend issues python-bindings gpt4all-bindings Python specific issues
Projects
None yet
Development

No branches or pull requests

1 participant