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

Inference on Large models with Multiple GPUs #166

Open

hvgazula opened this issue Nov 27, 2023 · 1 comment

Assignees

Collaborator

hvgazula commented Nov 27, 2023

large models > 30b parameters. explore using accelerate/fabric.

hvgazula self-assigned this

Collaborator Author

hvgazula commented Nov 27, 2023

since we are already using accelerate, set device_map="auto" in *.from_pretrained() and we should be good to go.

Note: explore quantization as well.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment