Not fully utilizing apple silicon gpu

by satvikahuja - opened Oct 7

Oct 7

•

I see that during inference, the gpu is not fully utilized and the cpu becomes fully used.
How can i fully use my gpu?

edit: i am getting faster speed and better utilisation when i am running on pytorch, anyway how could get better speeds while using coreml?

Oct 7

Hi Satvikahuja, I'm not a specialist, but do you try to convert the code for CoreML?

Let me know if these documents help you. Good luck

satvikahuja changed discussion status to closed Oct 7

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment