Getting CoreML to run inference on already allocated gpu buffers

Machine Learning & AI Core ML
CeNiEi OP
Created 17h
Replies 0
Boosts 0
Views 95
Participants 1

I am running some experiments with WebGPU using the wgpu crate in rust. I have some Buffers already allocated in the GPU.

Is it possible to use those already existing buffers directly as inputs to a predict call in CoreML? I want to prevent gpu to cpu download time as much as possible.

Or are there any other ways to do something like this. Is this only possible using the latest Tensor object which came out with Metal 4 ?

Replies  0
Boosts  0
Views  95
Participants  1
Getting CoreML to run inference on already allocated gpu buffers
First post date Last post date
 
 
Q