Closed ankitm3k closed 1 month ago
This PR adds new options to enable devices during inference runtime for machines having a iGPU (GPU.0) and dGPU (GPU.1)
We are now able to run inference with device_type as AUTO:GPU.1,CPU and further more combinations
LGTM
Description
This PR adds new options to enable devices during inference runtime for machines having a iGPU (GPU.0) and dGPU (GPU.1)
Motivation and Context
We are now able to run inference with device_type as AUTO:GPU.1,CPU and further more combinations