microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
https://onnxruntime.ai
MIT License
13.59k stars 2.77k forks source link

Device selection through onnxruntime-directml #18716

Open ramkrishna2910 opened 7 months ago

ramkrishna2910 commented 7 months ago

Describe the issue

Hi,

I am using directml through onnxruntime and my platform has multiple directx 12 supported devices. Is there a recommended way to enumerate and select specific devices through python APIs?

Thanks

To reproduce

ort.InferenceSession API does not provide an option for device selection.

onnx_session = ort.InferenceSession(onnx_file_path, sess_options, providers=['DmlExecutionProvider'])

Urgency

No response

Platform

Windows

OS Version

10

ONNX Runtime Installation

Released Package

ONNX Runtime Version or Commit ID

1.15.1

ONNX Runtime API

Python

Architecture

X64

Execution Provider

DirectML

Execution Provider Library Version

No response

github-actions[bot] commented 6 months ago

This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details.