microsoft / microsoft/onnxruntime

Does onnxruntime-openvino EP only use the operator acceleration of openvino?

Open
#14,726 2 comments 1 reaction 1 assignee View on GitHub

@HectorSVC is already working on this.

Since Feb 18, 2023.

ep:OpenVINO
Dominant language
C++
Stars
21.9k
Forks
4.2k
Avg merge
4d 11h
Merged PRs (30d)
184

Description

### Describe the issue

I want to ask about the underlying principle of onnxruntime EP.

### To reproduce

Because I found that the multithreading mechanism of onnxruntime seems to be different from that of openvino.

If onnxruntime-openvino is used, will ort use vino's asynchronous multithreading library? Or is it just using vino's optimization for graph optimization and operator optimization, and ort's is still useing his own Multi-thread mechanism?

There is another problem here. onnxruntime will optimize the Computational Graph, and openvino will also optimize the Computational Graph. If you use openvino EP, how do you know whose graph optimization is the best?

Thank you very much.

### Urgency

_No response_

### Platform

Linux

### OS Version

20.04

### ONNX Runtime Installation

Released Package

### ONNX Runtime Version or Commit ID

lastest

### ONNX Runtime API

Python

### Architecture

X64

### Execution Provider

Default CPU

### Execution Provider Library Version

_No response_

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.