How to use int8 model with openvino

[oldma3095]

Describe the issue

I have used NNCF on the model to get three files: best.xml, best.bin, and metadata.yaml.
How to use them in the openvino C/C++ API of onnxruntime.

To reproduce

best.xml
best.bin
metadata.yaml

Urgency

No response

Platform

Linux

OS Version

ubuntu

ONNX Runtime Installation

Released Package

ONNX Runtime Version or Commit ID

1.17.1

ONNX Runtime API

C

Architecture

X64

Execution Provider

OpenVINO

Execution Provider Library Version

No response

[sfatimar]

NNCF will give ONNX Format also as output for Post Training Quantization. https://github.com/openvinotoolkit/nncf/blob/develop/docs/compression_algorithms/post_training/Quantization.md

https://github.com/openvinotoolkit/nncf/blob/develop/docs/compression_algorithms/Quantization.md will also give Pytorch Model as output which can be converted to ONNX

[github-actions]

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.