Can you suggest a way regarding how I can export an INT8 Quantized PyTorch model to ONNX/Openvino?
I found GitHub - openvinotoolkit/nncf: Neural Network Compression Framework for enhanced OpenVINO™ inference
Do you have a better suggestion?
Can you suggest a way regarding how I can export an INT8 Quantized PyTorch model to ONNX/Openvino?
I found GitHub - openvinotoolkit/nncf: Neural Network Compression Framework for enhanced OpenVINO™ inference
Do you have a better suggestion?