PTQ#
Or updating an existing operator to a new Opset version.
Table of Contents#
[Nvidia PTQ](#Nvidia PTQ Principle)
[Ptq configuration file description](#nvidia ptq configuration file description)
[performance comparison](#nvidia performance comparison)
[QNN PTQ](#QNN PTQ Principle)
[Ptq configuration file description](#qnn ptq configuration file description)
[performance comparison](#qnn performance comparison)
Nvidia PTQ Principle#
Operators are the basic building blocks used to define ONNX models. With a rich set of operators, ONNX can describe most DNN and ML models from various frameworks. Functions enable expressing complex operators in terms of more primitive operators. The ONNX specification includes a core set of operators that enable many models. It is a non-goal to add all possible operators, however more operators are added as needed to cover evolving needs.
In this document, we describe the process of accepting a new proposed operator and how to properly submit a new operator as part of ONNX standard. The goal is to improve on what we currently have based on our experience, learning and feedbacks we gathered from the community.
nvidia ptq configuration file description#
nvidia performance comparison#
QNN PTQ Principle#
Operators are the basic building blocks used to define ONNX models. With a rich set of operators, ONNX can describe most DNN and ML models from various frameworks. Functions enable expressing complex operators in terms of more primitive operators. The ONNX specification includes a core set of operators that enable many models. It is a non-goal to add all possible operators, however more operators are added as needed to cover evolving needs.
In this document, we describe the process of accepting a new proposed operator and how to properly submit a new operator as part of ONNX standard. The goal is to improve on what we currently have based on our experience, learning and feedbacks we gathered from the community.