Quantization user guide

This quantization user guide is organized into the following sections.

AIMET features

AIMET features gives an overview of the quantization and other tools available in AIMET.

Quantization workflow

Quantization workflow is a step-by-step guide to preparing a model for deployment on a target device using AIMET.

Debugging guidelines

Debugging guidelines provides steps to improve the performance of a quantized model.

On-target inference

On-target inference describes how to deploy a quantized model to a target runtime.