Tutorial Overview

In this documentation, we provide tutorials on how to use the Mobilint® Compiler SDK, qubee. The qubee compiler is a tool that compiles deep learning models into Mobilint IR (MXQ) format, which can be executed on Mobilint devices such as ARIES and REGULUS.

The examples below demonstrate how to compile commonly used open-source deep learning models, including ResNet50, YOLOv8, and Llama-3.2, from start to finish, from preparing the calibration dataset to compiling the model.

We assume you have already installed the Mobilint Compiler SDK, qubee on the provided Docker container. If you have not installed it yet, please refer to the installation section.