```{toctree}
:hidden:
:maxdepth: 2
:caption: Get Started
Introduction <self>
Installation <installation.md>
Quick Start <quick_start.md>
```

```{toctree}
:hidden:
:maxdepth: 2
:caption: Tutorial
Overview <tutorial_overview.md>
Classification models <tutorial_classification.md>
YOLO models <tutorial_yolo.md>
LLM models <tutorial_llm.md>
```

```{toctree}
:hidden:
:maxdepth: 2
:caption: Capabilities
Supported Frameworks <supported.md>
CPU Offloading <cpu_offloading.md>
```

```{toctree}
:hidden:
:maxdepth: 2
:caption: Reference
API <../doxygen/html_en/group__API>
Classes <../doxygen/html_en/annotated_classes>
Files <../doxygen/html_en/files>
Deprecated List <../doxygen/html_en/deprecated>
Changelog <CHANGELOG.md>
Revisions <revisions.md>
License <license.md>
```

# Introduction
Mobilint® Model Compiler (i.e., Compiler) is a tool that converts models from deep learning frameworks (ONNX, PyTorch, Keras, TensorFlow, etc...) into Mobilint® Model eXeCUtable (i.e., MXQ), a format executable by Mobilint® Neural Processing Unit (NPU). This is the **qbcompiler**, Mobilint's SDK documentation. In this documentation, you can learn how to use it, what frameworks it supports, etc. A set of functions you can use to interact with the SDK will be given below. An input to qbcompiler is a trained deep learning model, its input shape, and calibration data. It will return MXQ (compiled model) as an output.

![SDK Components](../res/image/qbcompiler.jpg "SDK Components"){width="60%" align="center"}