# Tutorials

This section contains helpful tutorials that assist users to become familiar with the Qualcomm® AI Engine Direct workflow,
and to be able to interact with Qualcomm® AI Engine Direct API and tools to enable their deep learning based use-cases.

## Getting Started

- [Tutorial: Executing your model on your target device](https://docs.qualcomm.com/doc/80-63442-10/topic/tutorial_convert_execute_cnn_model.html)
- [Using the Sample App: Compile and run an app that uses your model](https://docs.qualcomm.com/doc/80-63442-10/topic/tutorial_tutorial_sample_app_linux.html)
- [Writing Your Own Sample App Tutorial: Create your own C++ application](https://docs.qualcomm.com/doc/80-63442-10/topic/sample_app.html)
- [Saver Tutorial: Save execution sequence with Saver and replay on a backend](https://docs.qualcomm.com/doc/80-63442-10/topic/saver_tutorial.html)

## Getting Started for Auto

For a complete guide to which pages apply to your chipset and target environment,
see the [Auto Platform Overview](https://docs.qualcomm.com/doc/80-63442-10/topic/auto_overview.html).

### Run Your First Model

- [HTP Backend on SA-series (LA GVM and LV GVM)](https://docs.qualcomm.com/doc/80-63442-10/topic/htp_auto_tutorial_2.html)
- [GPU Backend on SA-series (LV GVM)](https://docs.qualcomm.com/doc/80-63442-10/topic/gpu_auto_tutorial_2.html)
- [HTP and LPAI on SA8797 QC Linux PVM](https://docs.qualcomm.com/doc/80-63442-10/topic/htp_auto_qclinux.html)
- [HTP Emulation on x86 using QEMU (evaluation)](https://docs.qualcomm.com/doc/80-63442-10/topic/htp_auto_qemu.html)

### Custom Op Packages — Auto

- [HTP with Custom Ops on SA-series (LA GVM and LV GVM)](https://docs.qualcomm.com/doc/80-63442-10/topic/htp_auto_tutorial_3.html)

### Optimize — Auto

- [Selecting NSP0 or NSP1 for HTP execution](https://docs.qualcomm.com/doc/80-63442-10/topic/htp_auto_single_nsp.html)
- [HTP and HTP MCP optimization (O=3, P-points, performance estimates)](https://docs.qualcomm.com/doc/80-63442-10/topic/htp_auto_optimization.html)

## Advanced

- [QNN HTP Shared Buffer Tutorial](https://docs.qualcomm.com/doc/80-63442-10/topic/htp_shared_buffer_tutorial.html)

## Custom Operators

- [Executing a shallow model using custom op package](https://docs.qualcomm.com/doc/80-63442-10/topic/tutorial1.html)
- [Converting and executing a CNN model with custom operations](https://docs.qualcomm.com/doc/80-63442-10/topic/general_tutorial3.html)

## Migrating

- [Migrating from Hexagon-nn to QNN](https://docs.qualcomm.com/doc/80-63442-10/topic/hexnn_migration.html)

## LoRA (Low Rank Adaptation)

- [LoRA Introduction](https://docs.qualcomm.com/doc/80-63442-10/topic/lora_intro.html)
- [LoRA v2](https://docs.qualcomm.com/doc/80-63442-10/topic/lora_v2_0_overview.html)
- [LoRA v3](https://docs.qualcomm.com/doc/80-63442-10/topic/lora_v3_overview.html)

    - [LoRA v3 Optimizations](https://docs.qualcomm.com/doc/80-63442-10/topic/lora_v3_optimizations.html)

Last Published: Jun 04, 2026

[Previous Topic
QAIRT Quantization Specification](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/applyencodings.md) [Next Topic
Tutorial: Converting and executing a CNN or ONNX model with QNN](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/tutorial_convert_execute_cnn_model.md)