# NPU development guide

***Copyright © Quectel Wireless Solutions Co., Ltd. 2026. All rights reserved.***

---

**Quectel Pi H1** product **SoC** integrates **Qualcomm ® Hexagon ™ Processor (NPU)**, a hardware accelerator dedicated to inference. To use **NPU** for model inference, **QAIRT (Qualcomm® AI Runtime SDK)** is required to port pre-trained models. **Qualcomm ®** provides a series of **SDKs** for **NPU** developers to facilitate users to deploy their models onto the **NPU**.

- Model quantification library: AIMET

- Model porting SDK: QAIRT

- Model application library: QAI-APP-BUILDER

- Online model conversion library: QAI-HUB

# Preparations

## Create Python execution environment

```shell
sudo apt install python3-numpy
python3.10 -m venv venv
. venv/bin/activate
```

## Download testing program

Download [npu-inference-sample-yolov8-for-h1](<https://developer.quectel.com/doc/files/quectel_pi/npu-inference-sample-yolov8-for-h1.zip>), unzip it and enter the directory.

```shell
unzip ai-test.zip
cd ai-test
chmod  +x *
```

# Execute AI inference

Execute the program to load the model and test dataset:

```shell
./qnn-net-run --backend ./libQnnHtp.so \
     --retrieve_context resnet50_aimet_quantized_6490.bin \
     --input_list test_list.txt --output_dir output_bin
```

# View results

Execute the script to view the results:

```shell
python3 show_resnet50_classifications.py \
      --input_list test_list.txt -o output_bin/ \
      --labels_file imagenet_classes.txt
```

Script output result:

```plaintext
Classification results
./images/cock.raw     [cock]
./images/goldfish.raw [goldfish]
./images/ice_bear.raw [ice bear]
./images/mouse.raw    [mouse]
```

# Test image collection

```{image} images/image_SkvibtMNvoAYekxfWFac3RNen0e.webp
:width: 945px
:height: 1417px
```

```{image} images/image_LQtLbctwfopAXbxdTF2cQpf6nFd.webp
:width: 998px
:height: 712px
```

```{image} images/image_XeLsbZJugot5bixm3BVccxvinwb.webp
:width: 1800px
:height: 3200px
```

```{image} images/image_Z4sub7OQ8ogXhHxEmkIcDiNLnIe.webp
:width: 1600px
:height: 1067px
```

# NPU software stack

## QAIRT

**QAIRT (Qualcomm ® AI Runtime ) SDK** is a software package that integrates **Qualcomm ® AI** software products, including **Qualcomm ® AI Engine Direct**, **Qualcomm ® Neural Processing SDK** and **Qualcomm ® Genie**. **QAIRT** provides developers with a complete set of tools for porting and deploying models on **Qualcomm®** hardware accelerators, as well as the **runtime** for executing models on **CPU, GPU**, and **NPU**.

Supported inference backends:

- CPU

- GPU

- NPU

```{image} images/image_VDEkbgnlwoYIVpxwduqch9VInwe.webp
:width: 946px
:height: 954px
```

**SoC** architecture comparison table

| **SoC** | **dsp_arch** | **soc_id** |
| --- | --- | --- |
| QCS6490 | v68 | 35 |
| QCS9075 | v73 | 77 |

## AIMET

[**AIMET**](<https://github.com/quic/aimet>)（**AI Model Efficiency Toolkit**）is a quantization tool for deep learning models such as **PyTorch** and **ONNX**. **AIMET** enhances model runtime performance by reducing computational load and memory footprint. With **AIMET**, developers can quickly iterate and find the optimal quantization configuration to achieve the best balance between accuracy and latency. Quantization models exported by **AIMET** can be compiled and deployed to the **Qualcomm NPU** via **QAIRT**, or executed directly using **ONNX Runtime**.

```{image} images/image_ZshabcFnDop7sKxqWrMchJy8nXc.webp
:width: 1468px
:height: 408px
```

## QAI-APPBUILDER

[**Quick AI Application Builder**](<https://github.com/quic/ai-engine-direct-helper>) (**QAI AppBuilder**) assists developers in deploying **AI** models and designing **AI** applications on **Qualcomm® SoC** platforms equipped with the **Qualcomm® Hexagon™ Processor (NPU)** based on the **Qualcomm® AI Runtime SDK**. This tool encapsulates the model deployment **APIs** into a set of simplified interfaces for loading models onto the **NPU** and executing inference, significantly reducing the complexity of model deployment for developers. Additionally, QAI AppBuilder provides several **Demos** for reference, helping developers quickly build their own NPU Applications.

```{image} images/image_KJrWb221Dox6TVxxql8cmVqanff.webp
:width: 1552px
:height: 902px
```

## QAI-Hub

[**Qualcomm® AI Hub**](<https://aihub.qualcomm.com/>) (**QAI-Hub**) is a one-stop online service platform for model conversion, offering online model compilation, quantization, performance analysis, inference, and download services. It automates the model conversion process from pre-trained model to device runtimes. Among them, [**Qualcomm® AI Hub Models**](<https://github.com/quic/ai-hub-models>)**(QAI-Hub-Models)** is a Python library based on **QAI-Hub**, enabling users to perform model quantization, compilation, inference, analysis, and download through the AI Hub service.

```{image} images/image_YCgzbrCDgo3RuqxabOCcYmLcnkb.webp
:width: 1610px
:height: 614px
```