# AI developer workflow documentation

The Qualcomm AI Runtime SDK facilitates high-performance machine learning inference on Qualcomm hardware.
It supports frameworks such as TensorFlow, PyTorch, ONNX, and LiteRT.
It’s designed to run already-trained networks quickly and efficiently on Qualcomm hardware.

## Overview

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewbox="0 0 16 16" fill="none" aria-label="icon-book-blue">
  <path d="M8 2V14M3.33333 2H12.6667C13.403 2 14 2.59695 14 3.33333V12.6667C14 13.403 13.403 14 12.6667 14H3.33333C2.59695 14 2 13.403 2 12.6667V3.33333C2 2.59695 2.59695 2 3.33333 2Z" stroke="#2A2AEA" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path>
</svg> Overview

https://docs.qualcomm.com/doc/80-70020-15B/topic/ai-ml-developer-workflow.html

## Compile and optimize an AI model

Covers model conversion, quantization, and accuracy fine tuning.

![aihubicon](data:image/png;base64,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)  Use AI Hub to optimize an AI model

Bring your own model or try preoptimized models in &lt; 5 min using AI Hub.

https://docs.qualcomm.com/doc/80-70020-15B/topic/ai-hub.html

![tfliteicon](data:image/png;base64,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)  Use LiteRT to optimize an AI model

Port your LiteRT AI models to Qualcomm platforms.

https://docs.qualcomm.com/doc/80-70020-15B/topic/tflite.html

<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewbox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-brain" aria-label="icon-brain"><path d="M12 5a3 3 0 1 0-5.997.125 4 4 0 0 0-2.526 5.77 4 4 0 0 0 .556 6.588A4 4 0 1 0 12 18Z"></path><path d="M12 5a3 3 0 1 1 5.997.125 4 4 0 0 1 2.526 5.77 4 4 0 0 1-.556 6.588A4 4 0 1 1 12 18Z"></path><path d="M15 13a4.5 4.5 0 0 1-3-4 4.5 4.5 0 0 1-3 4"></path><path d="M17.599 6.5a3 3 0 0 0 .399-1.375"></path><path d="M6.003 5.125A3 3 0 0 0 6.401 6.5"></path><path d="M3.477 10.896a4 4 0 0 1 .585-.396"></path><path d="M19.938 10.5a4 4 0 0 1 .585.396"></path><path d="M6 18a4 4 0 0 1-1.967-.516"></path><path d="M19.967 17.484A4 4 0 0 1 18 18"></path></svg>  Use Qualcomm AI Runtime SDK to optimize an AI model

Port your models using the all-in- one, easily customizable Qualcomm AI Runtime (QAIRT) SDK

https://docs.qualcomm.com/doc/80-70020-15B/topic/qairt.html

## Run AI/ML sample applications

Run the default sample app to run AI/ML models or customize the sample app using either
a Qualcomm evaluation kit or [Qualcomm Device Cloud (QDC)](https://qdc.qualcomm.com).

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="17" viewbox="0 0 16 17" fill="none" aria-label="icon-book">
<path d="M8 2.5V14.5M3.33333 2.5H12.6667C13.403 2.5 14 3.09695 14 3.83333V13.1667C14 13.903 13.403 14.5 12.6667 14.5H3.33333C2.59695 14.5 2 13.903 2 13.1667V3.83333C2 3.09695 2.59695 2.5 3.33333 2.5Z" stroke="#717171" stroke-width="1.33333" stroke-linecap="round" stroke-linejoin="round"></path>
</svg> Run a sample application using EVK

Classify images with the default sample application and an EVK.

https://docs.qualcomm.com/doc/80-70020-15B/topic/sample-app-evk.html

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="17" viewbox="0 0 16 17" fill="none" aria-label="icon-book">
<path d="M8 2.5V14.5M3.33333 2.5H12.6667C13.403 2.5 14 3.09695 14 3.83333V13.1667C14 13.903 13.403 14.5 12.6667 14.5H3.33333C2.59695 14.5 2 13.903 2 13.1667V3.83333C2 3.09695 2.59695 2.5 3.33333 2.5Z" stroke="#717171" stroke-width="1.33333" stroke-linecap="round" stroke-linejoin="round"></path>
</svg> Run a sample application using QDC

Classify images with the default sample application and <abbr title="Qualcomm Device Cloud">qualcomm Device Cloud (QDC)</abbr>.

https://docs.qualcomm.com/doc/80-70020-15B/topic/sample-app-qdc.html

## Develop your own application

Covers how to implement your own application on a Qualcomm platform.
This is an advanced topic and is for experienced developers.

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="17" viewbox="0 0 16 17" fill="none" aria-label="icon-book">
<path d="M8 2.5V14.5M3.33333 2.5H12.6667C13.403 2.5 14 3.09695 14 3.83333V13.1667C14 13.903 13.403 14.5 12.6667 14.5H3.33333C2.59695 14.5 2 13.903 2 13.1667V3.83333C2 3.09695 2.59695 2.5 3.33333 2.5Z" stroke="#717171" stroke-width="1.33333" stroke-linecap="round" stroke-linejoin="round"></path>
</svg>  Develop your own AI/ML application with the Qualcomm Visual Studio Code Extension

https://docs.qualcomm.com/doc/80-70020-15B/topic/develop-your-own-application-ide.html

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="17" viewbox="0 0 16 17" fill="none" aria-label="icon-book">
<path d="M8 2.5V14.5M3.33333 2.5H12.6667C13.403 2.5 14 3.09695 14 3.83333V13.1667C14 13.903 13.403 14.5 12.6667 14.5H3.33333C2.59695 14.5 2 13.903 2 13.1667V3.83333C2 3.09695 2.59695 2.5 3.33333 2.5Z" stroke="#717171" stroke-width="1.33333" stroke-linecap="round" stroke-linejoin="round"></path>
</svg>  Develop your own AI/ML application with Qualcomm IM SDK

https://docs.qualcomm.com/doc/80-70020-15B/topic/develop-your-own-application-im-sdk.html

## Use AI Hub models and labels with the GStreamer API

Explains how to use AI Hub models and labels with GStreamer commands on Qualcomm evaluation kits.

<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewbox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-image" aria-label="icon-image"><rect width="18" height="18" x="3" y="3" rx="2" ry="2"></rect><circle cx="9" cy="9" r="2"></circle><path d="m21 15-3.086-3.086a2 2 0 0 0-2.828 0L6 21"></path></svg>  Classify images

https://docs.qualcomm.com/doc/80-70020-15B/topic/image-classification.html

<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewbox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-scan-eye" aria-label="icon-detect"><path d="M3 7V5a2 2 0 0 1 2-2h2"></path><path d="M17 3h2a2 2 0 0 1 2 2v2"></path><path d="M21 17v2a2 2 0 0 1-2 2h-2"></path><path d="M7 21H5a2 2 0 0 1-2-2v-2"></path><circle cx="12" cy="12" r="1"></circle><path d="M18.944 12.33a1 1 0 0 0 0-.66 7.5 7.5 0 0 0-13.888 0 1 1 0 0 0 0 .66 7.5 7.5 0 0 0 13.888 0"></path></svg>  Detect objects

https://docs.qualcomm.com/doc/80-70020-15B/topic/object-detection.html

<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewbox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-scan-text" aria-label="icon-text-segment"><path d="M3 7V5a2 2 0 0 1 2-2h2"></path><path d="M17 3h2a2 2 0 0 1 2 2v2"></path><path d="M21 17v2a2 2 0 0 1-2 2h-2"></path><path d="M7 21H5a2 2 0 0 1-2-2v-2"></path><path d="M7 8h8"></path><path d="M7 12h10"></path><path d="M7 16h6"></path></svg>  Apply semantic segmentation to frames of a video

https://docs.qualcomm.com/doc/80-70020-15B/topic/semantic-segmentation.html

<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewbox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-image-upscale" aria-label="icon-upscale"><path d="M16 3h5v5"></path><path d="M17 21h2a2 2 0 0 0 2-2"></path><path d="M21 12v3"></path><path d="m21 3-5 5"></path><path d="M3 7V5a2 2 0 0 1 2-2"></path><path d="m5 21 4.144-4.144a1.21 1.21 0 0 1 1.712 0L13 19"></path><path d="M9 3h3"></path><rect x="3" y="11" width="10" height="10" rx="1"></rect></svg>  Upscale images with super resolution

https://docs.qualcomm.com/doc/80-70020-15B/topic/super-resolution.html

## Troubleshooting and FAQ

<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewbox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-file-question" aria-label="icon-question"><path d="M12 17h.01"></path><path d="M15 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V7z"></path><path d="M9.1 9a3 3 0 0 1 5.82 1c0 2-3 3-3 3"></path></svg> Further support

Get answers to common questions and learn how to get additional help.

https://docs.qualcomm.com/doc/80-70020-15B/topic/troubleshooting.html

## Model porting best practices

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="17" viewbox="0 0 16 17" fill="none" aria-label="icon-book">
<path d="M8 2.5V14.5M3.33333 2.5H12.6667C13.403 2.5 14 3.09695 14 3.83333V13.1667C14 13.903 13.403 14.5 12.6667 14.5H3.33333C2.59695 14.5 2 13.903 2 13.1667V3.83333C2 3.09695 2.59695 2.5 3.33333 2.5Z" stroke="#717171" stroke-width="1.33333" stroke-linecap="round" stroke-linejoin="round"></path>
</svg> Export YoloV8 model using Neural Processing Engine SDK

https://docs.qualcomm.com/doc/80-70020-15B/topic/appx-export-yolov8.html

<svg xmlns="http://www.w3.org/2000/svg" width="16" height="17" viewbox="0 0 16 17" fill="none" aria-label="icon-book">
<path d="M8 2.5V14.5M3.33333 2.5H12.6667C13.403 2.5 14 3.09695 14 3.83333V13.1667C14 13.903 13.403 14.5 12.6667 14.5H3.33333C2.59695 14.5 2 13.903 2 13.1667V3.83333C2 3.09695 2.59695 2.5 3.33333 2.5Z" stroke="#717171" stroke-width="1.33333" stroke-linecap="round" stroke-linejoin="round"></path>
</svg> Run the demo

https://docs.qualcomm.com/doc/80-70020-15B/topic/appx-export-yolov8.html#appx-run-the-demo

Last Published: Oct 10, 2025

[Next Topic
Overview](https://docs.qualcomm.com/bundle/publicresource/80-70020-15B/topics/ai-ml-developer-workflow.md)