Public
Star 历史趋势
数据来源: GitHub API · 生成自 Stargazers.cn
README.md
Qualcomm® AI Hub Apps
The Qualcomm® AI Hub Apps are a collection of sample apps and tutorials to help deploy machine learning models on Qualcomm® devices.
Each app is designed to work with one or more models from Qualcomm® AI Hub Models.
With this repository, you can...
- Explore apps optimized for on-device deployment of various machine learning tasks.
- View open-source app recipes for running Qualcomm® AI Hub Models on local devices.
- Find tutorials for end-to-end workflows.
Overview
Supported runtimes
- TensorFlow Lite
- ONNX
- Genie SDK (Generative AI runtime on top of Qualcomm® AI Engine Direct SDK)
Supported Deployment Targets
- Android 11 Red Velvet Cake & Newer, API v30+
- Windows 11
- Ubuntu 24.04+
Supported compute units
- CPU, GPU, NPU (includes hexagon HTP)
Chipsets supported for NPU Acceleration
- Snapdragon X2 Elite
- Snapdragon X Elite
- Snapdragon 8 Elite Gen 5
- Snapdragon 8 Elite
- Snapdragon 8 Gen 3
- Snapdragon 8 Gen 2
- ... and all other Snapdragon® chipsets supported by the QAIRT SDK
Weight and activation type required for NPU Acceleration:
- Floating Point: FP16 (All Snapdragon® chipsets with Hexagon® Architecture v69 or newer)
- Integer : INT8 or INT16 (All Snapdragon® chipsets)
NOTE: Some of these apps will run without NPU acceleration on non-Snapdragon® chipsets.
Getting Started with Apps
-
Search for your desired OS & app in the tables below.
-
The README of the selected app will contain build & installation instructions.
Contributors: See CONTRIBUTING.md for dev setup, repo architecture, and how to add new apps.
Android App Directory
| Task | Language | Inference API | Special Tags |
|---|---|---|---|
| ChatApp | Java/C++ | Genie SDK | LLM, GenAI |
| Image Classification | Java | TensorFlow Lite | |
| Object Detection | Java | TensorFlow Lite | OpenCV, Live Camera Feed |
| Semantic Segmentation | Java | TensorFlow Lite | OpenCV, Live Camera Feed |
| Super Resolution | Java | TensorFlow Lite | |
| WhisperKit (Speech to Text)* | Various | TensorFlow Lite | |
| GenieX Chat Android | Kotlin/Java | GenieX |
Windows App Directory
| Task | Language | Inference API | Special Tags |
|---|---|---|---|
| ChatApp | C++ | Genie SDK | LLM, GenAI |
| Image Classification | C++ | ONNX | OpenCV |
| Object Detection | C++ | ONNX | OpenCV |
| Super Resolution | C++ | ONNX | OpenCV |
| Whisper Speech-to-Text | Python | ONNX | |
| Stable Diffusion Image Generation | Python | ONNX | |
| GenieX Chat Windows* | Go | GenieX | |
| SAM3 Segmentation Windows | Python | ONNX |
Ubuntu App Directory
| Task | Language | Inference API | Special Tags |
|---|---|---|---|
| Hand Gesture Recognition | Python | TensorFlow Lite | GStreamer |
| Posenet Pose Estimation | Python | TensorFlow Lite | GStreamer |
| YamNet Audio Classification | Python | TensorFlow Lite | |
| Portrait Segmentation | Python | TensorFlow Lite | |
| Face Recognition | Python | TensorFlow Lite | GStreamer |
| 3D Object Detection | Python | TensorFlow Lite | GStreamer |
| Semantic Segmentation | Python | TensorFlow Lite | GStreamer |
* Source available on GitHub; not included in the CLI release.
Tutorials Directory
| Tutorial | Topic |
|---|---|
| LLM on-device deployment | Exporting and deploying Large Language Model (LLM) using Genie SDK |
| LLM on-device deployment with GenieX | Running and exporting Large Language Models (LLMs) with the GenieX runtime |
LICENSE
Qualcomm® AI Hub Apps is licensed under BSD-3. See the LICENSE file.