Qualcomm has unveiled its AI Hub, a comprehensive library of pre-optimized AI models ready to run on devices running Snapdragon and Qualcomm platforms.
These models support a wide range of applications, including natural language processing, computer vision and anomaly detection, and are designed to deliver high performance with minimal power consumption, a critical factor for mobile and edge devices.
The AI Hub library currently contains more than 75 popular AI and generative AI models, including Whisper, ControlNet, Stable Diffusion and Baichuan 7B. All models are bundled in different runtimes and are optimized to leverage the hardware acceleration of the Qualcomm AI Engine across all cores (NPU, CPU and GPU). According to Qualcomm, they will deliver four times faster inference times.
Documentation and tutorials provided
The AI Hub also automatically handles model translation from the source framework to popular runtimes. It works directly with the Qualcomm AI Engine direct SDK and applies hardware-aware optimizations. Developers can search for models according to their needs, download them and integrate them into their applications, saving time and resources.
The AI Hub also provides developers with tools and resources to customize these models, and they can refine them using the Qualcomm Neural Processing SDK and the AI Model Efficiency Toolkit, both available on the platform.
To use the AI Hub, developers need a trained model in PyTorch, TorchScript, ONNX, or TensorFlow Lite format, and an understanding of the deployment target, which can be a specific device (such as the Samsung Galaxy S23 Ultra ) or a range of devices. .
However, the AI Hub is not exclusive to experienced developers. It also serves as a learning platform and provides extensive documentation and tutorials for those venturing into the world of AI.
Qualcomm plans to regularly update the AI Hub with new models and support for additional platforms and operating systems. Developers can sign up to access these models on cloud-hosted devices based on Qualcomm platforms and gain early access to new features and AI models.