Artificial Intelligence

AI is changing everything. Combined with powerful, energy efficient processors and ubiquitous connectivity to the wireless edge, intelligence is moving to more devices, changing industries, and inventing new experiences.

On-device AI allows for real-time responsiveness, improved privacy, and enhanced reliability along with better overall performance and with or without a network connection. Our Qualcomm Artificial Intelligence (AI) Engine along with our AI Software and Hardware tools (including our Qualcomm® Neural Processing SDK for AI) as outlined below, are designed to accelerate your on-device AI-enabled applications and experiences.

The Qualcomm Artificial Intelligence (AI) Engine is available on supported Snapdragon® 8 Gen 1, 888, 865, 855, 845, 835, 821, 820 and 660 mobile platforms.

Snapdragon and Qualcomm Neural Processing are products of Qualcomm Technologies, Inc. and/or its subsidiaries.

Sign up to be notified of artificial intelligence updates from QDN

Voice isolation technology can virtually eliminate background noises as users speak in real-time and with the utmost power efficiency. Find out how you can use it in your development with our Windows...
Quantization-aware Training (QAT) is a powerful feature in our AI Model Efficiency Toolkit (AIMET). It employs user-configurable rules and a small calibration dataset to simulate quantization noise...
Machine learning (ML) practitioners developing neural networks for mobile generally need their models to be fast, small, and consume low power. Here we explore how AIMET’s post-training quantization...
Running machine learning inference on mobile devices is so 2020. Are you ready to run training on mobile? Get OpenCL ML SDK 2.0 and read this article to see how we do it (spoiler: batch size = 1)....

Archive of older versions of Neural Processing SDK
AIMET is an open-source library for optimizing trained neural network models.
Download the newest version of our Neural Processing SDK, or access any of our archived versions of the SDK.
This SDK is engineered to supply computer vision algorithms for Snapdragon platforms.

Single-board computer (SBC) built on the Snapdragon 888 mobile platform.
Designed for mobile device development on the Snapdragon 865 mobile platform.
High-performance development device designed to support on-device AI application development
A highly integrated and optimized Android development kit designed on the Snapdragon 855 mobile platform

Qualcomm AI Research works to advance AI and make its core capabilities – perception, reasoning, and action – ubiquitous across devices. The goal is to make breakthroughs in fundamental AI research and scale them across industries. One way we contribute innovative and impactful AI research to the rest of the community is through novel papers at academic conferences.

Beyond papers, the Qualcomm Innovation Center (QuIC) actively contributes code based on this breakthrough research to open source projects.

The AI Model Efficiency Toolkit (AIMET) is a library that provides advanced quantization and compression techniques for trained neural network models. QuIC open sourced AIMET on GitHub to collaborate with other leading AI researchers, provide a simple library plugin for AI developers, and help migrate the ecosystem toward integer inference. Read the blog post or watch some informational AIMET videos to learn more.

The AIMET Model Zoo, another GitHub project, provides the recipe for quantizing popular 32-bit floating point (FP32) models to 8-bit integer (INT8) models with little loss in accuracy. Read the blog post to learn more. Check out the Qualcomm Innovation Center YouTube channel for informational videos on our open source projects to help developers get started.

Data is another crucial element for machine learning. If you need the Qualcomm Abstract Syntax Tree (QAST) dataset that was used to support the experiments in our workshop paper at ICLR 2019: Simulating Execution Time of Tensor Programs Using Graph Neural Networks, check out our QAST Project Page. We hope this new dataset will benefit the graph research community and raise interest in Optimizing Compiler research.