Bringing AI to the edge: Hackathon Windows ML

Lee_Stott

Microsoft

May 21, 2025

We’re excited to announce our support and participation for the upcoming global series of Edge AI hackathons, hosted by Qualcomm Technologies.

AI Developer Hackathon Windows ML Hosted by Qualcomm on SnapDragonX

We’re excited to announce our support and participation for the upcoming global series of Edge AI hackathons, hosted by Qualcomm Technologies.

The first is on June 14-15 in Bangalore.

We see a world of hybrid AI, developing rapidly as new generation of intelligent applications get built for diverse scenarios. These range from mobile, desktop, spatial computing and extending all the way to industrial and automotive. Mission critical workloads oscillate between decision-making in the moment, on device, to fine tuning models on the cloud. We believe we are in the early stages of development of agentic applications that efficiently run on the edge for scenarios needing local deployment and on-device inferencing.

Microsoft Windows ML

Windows ML – a cutting-edge runtime optimized for performant on-device model inference and simplified deployment, and the foundation of Windows AI Foundry.

Windows ML is designed to support developers creating AI-infused applications with ease, harnessing the incredible strength of Windows’ diverse hardware ecosystem whether it’s for entry-level laptops, Copilot+ PCs or top-of-the-line AI workstations. It’s built to help developers leverage the client silicon best suited for their specific workload on any given device whether it’s an NPU for low-power and sustained inference, a GPU for raw horsepower or CPU for the broadest footprint and flexibility. Introducing Windows ML: The future of machine learning development on Windows - Windows Developer Blog

Getting Started

To get started, install AI Toolkit, leverage one of our conversion and optimization templates, or start building your own. Explore documentation and code samples available on Microsoft Learn, check out AI Dev Gallery (install, documentation) for demos and more samples to help you get started with Windows ML.

Microsoft and Qualcomm Technologies: A strong collaboration

Microsoft and Qualcomm Technologies’ collaboration bring new advanced AI features into Copilot+ PCs, leveraging the Snapdragon X Elite. Microsoft Research has played a pivotal role by optimizing new lightweight LLMs, such as Phi Silica, specifically for on-device execution with the Hexagon NPU. These models are designed to run efficiently on Hexagon NPUs, enabling multimodal AI experiences like vision-language tasks directly on Copilot+ PCs without relying on the cloud.

Additionally, Microsoft has made DeepSeek R1 7B and 14B distilled models available via Azure AI Foundry, further expanding the AI ecosystem on the edge. This collaboration marks a significant step in democratizing AI by making powerful, efficient models accessible on everyday devices

Windows AI Foundry expands AI capabilities by providing high-performance built-in models and supports developers' custom models with silicon performance. This developer platform plays a key role in this collaboration. Windows ML enables Windows 11 and Copilot+ PCs to use the Hexagon NPU for power efficient inference.

Scaling optimization through Olive toolchain

The Windows ML foundation of the Windows AI Foundry provides a unified platform for AI development across various hardware architectures and brings silicon performance using QNN Execution provider. This stack includes Windows ML and toolchains like Olive, easily accessible in AI Toolkit for VS Code, which streamlines model optimization and deployment.

Qualcomm Technologies has contributed to Microsoft’s Olive, an open-source model optimization tool that enhances AI performance by optimizing models for efficient inference on client systems. This tool is particularly beneficial for running LLMs and GenAI workloads on Qualcomm Technologies’ platforms.

Real-World Applications

Through Qualcomm Technologies and Microsoft’s collaboration we have partnered with top developers to adopt Windows ML and have demonstrated impressive performance for their AI features. Independent Solution Vendors (ISVs) such as Powder, Topaz Labs, Camo and McAfee,

Join us at the Hackathon

With the recent launch of Qualcomm Snapdragon® X Elite-powered Windows laptops, developers can now take advantage of powerful NPUs (Neural Processing Units) to deploy AI applications that are both responsive and energy-efficient. These new devices open up a world of opportunities for developers to rethink how applications are built from productivity tools to creative assistants and intelligent agents all running directly on the device.

Our mission has always been to enable high-quality AI experiences using compact, optimized models. These models are tailor-made for edge computing, offering faster inference, lower memory usage, and enhanced privacy without compromising performance.

We encourage all application developers whether you’re building with open-source SLMs (small language models), working on smart assistants, or exploring new on-device AI use cases to join us at the event.

You can register here: https://www.qualcomm.com/support/contact/forms/edge-ai-developer-hackathon-bengaluru-proposal-submission