@PyTorch: Join us October 17-18 in San Francisco for the ExecuTorch Hackathon. Developers will build and deploy PyTorch models wi…
Summary
The ExecuTorch Hackathon is a two-day event in San Francisco where developers form teams to build and deploy PyTorch models on edge hardware using the ExecuTorch framework, with tracks for compute, mobile+XR, and IoT, sponsored by Meta, Qualcomm, and others.
View Cached Full Text
Cached at: 09/24/26, 10:34 PM
Join us October 17-18 in San Francisco for the ExecuTorch Hackathon.
Developers will build and deploy PyTorch models with ExecuTorch across Compute, Mobile + XR, and IoT tracks.
Teams will get hands-on with Snapdragon-powered PCs, Samsung Galaxy devices, and Arduino hardware while exploring what’s possible with open-source, on-device AI. Form a team, submit a proposal, and help shape the future of AI at the edge.
Submit your proposal here:
ExecuTorch Hackathon · Luma
Source: https://luma.com/executorch-hackathon NOTE: By registering for the Luma, you are submitting an application to participate. We will reach out on a rolling basis to let you know whether you’ve been accepted.There are a limited number of devices, we can support up to 200 participants.
This event is sponsored by Meta, Qualcomm, GitHub, Open Intelligence Foundation, and the PyTorch Foundation.
Join developers, researchers, and builders for the upcoming ExecuTorch Hackathon on October 17 -18 at Founder’s Inc., officially part ofOpen Source AI Week 2026.
Hosted in collaboration withQualcomm,Meta,GitHub,the PyTorch Foundation, andOpen Intelligence Foundation, this hands-on event will challenge teams to build innovative AI experiences powered byExecuTorch—an open-source framework for deploying and running PyTorch models efficiently on edge and on-device hardware.
Participants will work in teams of 3–5 people and select one of three tracks outlined below. Each team will receive a device from their selected track to use during the event. Builders will also get access to GitHub Copilot Pro+ to support their builds.
Compute Track
Build AI applications optimized for theCopilot+ PCpowered by Snapdragon® X Elite processors, exploring the potential of powerful, efficient on-device AI computing.
Mobile + XR Track
Create AI-powered experiences for theSamsung Galaxy S25 Ultrapowered by Snapdragon 8 Elite andSamsung****Galaxy XRpowered by Snapdragon® XR2+ Gen 2 processor, with a focus on mobile intelligence, immersive interaction, and multimodal applications.
IoT Track
Develop intelligent edge and embedded applications using theArduino®VENTUNO™ Q boards, combining on-device AI with real-time sensing, control, and connected experiences. Choose from an assortment of modulinos and accessories to complete your project (available on a first come, first served basis).
To participate, interested teams must select a track, form a team of 3–5, and submit a project proposal by October 4. Selected teams will be announced by October 7.
Prizes
The top team in each track will receive a prize package for every member of the team: Meta AI glasses and an Arduino® UNO™ Q. Build a standout project, demonstrate the potential of on-device AI, and take home hardware to continue exploring the edge.
GitHub will also award a one-year subscription to Copilot Pro to the winner.
Whether you are an experienced edge AI developer or eager to explore the future of open-source, on-device intelligence, the ExecuTorch Hackathon is an opportunity to collaborate, experiment, and build with the latest hardware and software across compute, mobile, XR, and IoT.
Questions? Join our Discord! Ask questions about the event, connect with other participants, form a team, receive event announcements, and stay up to date throughout the hackathon.
👉Join here:Join Discord Server
Bring your ideas. Build with ExecuTorch. Help shape the future of open-source, on device AI.
About Open Intelligence Foundation
TheOpen Intelligence Foundationis a community-first nonprofit founded to protect, strengthen, and advance open-source AI, open models, and open science. Supported by a large community of volunteers and organizations, it takes a bottom-up approach to collaboration, working with academia and researchers to support research, development, and education in open-source AI. The foundation also leadsOpen Source AI Week, a community-run initiative celebrating open-source AI.
About Founders, Inc. Founders, Inc.backs early-stage founders in emerging tech with first checks and 55,000 sq. ft. of lab space in San Francisco’s Fort Mason. They run year-round programs to help ambitious builders to go from early stage to scalable companies.
Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Arduino and VENTUNO are trademarks or registered trademarks of Arduino S.r.l.
Similar Articles
@PyTorch: Build AI on the edge with ExecuTorch at a two-day @Meta + @Arm hackathon at San Francisco State University. Students, d…
A two-day hackathon at San Francisco State University, organized by Meta and Arm, focused on building AI applications on the edge using ExecuTorch on Arm-powered devices, with technical talks, workshops, and prizes.
@PyTorch: PyTorch Foundation supported the ExecuTorch Hackathon in San Francisco, where more than 100 participants across 20+ tea…
The PyTorch Foundation supported the ExecuTorch Hackathon in San Francisco, where over 100 participants built real-time on-device AI applications using PyTorch and ExecuTorch on Snapdragon-powered Samsung Galaxy S25 Ultra devices. Winning projects included SafeScreen AI, SixthSense, and Toddle AI, showcasing local execution benefits for responsiveness, privacy, and offline capability.
@PyTorch: #PyTorch meets TPUs, Trainium, edge devices, resilient training, and more. Catch quick live demos in the #PyTorchCon No…
The PyTorch Conference North America will feature live demos on integrating PyTorch with TPUs, Trainium, edge devices, and resilient training on October 20-21 in San Jose.
@PyTorch: Build #AI that ships. The Applications Track at #PyTorchCon, Oct 20-21 in San Jose, showcases how developers are using …
PyTorch Conference North America (Oct 20-21, San Jose) will feature an Applications Track showcasing how developers use PyTorch across LLMs, multimodal AI, robotics, scientific computing, and production deployments. The event also includes tracks on core PyTorch, inference, kernel engineering, and responsible AI.
ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device
This article introduces ExecuTorch, a unified PyTorch-native deployment framework designed to run AI models on diverse edge devices without requiring model conversion or reimplementation.