Build Apps w/ Local AI for Unmetered Intelligence on every Windows PC | BRK260
Windows ai Local ai Machine learning Foundry local Webnn Windows ml Microsoft build On Device inference Model optimization Ai deployment Copilot Npu Gpu Cpu inference
This session covers Windows AI APIs that now extend beyond Copilot+ devices, using Foundry Local to run open-source models locally. Developers learn to leverage Foundry Toolkit for model optimization, deploy custom AI workloads across GPU/NPU/CPU via Windows ML, and utilize WebNN for web app integration. Ideal for developers building performant, secure AI-powered Windows applications with on-device inference capabilities.
Related videos
Expand local AI reach with Windows ML | OD851
From prompt to app, build AI powered apps on Windows | DEM345
I need to rant about local models
Azure Storage for AI workloads | OD870
How to Run LLMs Locally (5 Easy Ways)
Beyond VLLM: Distributed LLM Inferencing With Llm-d on Kubernetes - Ravindra Patil, Red Hat
Under the hood for startups: How Google DeepMind makes modeling decisions
The Download: Claude Fable 5, new Copilot features, Microsoft Build recap & more
Tell us about the labs at Build
From Skeptic to Superpower: Real‑World AI Coding Workflows That Scale | BRK229
From CLI to PR: Automating the path to merged code | BRK203
