Azure Storage for AI workloads | OD870
Azure storage Ai inference Azure ai Machine learning Gpu optimization Azure blob Nixl Run:ai Azure foundry Ai workloads Enterprise ai Microsoft build
This Microsoft Build 2026 session covers how Azure Storage enables scalable AI inference by reducing GPU idle time, accelerating model loading, and optimizing data access. It demonstrates practical integration with Azure NIXL, Run:AI Streamer, Azure Foundry, and AKS for enterprise AI deployments, targeting developers and architects building production AI systems.