Azure Maia will scale to multi

Feeds.4Sysops •IT News • October 12, 2026

Azure Maia is Microsoft’s family of custom AI accelerators and systems for Azure data centers, built to run AI inference workloads. Unlike Nvidia GPUs, Maia is Microsoft-designed hardware; the company says Maia 300 is intended to deliver up to 40% more tokens per megawatt than leading GPU-based systems. Microsoft plans to scale its Azure Maia AI accelerator family to multi-gigawatt deployments starting in 2027, making it the primary inference system for Microsoft products and services. Maia 200 is already running production workloads; Maia 300 is expected to deliver up to 40% more tokens per megawatt than leading GPU systems. Source

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Microsoft Unveils Maia 300 AI Chip for Enhanced Inference Efficiency On October 12, 2026, Microsoft announced the Maia 300, its third-generation AI chip, aimed at reducing reliance on Nvidia GPUs. The Maia 300 is designed to deliver 40% more tokens per megawatt than leading GPU systems and will be rolled out in 2027. The chip will serve as the primary AI inference system for Microsoft products, including Microsoft Copilot and GitHub Copilot. The Maia 200 is already operational, supporting various AI workloads across Microsoft services. The Maia 300 architecture utilizes a chiplet design to enhance efficiency and performance for complex AI tasks. This development is part of Microsoft's broader strategy to optimize its AI infrastructure and compete with industry leaders like Google DeepMind and OpenAI. 4 sources 6

Extracted Entities

Companies (2)

Azure Microsoft