Microsoft’s new AI chip makes it less reliant on Nvidia’s GPUs
Posts from this topic will be added to your daily email digest and your homepage feed.
TL;DR
- Microsoft's Maia 300 chip is the third generation of its in-house AI chip.
- It is designed as the primary AI inference system for Microsoft's products and services.
- Maia 300 will begin rolling out to production AI workloads in 2027.
- The chip is expected to improve cost and efficiency, delivering 40% more tokens per megawatt compared to leading GPU-based systems.
- It is designed to handle advanced AI workloads like long-context reasoning and agentic tasks.
- Maia 300 aims to reduce Microsoft's reliance on chips from Nvidia and AMD.
- The previous generation, Maia 200, is already in use for AI services like Microsoft Copilot.