Microsoft's self-developed chip Maia 200 enters production
The story so far
Microsoft announces that its self-developed AI accelerator Maia 200 has entered mass production, used to run its largest-scale front-end AI models. The chip boosts token processing per watt by up to 1.7 times in built-in AI features such as Microsoft Teams, Copilot, and Cowork. Maia 200 has been deployed in the U.S., Europe, and Australia to serve production workloads like Microsoft Copilot, and will gradually support GitHub Copilot and Microsoft Foundry. Microsoft also plans to expand Azure Maia systems to multi-gigawatt deployments by 2027, making it the main reasoning infrastructure for Microsoft products and services.
AI-written from the reports · Updated 21 hours ago
Coverage timeline
Follow the coverage to see every side of the story.
- ITHome · AIMicrosoft Maia 200 chip enters production, token performance per watt improved by 1.7 times.
Microsoft announces that its self-developed AI accelerator Maia 200 has entered mass production, used to run its largest-scale front-end AI models. The chip provides up to a 1.7x increase in token processing per watt in built-in AI features such as Microsoft Teams, Copilot, and Cowork.
Heat over time
- Now
- 5
- Peak
- 1018 Nov, 09:00
- 24h change
- –
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.