Microsoft has announced ambitious plans to scale its in-house Azure Maia AI chips to gigawatt levels by 2027. This strategic move will position the Maia chips as the main AI inference system across all Microsoft products, marking a significant shift in the company’s hardware strategy.
The upcoming Maia 300 chip is projected to deliver 40 percent more tokens per megawatt compared to current leading GPU systems. Microsoft CEO Satya Nadella described this initiative as ‘our biggest bet yet on our own silicon,’ emphasizing the company’s commitment to developing proprietary technology that can enhance AI capabilities.
This shift not only highlights Microsoft’s investment in AI infrastructure but also reflects a broader trend in the tech industry toward custom silicon solutions, which are increasingly seen as essential for optimizing performance and efficiency in AI applications.
Compiled automatically by the Tech AI Newsdesk from public AI-news sources and summarised in our own words.
