Microsoft plans to scale Azure Maia AI chips to multi-gigawatt levels by 2027
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
Microsoft will deploy its Azure Maia AI chips at multi-gigawatt scale starting in 2027 as its main product inference system, with CEO Satya Nadella calling it the company's biggest silicon bet. The current Maia 200 runs Microsoft Copilot, GitHub Copilot, and Foundry, and delivers up to 1.7 times more tokens per watt than leading GPUs in Teams. Its successor, Maia 300, launches in 2027 with a 96-chip rack producing up to seven times the tokens of a Maia 200 rack and offering 40 percent more tokens per megawatt than leading GPU systems.
Continue in the app — vote & join in ➔Source: The Decoder (AI) · via ahirlevel.hu