微软发射200个AI芯片, 优于竞争对手, 来减少对第三方硬件的依赖。 Microsoft launches Maia 200 AI chip, outperforming rivals, to cut dependence on third-party hardware.

微软推出了Maia 200,其第二代AI芯片,基于TSMC的3nm工艺,具有增强的FP4和FP8性能,超过亚马逊的Trainium3和谷歌的TPUv7. Microsoft has launched the Maia 200, its second-generation AI chip, built on TSMC’s 3nm process with enhanced FP4 and FP8 performance, surpassing Amazon’s Trainium3 and Google’s TPU v7. 它在爱荷华部署,并扩大到亚利桑那州,它支持Azure、副驾驶和主要的AI型模型,而新的SDK和Triton编译器则旨在对抗Nvidia的CUDA。 Deployed in Iowa and expanding to Arizona, it supports Azure, Copilot, and major AI models, while a new SDK and Triton compiler aim to rival Nvidia’s CUDA. 这个芯片标志着微软努力减少对第三方硬件的依赖并加强其AI基础设施。 The chip marks Microsoft’s push to reduce reliance on third-party hardware and strengthen its AI infrastructure.