Microsoft CTO Plans to Replace AMD and NVIDIA GPUs with In-House Chips

Microsoft aims to transition most of its AI workloads from Nvidia and AMD GPUs to its own custom accelerators, focusing on performance per dollar for its hyperscale cloud operations. CTO Kevin Scott indicated that the company is developing a second-generation Maia accelerator for improved performance, alongside its custom CPU, Cobalt, and other security-focused silicon.

Want More Context? 🔎