Microsoft looks to free itself from GPU shackles by designing custom AI chips
Microsoft, looking to escape the clutches of GPU vendors, is designing chips for training -- and running -- AI models.
Source: techcrunch.com
Stay updated with breaking news from Second Generation Maia. Get real-time updates on events, politics, business, and more. Visit us for reliable news and exclusive interviews.
Microsoft, looking to escape the clutches of GPU vendors, is designing chips for training -- and running -- AI models.
Most companies developing AI models, particularly generative AI models like ChatGPT, GPT-4 Turbo and Stable Diffusion, rely heavily on GPUs. Today at its 2023 Ignite conference, Microsoft unveiled two custom-designed, in-house and data center-bound AI chips: the Azure Maia 100 AI Accelerator and the Azure Cobalt 100 CPU. Maia 100 can be used to train and run AI models, while Cobalt 100 is designed to run general purpose workloads.