Meta Plans to Deploy Its Own AI Chips This Year to Reduce Dependence on Nvidia GPUs
站长之家
37
Social media giant Meta plans to deploy a custom-designed second-generation AI chip, named Artemis, in its data centers this year. Meta CEO Mark Zuckerberg announced plans to use 340,000 Nvidia H100 GPUs, totaling around 600,000 GPUs for running and training AI systems. This move aims to reduce reliance on Nvidia chips and control the costs of AI workloads. The new chip will be used for "inference" in running AI models, bringing greater flexibility and autonomy.
© Copyright AIbase Base 2024, Click to View Source - https://www.aibase.com/news/5176