Meta details its two new data center scale clusters, both containing 24,576 Nvidia H100 GPUs that the company is using for AI workloads like training Llama 3 (Charlotte Trueman/DatacenterDynamics)

Charlotte Trueman / DatacenterDynamics:

Meta details its two new data center scale clusters, both containing 24,576 Nvidia H100 GPUs that the company is using for AI workloads like training Llama 3  —  Have been built to support AI research and development  —  Meta has shared the details of the hardware, network, storage, design …

ai workloads center data data center gpus h100 llama llama 3 meta nvidia nvidia h100 scale the company training workloads