Meta has introduced its Grand Teton next-generation AI platform that packs in more memory, network bandwidth and compute capacity than the previous generation Zion platform.
Grand Teton sports twice the network bandwidth and four times the bandwidth between host processors and GPU accelerators compared to Zion.
AI models are used extensively across Meta for services such as news feed, content recommendations and hate-speech identification.
“As AI models become increasingly sophisticated, so will their associated workloads. Grand Teton has been designed with greater compute capacity to better support memory-bandwidth-bound workloads at Meta, such as our open source DLRMs. Grand Teton’s expanded operational compute power envelope also optimises it for compute-bound workloads, such as content understanding,” said Alexis Bjorlin, Vice President of Meta Infrastructure Hardware.
Named after the 13,000-foot mountain in Wyoming, Grand Teton uses NVIDIA H100 Tensor Core GPUs to train and run AI models that are rapidly growing in their size and capabilities, requiring greater compute.
The NVIDIA H100 is designed for performance as well as energy efficiency. When connected with NVIDIA networking across thousands of servers in hyperscale data centres, H100-accelerated servers can be 300x more energy efficient than CPU-only servers.
“With Meta sharing the H100-powered Grand Teton platform, system builders around the world will soon have access to an open design for hyperscale data centre compute infrastructure to supercharge AI across industries,” said Ian Buck, Vice President of Hyperscale and High Performance Computing at NVIDIA.