Looking into the Ultraclusters page you linked to in a sibling comment, it seems like the host machines pretty much fill out their PCIe connections with Infiniband networking to reach that figure:
EFA is also coupled with NVIDIA GPUDirect RDMA (P5, P4d) and
NeuronLink (Trn1) to enable low-latency accelerator-to-accelerator
communication between servers with operating system bypass.
Looking into the Ultraclusters page you linked to in a sibling comment, it seems like the host machines pretty much fill out their PCIe connections with Infiniband networking to reach that figure:
https://aws.amazon.com/ec2/ultraclusters/