$ vishctl get notes -l topic=nccl

#nccl

1 note

Pixel art Kubernetes GPU cluster with two servers, cyan GPU interconnects, and a violet network fabric

Kubernetes GPU Platform Engineering: From nvidia-smi to NCCL

A simple, layered guide to GPUs on Kubernetes: GPU Operator, NUMA and PCIe, RDMA, SR-IOV and Multus, NVLink and NCCL, with a troubleshooting question for every layer.