October 9, 2026
A beginner's guide to GPU-aware Kubernetes: how DRA picks the right GPU, how Kueue starts a job only when all of it fits, and where the NVIDIA GPU Operator and Run:ai fit in.
October 7, 2026
How LLM inference scales past one GPU: data, pipeline, tensor and expert parallelism, prefill/decode disaggregation, and running it all on Kubernetes.
August 2, 2026
Field notes on Kubernetes networking: what really happened to ingress-nginx, what Gateway API and ingress2gateway do and don’t solve, and what’s genuinely still missing before you cut over.
July 13, 2026
Exposing the parallel-by-default execution of Bend as highly scalable, multi-cloud serverless endpoints.