kubernetes

LLM inference metrics for SREs: TTFT, TPOT, KV cache, HBM bandwidth, and how they connect to real production behavior.

Kubernetes Gateway API Inference Extension: What It Is and Why It Matters

How the ndots option works in Kubernetes DNS resolution, including resolv.conf behavior, search domains, and why DNS queries can multiply inside pods.

A practical introduction to KubeRay, Ray clusters on Kubernetes, and how cloud-native infrastructure supports scalable AI and ML workloads.

How Talos simplifies Kubernetes operations on bare metal with an immutable, API-driven operating system built for reliability and security.