Blog

Field notes on sovereign AI infrastructure

Technical notes from the prokube team about Kubernetes, MLOps, LLMs, agentic AI, and the infrastructure patterns behind production AI systems.

AI Gateway, API Gateway, Gateway API, and friends: A Map Through the Gateway Confusion

Why "gateway" in cloud native and AI now means almost anything, and how to avoid losing the plot completely.

AI GatewayKubernetesGateway APILLMsAgentic AI

Read article

Self-hosting Gemma 4 on Kubernetes with KServe and vLLM

April 10, 202610 min read

Reyan, Christian

Self-Hosting Gemma 4 on Kubernetes with KServe and vLLM

How we ran the Gemma 4 31B instruction-tuned model on a single A100 80GB GPU using KServe and vLLM, including the custom runtime, PVC setup, tuning flags, verification, monitoring, and troubleshooting notes.

Gemma 4KServevLLMKubernetesLLMs

Read article