prokube.ai Blog https://prokube.ai/en/blog/ 2026-08-19T00:00:00.000Z Articles about sovereign AI infrastructure, Kubernetes, MLOps, and agentic workloads. How to Run Qwen 3.8 27B on Kubernetes with KServe https://prokube.ai/en/blog/serving-qwen38-27b-kserve-vllm/ 2026-08-19T00:00:00.000Z 2026-08-19T00:00:00.000Z Dr. Christian Geier A complete KServe setup for Qwen3.8 27B, including a reusable vLLM runtime, BF16 and FP8 deployment settings, H100 NVL validation, and the most important tuning knobs. AI Gateway, API Gateway, Gateway API, and friends: A Map Through the Gateway Confusion https://prokube.ai/en/blog/ai-gateway-api-gateway-gateway-api/ 2026-06-21T00:00:00.000Z 2026-06-21T00:00:00.000Z Dr.-Ing. Henrik Steude Why "gateway" in cloud native and AI now means almost anything, and how to avoid losing the plot completely. Self-Hosting Gemma 4 on Kubernetes with KServe and vLLM https://prokube.ai/en/blog/self-hosting-gemma-4-kubernetes-kserve-vllm/ 2026-04-10T00:00:00.000Z 2026-04-10T00:00:00.000Z Reyan Korel Erben Dr. Christian Geier 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.