Blog

Four days of hacking in Potsdam

From 21st to 24th of July, the Naira team joined multiple open-source projects from the ApeiroRA and NeoNephos ecosystem in the SAP Innovation Center in Potsdam for a four-day hackathon. Our goal was simple to state and a lot more fun to build: bring sovereign inference and AI engineering closer together and figure out where the pieces of the wider ecosystem actually fit.

Read Article

DSC05275

Meine eigene KI: Ein lokaler Chatbot als Praktikumsprojekt

Artificial intelligence has become part of our everyday lives. Many people use programs such as ChatGPT without knowing exactly what happens in the background or where their data is sent. During my internship, I wanted to understand how an AI chatbot works and develop my own chatbot that runs directly on my computer.

Read Article

Bildschirmfoto 2026 07 29 um 14 26 02
Kubernetes, Platform Engineering

Serving LLMs in Production: vLLM, KServe, and the Deployment Decisions That Matter

GPU memory pressure, batching inefficiencies, and autoscaling complexity make LLM serving fundamentally different from traditional ML. We compare three production deployment strategies for vLLM — standalone, KServe, and BentoML — then go deep on KServe with deployment patterns, canary rollouts, and its role in a broader LLMOps platform.

Read Article

Thumbnail streaming tokens in bottleneck

Running Multi-Tenant GPU Workloads on Scaleway with vCluster

Namespace-per-team is the default way to share a GPU cluster. It's also the wrong one. This is what true multi-tenancy looks like in Terraform.

Read Article

The AI Gateway Landscape: agentgateway, LiteLLM, Kong and Envoy AI Gateway

Throughout out recent events we have seen that AI Gateways have become the single most important entry point for companies. Because every team building with LLMs eventually hits the same issue: it starts with a single <Your Favorite AI Provider> key for one service and eighteen months later you have a dozen services, five model providers, a pile of MCP tool servers and no single place to answer "who's calling what, at what cost, under what policy."  

Read Article

FLUX 2026 07 20 16 26 54

Multi-Tenant Observability with vCluster: Centralized Metrics and Logs Using Prometheus, Loki, and Grafana

Discover how platform teams can implement centralized metrics and logging for multi-tenant Kubernetes using vCluster. This article walks through such an architecture for private-node vClusters, showing how a centralized observability stack can serve many isolated tenant clusters, laying the foundation for scalable, production-ready multi-tenant observability.

 

Read Article