From Ollama to Production: Deploying vLLM with PagedAttention and Real-Time Metrics
A hands-on guide to deploying vLLM in production with Docker: optimize VRAM with PagedAttention, manage high concurrency, and monitor key telemetry metrics in real time.
From Floating Windows to Tiling: Surviving the Leap
How I transitioned from a traditional desktop environment (GNOME) to a tiling window manager (Hyprland) without losing my mind.
How to Deploy a Local LLM (Ollama) on Self-Hosted Infrastructure Without Depending on OpenAI or Anthropic
A detailed guide to hosting and running local Large Language Models with Ollama, Open WebUI, and Docker in our HomeLab, ensuring total privacy, zero API costs, and absolute control.
Management Block I - Administration
How I manage my infrastructure, covering the administration part
The Ultimate Jump to Linux: A Complete Survival Guide
From Windows to Linux without dying in the attempt: tips, distributions, software equivalents, installing drivers, and the right mindset for the perfect migration.
How Lemoe's Models Were Created
How the Artificial Intelligence models for the LEMoE project were trained and optimized.
Network Block II - Services
Third part of my homelab
My HomeLab: Spec Sheet & Services
A comprehensive detail of the physical infrastructure, local network topology, and interactive self-hosted services catalog.
Network Block I - Domains
Second part of my homelab
Introduction to my HomeLab
First part of how I built my homelab