11 minLLM Inference Metrics Explained (vLLM, SGLang, TensorRT-LLM): Build a Dashboard That DiagnosesA question-led explanation of model-server monitoring: what is waiting, where request time goes, whether work repeats and whether batches fill. Metric names vary between engines and versions.
Open video
vLLM Office Hours #21 - vLLM Production Stack Deep Dive - March 6, 2025Understand runtime optimisations before choosing more hardware. Advanced production material, not current GuideLLM CLI, illustrative cost claims or own-workload measurement.
Open video
Build a private, self-hosted LLM server with Proxmox, PCle passthrough, Ollama, Open WebUI & NixOSProvide controlled private access to a shared model server. Proxmox/NixOS/Tailscale architecture, not Caddy/Compose/SSO implementation; don't replace approved stack.
Open video
Migrate Docker Volumes from one Host to another // backup and restoreBack up and restore named container volumes across hosts. Docker commands differ from Podman; doesn't prove application-consistent database backups.
Open video
Local ChatGPT AI Server with LM Studio + Open WebUIConnect an Open WebUI client to an LM Studio model server. 2024 Fedora/Python setup, not AI Desk/Podman; current auth and network defaults differ.
Open video
10 minHow to Install LM Studio on Windows 11 | Run AI Models Locally (2026)Install LM Studio, download a fitting model and start local chat on Windows. Windows-specific; not proof of offline operation or current sizing.
Open video