LLM Launcher | Documentation

📄️ Overview

LLM Launcher is the part of Cordatus you use to put a model into service. It covers everything

Get a model serving on your own hardware in about 10 minutes. This page is the short version;

AI Launch is the one-dialog path to a running model. You give it a Hugging Face repository id —

This guide covers the full launch wizard: the path you take when you want to choose the image, the

LLM Launcher → Containers is where everything you have launched lives: running and stopped

LLM Launcher → Environments gives you popular deep learning and machine learning frameworks as

LLM Launcher → LLM Models is the model catalogue. It brings four sources together — Hugging

User Models is the fourth tab of the LLM Models page: the models that already

The serving layer is the pair of services that sit in front of your models:

A Sparkrun cluster is one or more NVIDIA DGX Spark devices that Cordatus can place a

LLM Launcher → Jetson AI Lab mirrors NVIDIA's Jetson AI Lab catalogue inside Cordatus, so you

The VRAM Calculator answers one question before you deploy anything: *will this model, with

The Private Registry is your own cloud storage for custom container images. Push an image once

NVIDIA AI Dynamo is a distributed runtime for large language models: prefill (reading the prompt)

NVIDIA VSS is a blueprint, not a single container: a video-ingestion engine orchestrating four