# Overview

> End-to-end guides for common AI workloads.

Each example starts from an empty account and ends with everything it created removed. Follow the steps in the console or the CLI.

<card-group>
<card icon="i-lucide-notebook-pen" title="Develop in JupyterLab" to="/examples/jupyterlab">

Run JupyterLab on a GPU instance and keep your notebooks on a network volume.

</card>

<card icon="i-lucide-message-square" title="Serve an LLM with vLLM" to="/examples/vllm-server">

Serve an OpenAI-compatible model at a public HTTPS address, protected by an API key.

</card>

<card icon="i-lucide-graduation-cap" title="Fine-tune with a Run Job" to="/examples/fine-tune-run-job">

Train a LoRA adapter on temporary compute and keep it on a network volume.

</card>

<card icon="i-lucide-monitor-cog" title="Launch GPUs from a CPU jumpbox" to="/examples/cpu-jumpbox">

Work from a small CPU instance and start GPUs only when you need them.

</card>
</card-group>
