# Welcome

> Deploy dedicated GPUs in minutes and pay by the second.

Featherless GPU Cloud runs AI and general compute workloads on dedicated GPU and CPU compute. Deploy an instance for development or a long-running service, submit a Run Job for a one-off command, and keep data on network volumes that outlive both.

## Get started

<card-group>
<card icon="i-lucide-rocket" title="Quickstart" to="/get-started/quickstart">

Deploy your first instance, run code on it, and stop it when you're done.

</card>

<card icon="i-lucide-book-open" title="Concepts" to="/get-started/concepts">

The terms used across the console, the CLI and these docs.

</card>

<card icon="i-lucide-key-round" title="Credentials" to="/get-started/credentials">

Add SSH keys, create API keys and connect private registries.

</card>

<card icon="i-lucide-terminal" title="Install the CLI" to="/cli">

Manage instances, Run Jobs and files from your terminal.

</card>
</card-group>

## Products

<card-group>
<card icon="i-lucide-server" title="Instances" to="/instances">

Dedicated GPU or CPU compute for development, notebooks and services.

</card>

<card icon="i-lucide-square-terminal" title="Run Jobs" to="/run-jobs">

Run a command on temporary compute and pay only while it runs.

</card>

<card icon="i-lucide-database" title="Storage" to="/storage">

Keep datasets, models and checkpoints on network volumes.

</card>

<card icon="i-lucide-box" title="Templates" to="/templates">

Start from an official environment or save your own launch settings.

</card>
</card-group>

## Examples

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

Open JupyterLab on a GPU instance with your work on a network volume.

</card>

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

Run an OpenAI-compatible model server on a public HTTPS address.

</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>

## Support

<card-group>
<card icon="i-simple-icons-discord" title="Discord" to="https://discord.com/invite/7gybCMPjVA">

Ask questions, report problems and talk to the team.

</card>
</card-group>
