# Titan Takeoff 🛫: Inference Server

{% hint style="danger" %}
These docs are outdated! Please check out <https://docs.titanml.co> for the latest information on the TitanML platform.\
\
If there's anything that's not covered there, please contact us on our [discord](https://discord.com/invite/83RmHTjZgf).
{% endhint %}

Iris Takeoff is an inference server designed for the super fast inference and deployment of large language models (LLMs) built by [TitanML](https://www.titanml.co/).&#x20;

Iris Takeoff is designed to be as easy as possible to start experimenting with and deploying generative text models with accelerated inference on both CPU and NVIDIA GPUs.&#x20;

You can check out the kinds of results you can achieve with the Takeoff server!!

{% embed url="<https://youtu.be/LvrEO_lNjcA>" %}