> For the complete documentation index, see [llms.txt](https://nx.docs.scailable.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nx.docs.scailable.net/ai-manager-v6.1.3/ai-manager-plugin/configure-the-plugin/runtime-selection.md).

# Runtime selection

{% hint style="info" %}
Nx Witness, Nx Go and Nx Meta will work in the same way for the configuration.
{% endhint %}

## Detect available runtimes

When first starting the plugin the AI Manager plugin will auto-detect the available runtimes for your server.

<figure><img src="/files/9eYz7zSXchdCQEjOw1XU" alt="Plugin settings showing the acceleration library installation progress with a prompt to wait and click Refresh"><figcaption><p>Detecting and installing the acceleration library</p></figcaption></figure>

After the detection is complete you will usually be presented with a list of the available runtimes to choose from

<figure><img src="/files/c82MJS3cIJicT7uHfAqk" alt="Plugin settings showing Multiple AI-capable devices detected with Generic CPU and Intel runtime options"><figcaption><p>Runtime selection — choose the acceleration library for your hardware</p></figcaption></figure>

Usually the default "Generic CPU" runtime is there for your system, and based on the hardware platform, or installed [AI Accelerators](/ai-manager-v6.1.3/ai-accelerators-support/supported-ai-accelerators.md) other options will appear. Currently Intel OpenVino, NVIDIA, Hailo, MemryX and more are available.