# How to Run a Custom Inference Workload

## Custom Inference

Learn how to deploy and run custom AI inference workloads with NVIDIA Run:ai.

{% embed url="<https://www.youtube.com/watch?v=kCb0n9A3sbc>" %}

{% hint style="info" %}
**Note**

This video was recorded using NVIDIA Run:ai version 2.25.9. The user interface, features, and workflows may differ in newer releases. For the latest information, refer to the current documentation.
{% endhint %}

### What You'll Learn:

* Deploy containerized inference workloads
* Allocate GPU resources for model serving
* Configure autoscaling for inference services
* Monitor inference workload status and performance
* Support production AI applications with NVIDIA Run:ai

### Related Documentation:

Follow the validated quickstart in the product documentation: [Run Your First Custom Inference Workload](/self-hosted/workloads-in-nvidia-run-ai/using-inference/quick-starts/inference-quickstart.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://run-ai-docs.nvidia.com/self-hosted/resources/videos/how-to-run-a-custom-inference-workload.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.