# Seldon Core Autoscaling

Seldon Core provides native autoscaling features for both Models and Servers, enabling automatic scaling based on inference load. The diagram below depicts an autoscaling implementation that uses both Model and Server autoscaling features native to Seldon Core (i.e. this implementation doesn't leverage HPA for autoscaling, an approach we cover [here](/seldon-core-2/user-guide/scaling/hpa-overview.md))

![Core Model Server Autoscaling](/files/n813fi7ryBSgWi7Zc8VK)

## Model Autoscaling

Models can automatically scale their replicas based on load. Enable it by setting `MinReplicas` or `MaxReplicas` in your model spec. For more detail on this setup see [here](/seldon-core-2/user-guide/scaling/core-autoscaling/core-autoscaling-models.md)

## Server Autoscaling

Server autoscaling automatically scales Servers based on Model needs. This implementation supports scaling in a Multi-Model Serving setup where multiple models are hosted on shared inference servers. For more detail on this setup see [here](/seldon-core-2/user-guide/scaling/core-autoscaling/core-autoscaling-servers.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://docs.seldon.ai/seldon-core-2/user-guide/scaling/core-autoscaling.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.