> For the complete documentation index, see [llms.txt](https://genos-docs.gitbook.io/default/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://genos-docs.gitbook.io/default/v1.9.3/basic-tutorials/guides/llm/serving-scaleout.md).

# 모델 서빙 스케일 아웃

### 서빙 스케일아웃

* 서빙 리비전 추가를 진행합니다.
* 서빙 리비전 추가 방법은 [LLM 모델 서빙 메뉴](https://github.com/genonai/genos-docs/tree/v1.9.3/basic-tutorials/guides/llm/interactive-blocks.md)를 참고하세요.

<figure><img src="https://541419907-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKhN1XWFV3oOVnFMMIHTE%2Fuploads%2Fgit-blob-021ad2426dcc70052ee449c87d2d07a9bc223263%2Fimage%20(40).png?alt=media" alt=""><figcaption></figcaption></figure>

* 리비전 목록에 서빙된 리비전이 2개가 되도록 하였습니다.

<figure><img src="https://541419907-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKhN1XWFV3oOVnFMMIHTE%2Fuploads%2Fgit-blob-d0d238be69c4424312f4e43b4c29a5e19a699cdd%2Fimage%20(70).png?alt=media" alt=""><figcaption></figcaption></figure>

* 기본 정보 탭에서 수정 버튼을 클릭합니다.

<figure><img src="https://541419907-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKhN1XWFV3oOVnFMMIHTE%2Fuploads%2Fgit-blob-5659f8f415ae4611589f1be03a4392e9c82a5b67%2Fimage%20(106).png?alt=media" alt=""><figcaption></figcaption></figure>

* 대표리비전의 트래픽을 분배하여 저장 버튼을 누릅니다.
* 대표 리비전에 연결된 서빙 리비전의 트래픽 분배를 설정하였습니다. 이제 대표리비전으로 호출하는 요청은 비율에 맞게 분산 처리 됩니다.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://genos-docs.gitbook.io/default/v1.9.3/basic-tutorials/guides/llm/serving-scaleout.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
