[Docs] how to add a new multi stage model document

[R2-Y]

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

add a document to explain how to add a new multi stage model

Test Plan

Test Result

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
• (Optional) Release notes update. If your change is user facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)

[SamitHuang]

i think we should make at least two sub-docs, like

1. How to add a Omni-modality model, e.g., qwen-omni, bagel,
2. How to add a Diffusion-only model, e.g. qwen-image, where the model implementation is mainly composed by diffusion pipeline

[congw729]

For the CI-DOCS failed, please build the doc locally and remove all errors/warnings. Even a warning will lead to a failed case.

Local Documentation Build

pip install -e ".[docs]"
mkdocs build
mkdocs serve

[congw729]

Consider also adding a reference file for qwen3-omni offline testing?

[R2-Y]

okay

[R2-Y]

@hsliuustc0106 please review