[Chore]: Update stable audio config to have audio output type

[zhangj1an]

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

Purpose

Fixes the review comment in vllm-project#2377 (comment).

Key changes

• Add vllm_omni/model_executor/stage_configs/stable_audio.yaml: single diffusion stage with final_output: true and final_output_type: audio.
• Register diffusers class → config in vllm_omni/entrypoints/utils.py: StableAudioPipeline → stable_audio.

Test Plan

Re-run python examples/offline_inference/text_to_audio/text_to_audio.py.

Test Result

The stable audio pipeline still works,

INFO 04-04 16:24:52 [omni_base.py:162] [Summary] {}
Processed prompts: 100%|██████████████████| 1/1 [00:04<00:00,  4.33s/it]
Total generation time: 4.34 seconds
Saved generated audio to stable_audio_output.wav

Generated 10.0s of audio at 44100 Hz

---

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. Please provide the test scripts & test commands. Please state the reasons if your codes don't require additional test scripts. For test file guidelines, please check the test style doc
• The test results. Please paste the results comparison before and after, or the e2e results.
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model. Please run mkdocs serve to sync the documentation editions to ./docs.
• (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)