[Bugfix] add inject model_arch to hf_overrides

[lengrongfu]

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

Purpose

Fixes: #2170

Test Plan

python -m vllm_omni.entrypoints.cli.main serve fishaudio/s2-pro --stage-configs-path vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml --omni --trust-remote-code --enforce-eager --gpu-memory-utilization 0.95

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. 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)

[david6666666]

@wuhang2014 ptal thx

[Gaohan123]

LGTM. Thanks!