[Misc] Enable tensor_parallel_size argument with online serving cmd

[JustQJ]

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

Purpose

Enable tensor-parallel-size argument for online serving when running Z-Image with TP=2

MODEL="${MODEL:-Tongyi-MAI/Z-Image-Turbo}"
PORT="${PORT:-8091}"
vllm serve "$MODEL" --omni \
    --port "$PORT" \
    --tensor-parallel-size 2

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)

[ZJY0516]

thanks for contribution. could you please also add enforce-eager too? it was introduced in #684 and added to online serving cmd

[JustQJ]

thanks for contribution. could you please also add enforce-eager too? it was introduced in #684 and added to online serving cmd

done

[Gaohan123]

LGTM. Thanks