[Bug][Hunyuanimage 3.0] fix different AR encode behavior between online and offline

[Bounty-hunter]

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

Purpose

The reason see #3499

We modify the online AR encoding behavior to be consistent with the offline AR (or DiT) path, i.e., using segment-wise encoding (build_prompt_tokenids).

Test Plan

vllm serve tencent/HunyuanImage-3.0-Instruct \
  --omni \
  --port 8091 \
  --stage-configs-path ./test_hunyuan_reuse.yaml \
  --enforce-eager

curl -X POST http://localhost:8091/v1/images/edits \
  -F "image=@./input_0_0.png" \
  -F "prompt=新年宠物海报，Q版圆润的可爱标题\"新年快乐汪\"，副标题\"HAPPY NEW YEAR\"。 鱼眼镜头，背景是房间门口，近景，上传的主体歪头笑，围着红色围巾，戴着红色毛线帽，高清，绒毛细节，面部特写。 宝丽莱相纸，超现实主义，写实主义，胶片摄影，打印颗粒感肌理。肌理，超写实，复古感。" \
  -F "bot_task=it2i_think" \
  -F "n=1" \
  -F "num_inference_steps=50" \
  -F "guidance_scale=2.5" \
  -F "seed=42" \
  | jq -r '.data[0].b64_json' \
  | base64 -d > result.png

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)

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: c2846f032a

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[princepride]

LGTM