[BugFix] Fixed the issue where --no-async-chunk was not working.

[amy-why-3459]

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

Purpose

fix #2933

Test Plan

vllm serve /home/models/Qwen3-Omni-30B-A3B-Instruct --omni --port 28889 --no-async-chunk

Test Result

(Worker pid=3867183) INFO 04-20 04:03:12 [qwen3_omni.py:1006] ============self.vllm_config.model_config.async_chunk:False
(APIServer pid=3866749) INFO 04-20 04:03:12 [stage_engine_core_client.py:172] [StageEngineCoreClient] Stage-2 adding request: chatcmpl-84dfae6f31fc3eb1
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502]
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] [Overall Summary]
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] +-----------------------------+------------+
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | Field                       |      Value |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] +-----------------------------+------------+
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | e2e_requests                |          1 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | e2e_wall_time_ms            | 11,939.418 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | e2e_total_tokens            |        301 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | e2e_avg_time_per_request_ms | 11,939.418 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | e2e_avg_tokens_per_s        |     25.211 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | e2e_stage_0_wall_time_ms    |  1,953.011 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | e2e_stage_1_wall_time_ms    |  3,227.079 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] | e2e_stage_2_wall_time_ms    |  1,626.541 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:502] +-----------------------------+------------+
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:528]
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:528] [RequestE2EStats [request_id=chatcmpl-84dfae6f31fc3eb1]]
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:528] +------------------+------------+
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:528] | Field            |      Value |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:528] +------------------+------------+
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:528] | e2e_total_ms     | 11,875.375 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:528] | e2e_total_tokens |        301 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:528] +------------------+------------+
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581]
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] [StageRequestStats [request_id=chatcmpl-84dfae6f31fc3eb1]]
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] +-------------------+-----------+-----------+-----------+
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] | Field             |         0 |         1 |         2 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] +-------------------+-----------+-----------+-----------+
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] | batch_id          |         1 |         1 |         1 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] | batch_size        |         1 |         1 |         1 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] | num_tokens_in     |        67 |         0 |         0 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] | num_tokens_out    |        30 |       204 |         0 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] | stage_gen_time_ms | 1,951.266 | 3,226.583 | 1,625.796 |
(APIServer pid=3866749) INFO 04-20 04:03:14 [stats.py:581] +-------------------+-----------+-----------+-----------+

---

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 usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits.
Credits must be used to enable repository wide code reviews.

[amy-why-3459]

@ZeldaHuang @lishunyang12 PTAL

[lishunyang12]

Thanks for your quick fix.

[lishunyang12]

I should have updated this logic in #2383 with introduction of a new flag --no-async-chunk