[Bugfix] Fix redundant shm broadcast warnings in diffusion workers

[SamitHuang]

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

Purpose

When running qwen-image gradio demo (or any diffusion model), the worker processes generate redundant log messages every 60 seconds:

INFO 12-01 05:28:41 [shm_broadcast.py:466] No available shared memory broadcast block found in 60 seconds. This typically happens when some processes are hanging or doing some time-cons

Test Plan

cd examples/offline_inference/qwen_image
python gradio_demo.py

Test Result

Before:

* Running on local URL:  http://127.0.0.1:7862
INFO:httpx:HTTP Request: GET http://127.0.0.1:7862/gradio_api/startup-events "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: HEAD http://127.0.0.1:7862/ "HTTP/1.1 200 OK"
* To create a public link, set `share=True` in `launch()`.
INFO:httpx:HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
INFO:vllm_omni.diffusion.omni_diffusion:Prepared 1 requests for generation.
INFO:vllm_omni.diffusion.diffusion_engine:Generation completed successfully.
INFO:vllm_omni.diffusion.omni_diffusion:Prepared 1 requests for generation.
INFO:vllm_omni.diffusion.diffusion_engine:Generation completed successfully.
INFO 12-01 05:28:41 [shm_broadcast.py:466] No available shared memory broadcast block found in 60 seconds. This typically happens when some processes are hanging or doing some time-cons
uming work (e.g. compilation).
INFO 12-01 05:29:41 [shm_broadcast.py:466] No available shared memory broadcast block found in 60 seconds. This typically happens when some processes are hanging or doing some time-cons
uming work (e.g. compilation).
INFO 12-01 05:30:41 [shm_broadcast.py:466] No available shared memory broadcast block found in 60 seconds. This typically happens when some processes are hanging or doing some time-cons
uming work (e.g. compilation).
...

After fix:

* Running on local URL:  http://127.0.0.1:7862
INFO:httpx:HTTP Request: GET http://127.0.0.1:7862/gradio_api/startup-events "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: HEAD http://127.0.0.1:7862/ "HTTP/1.1 200 OK"
* To create a public link, set `share=True` in `launch()`.
INFO:httpx:HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"

---

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]

I'm not sure it's ok to use indefinite=True instead of use a suitable large enough number

[ZJY0516]

This is acceptable for the rc1 release