[Test] Add L4 complete diffusion feature test for LTX-2 model

[Songrui625]

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

Purpose

This PR adds L4 complete diffusion feature test for LTX-2 model (include single-stage pipeline and two-stages pipeline) refer to #2087, follow up #1832 and #2260.

Models coverage:

• Lightricks/LTX-2 LTX2Pipeline (single-stage inference for T2V)
• Lightricks/LTX-2 -> LTX2Pipeline (single-stage inference for I2V)
• rootonchair/LTX-2-19b-distilled -> LTX2TwoStagesPipeline (two-stages inference for T2V)
• rootonchair/LTX-2-19b-distilled -> LTX2ImageToVideoTwoStagesPipeline (two-stages inference for I2V)

Test features:

• Layerwise-Offloading
• Cache-DiT
• CFG-Parallel
• Ulysses-SP
• Ring-Attention
• HSDP

Test Plan

python -m pytest -v -s ./tests/e2e/online_serving/test_ltx2_expansion.py -m advanced_model --run-level=advanced_model
All 16 tests passed

Test Result

================================================================================================= warnings summary =================================================================================================
<frozen importlib._bootstrap>:488
  <frozen importlib._bootstrap>:488: DeprecationWarning: builtin type SwigPyPacked has no __module__ attribute

<frozen importlib._bootstrap>:488
  <frozen importlib._bootstrap>:488: DeprecationWarning: builtin type SwigPyObject has no __module__ attribute

../../.venv/lib/python3.12/site-packages/torch/jit/_script.py:362: 14 warnings
  /app/.venv/lib/python3.12/site-packages/torch/jit/_script.py:362: DeprecationWarning: `torch.jit.script_method` is deprecated. Please switch to `torch.compile` or `torch.export`.
    warnings.warn(

../../.venv/lib/python3.12/site-packages/_pytest/config/__init__.py:1434
  /app/.venv/lib/python3.12/site-packages/_pytest/config/__init__.py:1434: PytestConfigWarning: Unknown config option: asyncio_mode

    self._warn_or_fail_if_strict(f"Unknown config option: {key}\n")

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
=================================================================================== 16 passed, 17 warnings in 544.40s (0:09:04) ====================================================================================

---

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.

[Songrui625]

This PR is ready to go until PR #2427 is merged.

[Songrui625]

The HSDP test currently fails due to #3062. This PR can be merged after that issue is resolved

[Songrui625]

@david6666666 Hi, David. I noticed that the LTX-2.3 pipeline (#2893) has been merged. Do we add L4 test in this PR or in a separate one.

[david6666666]

@david6666666 Hi, David. I noticed that the LTX-2.3 pipeline (#2893) has been merged. Do we add L4 test in this PR or in a separate one.

Yes this is X2V function test, we should add L4 test. @yenuo26 ptal thx