[Model] Add native MAGI-2 Preview diffusion support (#5918)

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>

tests/model_tests/diffusion/test_alignment.py

@@ -1,3 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
+
 """
 Tests for alignment between _DIFFUSION_MODELS and DIFFUSION_TEST_SETTINGS; if
 tests in this file are failing, you are probably adding a new model, and need
@@ -64,6 +67,9 @@ EXCLUDED_MODELS = [
     # Requires camera/action assets and persistent AR state; covered by its
     # dedicated contract tests and real-checkpoint E2E smoke instead.
     "LingBotWorldCausalDMDPipeline",
+    # The 270+ GiB multimodal checkpoint needs 4/8-way native sequence/head
+    # parallel execution; covered by focused native contract and GPU tests.
+    "Magi2Pipeline",
     "OmniVoicePipeline",
     "OmniVoice",
     "Cosmos3OmniDiffusersPipeline",