[CI][Bugfix] Fix LTX audio-video warmup output typing (#3964)

Signed-off-by: david6666666 <530634352@qq.com>

tests/diffusion/test_diffusion_engine_dummy_run.py

@@ -0,0 +1,57 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+import pytest
+
+from vllm_omni.diffusion import diffusion_engine
+
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.diffusion]
+
+
+def test_dummy_run_num_frames_uses_explicit_model_setting(monkeypatch: pytest.MonkeyPatch) -> None:
+    class JointAudioVideoModel:
+        dummy_run_num_frames = 2
+
+    monkeypatch.setattr(
+        diffusion_engine.DiffusionModelRegistry,
+        "_try_load_model_cls",
+        lambda model_class_name: JointAudioVideoModel,
+    )
+
+    assert diffusion_engine.get_dummy_run_num_frames("joint_audio_video", supports_audio_input=False) == 2
+
+
+def test_dummy_run_num_frames_keeps_audio_output_default(monkeypatch: pytest.MonkeyPatch) -> None:
+    class AudioOutputModel:
+        support_audio_output = True
+
+    monkeypatch.setattr(
+        diffusion_engine.DiffusionModelRegistry,
+        "_try_load_model_cls",
+        lambda model_class_name: AudioOutputModel,
+    )
+
+    assert diffusion_engine.get_dummy_run_num_frames("audio_output", supports_audio_input=False) == 2
+
+
+def test_dummy_run_num_frames_defaults_to_single_frame(monkeypatch: pytest.MonkeyPatch) -> None:
+    class VideoOnlyModel:
+        pass
+
+    monkeypatch.setattr(
+        diffusion_engine.DiffusionModelRegistry,
+        "_try_load_model_cls",
+        lambda model_class_name: VideoOnlyModel,
+    )
+
+    assert diffusion_engine.get_dummy_run_num_frames("video_only", supports_audio_input=False) == 1
+
+
+def test_dummy_run_num_frames_uses_audio_input_fallback(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(
+        diffusion_engine.DiffusionModelRegistry,
+        "_try_load_model_cls",
+        lambda model_class_name: None,
+    )
+
+    assert diffusion_engine.get_dummy_run_num_frames("unknown", supports_audio_input=True) == 2