[MiniMax-H3] TeaCache support and Cache-DiT validation (#5840)

Signed-off-by: dpeng123 <diyapeng123@gmail.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>

tests/diffusion/models/minimax_h3/test_minimax_h3_e2e.py

@@ -19,7 +19,7 @@ MODEL_ENV = "VLLM_TEST_MINIMAX_H3_FL2VA_MODEL"
 def _assert_joint_output(outputs):
     assert len(outputs) == 1
     frames = np.asarray(outputs[0].images[0])
-    assert frames.shape == (39, 256, 448, 3)
+    assert frames.shape == (107, 256, 448, 3)
     multimodal = outputs[0].multimodal_output
     assert multimodal is not None
     assert np.asarray(multimodal["audio"]).shape[1] == 2
@@ -122,6 +122,58 @@ def test_minimax_h3_t2va_fp8_single_gpu_smoke():
                 output_type="np",
                 extra_args={
                     "task": "t2va",
+                    "duration": 4.0,
+                    "aspect_ratio": "16:9",
+                    "flow_shift": 12.0,
+                    "audio_flow_shift": 3.0,
+                },
+            ),
+            use_tqdm=False,
+        )
+    finally:
+        engine.close()
+
+    _assert_joint_output(outputs)
+
+
+@pytest.mark.skipif(
+    not os.environ.get(MODEL_ENV),
+    reason=f"set {MODEL_ENV} to an authorized FL2VA checkpoint path",
+)
+def test_minimax_h3_t2va_teacache_single_gpu_smoke():
+    import torch
+
+    from vllm_omni.diffusion.data import DiffusionParallelConfig
+    from vllm_omni.entrypoints.omni import Omni
+    from vllm_omni.inputs.data import OmniDiffusionSamplingParams
+
+    if torch.accelerator.device_count() < 1:
+        pytest.skip("MiniMax H3 TeaCache smoke requires a CUDA device")
+
+    engine = Omni(
+        model=os.environ[MODEL_ENV],
+        cache_backend="tea_cache",
+        cache_config={"rel_l1_thresh": 0.17},
+        parallel_config=DiffusionParallelConfig(ulysses_degree=1),
+        trust_remote_code=True,
+        enable_cpu_offload=True,
+        enforce_eager=True,
+    )
+    try:
+        outputs = engine.generate(
+            "A quiet cinematic night scene with matching ambient sound.",
+            OmniDiffusionSamplingParams(
+                height=256,
+                width=448,
+                num_frames=29,
+                fps=24,
+                num_inference_steps=2,
+                seed=42,
+                output_type="np",
+                extra_args={
+                    "task": "t2va",
+                    "duration": 4.0,
+                    "aspect_ratio": "16:9",
                     "flow_shift": 12.0,
                     "audio_flow_shift": 3.0,
                 },