[Model] Support SenseNova-U1.5-8B-MoT and its distilled 8-step LoRA (#6516)

Signed-off-by: MrlixiangWE <mrdanaer@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

tests/diffusion/test_diffusion_worker.py

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 
 """
 Unit tests for DiffusionWorker class.
@@ -143,6 +143,21 @@ class TestDiffusionWorkerSleep:
         assert "buffer1" in mock_gpu_worker._sleep_saved_buffers
         assert "buffer2" in mock_gpu_worker._sleep_saved_buffers
 
+    def test_sleep_level_2_releases_captures_through_the_model_runner(self, mocker: MockerFixture, mock_gpu_worker):
+        """Level 2 discards the memory captures were recorded against, and the
+        runner owns the release. The worker asks it once and does not reach past
+        it into the pipeline."""
+        mock_platform = mocker.patch("vllm_omni.diffusion.worker.diffusion_worker.current_omni_platform")
+        mock_platform.get_free_memory.side_effect = [10 * 1024**3, 12 * 1024**3]
+        mock_platform.get_device_total_memory.return_value = 80 * 1024**3
+        mocker.patch("vllm_omni.diffusion.worker.diffusion_worker.get_process_gpu_memory", side_effect=[0, 0])
+        mock_gpu_worker.model_runner.pipeline.named_buffers = mocker.Mock(return_value=[])
+
+        mock_gpu_worker.sleep(level=2)
+
+        mock_gpu_worker.model_runner.release_captured_graphs.assert_called_once_with()
+        mock_gpu_worker.model_runner.pipeline.release_captured_graphs.assert_not_called()
+
     def test_sleep_memory_freed_validation(self, mocker: MockerFixture, mock_gpu_worker):
         """Test that sleep validates memory was actually freed."""
         mock_allocator_class = patch_cumem_allocator(mocker)