[Model][Feat] Support Minimax-H3 quality grading requests through dynamic loading/unloading with Cache-DiT (#5853)

Signed-off-by: mglyn <1203789601@qq.com>

tests/entrypoints/openai_api/test_serving_chat_sampling_params.py

@@ -95,6 +95,7 @@ def test_serving_boundary_normalizes_declared_root_and_nested_extras(serving_cha
         messages=[],
         modalities=["image"],
         num_inference_steps=7,
+        quality="high",
         size="768x512",
         negative_prompt="avoid blur",
         lora={"name": "adapter"},
@@ -110,6 +111,7 @@ def test_serving_boundary_normalizes_declared_root_and_nested_extras(serving_cha
     }
     assert diffusion_request_args["cfg_text_scale"] == 7.0
     assert diffusion_request_args["num_inference_steps"] == 7
+    assert diffusion_request_args["quality"] == "high"
     assert diffusion_request_args["size"] == "768x512"
     assert diffusion_request_args["negative_prompt"] == "avoid blur"
     assert diffusion_request_args["lora"] == {"name": "adapter"}
@@ -133,6 +135,19 @@ def test_unknown_root_extra_does_not_claim_canonical_extra(serving_chat):
     assert "pipeline_option" not in diffusion_request_args
 
 
+def test_serving_boundary_rejects_invalid_quality(serving_chat):
+    serving_chat._diffusion_extra_body_params = frozenset()
+    request = ChatCompletionRequest(
+        model="test",
+        messages=[],
+        modalities=["image"],
+        quality="medium",
+    )
+
+    with pytest.raises(ValueError, match="quality must be one of"):
+        serving_chat._normalize_diffusion_request_args(request)
+
+
 def test_unregistered_cfg_scale_aliases_common_true_cfg_scale(serving_chat):
     serving_chat._diffusion_extra_body_params = frozenset()
     request = ChatCompletionRequest(
@@ -226,6 +241,7 @@ def test_pure_consumer_preserves_defaults_and_separate_cfg_owners(serving_chat,
         negative_prompt="avoid blur",
         cfg_scale=7.0,
         true_cfg_scale=2.0,
+        quality="high",
         extra_body={"extra_args": {"solver": "ddim"}},
     )
 
@@ -239,6 +255,7 @@ def test_pure_consumer_preserves_defaults_and_separate_cfg_owners(serving_chat,
     }
     assert sampling_params.true_cfg_scale == 2.0
     assert sampling_params.num_inference_steps == 7
+    assert sampling_params.quality == "high"
     assert (sampling_params.height, sampling_params.width) == (512, 768)
     assert captured["prompt"]["negative_prompt"] == "avoid blur"
     assert response.error.message == "No output generated from AsyncOmni"
@@ -310,6 +327,7 @@ def test_mixed_consumer_keeps_root_common_args_with_nested_extras(serving_chat,
     assert sampling_params_list[0].extra_args == {"target_h": 512, "target_w": 768}
     diffusion_params = sampling_params_list[1]
     assert diffusion_params.num_inference_steps == 7
+    assert diffusion_params.quality is None
     assert (diffusion_params.height, diffusion_params.width) == (512, 768)
     assert diffusion_params.extra_args == {"solver": "euler"}
     assert captured["prompt"]["negative_prompt"] == "avoid blur"

tests/entrypoints/openai_api/test_serving_video_output_stream.py

@@ -17,6 +17,7 @@ from pytest_mock import MockerFixture
 from starlette.testclient import TestClient
 
 from tests.helpers.media import generate_synthetic_image
+from vllm_omni.entrypoints.openai.protocol.videos import VideoGenerationRequest
 from vllm_omni.entrypoints.openai.serving_video_output_stream import OmniStreamingVideoOutputHandler
 from vllm_omni.inputs.data import OmniDiffusionSamplingParams
 from vllm_omni.outputs import OmniRequestOutput
@@ -103,6 +104,55 @@ def _build_test_app(
 class TestStreamingVideoOutputWebSocket:
     """WebSocket protocol tests for streaming generated video output."""
 
+    def test_sampling_params_quality_reaches_h3_pipeline_boundary(
+        self,
+        mocker: MockerFixture,
+    ) -> None:
+        async def mock_generate(*_args, **_kwargs):
+            if False:
+                yield None
+
+        _app, handler, _engine_client = _build_test_app(
+            mocker=mocker,
+            streaming_chunks=[],
+            mock_generate=mock_generate,
+        )
+        request_data = handler._coerce_request_data(
+            {
+                "type": "session.start",
+                "prompt": "H3 streaming quality",
+                "sampling_params": {"quality": "high"},
+            }
+        )
+        request = VideoGenerationRequest(**request_data)
+
+        _prompt, sampling_params, _video_params = asyncio.run(handler._build_prompt_and_sampling_params(request))
+
+        assert sampling_params.quality == "high"
+
+    def test_omitted_quality_preserves_engine_default(self, mocker: MockerFixture) -> None:
+        async def mock_generate(*_args, **_kwargs):
+            if False:
+                yield None
+
+        _app, handler, engine_client = _build_test_app(
+            mocker=mocker,
+            streaming_chunks=[],
+            mock_generate=mock_generate,
+        )
+        engine_client.default_sampling_params_list = [OmniDiffusionSamplingParams(quality="high")]
+        request_data = handler._coerce_request_data(
+            {
+                "type": "session.start",
+                "prompt": "H3 streaming default quality",
+            }
+        )
+        request = VideoGenerationRequest(**request_data)
+
+        _prompt, sampling_params, _video_params = asyncio.run(handler._build_prompt_and_sampling_params(request))
+
+        assert sampling_params.quality == "high"
+
     def test_streaming_session_emits_video_start_binary_chunks_and_done(self, mocker: MockerFixture):
         """A full session delivers video.start, binary chunks, then session.done."""
 

tests/entrypoints/openai_api/test_video_server.py

@@ -868,6 +868,7 @@ def test_default_sampling_params_apply_to_video_requests(test_client, mocker: Mo
         OmniDiffusionSamplingParams(
             num_inference_steps=4,
             guidance_scale=7.5,
+            quality="high",
             generator_device="cpu",
             enable_frame_interpolation=True,
             frame_interpolation_exp=2,
@@ -890,6 +891,7 @@ def test_default_sampling_params_apply_to_video_requests(test_client, mocker: Mo
     captured = engine.captured_sampling_params_list[0]
     assert captured.num_inference_steps == 4
     assert captured.guidance_scale == 7.5
+    assert captured.quality == "high"
     assert captured.generator_device == "cpu"
     assert captured.enable_frame_interpolation is True
     assert captured.frame_interpolation_exp == 2
@@ -1445,6 +1447,7 @@ def test_invalid_uploaded_input_reference_returns_400(test_client):
 def test_video_request_validation():
     req = VideoGenerationRequest(prompt="test")
     assert req.prompt == "test"
+    assert req.quality is None
     assert req.generate_sound is False
     assert req.sound_duration is None
     assert VideoGenerationRequest(prompt="test", generate_sound=True, sound_duration=1.5).generate_sound is True
@@ -1464,6 +1467,8 @@ def test_video_request_validation():
         VideoGenerationRequest(prompt="test", frame_interpolation_scale=0)
     with pytest.raises(ValueError):
         VideoGenerationRequest(prompt="test", sound_duration=0)
+    with pytest.raises(ValueError):
+        VideoGenerationRequest(prompt="test", quality="medium")
 
 
 def test_list_videos_supports_order_after_and_limit(test_client, mocker: MockerFixture):
@@ -1975,6 +1980,7 @@ def test_sync_sampling_params_pass_through(test_client, mocker: MockerFixture):
             "num_inference_steps": "30",
             "guidance_scale": "6.5",
             "seed": "42",
+            "quality": "high",
         },
     )
     assert response.status_code == 200
@@ -1983,6 +1989,7 @@ def test_sync_sampling_params_pass_through(test_client, mocker: MockerFixture):
     assert captured.num_inference_steps == 30
     assert captured.guidance_scale == 6.5
     assert captured.seed == 42
+    assert captured.quality == "high"
 
 
 def test_sync_frame_interpolation_params_pass_to_sampling_params(test_client, mocker: MockerFixture):
@@ -2018,6 +2025,7 @@ def test_sync_default_sampling_params_apply_to_video_requests(test_client, mocke
         OmniDiffusionSamplingParams(
             num_inference_steps=4,
             guidance_scale=7.5,
+            quality="high",
             enable_frame_interpolation=True,
             frame_interpolation_exp=2,
             frame_interpolation_scale=0.5,
@@ -2038,6 +2046,7 @@ def test_sync_default_sampling_params_apply_to_video_requests(test_client, mocke
     captured = engine.captured_sampling_params_list[0]
     assert captured.num_inference_steps == 4
     assert captured.guidance_scale == 7.5
+    assert captured.quality == "high"
     assert captured.enable_frame_interpolation is True
     assert captured.frame_interpolation_exp == 2
     assert captured.frame_interpolation_scale == 0.5