[release v0.18.0.post1] Fix default sampling params for /v1/videos (#3021)

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

tests/entrypoints/openai_api/test_video_server.py

@@ -62,6 +62,7 @@ class MockVideoResult:
 class FakeAsyncOmni:
     def __init__(self):
         self.stage_configs = [SimpleNamespace(stage_type="diffusion")]
+        self.default_sampling_params_list = [OmniDiffusionSamplingParams()]
         self.captured_prompt = None
         self.captured_sampling_params_list = None
 
@@ -457,6 +458,87 @@ def test_frame_interpolation_params_pass_to_diffusion_sampling_params(test_clien
     assert captured.frame_interpolation_model_path == "local-rife"
 
 
+def test_default_sampling_params_apply_to_video_requests(test_client, mocker: MockerFixture):
+    mocker.patch(
+        "vllm_omni.entrypoints.openai.serving_video._encode_video_bytes",
+        return_value=b"fake-video",
+    )
+    engine = test_client.app.state.openai_serving_video._engine_client
+    engine.default_sampling_params_list = [
+        OmniDiffusionSamplingParams(
+            num_inference_steps=4,
+            guidance_scale=7.5,
+            generator_device="cpu",
+            enable_frame_interpolation=True,
+            frame_interpolation_exp=2,
+            frame_interpolation_scale=0.5,
+            frame_interpolation_model_path="default-rife",
+        )
+    ]
+
+    response = test_client.post(
+        "/v1/videos",
+        data={
+            "prompt": "default param pass-through",
+        },
+    )
+
+    assert response.status_code == 200
+    video_id = response.json()["id"]
+    _wait_for_status(test_client, video_id, VideoGenerationStatus.COMPLETED.value)
+
+    captured = engine.captured_sampling_params_list[0]
+    assert captured.num_inference_steps == 4
+    assert captured.guidance_scale == 7.5
+    assert captured.generator_device == "cpu"
+    assert captured.enable_frame_interpolation is True
+    assert captured.frame_interpolation_exp == 2
+    assert captured.frame_interpolation_scale == 0.5
+    assert captured.frame_interpolation_model_path == "default-rife"
+
+
+def test_request_params_override_default_video_sampling_params(test_client, mocker: MockerFixture):
+    mocker.patch(
+        "vllm_omni.entrypoints.openai.serving_video._encode_video_bytes",
+        return_value=b"fake-video",
+    )
+    engine = test_client.app.state.openai_serving_video._engine_client
+    engine.default_sampling_params_list = [
+        OmniDiffusionSamplingParams(
+            num_inference_steps=4,
+            guidance_scale=7.5,
+            enable_frame_interpolation=True,
+            frame_interpolation_exp=2,
+            frame_interpolation_scale=0.5,
+            frame_interpolation_model_path="default-rife",
+        )
+    ]
+
+    response = test_client.post(
+        "/v1/videos",
+        data={
+            "prompt": "explicit override",
+            "num_inference_steps": "8",
+            "enable_frame_interpolation": "false",
+            "frame_interpolation_exp": "1",
+            "frame_interpolation_scale": "1.0",
+            "frame_interpolation_model_path": "custom-rife",
+        },
+    )
+
+    assert response.status_code == 200
+    video_id = response.json()["id"]
+    _wait_for_status(test_client, video_id, VideoGenerationStatus.COMPLETED.value)
+
+    captured = engine.captured_sampling_params_list[0]
+    assert captured.num_inference_steps == 8
+    assert captured.guidance_scale == 7.5
+    assert captured.enable_frame_interpolation is False
+    assert captured.frame_interpolation_exp == 1
+    assert captured.frame_interpolation_scale == 1.0
+    assert captured.frame_interpolation_model_path == "custom-rife"
+
+
 def test_worker_fps_multiplier_is_applied_to_async_encoding(test_client, mocker: MockerFixture):
     fps_values = []
     engine = test_client.app.state.openai_serving_video._engine_client

vllm_omni/entrypoints/openai/api_server.py

@@ -2033,9 +2033,9 @@ async def create_video(
     true_cfg_scale: float | None = Form(default=None),
     seed: int | None = Form(default=None),
     negative_prompt: str | None = Form(default=None),
-    enable_frame_interpolation: bool = Form(default=False),
-    frame_interpolation_exp: int = Form(default=1, ge=1),
-    frame_interpolation_scale: float = Form(default=1.0, gt=0.0),
+    enable_frame_interpolation: bool | None = Form(default=None),
+    frame_interpolation_exp: int | None = Form(default=None, ge=1),
+    frame_interpolation_scale: float | None = Form(default=None, gt=0.0),
     frame_interpolation_model_path: str | None = Form(default=None),
     lora: str | None = Form(default=None),
     extra_params: str | None = Form(default=None),

vllm_omni/entrypoints/openai/serving_video.py

@@ -3,6 +3,7 @@
 
 from __future__ import annotations
 
+import copy
 import time
 from dataclasses import dataclass
 from http import HTTPStatus
@@ -96,7 +97,7 @@ class OmniOpenAIServingVideo:
         if request.negative_prompt is not None:
             prompt["negative_prompt"] = request.negative_prompt
 
-        gen_params = OmniDiffusionSamplingParams()
+        gen_params = self._resolve_default_sampling_params()
 
         input_image = None if reference_image is None else reference_image.data
         vp = request.resolve_video_params()
@@ -114,22 +115,27 @@ class OmniOpenAIServingVideo:
         if vp.fps is not None:
             gen_params.fps = vp.fps
             gen_params.frame_rate = float(vp.fps)
-        gen_params.enable_frame_interpolation = request.enable_frame_interpolation
-        gen_params.frame_interpolation_exp = request.frame_interpolation_exp
-        gen_params.frame_interpolation_scale = request.frame_interpolation_scale
-        gen_params.frame_interpolation_model_path = request.frame_interpolation_model_path
+        provided_fields = request.model_fields_set
+        if "enable_frame_interpolation" in provided_fields:
+            gen_params.enable_frame_interpolation = request.enable_frame_interpolation
+        if "frame_interpolation_exp" in provided_fields:
+            gen_params.frame_interpolation_exp = request.frame_interpolation_exp
+        if "frame_interpolation_scale" in provided_fields:
+            gen_params.frame_interpolation_scale = request.frame_interpolation_scale
+        if "frame_interpolation_model_path" in provided_fields:
+            gen_params.frame_interpolation_model_path = request.frame_interpolation_model_path
 
-        if request.num_inference_steps is not None:
+        if "num_inference_steps" in provided_fields and request.num_inference_steps is not None:
             gen_params.num_inference_steps = request.num_inference_steps
-        if request.guidance_scale is not None:
+        if "guidance_scale" in provided_fields and request.guidance_scale is not None:
             gen_params.guidance_scale = request.guidance_scale
-        if request.guidance_scale_2 is not None:
+        if "guidance_scale_2" in provided_fields and request.guidance_scale_2 is not None:
             gen_params.guidance_scale_2 = request.guidance_scale_2
-        if request.true_cfg_scale is not None:
+        if "true_cfg_scale" in provided_fields and request.true_cfg_scale is not None:
             gen_params.true_cfg_scale = request.true_cfg_scale
-        if request.seed is not None:
+        if "seed" in provided_fields and request.seed is not None:
             gen_params.seed = request.seed
-        if request.boundary_ratio is not None:
+        if "boundary_ratio" in provided_fields and request.boundary_ratio is not None:
             gen_params.boundary_ratio = request.boundary_ratio
 
         logger.info(
@@ -137,7 +143,7 @@ class OmniOpenAIServingVideo:
             request.boundary_ratio,
             gen_params.boundary_ratio,
         )
-        if request.flow_shift is not None:
+        if "flow_shift" in provided_fields and request.flow_shift is not None:
             gen_params.extra_args["flow_shift"] = request.flow_shift
 
         if request.extra_params is not None:
@@ -241,6 +247,17 @@ class OmniOpenAIServingVideo:
                 video_codec_options = {str(k): str(v) for k, v in extra_codec_options.items()}
         return video_codec_options
 
+    def _resolve_default_sampling_params(self) -> OmniDiffusionSamplingParams:
+        default_sampling_params_list = getattr(self._engine_client, "default_sampling_params_list", None)
+        if default_sampling_params_list:
+            for params in default_sampling_params_list:
+                if isinstance(params, OmniDiffusionSamplingParams):
+                    # Requests mutate sampling params in-place, including
+                    # nested dict fields like extra_args. Deep-copy the stage
+                    # defaults so one request cannot leak state into another.
+                    return copy.deepcopy(params)
+        return OmniDiffusionSamplingParams()
+
     @staticmethod
     def _resolve_video_fps_multiplier(result: Any) -> int:
         custom_output = getattr(result, "custom_output", None)