[Model][Frontend] MiniMax-H3: Add opt-in planar video response encoding (#6288)

Signed-off-by: MosCloud <bwzhang1991@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/entrypoints/openai/serving_video.py

@@ -9,7 +9,8 @@ from collections.abc import Mapping
 from dataclasses import dataclass
 from functools import cached_property
 from http import HTTPStatus
-from typing import Any, cast
+from types import SimpleNamespace
+from typing import TYPE_CHECKING, Any, cast
 
 from fastapi import HTTPException
 from PIL import Image
@@ -29,7 +30,10 @@ from vllm_omni.entrypoints.openai.stage_params import (
     get_default_sampling_params_list,
 )
 from vllm_omni.entrypoints.openai.utils import get_stage_type, parse_lora_request
-from vllm_omni.entrypoints.openai.video_api_utils import _encode_video_bytes, encode_video_base64
+from vllm_omni.entrypoints.openai.video_api_utils import (
+    _encode_video_bytes,
+    encode_video_base64,
+)
 from vllm_omni.inputs.data import OmniDiffusionSamplingParams, OmniTextPrompt
 from vllm_omni.model_extras import should_preserve_reference_image_size
 from vllm_omni.outputs.output_metadata import (
@@ -40,6 +44,9 @@ from vllm_omni.outputs.output_metadata import (
 
 logger = init_logger(__name__)
 
+if TYPE_CHECKING:
+    from vllm_omni.diffusion.data import OmniDiffusionConfig
+
 
 @dataclass
 class ReferenceImage:
@@ -90,6 +97,12 @@ class OmniOpenAIServingVideo:
         self._model_name = model_name
         self._stage_configs = stage_configs
 
+    def _resolve_diffusion_od_config(self) -> OmniDiffusionConfig | SimpleNamespace | None:
+        get_od_config = getattr(self._engine_client, "get_diffusion_od_config", None)
+        if callable(get_od_config):
+            return get_od_config()
+        return getattr(self._engine_client, "od_config", None)
+
     @property
     def model_name(self) -> str | None:
         return self._model_name
@@ -105,8 +118,7 @@ class OmniOpenAIServingVideo:
     @cached_property
     def preserves_reference_image_size(self) -> bool:
         """Return whether the active pipeline owns reference-image resizing."""
-        get_od_config = getattr(self._engine_client, "get_diffusion_od_config", None)
-        od_config = get_od_config() if callable(get_od_config) else getattr(self._engine_client, "od_config", None)
+        od_config = self._resolve_diffusion_od_config()
         model_class_name = None if od_config is None else getattr(od_config, "model_class_name", None)
         model = getattr(od_config, "model", None) if od_config is not None else None
         model = model or self.model_name
@@ -120,8 +132,7 @@ class OmniOpenAIServingVideo:
     @property
     def supports_mixed_reference_inputs(self) -> bool:
         """Return whether the configured diffusion model accepts mixed refs."""
-        get_od_config = getattr(self._engine_client, "get_diffusion_od_config", None)
-        od_config = get_od_config() if callable(get_od_config) else getattr(self._engine_client, "od_config", None)
+        od_config = self._resolve_diffusion_od_config()
         if od_config is None:
             return False
 
@@ -332,7 +343,11 @@ class OmniOpenAIServingVideo:
         video_data = [
             VideoData(
                 b64_json=(
-                    encode_video_base64(video, fps=artifacts.output_fps, video_codec_options=video_codec_options)
+                    encode_video_base64(
+                        video,
+                        fps=artifacts.output_fps,
+                        video_codec_options=video_codec_options,
+                    )
                     if artifacts.audios[idx] is None
                     else encode_video_base64(
                         video,