[Refactor] Migrate Legacy Stage Configs to the Pipeline Registry (#5031)

Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: zwhzzz0821 <zwhzzz0821@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/model_executor/models/hunyuan_video/__init__.py

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project

vllm_omni/model_executor/models/hunyuan_video/pipeline.py

@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""HunyuanVideo-1.5 pipeline topology."""
+
+from vllm_omni.config.stage_config import (
+    PipelineConfig,
+    StageExecutionType,
+    StagePipelineConfig,
+)
+
+HUNYUAN_VIDEO_15_PIPELINE = PipelineConfig(
+    model_type="hunyuan_video_15",
+    model_arch="HunyuanVideo15Pipeline",
+    diffusers_class_name="HunyuanVideo15Pipeline",
+    stages=(
+        StagePipelineConfig(
+            stage_id=0,
+            model_stage="dit",
+            execution_type=StageExecutionType.DIFFUSION,
+            input_sources=(),
+            final_output=True,
+            final_output_type="video",
+            model_arch="HunyuanVideo15Pipeline",
+        ),
+    ),
+)

vllm_omni/model_executor/models/step_audio2/__init__.py

@@ -1,3 +0,0 @@
-from .step_audio2 import StepAudio2ForConditionalGeneration
-
-__all__ = ["StepAudio2ForConditionalGeneration"]

vllm_omni/model_executor/models/step_audio2/pipeline.py

@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Step-Audio2 pipeline topologies (frozen)."""
+
+from vllm_omni.config.stage_config import (
+    PipelineConfig,
+    StageExecutionType,
+    StagePipelineConfig,
+)
+
+_PROC = "vllm_omni.model_executor.stage_input_processors.step_audio2"
+_HF_ARCHITECTURES = (
+    "StepAudio2ForCausalLM",
+    "StepAudio2ForConditionalGeneration",
+)
+
+
+STEP_AUDIO2_PIPELINE = PipelineConfig(
+    model_type="step_audio_2",
+    model_arch="StepAudio2ForConditionalGeneration",
+    hf_architectures=_HF_ARCHITECTURES,
+    stages=(
+        StagePipelineConfig(
+            stage_id=0,
+            model_stage="step_audio2_thinker",
+            execution_type=StageExecutionType.LLM_AR,
+            input_sources=(),
+            final_output=True,
+            final_output_type="text",
+            owns_tokenizer=True,
+            requires_multimodal_data=True,
+            engine_output_type="latent",
+            model_arch="StepAudio2ThinkerForConditionalGeneration",
+            async_chunk_process_next_stage_input_func=f"{_PROC}.thinker2token2wav_async_chunk",
+            sampling_constraints={"detokenize": True},
+        ),
+        StagePipelineConfig(
+            stage_id=1,
+            model_stage="token2wav",
+            execution_type=StageExecutionType.LLM_GENERATION,
+            input_sources=(0,),
+            final_output=True,
+            final_output_type="audio",
+            engine_output_type="audio",
+            model_arch="StepAudio2Token2WavModel",
+            sync_process_input_func=f"{_PROC}.thinker2token2wav",
+            sampling_constraints={"detokenize": False},
+        ),
+    ),
+)
+
+
+STEP_AUDIO2_ASR_PIPELINE = PipelineConfig(
+    model_type="step_audio_2_asr",
+    model_arch="StepAudio2ForConditionalGeneration",
+    stages=(
+        StagePipelineConfig(
+            stage_id=0,
+            model_stage="step_audio2_thinker",
+            execution_type=StageExecutionType.LLM_AR,
+            input_sources=(),
+            final_output=True,
+            final_output_type="text",
+            owns_tokenizer=True,
+            requires_multimodal_data=True,
+            engine_output_type="text",
+            model_arch="StepAudio2ThinkerForConditionalGeneration",
+            sampling_constraints={"detokenize": True},
+        ),
+    ),
+)

vllm_omni/model_executor/models/wan2_2/__init__.py

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project

vllm_omni/model_executor/models/wan2_2/pipeline.py

@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Wan2.2 TI2V pipeline topology."""
+
+from vllm_omni.config.stage_config import (
+    PipelineConfig,
+    StageExecutionType,
+    StagePipelineConfig,
+)
+
+WAN2_2_TI2V_PIPELINE = PipelineConfig(
+    model_type="wan2_2_ti2v",
+    model_arch="WanPipeline",
+    diffusers_class_name="WanPipeline",
+    stages=(
+        StagePipelineConfig(
+            stage_id=0,
+            model_stage="dit",
+            execution_type=StageExecutionType.DIFFUSION,
+            input_sources=(),
+            final_output=True,
+            final_output_type="video",
+            model_arch="WanPipeline",
+        ),
+    ),
+)