106 lines
4.0 KiB
Python
106 lines
4.0 KiB
Python
from dataclasses import dataclass
|
|
from typing import Optional
|
|
|
|
from vllm.engine.arg_utils import EngineArgs
|
|
from vllm.v1.engine.async_llm import AsyncEngineArgs
|
|
|
|
from vllm_omni.config import OmniModelConfig
|
|
|
|
|
|
@dataclass
|
|
class OmniEngineArgs(EngineArgs):
|
|
"""Engine arguments for omni models, extending base EngineArgs.
|
|
|
|
Adds omni-specific configuration fields for multi-stage pipeline
|
|
processing and output type specification.
|
|
|
|
Args:
|
|
stage_id: Identifier for the stage in a multi-stage pipeline (default: 0)
|
|
model_stage: Stage type identifier, e.g., "thinker" or "talker"
|
|
(default: "thinker")
|
|
model_arch: Model architecture name
|
|
(default: "Qwen2_5OmniForConditionalGeneration")
|
|
engine_output_type: Optional output type specification for the engine.
|
|
Used to route outputs to appropriate processors (e.g., "image",
|
|
"audio", "latents"). If None, output type is inferred.
|
|
"""
|
|
|
|
stage_id: int = 0
|
|
model_stage: str = "thinker"
|
|
model_arch: str = "Qwen2_5OmniForConditionalGeneration"
|
|
engine_output_type: Optional[str] = None
|
|
|
|
def create_model_config(self) -> OmniModelConfig:
|
|
"""Create an OmniModelConfig from these engine arguments.
|
|
|
|
Returns:
|
|
OmniModelConfig instance with all configuration fields set
|
|
"""
|
|
# First, get the base ModelConfig from the parent class
|
|
base_config = super().create_model_config()
|
|
|
|
# Create OmniModelConfig by copying all base config attributes
|
|
# and adding the new omni-specific fields
|
|
config_dict = base_config.__dict__.copy()
|
|
|
|
# Add the new omni-specific fields
|
|
config_dict["stage_id"] = self.stage_id
|
|
config_dict["model_stage"] = self.model_stage
|
|
config_dict["model_arch"] = self.model_arch
|
|
config_dict["engine_output_type"] = self.engine_output_type
|
|
|
|
# Create and return the OmniModelConfig instance
|
|
omni_config = OmniModelConfig(**config_dict)
|
|
omni_config.hf_config.architectures = omni_config.architectures
|
|
|
|
return omni_config
|
|
|
|
|
|
@dataclass
|
|
class AsyncOmniEngineArgs(AsyncEngineArgs):
|
|
"""Async engine arguments for omni models, extending base AsyncEngineArgs.
|
|
|
|
Adds omni-specific configuration fields for multi-stage pipeline
|
|
processing and output type specification in async contexts.
|
|
|
|
Args:
|
|
stage_id: Identifier for the stage in a multi-stage pipeline (default: 0)
|
|
model_stage: Stage type identifier, e.g., "thinker" or "talker"
|
|
(default: "thinker")
|
|
model_arch: Model architecture name
|
|
(default: "Qwen2_5OmniForConditionalGeneration")
|
|
engine_output_type: Optional output type specification for the engine.
|
|
Used to route outputs to appropriate processors (e.g., "image",
|
|
"audio", "latents"). If None, output type is inferred.
|
|
"""
|
|
|
|
stage_id: int = 0
|
|
model_stage: str = "thinker"
|
|
model_arch: str = "Qwen2_5OmniForConditionalGeneration"
|
|
engine_output_type: Optional[str] = None
|
|
|
|
def create_model_config(self) -> OmniModelConfig:
|
|
"""Create an OmniModelConfig from these engine arguments.
|
|
|
|
Returns:
|
|
OmniModelConfig instance with all configuration fields set
|
|
"""
|
|
# First, get the base ModelConfig from the parent class
|
|
base_config = super().create_model_config()
|
|
|
|
# Create OmniModelConfig by copying all base config attributes
|
|
# and adding the new omni-specific fields
|
|
config_dict = base_config.__dict__.copy()
|
|
|
|
# Add the new omni-specific fields
|
|
config_dict["stage_id"] = self.stage_id
|
|
config_dict["model_stage"] = self.model_stage
|
|
config_dict["model_arch"] = self.model_arch
|
|
config_dict["engine_output_type"] = self.engine_output_type
|
|
|
|
# Create and return the OmniModelConfig instance
|
|
omni_config = OmniModelConfig(**config_dict)
|
|
omni_config.hf_config.architectures = omni_config.architectures
|
|
|
|
return omni_config
|