[Renderer] Move InputPreprocessor into Renderer (2/2) (#34560)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/engine/protocol.py

@@ -11,13 +11,12 @@ from vllm.distributed.weight_transfer.base import (
     WeightTransferInitRequest,
     WeightTransferUpdateRequest,
 )
-from vllm.inputs.data import PromptType
+from vllm.inputs.data import ProcessorInputs, PromptType
 from vllm.lora.request import LoRARequest
 from vllm.outputs import PoolingRequestOutput, RequestOutput
 from vllm.plugins.io_processors import IOProcessor
 from vllm.pooling_params import PoolingParams
 from vllm.renderers import BaseRenderer
-from vllm.renderers.inputs import DictPrompt, TokPrompt
 from vllm.sampling_params import SamplingParams
 from vllm.tasks import SupportedTask
 from vllm.v1.engine import EngineCoreRequest
@@ -35,7 +34,7 @@ class StreamingInput:
     where inputs are provided via an async generator.
     """
 
-    prompt: PromptType
+    prompt: ProcessorInputs
     sampling_params: SamplingParams | None = None
 
 
@@ -69,8 +68,7 @@ class EngineClient(ABC):
         self,
         prompt: EngineCoreRequest
         | PromptType
-        | DictPrompt
-        | TokPrompt
+        | ProcessorInputs
         | AsyncGenerator[StreamingInput, None],
         sampling_params: SamplingParams,
         request_id: str,
@@ -81,6 +79,7 @@ class EngineClient(ABC):
         trace_headers: Mapping[str, str] | None = None,
         priority: int = 0,
         data_parallel_rank: int | None = None,
+        reasoning_ended: bool | None = None,
     ) -> AsyncGenerator[RequestOutput, None]:
         """Generate outputs for a request."""
         ...
@@ -88,13 +87,14 @@ class EngineClient(ABC):
     @abstractmethod
     def encode(
         self,
-        prompt: PromptType | DictPrompt | TokPrompt,
+        prompt: PromptType | ProcessorInputs,
         pooling_params: PoolingParams,
         request_id: str,
         lora_request: LoRARequest | None = None,
         trace_headers: Mapping[str, str] | None = None,
         priority: int = 0,
         tokenization_kwargs: dict[str, Any] | None = None,
+        reasoning_ended: bool | None = None,
     ) -> AsyncGenerator[PoolingRequestOutput, None]:
         """Generate outputs for a request from a pooling model."""
         ...