[Misc] Reorganize inputs (#35182)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-03-25 10:22:54 -07:00
committed by GitHub
parent 678b3c99e8
commit ba2f0acc2d
142 changed files with 1212 additions and 1342 deletions
+5 -5
View File
@@ -21,7 +21,7 @@ from vllm.distributed.weight_transfer.base import (
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.engine.protocol import EngineClient, StreamingInput
from vllm.entrypoints.serve.elastic_ep.middleware import set_scaling_elastic_ep
from vllm.inputs import ProcessorInputs, PromptType
from vllm.inputs import EngineInput, PromptType
from vllm.logger import init_logger
from vllm.lora.request import LoRARequest
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
@@ -139,7 +139,7 @@ class AsyncLLM(EngineClient):
self.model_config.io_processor_plugin,
)
# Convert TokPrompt --> EngineCoreRequest.
# Convert EngineInput --> EngineCoreRequest.
self.input_processor = InputProcessor(self.vllm_config, renderer)
# Converts EngineCoreOutputs --> RequestOutput.
@@ -290,7 +290,7 @@ class AsyncLLM(EngineClient):
request_id: str,
prompt: EngineCoreRequest
| PromptType
| ProcessorInputs
| EngineInput
| AsyncGenerator[StreamingInput, None],
params: SamplingParams | PoolingParams,
arrival_time: float | None = None,
@@ -530,7 +530,7 @@ class AsyncLLM(EngineClient):
self,
prompt: EngineCoreRequest
| PromptType
| ProcessorInputs
| EngineInput
| AsyncGenerator[StreamingInput, None],
sampling_params: SamplingParams,
request_id: str,
@@ -776,7 +776,7 @@ class AsyncLLM(EngineClient):
async def encode(
self,
prompt: PromptType | ProcessorInputs,
prompt: PromptType | EngineInput,
pooling_params: PoolingParams,
request_id: str,
lora_request: LoRARequest | None = None,