[Frontend][4/n] Improve pooling entrypoints | pooling. (#39153)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-04-09 10:09:45 +00:00
committed by GitHub
parent b6c9be509e
commit 66c079ae83
43 changed files with 554 additions and 733 deletions
+2 -14
View File
@@ -6,14 +6,11 @@ from typing import TypeAlias
import numpy as np
from fastapi.responses import JSONResponse
from vllm.config import ModelConfig
from vllm.entrypoints.chat_utils import ChatTemplateConfig
from vllm.entrypoints.openai.engine.protocol import UsageInfo
from vllm.entrypoints.pooling.base.serving import PoolingServing
from vllm.entrypoints.pooling.typing import PoolingServeContext
from vllm.logger import init_logger
from vllm.outputs import ClassificationOutput
from vllm.renderers import BaseRenderer
from .io_processor import ClassifyIOProcessor
from .protocol import (
@@ -31,17 +28,8 @@ ClassificationServeContext: TypeAlias = PoolingServeContext[ClassificationReques
class ServingClassification(PoolingServing):
request_id_prefix = "classify"
def init_io_processor(
self,
model_config: ModelConfig,
renderer: BaseRenderer,
chat_template_config: ChatTemplateConfig,
) -> ClassifyIOProcessor:
return ClassifyIOProcessor(
model_config=model_config,
renderer=renderer,
chat_template_config=chat_template_config,
)
def init_io_processor(self, *args, **kwargs) -> ClassifyIOProcessor:
return ClassifyIOProcessor(*args, **kwargs)
async def _build_response(
self,