[Frontend][last/5] Improve pooling entrypoints | clean up. (#39675)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-04-16 07:53:23 -07:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 5e5afafa21
commit 4e8c3f1c19
29 changed files with 466 additions and 428 deletions
@@ -5,13 +5,14 @@ from fastapi import APIRouter, Depends, Request
from fastapi.responses import Response
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.pooling.classify.protocol import ClassificationRequest
from vllm.entrypoints.pooling.classify.serving import ServingClassification
from vllm.entrypoints.utils import (
load_aware_call,
with_cancellation,
)
from .protocol import ClassificationRequest
from .serving import ServingClassification
router = APIRouter()
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm.entrypoints.pooling.base.io_processor import PoolingIOProcessor
from ..base.io_processor import PoolingIOProcessor
class ClassifyIOProcessor(PoolingIOProcessor):
@@ -9,15 +9,16 @@ from pydantic import Field
from vllm import PoolingParams
from vllm.config import ModelConfig
from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel, UsageInfo
from vllm.entrypoints.pooling.base.protocol import (
from vllm.logger import init_logger
from vllm.renderers import TokenizeParams
from vllm.utils import random_uuid
from ..base.protocol import (
ChatRequestMixin,
ClassifyRequestMixin,
CompletionRequestMixin,
PoolingBasicRequestMixin,
)
from vllm.logger import init_logger
from vllm.renderers import TokenizeParams
from vllm.utils import random_uuid
logger = init_logger(__name__)
+2 -2
View File
@@ -7,11 +7,11 @@ import numpy as np
from fastapi.responses import JSONResponse
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 ..base.serving import PoolingServing
from ..typing import PoolingServeContext
from .io_processor import ClassifyIOProcessor
from .protocol import (
ClassificationData,