40 lines
1.1 KiB
Python
40 lines
1.1 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
from http import HTTPStatus
|
|
|
|
from fastapi import APIRouter, Depends, Request
|
|
|
|
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
|
from vllm.entrypoints.serve.utils.api_utils import (
|
|
load_aware_call,
|
|
validate_json_request,
|
|
with_cancellation,
|
|
)
|
|
|
|
from .protocol import PoolingRequest
|
|
from .serving import ServingPooling
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
def pooling(request: Request) -> ServingPooling:
|
|
handler = getattr(request.app.state, "serving_pooling", None)
|
|
if handler is None:
|
|
raise NotImplementedError("The model does not support Pooling API")
|
|
return handler
|
|
|
|
|
|
@router.post(
|
|
"/pooling",
|
|
dependencies=[Depends(validate_json_request)],
|
|
responses={
|
|
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
|
|
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
|
|
},
|
|
)
|
|
@with_cancellation
|
|
@load_aware_call
|
|
async def create_pooling(request: PoolingRequest, raw_request: Request):
|
|
handler = pooling(raw_request)
|
|
return await handler(request, raw_request)
|