wehub-resource-sync
75 lines
2.6 KiB
Python
75 lines
2.6 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 fastapi.responses import JSONResponse
|
|
|
|
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionResponse
|
|
from vllm.entrypoints.openai.completion.protocol import CompletionResponse
|
|
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
|
from vllm.entrypoints.serve.utils.api_utils import validate_json_request
|
|
from vllm.logger import init_logger
|
|
|
|
from ..token_in_token_out.protocol import (
|
|
DerenderChatRequest,
|
|
DerenderCompletionRequest,
|
|
)
|
|
from .serving import ServingDerender
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
def derender(request: Request) -> ServingDerender | None:
|
|
return getattr(request.app.state, "serving_derender", None)
|
|
|
|
|
|
@router.post(
|
|
"/v1/chat/completions/derender",
|
|
dependencies=[Depends(validate_json_request)],
|
|
response_model=ChatCompletionResponse,
|
|
responses={
|
|
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
|
|
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
|
|
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
|
|
},
|
|
)
|
|
async def derender_chat_completion(request: DerenderChatRequest, raw_request: Request):
|
|
handler = derender(raw_request)
|
|
if handler is None:
|
|
raise NotImplementedError(
|
|
"The model does not support Chat Completions Derender API"
|
|
)
|
|
|
|
result = await handler.derender_chat_response(request)
|
|
|
|
if isinstance(result, ErrorResponse):
|
|
return JSONResponse(content=result.model_dump(), status_code=result.error.code)
|
|
|
|
return JSONResponse(content=result.model_dump())
|
|
|
|
|
|
@router.post(
|
|
"/v1/completions/derender",
|
|
dependencies=[Depends(validate_json_request)],
|
|
response_model=CompletionResponse,
|
|
responses={
|
|
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
|
|
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
|
|
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
|
|
},
|
|
)
|
|
async def derender_completion(request: DerenderCompletionRequest, raw_request: Request):
|
|
handler = derender(raw_request)
|
|
if handler is None:
|
|
raise NotImplementedError("The model does not support Completions Derender API")
|
|
|
|
result = await handler.derender_completion_response(request)
|
|
|
|
if isinstance(result, ErrorResponse):
|
|
return JSONResponse(content=result.model_dump(), status_code=result.error.code)
|
|
|
|
return JSONResponse(content=result.model_dump())
|