[Frontend] Add GPU-less render serving path (vllm launch render) (#36166)
This commit is contained in:
@@ -0,0 +1,87 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
from http import HTTPStatus
|
||||
|
||||
from fastapi import APIRouter, Depends, FastAPI, Request
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.utils import validate_json_request
|
||||
from vllm.entrypoints.serve.render.serving import OpenAIServingRender
|
||||
from vllm.entrypoints.utils import create_error_response
|
||||
from vllm.logger import init_logger
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def render(request: Request) -> OpenAIServingRender | None:
|
||||
return getattr(request.app.state, "openai_serving_render", None)
|
||||
|
||||
|
||||
@router.post(
|
||||
"/v1/chat/completions/render",
|
||||
dependencies=[Depends(validate_json_request)],
|
||||
response_model=list,
|
||||
responses={
|
||||
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
|
||||
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
|
||||
HTTPStatus.NOT_IMPLEMENTED.value: {"model": ErrorResponse},
|
||||
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
|
||||
},
|
||||
)
|
||||
async def render_chat_completion(request: ChatCompletionRequest, raw_request: Request):
|
||||
handler = render(raw_request)
|
||||
if handler is None:
|
||||
error = create_error_response(
|
||||
message="The model does not support Chat Completions Render API",
|
||||
err_type="NotFoundError",
|
||||
status_code=HTTPStatus.NOT_FOUND,
|
||||
)
|
||||
return JSONResponse(
|
||||
status_code=HTTPStatus.NOT_FOUND, content=error.model_dump()
|
||||
)
|
||||
|
||||
result = await handler.render_chat_request(request)
|
||||
|
||||
if isinstance(result, ErrorResponse):
|
||||
return JSONResponse(content=result.model_dump(), status_code=result.error.code)
|
||||
|
||||
return JSONResponse(content=result)
|
||||
|
||||
|
||||
@router.post(
|
||||
"/v1/completions/render",
|
||||
dependencies=[Depends(validate_json_request)],
|
||||
response_model=list,
|
||||
responses={
|
||||
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
|
||||
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
|
||||
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
|
||||
},
|
||||
)
|
||||
async def render_completion(request: CompletionRequest, raw_request: Request):
|
||||
handler = render(raw_request)
|
||||
if handler is None:
|
||||
error = create_error_response(
|
||||
message="The model does not support Completions Render API",
|
||||
err_type="NotFoundError",
|
||||
status_code=HTTPStatus.NOT_FOUND,
|
||||
)
|
||||
return JSONResponse(
|
||||
status_code=HTTPStatus.NOT_FOUND, content=error.model_dump()
|
||||
)
|
||||
|
||||
result = await handler.render_completion_request(request)
|
||||
|
||||
if isinstance(result, ErrorResponse):
|
||||
return JSONResponse(content=result.model_dump(), status_code=result.error.code)
|
||||
|
||||
return JSONResponse(content=result)
|
||||
|
||||
|
||||
def attach_router(app: FastAPI) -> None:
|
||||
app.include_router(router)
|
||||
Reference in New Issue
Block a user