[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
@@ -0,0 +1,77 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
|
||||
from http import HTTPStatus
|
||||
|
||||
from fastapi import APIRouter, Depends, FastAPI, HTTPException, Request
|
||||
from fastapi.responses import JSONResponse, StreamingResponse
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionResponse,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.orca_metrics import metrics_header
|
||||
from vllm.entrypoints.openai.utils import validate_json_request
|
||||
from vllm.entrypoints.utils import (
|
||||
load_aware_call,
|
||||
with_cancellation,
|
||||
)
|
||||
from vllm.logger import init_logger
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
ENDPOINT_LOAD_METRICS_FORMAT_HEADER_LABEL = "endpoint-load-metrics-format"
|
||||
|
||||
|
||||
def chat(request: Request) -> OpenAIServingChat | None:
|
||||
return request.app.state.openai_serving_chat
|
||||
|
||||
|
||||
@router.post(
|
||||
"/v1/chat/completions",
|
||||
dependencies=[Depends(validate_json_request)],
|
||||
responses={
|
||||
HTTPStatus.OK.value: {"content": {"text/event-stream": {}}},
|
||||
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
|
||||
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
|
||||
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
|
||||
},
|
||||
)
|
||||
@with_cancellation
|
||||
@load_aware_call
|
||||
async def create_chat_completion(request: ChatCompletionRequest, raw_request: Request):
|
||||
metrics_header_format = raw_request.headers.get(
|
||||
ENDPOINT_LOAD_METRICS_FORMAT_HEADER_LABEL, ""
|
||||
)
|
||||
handler = chat(raw_request)
|
||||
if handler is None:
|
||||
base_server = raw_request.app.state.openai_serving_tokenization
|
||||
return base_server.create_error_response(
|
||||
message="The model does not support Chat Completions API"
|
||||
)
|
||||
try:
|
||||
generator = await handler.create_chat_completion(request, raw_request)
|
||||
except Exception as e:
|
||||
raise HTTPException(
|
||||
status_code=HTTPStatus.INTERNAL_SERVER_ERROR.value, detail=str(e)
|
||||
) from e
|
||||
if isinstance(generator, ErrorResponse):
|
||||
return JSONResponse(
|
||||
content=generator.model_dump(), status_code=generator.error.code
|
||||
)
|
||||
|
||||
elif isinstance(generator, ChatCompletionResponse):
|
||||
return JSONResponse(
|
||||
content=generator.model_dump(),
|
||||
headers=metrics_header(metrics_header_format),
|
||||
)
|
||||
|
||||
return StreamingResponse(content=generator, media_type="text/event-stream")
|
||||
|
||||
|
||||
def attach_router(app: FastAPI):
|
||||
app.include_router(router)
|
||||
Reference in New Issue
Block a user