Add /v1/chat/completions/batch endpoint for batched chat completions (#38011)

Signed-off-by: Matej Rojec <64556640+MatejRojec@users.noreply.github.com>
This commit is contained in:
Matej Rojec
2026-03-26 12:13:33 +08:00
committed by GitHub
parent e6bf9f15ec
commit 2908094567
8 changed files with 771 additions and 21 deletions
@@ -7,7 +7,9 @@ from http import HTTPStatus
from fastapi import APIRouter, Depends, FastAPI, Request
from fastapi.responses import JSONResponse, StreamingResponse
from vllm.entrypoints.openai.chat_completion.batch_serving import OpenAIServingChatBatch
from vllm.entrypoints.openai.chat_completion.protocol import (
BatchChatCompletionRequest,
ChatCompletionRequest,
ChatCompletionResponse,
)
@@ -31,6 +33,10 @@ def chat(request: Request) -> OpenAIServingChat | None:
return request.app.state.openai_serving_chat
def batch_chat(request: Request) -> OpenAIServingChatBatch | None:
return request.app.state.openai_serving_chat_batch
@router.post(
"/v1/chat/completions",
dependencies=[Depends(validate_json_request)],
@@ -68,5 +74,33 @@ async def create_chat_completion(request: ChatCompletionRequest, raw_request: Re
return StreamingResponse(content=generator, media_type="text/event-stream")
@router.post(
"/v1/chat/completions/batch",
dependencies=[Depends(validate_json_request)],
responses={
HTTPStatus.OK.value: {},
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
HTTPStatus.NOT_IMPLEMENTED.value: {"model": ErrorResponse},
},
)
@with_cancellation
@load_aware_call
async def create_batch_chat_completion(
request: BatchChatCompletionRequest, raw_request: Request
):
handler = batch_chat(raw_request)
if handler is None:
raise NotImplementedError("The model does not support Chat Completions API")
result = await handler.create_batch_chat_completion(request, raw_request)
if isinstance(result, ErrorResponse):
return JSONResponse(content=result.model_dump(), status_code=result.error.code)
return JSONResponse(content=result.model_dump())
def attach_router(app: FastAPI):
app.include_router(router)