[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:
@@ -6,7 +6,7 @@ from fastapi import APIRouter, Depends, HTTPException, Request
|
||||
from fastapi.responses import JSONResponse, StreamingResponse
|
||||
from typing_extensions import assert_never
|
||||
|
||||
from vllm.entrypoints.openai.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.utils import validate_json_request
|
||||
from vllm.entrypoints.pooling.embed.protocol import (
|
||||
EmbeddingBytesResponse,
|
||||
|
||||
Reference in New Issue
Block a user