[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:
@@ -10,10 +10,12 @@ from fastapi.responses import JSONResponse
|
||||
from typing_extensions import assert_never
|
||||
|
||||
from vllm.entrypoints.openai.api_server import validate_json_request
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
ErrorResponse,
|
||||
)
|
||||
from vllm.entrypoints.serve.tokenize.protocol import (
|
||||
DetokenizeRequest,
|
||||
DetokenizeResponse,
|
||||
ErrorResponse,
|
||||
TokenizeRequest,
|
||||
TokenizeResponse,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user