[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:
@@ -9,11 +9,11 @@ from fastapi import Request
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.logger import RequestLogger
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
ErrorResponse,
|
||||
UsageInfo,
|
||||
)
|
||||
from vllm.entrypoints.openai.serving_engine import OpenAIServing
|
||||
from vllm.entrypoints.openai.engine.serving import OpenAIServing
|
||||
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
|
||||
from vllm.entrypoints.pooling.score.protocol import (
|
||||
RerankDocument,
|
||||
|
||||
Reference in New Issue
Block a user