[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:
@@ -12,11 +12,11 @@ from typing_extensions import assert_never, override
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
|
||||
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 (
|
||||
from vllm.entrypoints.openai.engine.serving import (
|
||||
EmbeddingServeContext,
|
||||
OpenAIServing,
|
||||
ServeContext,
|
||||
|
||||
Reference in New Issue
Block a user