[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:
@@ -5,7 +5,10 @@ from collections.abc import Sequence
|
||||
|
||||
from transformers import PreTrainedTokenizerBase
|
||||
|
||||
from vllm.entrypoints.openai.protocol import ChatCompletionRequest, DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.logger import init_logger
|
||||
from vllm.reasoning import ReasoningParser
|
||||
from vllm.reasoning.deepseek_r1_reasoning_parser import DeepSeekR1ReasoningParser
|
||||
|
||||
Reference in New Issue
Block a user