[Frontend] Consolidate online serving utils. (#44479)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
@@ -15,7 +15,6 @@ from transformers import PreTrainedTokenizerBase
|
||||
|
||||
import vllm.envs as envs
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.logger import RequestLogger
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaMessage,
|
||||
ErrorResponse,
|
||||
@@ -24,7 +23,8 @@ from vllm.entrypoints.openai.engine.protocol import (
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.serving import OpenAIServing, SpeechToTextRequest
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.utils import get_max_tokens
|
||||
from vllm.entrypoints.serve.utils.api_utils import get_max_tokens
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.inputs import EncoderDecoderInput, EngineInput
|
||||
from vllm.logger import init_logger
|
||||
|
||||
Reference in New Issue
Block a user