[Frontend] Consolidate online serving utils. (#44479)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
@@ -10,7 +10,7 @@ if TYPE_CHECKING:
|
||||
from starlette.datastructures import State
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.logger import RequestLogger
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.tasks import SupportedTask
|
||||
else:
|
||||
RequestLogger = object
|
||||
@@ -65,9 +65,9 @@ async def init_generate_state(
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
|
||||
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
|
||||
from vllm.entrypoints.openai.fingerprint import set_default_fingerprint_mode
|
||||
from vllm.entrypoints.openai.responses.serving import OpenAIServingResponses
|
||||
from vllm.entrypoints.serve.disagg.serving import ServingTokens
|
||||
from vllm.entrypoints.serve.utils.fingerprint import set_default_fingerprint_mode
|
||||
|
||||
# Applied before any serving class is constructed so that each one picks
|
||||
# up the chosen mode on its first cache miss.
|
||||
|
||||
@@ -6,7 +6,7 @@ from vllm.config import ModelConfig
|
||||
from vllm.tasks import SupportedTask
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from vllm.entrypoints.sagemaker.api_router import (
|
||||
from vllm.entrypoints.serve.sagemaker.api_router import (
|
||||
EndpointFn,
|
||||
GetHandlerFn,
|
||||
RequestType,
|
||||
|
||||
@@ -10,8 +10,11 @@ from vllm.entrypoints.generate.generative_scoring.serving import (
|
||||
ServingGenerativeScoring,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.utils import validate_json_request
|
||||
from vllm.entrypoints.utils import load_aware_call, with_cancellation
|
||||
from vllm.entrypoints.serve.utils.api_utils import (
|
||||
load_aware_call,
|
||||
validate_json_request,
|
||||
with_cancellation,
|
||||
)
|
||||
from vllm.logger import init_logger
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
@@ -18,7 +18,6 @@ from fastapi import Request
|
||||
from pydantic import Field
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.logger import RequestLogger
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
ErrorResponse,
|
||||
OpenAIBaseModel,
|
||||
@@ -26,6 +25,7 @@ from vllm.entrypoints.openai.engine.protocol import (
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.serving import OpenAIServing
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.inputs import EngineInput, tokens_input
|
||||
from vllm.logger import init_logger
|
||||
from vllm.outputs import RequestOutput
|
||||
|
||||
Reference in New Issue
Block a user