[Frontend] Consolidate online serving utils. (#44479)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-06-04 06:49:31 +00:00
committed by GitHub
parent b4b4aaa70e
commit d01d0b4646
81 changed files with 466 additions and 435 deletions
+1 -1
View File
@@ -16,9 +16,9 @@ from vllm import PoolingParams, PoolingRequestOutput, envs
from vllm.config import VllmConfig
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.chat_utils import ChatTemplateConfig
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
from vllm.exceptions import VLLMNotFoundError
from vllm.inputs import EngineInput
from vllm.lora.request import LoRARequest
@@ -4,9 +4,9 @@
from fastapi import APIRouter, Depends, Request
from fastapi.responses import Response
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.utils import (
from vllm.entrypoints.serve.utils.api_utils import (
load_aware_call,
validate_json_request,
with_cancellation,
)
+5 -2
View File
@@ -6,8 +6,11 @@ from http import HTTPStatus
from fastapi import APIRouter, Depends, Request
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 .protocol import CohereEmbedRequest, EmbeddingRequest
from .serving import ServingEmbedding
+2 -2
View File
@@ -21,12 +21,12 @@ if TYPE_CHECKING:
from starlette.datastructures import State
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.sagemaker.api_router import (
from vllm.entrypoints.serve.sagemaker.api_router import (
EndpointFn,
GetHandlerFn,
RequestType,
)
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
else:
RequestLogger = object
@@ -5,8 +5,11 @@ from http import HTTPStatus
from fastapi import APIRouter, Depends, Request
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 .protocol import PoolingRequest
from .serving import ServingPooling
@@ -5,8 +5,11 @@ from http import HTTPStatus
from fastapi import APIRouter, Depends, Request
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
from .protocol import RerankRequest, ScoreRequest