[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
@@ -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
+1 -1
View File
@@ -12,7 +12,7 @@ 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
@@ -9,9 +9,9 @@ from typing import Literal, cast
import numpy as np
from vllm.engine.protocol import EngineClient, StreamingInput
from vllm.entrypoints.logger import RequestLogger
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 PromptType
from vllm.logger import init_logger
from vllm.model_executor.models.interfaces import SupportsRealtime
@@ -9,7 +9,7 @@ from fastapi import APIRouter, Form, Request
from fastapi.responses import JSONResponse, StreamingResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.utils import (
from vllm.entrypoints.serve.utils.api_utils import (
load_aware_call,
with_cancellation,
)
@@ -5,12 +5,12 @@ from collections.abc import AsyncGenerator
from fastapi import Request
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
RequestResponseMetadata,
)
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
from vllm.logger import init_logger
from vllm.outputs import RequestOutput
@@ -9,7 +9,7 @@ from fastapi import APIRouter, Form, Request
from fastapi.responses import JSONResponse, StreamingResponse
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.utils import (
from vllm.entrypoints.serve.utils.api_utils import (
load_aware_call,
with_cancellation,
)
@@ -5,12 +5,12 @@ from collections.abc import AsyncGenerator
from fastapi import Request
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
RequestResponseMetadata,
)
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
from vllm.logger import init_logger
from vllm.outputs import RequestOutput