[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
@@ -13,7 +13,6 @@ import pybase64 as base64
from fastapi import Request
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
from vllm.entrypoints.openai.completion.protocol import (
CompletionLogProbs,
CompletionRequest,
@@ -34,7 +33,8 @@ from vllm.entrypoints.openai.engine.serving import (
clamp_prompt_logprobs,
)
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.utils import get_max_tokens, should_include_usage
from vllm.entrypoints.serve.utils.api_utils import get_max_tokens, should_include_usage
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
from vllm.exceptions import VLLMValidationError
from vllm.inputs import EngineInput
from vllm.logger import init_logger