[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
+2 -2
View File
@@ -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.