xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-20 13:37:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

updated

Browse Source 
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
This commit is contained in:
Robert Shaw 2025-03-22 18:50:48 -04:00
parent 2fec6e0b5c
commit 24cbbe4778
2 changed files with 3 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/entrypoints/openai/api_server.py
View File

@ -137,8 +137,9 @@ async def build_async_engine_client(
# Context manager to handle engine_client lifecycle # Context manager to handle engine_client lifecycle
# Ensures everything is shutdown and cleaned up on error/exit # Ensures everything is shutdown and cleaned up on error/exit
engine_args = AsyncEngineArgs.from_cli_args(args) engine_args = AsyncEngineArgs.from_cli_args(args)
async with build_async_engine_client_from_engine_args( async with build_async_engine_client_from_engine_args(
engine_args, args.disable_frontend_multiprocessing) as engine: engine_args, args.disable_frontend_multiprocessing) as engine:
yield engine yield engine
@ -159,6 +160,7 @@ async def build_async_engine_client_from_engine_args(
usage_context = UsageContext.OPENAI_API_SERVER usage_context = UsageContext.OPENAI_API_SERVER
vllm_config = engine_args.create_engine_config(usage_context=usage_context) vllm_config = engine_args.create_engine_config(usage_context=usage_context)
# V1 AsyncLLM.
if envs.VLLM_USE_V1: if envs.VLLM_USE_V1:
if disable_frontend_multiprocessing: if disable_frontend_multiprocessing:
logger.warning( logger.warning(

16
vllm/entrypoints/openai/protocol.py
View File

@ -1649,19 +1649,3 @@ class TranscriptionResponseVerbose(OpenAIBaseModel):
words: Optional[list[TranscriptionWord]] = None words: Optional[list[TranscriptionWord]] = None
"""Extracted words and their corresponding timestamps.""" """Extracted words and their corresponding timestamps."""
class ZmqMsgRequest(BaseModel):
request_id: str
type: str
body: Union[CompletionRequest]
class ZmqMsgResponse(BaseModel):
request_id: str
type: str
stop: bool = True
body_type: Literal["str", "response"] = "str"
body: str
model_config = ConfigDict(arbitrary_types_allowed=True)