biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Core] Use uvloop with zmq-decoupled front-end (#7570)

Browse Source
This commit is contained in:
Nick Hill
2024-08-15 22:48:07 -07:00
committed by GitHub
parent 54bd9a03c4
commit 9587b050fb
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/entrypoints/openai/rpc/server.py
View File

@@ -3,6 +3,7 @@ import signal
from typing import Any, Coroutine from typing import Any, Coroutine
import cloudpickle import cloudpickle
import uvloop
import zmq import zmq
import zmq.asyncio import zmq.asyncio
from typing_extensions import Never from typing_extensions import Never
@@ -217,4 +218,4 @@ async def run_server(server: AsyncEngineRPCServer):
def run_rpc_server(async_engine_args: AsyncEngineArgs, def run_rpc_server(async_engine_args: AsyncEngineArgs,
usage_context: UsageContext, rpc_path: str): usage_context: UsageContext, rpc_path: str):
server = AsyncEngineRPCServer(async_engine_args, usage_context, rpc_path) server = AsyncEngineRPCServer(async_engine_args, usage_context, rpc_path)
asyncio.run(run_server(server)) uvloop.run(run_server(server))