Skip to content

[Bugfix] Concurrent requests to model are currently limited to 100 due to aiohttp default #767

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ruizhang0101 merged 8 commits into from
Dec 20, 2025
+4 −1
Merged

[Bugfix] Concurrent requests to model are currently limited to 100 due to aiohttp default #767

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
b11db8b
Set aiohttp ClientSession to use unlimited connections
Dec 15, 2025
c0784b8
set transcription default langauge to "de"
Dec 15, 2025
c7713af
format aiohttp.Clientsession
Dec 19, 2025
a7981e4
Set aiohttp ClientSession to use unlimited connections
dermodmaster Dec 11, 2025
9c1347d
Add missing connector_owner parameter to the aiohttp.ClientSession in…
dermodmaster Dec 11, 2025
0a1dc37
Format aiohttp_client.py with black
dermodmaster Dec 19, 2025
779c9fb
Revert unnecessary commit
dermodmaster Dec 19, 2025
f906c36
Merge branch 'main' into fix/aiohttp-unlimited-connections
ruizhang0101 Dec 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion src/vllm_router/aiohttp_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,10 @@ def start(self):
"""Instantiate the client. Call from the FastAPI startup hook."""
# To fully leverage the router's concurrency capabilities,
# we set the maximum number of connections to be unlimited.
self.async_client = aiohttp.ClientSession()
connector = aiohttp.TCPConnector(limit=0)
self.async_client = aiohttp.ClientSession(
connector=connector, connector_owner=True
)
logger.info(f"aiohttp ClientSession instantiated. Id {id(self.async_client)}")

async def stop(self):
Expand Down