Skip to content

[Bugfix][Router] Run KvawareRouter /tokenize fallback in executor to avoid blocking event loop #1069

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

Open
Asthenia0412 wants to merge 2 commits into
base: main
Choose a base branch
from
+7 −3
Open

[Bugfix][Router] Run KvawareRouter /tokenize fallback in executor to avoid blocking event loop #1069

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8137dd8
fix: Run KvawareRouter /tokenize fallback in executor to avoid blocki…
Aug 29, 2026
2a62aa4
fix: Address review feedback — use shared aiohttp session for /tokeni…
Aug 29, 2026
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
14 changes: 10 additions & 4 deletions src/vllm_router/routers/routing_logic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -402,10 +402,16 @@ async def route_request(
"model": endpoints[0].model_names[0],
"prompt": request_json.get("prompt", ""),
}
body = requests.post(
remote_url, headers=headers, json=data, timeout=10
).json()
token_ids = body["tokens"]
# Run the blocking HTTP call in an executor so it does not
# stall the event loop (mirrors tokenize_prompt fallback).
loop = asyncio.get_running_loop()
response = await loop.run_in_executor(
None,
lambda: requests.post(
remote_url, headers=headers, json=data, timeout=10
),
)
token_ids = response.json()["tokens"]

@gemini-code-assist gemini-code-assist Bot Aug 29, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Since route_request is an asynchronous function and has access to the request object, we can leverage the shared aiohttp client session from request.app.state.aiohttp_client_wrapper() instead of using requests.post in an executor.

Using requests.post without a session creates a new TCP connection for every fallback request, which is highly inefficient under load and can lead to socket exhaustion. Utilizing the shared aiohttp client session enables connection reuse and avoids the overhead of thread-pool execution.

            client = request.app.state.aiohttp_client_wrapper()
            async with client.post(
                remote_url, headers=headers, json=data, timeout=10
            ) as response:
                response_json = await response.json()
                token_ids = response_json["tokens"]


event_id = "Lookup" + str(uuid.uuid4())
msg = LookupMsg(tokens=token_ids, event_id=event_id)
Expand Down