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

[dermodmaster]

Currently vllm-router limits the concurrent requests to 100 while using the AiohttpClientWrapper in aiohttp_client.py.
In my test scenario the deployment router will not proxy more than 100 concurrent llm requests to the model.
This is because the aiohttp.ClientSession() will create a aiohttp.TCPConnector which default limit is 100 concurrent requests (see aiohttp docs for TCPConnector).

As the already implemented comment says, it is intended to have unlimited connections there, but the implementation itself is missing:

    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()
        logger.info(f"aiohttp ClientSession instantiated. Id {id(self.async_client)}")

I propose to create a aiohttp.TCPConnector with limit=0 which equals unlimited and pass it to the created aiohttp.ClientSession().

FIX #765

---

• Make sure the code changes pass the pre-commit checks.
• Sign-off your commit by using -s when doing git commit
• Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].

Detailed Checklist (Click to Expand)

Thank you for your contribution to production-stack! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Feat] for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).
• [Router] for changes to the vllm_router (e.g., routing algorithm, router observability, etc.).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• Pass all linter checks. Please use pre-commit to format your code. See README.md for installation.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.

DCO and Signed-off-by

When contributing changes to this project, you must agree to the DCO. Commits must include a Signed-off-by: header which certifies agreement with the terms of the DCO.

Using -s with git commit will automatically add this header.

What to Expect for the Reviews

We aim to address all PRs in a timely manner. If no one reviews your PR within 5 days, please @-mention one of YuhanLiu11
, Shaoting-Feng or ApostaC.

[gemini-code-assist]

Summary of Changes

Hello @dermodmaster, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a concurrency limitation within the vllm-router's AiohttpClientWrapper. Previously, the aiohttp.ClientSession implicitly used a TCPConnector with a default limit of 100 concurrent requests, hindering the router's ability to handle more concurrent operations. The change explicitly configures the ClientSession to use an aiohttp.TCPConnector with limit=0, effectively enabling unlimited connections and allowing the router to operate at its full potential.

Highlights

• Unlimited Connections: The aiohttp.ClientSession in vllm-router is now configured to use an unlimited number of concurrent connections by setting aiohttp.TCPConnector(limit=0).
• Concurrency Improvement: This change removes the default limit of 100 concurrent requests, allowing the router to fully leverage its intended concurrency capabilities.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly addresses an issue where the aiohttp.ClientSession was limited to 100 concurrent connections by default, contrary to the intended behavior of having unlimited connections. The approach of using aiohttp.TCPConnector with limit=0 is correct for this purpose. However, my review identified a potential resource leak. When an external connector is passed to ClientSession, it doesn't take ownership by default, meaning it won't be closed automatically. I've provided a specific comment with a code suggestion to fix this by setting connector_owner=True. With this change, the implementation will be robust.

[zerofishnoodles]

Could you fix the pre-commit issue?

[dermodmaster]

@zerofishnoodles Yes, sry should be fixed now.

[zerofishnoodles]

LGTM