Add similar to vllm wait --ready-check-timeout-sec parameter for benchmark script #15466
Conversation
Summary of ChangesHello @almaslof, 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 enhances the Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Using Gemini Code AssistThe 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
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 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
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a wait_for_server function to the benchmarking script, allowing it to wait for the server to be ready before starting the benchmark. This is controlled by a new --ready-check-timeout-sec command-line argument. The implementation is clean and effective. I have a couple of suggestions to improve code clarity and reusability.
python/sglang/bench_serving.py
Outdated
| return {} | ||
|
|
||
|
|
||
| def wait_for_server(url: str, timeout_sec: int = 60) -> bool: |
There was a problem hiding this comment.
This is a useful utility function. Consider moving it to a more general location like a utility module (e.g., python/sglang/srt/utils/common.py) so it can be reused across the project. For instance, there is very similar logic in _execute_server_warmup function in python/sglang/srt/entrypoints/http_server.py that could be replaced by this new function.
python/sglang/bench_serving.py
Outdated
| except (requests.exceptions.ConnectionError, | ||
| requests.exceptions.Timeout, | ||
| requests.exceptions.RequestException) as e: |
There was a problem hiding this comment.
The tuple of exceptions caught here is redundant. requests.exceptions.ConnectionError and requests.exceptions.Timeout are both subclasses of requests.exceptions.RequestException. You can simplify this by just catching requests.exceptions.RequestException. Also, since the exception variable e is not used, it can be omitted.
except requests.exceptions.RequestException:
almaslof
changed the title
1 participant
Motivation
vllm bench servecommand has a command line argument--ready-check-timeout-sec(link)Adding it to sglang.
It is useful when running sequence of benchmarking scenarios.
There is wait_for_server function in utils, but is accepts
base_urland then appends it.Keeping added function inside
bench_serving.pyas the script seems to be designed to be dependency free from the rest of sglang's codebase.Modifications
Added
wait_for_endpointfunction intopython/sglang/bench_serving.pyscript.