Fix: Check the type of params to be a Sequence not list. #19910
Conversation
Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com>
|
👋 Hi! Thank you for contributing to the vLLM project. 💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels. Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can either: Add 🚀 |
There was a problem hiding this comment.
Summary of Changes
Hello @rabinadk1, 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 specific type validation bug in the _validate_and_add_requests method located in llm.py. The core change involves broadening the accepted type for params and lora_request from a strict list to any Sequence type. This ensures that the method correctly handles various sequence inputs, such as tuples, thereby enhancing the flexibility and correctness of the API's input validation.
Highlights
- Type System Improvement: The type checks for
paramsandlora_requestwithin the_validate_and_add_requestsmethod invllm/entrypoints/llm.pyhave been updated fromlistto the more generalSequenceabstract base class. - Bug Fix: This change resolves an issue where inputs provided as
tupleforparamsorlora_requestwould incorrectly fail validation, despite being valid sequence types, thus improving the method's robustness.
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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| 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 issue 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 is currently in preview and 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 to provide feedback.
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
-
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. ↩
There was a problem hiding this comment.
Code Review
This pull request correctly addresses an issue where type checks for params and lora_request in the _validate_and_add_requests method were too restrictive, using isinstance(..., list) instead of isinstance(..., Sequence). The changes align the implementation with the function's type hints, which already allow for general Sequence types (like tuple) for these parameters.
The modifications on lines 1453, 1457, and 1461 in vllm/entrypoints/llm.py replace list with Sequence in isinstance checks. This makes the validation logic more robust and correctly supports a wider range of sequence types as intended.
The change is well-targeted, and the PR description, including the test plan and results, clearly explains the purpose and verifies the fix. I find no issues of medium, high, or critical severity. The code quality and clarity are improved by this change.
|
Thanks @rabinadk1 |
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com>
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com> Signed-off-by: juncheoll <th6re8e@naver.com>
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com> Signed-off-by: fhl <2410591650@qq.com>
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com>
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com>
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com> Signed-off-by: Will Eaton <weaton@redhat.com>
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com>
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com>
…t#19910) Signed-off-by: Rabin Adhikari <rabin.adk1@gmail.com> Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
Essential Elements of an Effective PR Description Checklist
Purpose
The method
_validate_and_add_requestsinllm.pyhas the type ofSequenceforparamsandlora_request, but the check is forlisttype. So, it doesn't work for thetupletype. Now, it does work for any of the sequence types.Test Plan
Passing the
paramsor thelora_requestwith a different length than the number of requests.Test Result
Now, when the lengths are different, ValueError is successfully thrown.
(Optional) Documentation Update