Conversation
Summary of ChangesHello @majiayu000, 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 introduces a 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 adds a revision parameter to the load_vllm function to allow specifying a model revision, which is then passed to the vLLM engine arguments. My feedback includes a suggestion to add a type hint for the new parameter to improve code clarity and consistency.
unsloth_zoo/vllm_utils.py
Outdated
| gpu_memory_utilization : float = 0.8, | ||
| max_seq_length : int = 8192, | ||
| dtype : torch.dtype = None, | ||
| revision = None, |
There was a problem hiding this comment.
For consistency with other parameters and for better code clarity, please add a type hint for the new revision parameter. Based on its usage, Optional[str] would be appropriate.
| revision = None, | |
| revision : Optional[str] = None, |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| max_seq_length : int = 8192, | ||
| dtype : torch.dtype = None, | ||
| revision = None, | ||
| training : bool = True, |
There was a problem hiding this comment.
Inserting revision between dtype and training changes the positional argument order, so any external callers using positional arguments after dtype will now pass their training boolean into revision, shifting the rest of the parameters. That silently alters behavior (e.g., training flips back to default True, float8_kv_cache stays False, etc.) and can cause wrong runtime settings. To avoid a backward-compat regression, add revision at the end or make the remaining parameters keyword-only.
Useful? React with 👍 / 👎.
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
TFTR |
2 participants
Summary
load_vllmand pass through to vLLM engine argsTest Plan