[Doc] Update docs for New Model Implementation #20115
Conversation
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
There was a problem hiding this comment.
Summary of Changes
Hello @DarkLight1337, 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 primarily focuses on enhancing the user experience and clarity of the documentation related to integrating new models into vLLM. It achieves this by restructuring the navigation menu for model implementation guides and by refining the main introductory page to be a more effective summary and a clearer gateway to detailed sub-sections, including a crucial tip for automatic model loading.
Highlights
- Documentation Navigation Restructuring: The
docs/.nav.ymlfile has been updated to transform the 'Model Implementation' section into a detailed sub-menu. This change explicitly lists theREADME.mdandmultimodal.mdfiles, alongside a glob pattern to include all other relevant documentation files within thecontributing/model/directory, improving discoverability of sub-pages. - Improved Model Contribution Guide: The
docs/contributing/model/README.mdfile has been significantly revised. Its title was changed from 'Adding a New Model' to 'Summary', and its content was rewritten to provide a high-level overview of model integration. It now includes an important note advising users to first attempt loading models via the Transformers backend, and clearly directs users to specific sub-pages for detailed step-by-step guides on implementing, registering, testing, and adding multi-modal support.
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 updates the documentation for adding a new model to vLLM, aiming to improve readability. The changes in docs/contributing/model/README.md are a significant improvement, making the guide clearer and more user-friendly. I've identified a potential issue in docs/.nav.yml where the use of a glob pattern could lead to duplicate entries in the navigation sidebar and have suggested a fix.
docs/.nav.yml
Outdated
| - Model Implementation: contributing/model | ||
| - Model Implementation: | ||
| - contributing/model/README.md | ||
| - contributing/model/* |
There was a problem hiding this comment.
The glob pattern * will expand to all files in the contributing/model/ directory, including README.md and multimodal.md which are already listed explicitly. This is likely to cause duplicate entries in the navigation menu.
To avoid this and to control the order of pages, it's better to explicitly list the files you want to include between README.md and multimodal.md.
- contributing/model/basic.md
- contributing/model/registration.md
- contributing/model/tests.md
|
👋 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 🚀 |
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Signed-off-by: Will Eaton <weaton@redhat.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.Purpose
Update the section to be easier to follow.
Test Plan
Test Result
(Optional) Documentation Update