cmake: Update vllm_flash_attn for vllm_kernels #20032
Conversation
|
👋 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 @seemethere, 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 focuses on updating a critical external dependency, vllm-flash-attn, by bumping its commit hash in the CMake configuration. This change is essential for addressing an import issue that arose during a recent package refactor and for integrating the latest features and fixes from the upstream flash-attention project, particularly those supporting vllm_kernels and an improved scheduler.
Highlights
- External Dependency Update: I've updated the
GIT_TAGfor thevllm-flash-attnexternal project withincmake/external_projects/vllm_flash_attn.cmake. The tag has been changed from763ad155a1c826f71ff318f41edb1e4e5e376ddbto5f3644181c7a15345ce20bfc65af117d3601b524. - Purpose and Impact: This update is a stepping stone towards resolving an import issue encountered during a package refactor. It incorporates recent upstream changes from the
flash-attentionrepository, specifically those related to setting up thevllm_kernelspackage and a newvarlen combine scheduler.
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
The pull request updates the vllm_flash_attn submodule to the latest main branch, resolving an import issue encountered during package refactoring. The change involves updating the GIT_TAG in the vllm_flash_attn.cmake file to point to the new commit hash.
| @@ -38,7 +38,7 @@ else() | |||
| FetchContent_Declare( | |||
| vllm-flash-attn | |||
| GIT_REPOSITORY https://github.com/vllm-project/flash-attention.git | |||
| GIT_TAG 763ad155a1c826f71ff318f41edb1e4e5e376ddb | |||
| GIT_TAG 5f3644181c7a15345ce20bfc65af117d3601b524 | |||
There was a problem hiding this comment.
It would be helpful to add a comment explaining why this commit was chosen. This provides context for future maintainers when considering updates to this dependency. Also, consider adding a comment on what the implications are of updating this dependency.
|
This pull request has merge conflicts that must be resolved before it can be |
Updates vllm_flash_attn to latest main, which includes 2 commits: * vllm_flash_attn: Setup for vllm_kernels package * varlen combine scheduler Full diff: vllm-project/flash-attention@763ad15...5f36441 Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
b78ab65 to
b419d47
Compare
Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
Signed-off-by: Eli Uriegas <eliuriegas@meta.com> Signed-off-by: Will Eaton <weaton@redhat.com>
Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
Signed-off-by: Eli Uriegas <eliuriegas@meta.com> Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.Purpose
Some stepping stones for #17419,
This resolves an import issue that I ran into while testing the package refactor.
Updates vllm_flash_attn to latest main, which includes 2 commits:
Full diff:
vllm-project/flash-attention@763ad15...5f36441
Test Plan
CI + some local testing
Test Result
(Optional) Documentation Update