chore: bump sgl-kernel v0.2.9 #8713
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @zhyncs, 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!
I've created this pull request to bump the sgl-kernel package version to 0.2.9. This change involves updating the version string across various project configuration files and ensuring that the Docker build process pulls the newly released kernel version. This is a routine maintenance update to incorporate the latest sgl-kernel improvements.
Highlights
- Version Updates: Updated the sgl-kernel version to 0.2.9 in pyproject.toml, pyproject_cpu.toml, pyproject_rocm.toml, and sgl_kernel/version.py.
- Dockerfile Update: Modified the docker/Dockerfile to install the sgl_kernel wheel from the v0.2.9 release.
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 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 or fill out our survey 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 bumps the version of sgl-kernel to 0.2.9. The version number has been updated consistently across the pyproject.toml files and sgl_kernel/version.py. However, I've found a critical issue in the Dockerfile where a Python 3.9 wheel is being installed in a Python 3.10 environment, which will likely cause failures. My review includes a comment with a suggested fix for this issue.
| @@ -63,7 +63,7 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip setuptools wheel html5li | |||
| && python3 -m pip install --no-cache-dir -e "python[${BUILD_TYPE}]" --extra-index-url https://download.pytorch.org/whl/cu${CUINDEX} \ | |||
| && python3 -m pip install --no-cache-dir nvidia-nccl-cu12==2.27.6 --force-reinstall --no-deps \ | |||
| && if [ "$CUDA_VERSION" = "12.8.1" ]; then \ | |||
| python3 -m pip install --no-cache-dir https://github.com/sgl-project/whl/releases/download/v0.2.8/sgl_kernel-0.2.8+cu128-cp39-abi3-manylinux2014_x86_64.whl --force-reinstall --no-deps ; \ | |||
| python3 -m pip install --no-cache-dir https://github.com/sgl-project/whl/releases/download/v0.2.9/sgl_kernel-0.2.9+cu128-cp39-abi3-manylinux2014_x86_64.whl --force-reinstall --no-deps ; \ | |||
There was a problem hiding this comment.
There's a Python version mismatch here. The Docker image is based on Ubuntu 22.04, which uses Python 3.10 as its default python3. However, the wheel being installed is for Python 3.9 (cp39). This will likely cause pip to fail to find a compatible distribution or lead to runtime errors.
To fix this, you should use a wheel built for Python 3.10 (cp310).
Additionally, to improve maintainability, consider defining the sgl-kernel version as a variable (e.g., ARG SGL_KERNEL_VERSION=0.2.9) at the top of the Dockerfile and using it to construct the URL. This would make future version bumps easier and less error-prone.
python3 -m pip install --no-cache-dir https://github.com/sgl-project/whl/releases/download/v0.2.9/sgl_kernel-0.2.9+cu128-cp310-abi3-manylinux2014_x86_64.whl --force-reinstall --no-deps ; \
Motivation
Modifications
Accuracy Test
Benchmark & Profiling
Checklist