-
Notifications
You must be signed in to change notification settings - Fork 112
Update cuda build #525
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Update cuda build #525
Conversation
ca071d0 to
cf7b528
Compare
|
Hi @YangZhou1997 @derekwin could you have a look at it ? |
|
LGTM! Thank you very much! |
|
@YangZhou1997 I have one question: Would it be advisable to include a .pre-commit-config.yaml file to ensure safe local validation before commits? |
|
Thanks @yiakwy-xpu-ml-framework-team for the PR, and @derekwin for reviewing. I am less familiar with the pre-commit check. Let me @MaoZiming to see how you think of the current pre-commit config. @yiakwy-xpu-ml-framework-team, re the build inside docker, I am thinking of making the build functions reusable such as Re the unnecessary |
|
@YangZhou1997 Sure. Once it is ready I can rebase on it the last branch. With more and more codes, I surelly need an automatic code cleaner to unify the styles. This is standard file we use in SGlang and vLLM. I am working on ep benchmark to better understand our design! Hope I can contribute to core funcion soon. Cheers! |
Description
Please include a summary of the changes and the related issue.
Add build scripts insider docker .
For some reasons, we our system is managed with official NVIDIA software management tools to configure images cross clusters.
Hence for quick test , we just build software inside docker.
OS : ubuntu 22.04
CUDA SDK : 12.8
Type of Change
How Has This Been Tested?
Include any tests here.
Checklist
format.sh.build_and_install.shto verify compilation.build_and_install.sh