Skip to content
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

[frontend] Replace is_inference with torch.no_grad for more elegant FX Graph output node arguments handling #231

Merged
merged 2 commits into from
Nov 28, 2023

Conversation

xTayEx
Copy link
Contributor

@xTayEx xTayEx commented Nov 4, 2023

No description provided.

Copy link
Member

@zhanghb97 zhanghb97 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please modify the BuddyLlama example with torch.no_grad as well.

…nt FX Graph output node arguments handling
Copy link
Member

@zhanghb97 zhanghb97 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks!

@zhanghb97 zhanghb97 merged commit cbdfc44 into buddy-compiler:main Nov 28, 2023
1 check passed
taiqzheng pushed a commit to taiqzheng/buddy-mlir that referenced this pull request Dec 26, 2023
…nt FX Graph output node arguments handling (buddy-compiler#231)

* [frontend] Replace `is_inference` with `torch.no_grad` for more elegant FX Graph output node arguments handling

* [frontend] Support diffrent argument dtype for the parameter combination/extraction logic
ShiHaoGao pushed a commit to ShiHaoGao/buddy-mlir that referenced this pull request Oct 18, 2024
…nt FX Graph output node arguments handling (buddy-compiler#231)

* [frontend] Replace `is_inference` with `torch.no_grad` for more elegant FX Graph output node arguments handling

* [frontend] Support diffrent argument dtype for the parameter combination/extraction logic
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants