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

Fuse optimization #1248

Open
wants to merge 19 commits into
base: BertMLM_fixes
Choose a base branch
from
Open

Fuse optimization #1248

wants to merge 19 commits into from

Conversation

xinhaoc
Copy link
Collaborator

@xinhaoc xinhaoc commented Dec 21, 2023

Description of changes:

Related Issues:

Linked Issues:

  • Issue #

Issues closed by this PR:

  • Closes #

This change is Reviewable

cudaStream_t stream;
checkCUDA(get_legion_stream(&stream));
Internal::forward_kernel(m, input_ptr, output_ptr, stream);
Internal::forward_kernel(m, input.get_float_ptr(), output.get_float_ptr(), stream);
Copy link
Collaborator

Choose a reason for hiding this comment

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

This signature does not match dropout_kernels.h, which adds another parameter: size_t num_elements

cudaStream_t stream;
checkCUDA(get_legion_stream(&stream));
Internal::backward_kernel(m, output_grad_ptr, input_grad_ptr, stream);
Internal::backward_kernel(m, output_grad.get_float_ptr(), input_grad.get_float_ptr(), stream);
Copy link
Collaborator

Choose a reason for hiding this comment

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

This signature does not match dropout_kernels.h, which adds another parameter: size_t num_elements

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Hi Pinku, I pushed some fix, please tell me if you meet any issue.

@jiazhihao
Copy link
Collaborator

@xinhaoc Should we close this PR?

@xinhaoc
Copy link
Collaborator Author

xinhaoc commented Sep 5, 2024

@xinhaoc Should we close this PR?

this is the working pr of candle project, let's keep it know

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.

3 participants