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

move HIPBLAS definitions into ggml-cuda.h to clean up ggml-cuda.cu #3

Closed
wants to merge 0 commits into from

Conversation

YellowRoseCx
Copy link
Collaborator

this moves HIPBLAS definitions into ggml-cuda.h instead of sticking them all on top of ggml-cuda.h. It makes the code a little cleaner and potentially versatile

Copy link
Owner

@SlyEcho SlyEcho left a comment

Choose a reason for hiding this comment

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

No, this would make pretty much all the code include a buch of CUDA or HIP stuff.

This is because ggm-cuda.h is included from ggml.c, llama-util.h, llama.cpp, llama.h.

But a dedicated header file for the defines is something I was contemplating.

@YellowRoseCx YellowRoseCx deleted the branch SlyEcho:hipblas July 2, 2023 20:41
@YellowRoseCx YellowRoseCx deleted the hipblas branch July 2, 2023 20:41
@YellowRoseCx YellowRoseCx restored the hipblas branch July 2, 2023 20:48
@YellowRoseCx YellowRoseCx reopened this Jul 2, 2023
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