Skip to content

Fix IQ3_XXS on Metal #5219

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

Merged
merged 1 commit into from
Jan 30, 2024
Merged

Fix IQ3_XXS on Metal #5219

merged 1 commit into from
Jan 30, 2024

Conversation

ikawrakow
Copy link
Contributor

What was the issue? Simply forgotten to update ggml-metal.metal with the latest version of iq3xxs_grid.

Having a copy-paste of the same data in 3 files is obviously error prone.

@ggerganov We need to factor out these into a separate header that gets included in ggml-quants.c, ggml-cuda.cu, and ggml-metal.metal. I had started doing that at some point but dropped based on your request. Time to do it now?

@ikawrakow ikawrakow requested a review from ggerganov January 30, 2024 16:52
Copy link
Member

@ggerganov ggerganov left a comment

Choose a reason for hiding this comment

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

Yes, I will do it

#5220

@ggerganov ggerganov merged commit fea4fd4 into master Jan 30, 2024
jordankanter pushed a commit to jordankanter/llama.cpp that referenced this pull request Feb 3, 2024
hodlen pushed a commit to hodlen/llama.cpp that referenced this pull request Apr 1, 2024
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