Skip to content

kompute: add mul_mat_q4_k shader #10097

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 1 commit into from
Oct 31, 2024
Merged

kompute: add mul_mat_q4_k shader #10097

merged 1 commit into from
Oct 31, 2024

Conversation

@slp
Copy link
Collaborator

@slp slp commented Oct 30, 2024

This is a more or less direct translation from the Metal implementation to GLSL.

@slp
kompute: add mul_mat_q4_k shader
85efc90 
This is a more or less direct translation from the Metal implementation
to GLSL.

Signed-off-by: Sergio Lopez <[email protected]>
@github-actions github-actions bot added ggml changes relating to the ggml tensor library for machine learning Kompute https://github.com/KomputeProject/kompute/ labels Oct 30, 2024
ggerganov
ggerganov approved these changes Oct 31, 2024
View reviewed changes
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.

Do the test-backend-ops pass successfully?

@slp
Copy link
Collaborator Author

slp commented Oct 31, 2024

Do the test-backend-ops pass successfully?

No, but it didn't before this change either. Seems like the kompute backend has rotten a bit during the last months. In the following weeks I intend to get it to pass test-backend-ops and port more shaders.

@ggerganov ggerganov merged commit 1329c0a into ggml-org:master Oct 31, 2024
53 checks passed
@ggerganov
Copy link
Member

Ok, thanks for helping out. If things are going well, I'll look to add the kompute backend to ggml-ci so we can have regular testing of the changes.

arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 15, 2024
@slp @arthw
kompute: add mul_mat_q4_k shader (ggml-org#10097)
cfb7da6 
This is a more or less direct translation from the Metal implementation
to GLSL.

Signed-off-by: Sergio Lopez <[email protected]>
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
@slp @arthw
kompute: add mul_mat_q4_k shader (ggml-org#10097)
a88efa9 
This is a more or less direct translation from the Metal implementation
to GLSL.

Signed-off-by: Sergio Lopez <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@ggerganov ggerganov ggerganov approved these changes

Assignees

No one assigned

Labels

ggml changes relating to the ggml tensor library for machine learning Kompute https://github.com/KomputeProject/kompute/

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@slp @ggerganov