Skip to content

[1/N] Update MMQ kernel catch up upstream llama.cpp implementation #3

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
Closed
wants to merge 6 commits into from
Closed

[1/N] Update MMQ kernel catch up upstream llama.cpp implementation #3

wants to merge 6 commits into from

Conversation

Isotr0py
Copy link
Owner

@Isotr0py Isotr0py commented Mar 17, 2025 •
edited
Loading

Refer to ggml-org/llama.cpp#7716 and ggml-org/llama.cpp#7921

  • Basic PR to support MMQ for i-matrix quantization in following PR.

Isotr0py added 6 commits March 16, 2025 17:24
@Isotr0py
move tiles function
e904800 
Signed-off-by: Isotr0py <[email protected]>
@Isotr0py
draft
37a6d8d 
Signed-off-by: Isotr0py <[email protected]>
@Isotr0py
fix warp size
8ad612b 
Signed-off-by: Isotr0py <[email protected]>
@Isotr0py
update and remove legacy code
fdf5257 
Signed-off-by: Isotr0py <[email protected]>
@Isotr0py
can build
ccf4a6b 
Signed-off-by: Isotr0py <[email protected]>
@Isotr0py
shmem
b98d327 
Signed-off-by: Isotr0py <[email protected]>
@Isotr0py Isotr0py mentioned this pull request Jul 26, 2025
Merged
@Isotr0py Isotr0py closed this Jul 26, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@Isotr0py