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

cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q #5772

Merged
merged 3 commits into from
Mar 1, 2024

Conversation

phymbert
Copy link
Collaborator

@phymbert phymbert commented Feb 28, 2024

Cleanup deprecated not used params.mul_mat_q and related docs. It can make confusion for user trying to optmize GPU inference performance: #3359 and #3412 .

Breaking upstream application if any using it.

@slaren
Copy link
Collaborator

slaren commented Feb 28, 2024

This option is no longer supported, and should be removed completely instead.

@phymbert phymbert marked this pull request as draft February 28, 2024 17:15
@phymbert
Copy link
Collaborator Author

@slaren Thanks, I did not checked :/, I will clean it up it then.

@phymbert phymbert changed the title server: docs: --no-mul-mat-q,-nommq cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q Feb 28, 2024
@phymbert phymbert added the breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility. label Feb 28, 2024
@phymbert phymbert marked this pull request as ready for review February 28, 2024 17:37
@phymbert
Copy link
Collaborator Author

phymbert commented Mar 1, 2024

@ggerganov Hi, as I got one approval, should I wait for yours ? thanks

@ggerganov ggerganov merged commit 3ab8b3a into master Mar 1, 2024
61 checks passed
@phymbert phymbert deleted the feature/server-mul-mat-q branch March 1, 2024 13:11
hazelnutcloud pushed a commit to hazelnutcloud/llama.cpp that referenced this pull request Mar 10, 2024
* cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q

* remove: mul_mat_q in compare llama bench and usage

* update llama-bench

---------

Co-authored-by: slaren <[email protected]>
jordankanter pushed a commit to jordankanter/llama.cpp that referenced this pull request Mar 13, 2024
* cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q

* remove: mul_mat_q in compare llama bench and usage

* update llama-bench

---------

Co-authored-by: slaren <[email protected]>
hodlen pushed a commit to hodlen/llama.cpp that referenced this pull request Apr 1, 2024
* cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q

* remove: mul_mat_q in compare llama bench and usage

* update llama-bench

---------

Co-authored-by: slaren <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants