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

ggml : do not crash when quantizing q4_x_x with an imatrix #9192

Merged
merged 1 commit into from
Aug 26, 2024

Conversation

slaren
Copy link
Collaborator

@slaren slaren commented Aug 26, 2024

Fixes #9190

@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label Aug 26, 2024
@bartowski1182
Copy link
Contributor

to confirm, does this just makes passing imatrix a no-op? or will it actually be useful in other parts of this quant schema that don't specifically use q4_0_x_x (and therefore still worth passing/using, just not as useful)

@slaren
Copy link
Collaborator Author

slaren commented Aug 26, 2024

I don't actually know what types are used in this quant schema, but if there are other types, they will still be able to use the imatrix, it will only be the q4_x_x (and q8_0) tensors that will not use the imatrix.

@slaren slaren merged commit 7d787ed into master Aug 26, 2024
53 checks passed
@slaren slaren deleted the sl/fix-q4xx-imatrix branch August 26, 2024 17:44
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 15, 2024
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ggml changes relating to the ggml tensor library for machine learning
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Bug: Can't make imatrix quant of Q4_0_X_X
3 participants