Skip to content

llama : avoid hardcoded QK_K constant#11061

Merged
ggerganov merged 1 commit intomasterfrom
gg/llama-refactor-2
Jan 8, 2025
Merged

llama : avoid hardcoded QK_K constant#11061
ggerganov merged 1 commit intomasterfrom
gg/llama-refactor-2

Conversation

@ggerganov
Copy link
Member

Use the actual block size.

@ggerganov ggerganov merged commit c07d437 into master Jan 8, 2025
@ggerganov ggerganov deleted the gg/llama-refactor-2 branch January 8, 2025 14:19
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Feb 26, 2025
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.

2 participants