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

Merged

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

slaren merged 1 commit into master from sl/fix-q4xx-imatrix

ggml : do not crash when quantizing q4_x_x with an imatrix

e279ce0f

ggerganov approved these changes on 2024-08-26

github-actions added ggml

slaren merged 7d787ed9 into master 1 year ago

slaren deleted the sl/fix-q4xx-imatrix branch 1 year ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

ggml

Milestone

No milestone