llama.cpp
ggml : fix I8MM Q4_1 scaling factor conversion
#10562
Merged

ggml : fix I8MM Q4_1 scaling factor conversion #10562

ggerganov merged 1 commit into master from gg/cpu-i8mm-fix-2
ggerganov
github-actions github-actions added testing
github-actions github-actions added ggml
ggerganov ggerganov changed the title ggml : fix row condition for i8mm kernels gml : fix I8MM runtime feature checks in CPU kernels 1 year ago
ggerganov
ggerganov commented on 2024-11-28
slaren
slaren commented on 2024-11-28
Base automatically changed from gg/cpu-q4_0-i8mm-fix to master 1 year ago
ggerganov ggerganov force pushed 1 year ago
ggerganov ggml : fix bug in Q4_1 x Q8_1 I8MM kernel
5acff8f3
ggerganov ggerganov force pushed to 5acff8f3 1 year ago
ggerganov ggerganov changed the title gml : fix I8MM runtime feature checks in CPU kernels ggml : fix I8MM Q4_1 scaling factor conversion 1 year ago
slaren
slaren approved these changes on 2024-11-29
ggerganov ggerganov merged f0678c5f into master 1 year ago
ggerganov ggerganov deleted the gg/cpu-i8mm-fix-2 branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone