llama.cpp
metal : add Q8_0 support
#2763
Merged

metal : add Q8_0 support #2763

ggerganov merged 3 commits into master from metal-add-q8_0
ggerganov
ggerganov metal : add dequantize_q8_0 kernel
46a0881c
ggerganov metal : add mul_mat_q8_0_f32 kernel
61c8259a
ggerganov metal : add Q8_0 mul_mm kernel
1202e06c
ggerganov ggerganov marked this pull request as ready for review 2 years ago
ggerganov ggerganov requested a review from lshzh-ww lshzh-ww 2 years ago
lshzh-ww
lshzh-ww approved these changes on 2023-08-24
ggerganov ggerganov merged d67777c2 into master 2 years ago
ggerganov ggerganov deleted the metal-add-q8_0 branch 2 years ago
ggerganov
lshzh-ww
ggerganov
sukualam

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone