llama.cpp
1.5 bit: we can do even better
#5999
Merged

1.5 bit: we can do even better #5999

ggerganov merged 6 commits into master from ik/even_better_iq1s
ikawrakow
iq1_s: we can do even better
82380acf
iq1_s: make scalar and AVX2 work with the new version
c09f7349
iq1_s: make Neon work with new version.
4fba3e00
iq1_s: make Metal work with new version
da4528bc
iq1_s: very slightly faster dequantize on Metal
436c65e1
iq1_s: fix dequantize on the CPU
5440a127
ikawrakow ikawrakow added breaking change
ggerganov
ggerganov approved these changes on 2024-03-11
ggerganov ggerganov merged 44ca159f into master 1 year ago
Artefact2
okpatil4u
ikawrakow

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone