llama.cpp
Speed-up ggml_vec_dot_q4_1() ARM_NEON
#900
Merged
Overview
Commits
6
Changes
View On GitHub

Speed-up ggml_vec_dot_q4_1() ARM_NEON #900

ggerganov merged 6 commits into master from opt-q4_1
ggerganov
unbounded
ggerganov ggml : speed-up q4_1 ARM_NEON by ~5%
2ae3164d
ggerganov ggerganov force pushed from 886c1b94 to 2ae3164d 2 years ago
ggerganov ggml : implement vaddvq when missing
14a0b207
ggerganov ggerganov force pushed to 14a0b207 2 years ago
ggerganov ggml : implement vminvq and vmaxvq when missing
be21d538
ggerganov ggml : implement vzip when missing
1b59a073
ggerganov ggml : fix comment
63f7ecf4
ggerganov ggml : try to use correct ifdef
99e7c9b9
ggerganov
ggerganov ggerganov merged d990e3ff into master 2 years ago
ggerganov ggerganov deleted the opt-q4_1 branch 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum