llama.cpp
CUDA: use mul_mat_q kernels by default
#2683
Merged
Overview
Commits
1
Changes
View On GitHub

CUDA: use mul_mat_q kernels by default #2683

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-mmq-default
JohannesGaessler
slaren
JohannesGaessler
ggerganov
ggerganov approved these changes on 2023-08-22
ggerganov
Ph0rk0z
ikawrakow
ikawrakow
JohannesGaessler CUDA: use mul_mat_q kernels by default
f6a8864f
JohannesGaessler JohannesGaessler force pushed to f6a8864f 2 years ago
JohannesGaessler
JohannesGaessler JohannesGaessler merged c63bb1d1 into master 2 years ago
klosax
slaren

Login to write a write a comment.

Login via GitHub

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