llama.cpp
CUDA: tuned mul_mat_q kernels
#2546
Merged
Overview
Commits
1
Changes
View On GitHub

CUDA: tuned mul_mat_q kernels #2546

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-faster-mmq-7
JohannesGaessler
JohannesGaessler CUDA: tuned mul_mat_q kernels
ca32203c
JohannesGaessler JohannesGaessler force pushed to ca32203c 2 years ago
slaren
Dampfinchen
JohannesGaessler
slaren
slaren approved these changes on 2023-08-08
Dampfinchen
ggerganov
JohannesGaessler
JohannesGaessler JohannesGaessler merged 25d43e0e into master 2 years ago
JohannesGaessler
LostRuins
JohannesGaessler
LostRuins
JohannesGaessler
Dampfinchen
LostRuins
Dampfinchen
SlyEcho
SlyEcho commented on 2023-08-09
LostRuins
LostRuins
Dampfinchen
JohannesGaessler
JohannesGaessler
LostRuins

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