llama.cpp
CUDA: faster non k-quant mul_mat_q kernels
#2483
Merged
Overview
Commits
1
Changes
View On GitHub

CUDA: faster non k-quant mul_mat_q kernels #2483

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-faster-mmq-3
JohannesGaessler
Dampfinchen
slaren
slaren approved these changes on 2023-08-02
JohannesGaessler CUDA: faster non k-quant mul_mat_q kernels
d6154f5b
JohannesGaessler JohannesGaessler force pushed to d6154f5b 2 years ago
JohannesGaessler JohannesGaessler merged 468ea24f into master 2 years ago
Nexesenex
JohannesGaessler
Nexesenex
cebtenzzre
Nexesenex
LostRuins
JohannesGaessler
Nexesenex
Nexesenex

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