llama.cpp
CUDA: faster k-quant mul_mat_q kernels
#2525
Merged

CUDA: faster k-quant mul_mat_q kernels #2525

JohannesGaessler
JohannesGaessler CUDA: faster k-quant mul_mat_q kernels
fe6a8f80
Loufe
JohannesGaessler
slaren
slaren
slaren commented on 2023-08-05
slaren
slaren approved these changes on 2023-08-05
JohannesGaessler JohannesGaessler merged f514d1b3 into master 2 years ago
JohannesGaessler

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone