llama.cpp
CUDA: revise q8_1 data layout for mul_mat_q
#7824
Merged
Overview
Commits
1
Changes
View On GitHub

CUDA: revise q8_1 data layout for mul_mat_q #7824

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-mmq-q8_1-2
JohannesGaessler
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
github-actions
slaren
slaren approved these changes on 2024-06-08
JohannesGaessler CUDA: revise q8_1 data layout for mul_mat_q
05a5fa08
JohannesGaessler JohannesGaessler force pushed to 05a5fa08 1 year ago
JohannesGaessler JohannesGaessler merged 42b53d19 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Nvidia GPU ggml
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum