llama.cpp
CUDA: fix MMQ for non-contiguous src0, add tests
#10021

Merged

CUDA: fix MMQ for non-contiguous src0, add tests #10021

JohannesGaessler merged 2 commits into ggml-org:master from JohannesGaessler:cuda-fix-permuted-mm

CUDA: fix MMQ for non-contiguous src0, add tests

b87dc5a4

github-actions added testing

github-actions added Nvidia GPU

github-actions added ggml

slaren commented on 2024-10-23

revise test code

4004bb70

JohannesGaessler added Review Complexity : Medium

slaren approved these changes on 2024-10-23

JohannesGaessler merged c39665f5 into master 1 year ago

Reviewers

slaren

Assignees

No one assigned

Labels

testing Nvidia GPU Review Complexity : Medium ggml

Milestone

No milestone