llama.cpp
CUDA: mul_mat_q=true as default for llama_context_params
#2912

Merged

CUDA: mul_mat_q=true as default for llama_context_params #2912

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-mmq-default-2

CUDA: mul_mat_q=true llama_context_params default

be1ddb14

slaren approved these changes on 2023-08-30

JohannesGaessler merged 8afe2280 into master 2 years ago

JohannesGaessler deleted the cuda-mmq-default-2 branch 1 year ago

Reviewers

slaren

Assignees

No one assigned

Labels

None yet

Milestone

No milestone