PR #5351 CUDA: mul_mat_vec_q for batch sizes > 1

CUDA: mul_mat_vec_q for batch sizes > 1 #5351

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-generalized-mmvq-4

CUDA: mul_mat_vec_q for batch sizes > 1

dbb795b9

JohannesGaessler force pushed to dbb795b9 2 years ago

ggerganov requested a review from

slaren 2 years ago

slaren approved these changes on 2024-02-06

JohannesGaessler merged 2c516611 into master 2 years ago

Reviewers

slaren

Assignees

No one assigned

Labels

None yet

Milestone

No milestone