Commit f6ce51e

authored and

committed

CUDA: add conv_2d_dw (ggml-org#14265)

* CUDA: add conv_2d_dw * better naming * simplify using template * Review: fix operation ordering in ggml-cuda, use __forceinline__, use more const

1 parent 056c737 commit f6ce51eCopy full SHA for f6ce51e

1 file changed

+107

-235

lines changed

+107

-235

lines changed

Comments

(0)