Morph MORPH
SIGN IN SIGN UP
dhruvhead / llama.cpp UNCLAIMED
0 0 0 C++

CUDA: use mul_mat_q kernels by default (#2683)

J
Johannes Gäßler committed
c63bb1d16a70c03440671b76954bb767513cead8
Parent: 3b6cfe7
Committed by GitHub <noreply@github.com> on 8/22/2023, 8:47:05 PM