Morph MORPH
SIGN IN SIGN UP
dhruvhead / llama.cpp UNCLAIMED
0 0 1 C++

CUDA: faster non k-quant mul_mat_q kernels (#2483)

J
Johannes Gäßler committed
468ea24fb4633a0d681f7ac84089566c1c6190cb
Parent: 4f6b60c
Committed by GitHub <noreply@github.com> on 8/2/2023, 4:04:04 PM