SIGN IN SIGN UP

ggml-cuda : perform cublas fp16 matrix multiplication as fp16 (#3370)

* ggml-cuda : perform cublas fp16 matrix multiplication as fp16

* try to fix rocm build

* restrict fp16 mat mul to volta and up
S
slaren committed
da0400344be12074e67dcabc565140289cf7efaa
Parent: e519621
Committed by GitHub <noreply@github.com> on 9/28/2023, 10:08:28 AM