0 0 0 C++

ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)

* Generalize quantize_fns for simpler FP16 handling

* Remove call to ggml_cuda_mul_mat_get_wsize

* ci : disable FMA for mac os actions

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

Stephan Walter committed 3y ago

1b107b8550dced48dc5f41184640061354226b96

Parent: 8567c76

Committed by GitHub <noreply@github.com> on 7/5/2023, 4:13:06 PM