mirror of
https://github.com/Lizonghang/prima.cpp.git
synced 2025-09-05 19:39:03 +00:00
* 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> |
||
---|---|---|
.. | ||
vdot | ||
CMakeLists.txt |