Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-10 04:20:24 +01:00
Code Issues Packages Projects Releases Wiki Activity
llama.cpp/pocs
History
Stephan Walter 1b107b8550
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>
2023-07-05 19:13:06 +03:00
..
vdot
ggml : generalize quantize_fns for simpler FP16 handling (#1237)
2023-07-05 19:13:06 +03:00
CMakeLists.txt
Adding a simple program to measure speed of dot products (#1041)
2023-04-18 19:00:14 +00:00