You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Since this type is platform specific, it would make sense to hide it by moving it in ggml-impl.h.
We will still expose an API for F16 <-> F32 conversions, but it sill operate on void * instead of ggml_fp16_t
The text was updated successfully, but these errors were encountered:
We could probably define it to uint16_t always, and only cast it to __fp16 in the ARM code that can take advantage of that. The CUDA one is weird, it should only be used when compiling ggml-cuda.cu, which never uses this type anyway.
Currently the
ggml_fp16_t
typedef is exposed in the public API:ggml/include/ggml/ggml.h
Lines 317 to 332 in 6b14d73
Since this type is platform specific, it would make sense to hide it by moving it in
ggml-impl.h
.We will still expose an API for F16 <-> F32 conversions, but it sill operate on
void *
instead ofggml_fp16_t
The text was updated successfully, but these errors were encountered: