std :: ml::gpu_mps
Function std::mps_sub_f16_chained
int mps_sub_f16_chained(
struct MpsBuf bufA,
const &unsigned short bHalf,
&unsigned short out,
unsigned long n,
)out[i] = bufA[i] - bHalf[i]/bBf[i] -- 'bHalf'/'bBf' is a plain CPU array of raw fp16/bf16 bits (e.g. a training target, pre-converted once with f32_to_fp16_bulk/f32_to_bf16_bulk before the loop), uploaded fresh each call, same shape as mps_sub_f32_chained.