std1.0.0-beta-7 SafeC docs

std :: ml::gpu_mps

Function std::mps_matmul_atb_f16_chained_ab

#include <std/ml/gpu_mps.h> source ยท definition

int mps_matmul_atb_f16_chained_ab(
    struct MpsBuf bufA,
    struct MpsBuf bufDC,
    &unsigned short out,
    unsigned long M,
    unsigned long K,
    unsigned long N,
)

dB[K,N] = A^T[K,M] . dC[M,N], A stored [M,K] -- both operands already device buffers, same shape as mps_matmul_atb_f32_chained_ab.