std1.0.0-beta-7 SafeC docs

std :: ml::gpu_mps

Function std::mps_matmul_abt_f16_persistent

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

int mps_matmul_abt_f16_persistent(
    struct MpsBuf bufDC,
    struct MpsBuf bufB,
    &unsigned short out,
    unsigned long M,
    unsigned long N,
    unsigned long K,
)

dA[M,K] = dC[M,N] . B^T[N,K], B stored [K,N] -- same shape as mps_matmul_abt_f32_persistent.