std1.0.0-beta-7 SafeC docs

std :: ml::gpu_mps

Function std::mps_matmul_f16_persistent

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

int mps_matmul_f16_persistent(
    struct MpsBuf bufA,
    struct MpsBuf bufB,
    &unsigned short out,
    unsigned long M,
    unsigned long K,
    unsigned long N,
)

out = bufA[M,K] . bufB[K,N] -- both operands already device buffers (e.g. from MpsBuf::upload_f16). Must be called within an open batch (mps_batch_begin()); 'out' is throwaway scratch (raw fp16/bf16 bits, not valid until mps_batch_end()) -- read the real result via MpsBuf::batch_last_output() and chain it into the next op, same pattern as mps_matmul_f32_persistent.