std1.0.0-beta-7 SafeC docs

std :: ml::gpu_mps

Function std::mps_add_bf16_chained

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

int mps_add_bf16_chained(
    struct MpsBuf bufA,
    struct MpsBuf bufB,
    &unsigned short out,
    unsigned long n,
)

out[i] = bufA[i] + bufB[i] with BOTH operands device buffers (pending or persistent) -- unlike mps_sub_bf16_chained above, whose second operand is a CPU array. For residual connections between chained ops.