std1.0.0-beta-7 SafeC docs

std :: ml::gpu_mps

Function std::mps_gelu_mul_bf16_chained

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

int mps_gelu_mul_bf16_chained(
    struct MpsBuf bufA,
    struct MpsBuf bufB,
    &unsigned short out,
    unsigned long n,
)

out[i] = gelu(bufA[i]) * bufB[i] -- mps_gated_gelu_bf16_chained with the gate and up operands in two separate device buffers.