std1.0.0-beta-7 SafeC docs

std :: ml::gpu_mps

Function std::mps_flash_attention

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

int mps_flash_attention(
    struct MpsBuf q,
    struct MpsBuf k,
    struct MpsBuf v,
    struct MpsBuf out,
    unsigned long heads,
    unsigned long seqLen,
    unsigned long kvLen,
    unsigned long headDim,
    float scale,
    int causal,
)