std :: ml::gpu_mps
#include <std/ml/gpu_mps.h> source ยท definition
#include <std/ml/gpu_mps.h>
int mps_linear_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, int causal, )