std :: ml::gpu_mps
Function std::mps_rmsnorm_bf16_chained
int mps_rmsnorm_bf16_chained(
struct MpsBuf bufX,
struct MpsBuf weightBuf,
&unsigned short out,
unsigned long rows,
unsigned long cols,
float eps,
)Row-wise RMSNorm: out[row,c] = x[row,c] * weight[c] / sqrt(mean(x[row,:]^2) + eps). 'bufX' is a pending or persistent device buffer of [rows, cols] bf16; 'weightBuf' is the [cols] weight, typically uploaded once via MpsBuf::upload and cached by the caller.