std1.0.0-beta-7 SafeC docs

std :: ml::attention

Function std::attention_forward_mask

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

&FloatTensor attention_forward_mask(
    const &FloatTensor Q,
    const &FloatTensor K,
    const &FloatTensor V,
    int causal,
    unsigned long window,
)

The two with a mask (causal 0/1, window 0 for none; see above).