Function at::_native_multi_head_attention_out¶

Function Documentation¶

inline ::std::tuple<at::Tensor&, at::Tensor&> at::_native_multi_head_attention_out(at::Tensor &out0, at::Tensor &out1, const at::Tensor &query, const at::Tensor &key, const at::Tensor &value, int64_t embed_dim, int64_t num_head, const at::Tensor &qkv_weight, const at::Tensor &qkv_bias, const at::Tensor &proj_weight, const at::Tensor &proj_bias, const ::std::optional<at::Tensor> &mask = {}, bool need_weights = true, bool average_attn_weights = true, ::std::optional<int64_t> mask_type = ::std::nullopt)¶