#pragma once

// @generated by torchgen/gen.py from Function.h

#include <ATen/Context.h>
#include <ATen/DeviceGuard.h>
#include <ATen/TensorUtils.h>
#include <ATen/TracerMode.h>
#include <ATen/core/Generator.h>
#include <ATen/core/Reduction.h>
#include <ATen/core/Tensor.h>
#include <c10/core/Scalar.h>
#include <c10/core/Storage.h>
#include <c10/core/TensorOptions.h>
#include <c10/util/Deprecated.h>
#include <c10/util/Optional.h>



#include <ATen/ops/_native_decoder_only_multi_head_attention_ops.h>

namespace at {


// aten::_native_decoder_only_multi_head_attention(Tensor query, Tensor key, Tensor value, int embed_dim, int num_head, Tensor qkv_weight, Tensor qkv_bias, Tensor proj_weight, Tensor proj_bias, Tensor? mask=None, Tensor? incr_key=None, Tensor? incr_value=None, bool need_weights=True, bool average_attn_weights=True) -> (Tensor, Tensor, Tensor, Tensor)
inline ::std::tuple<at::Tensor,at::Tensor,at::Tensor,at::Tensor> _native_decoder_only_multi_head_attention(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 c10::optional<at::Tensor> & mask={}, const c10::optional<at::Tensor> & incr_key={}, const c10::optional<at::Tensor> & incr_value={}, bool need_weights=true, bool average_attn_weights=true) {
    return at::_ops::_native_decoder_only_multi_head_attention::call(query, key, value, embed_dim, num_head, qkv_weight, qkv_bias, proj_weight, proj_bias, mask, incr_key, incr_value, need_weights, average_attn_weights);
}

// aten::_native_decoder_only_multi_head_attention.out(Tensor query, Tensor key, Tensor value, int embed_dim, int num_head, Tensor qkv_weight, Tensor qkv_bias, Tensor proj_weight, Tensor proj_bias, Tensor? mask=None, Tensor? incr_key=None, Tensor? incr_value=None, bool need_weights=True, bool average_attn_weights=True, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!))
inline ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &,at::Tensor &> _native_decoder_only_multi_head_attention_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, 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 c10::optional<at::Tensor> & mask={}, const c10::optional<at::Tensor> & incr_key={}, const c10::optional<at::Tensor> & incr_value={}, bool need_weights=true, bool average_attn_weights=true) {
    return at::_ops::_native_decoder_only_multi_head_attention_out::call(query, key, value, embed_dim, num_head, qkv_weight, qkv_bias, proj_weight, proj_bias, mask, incr_key, incr_value, need_weights, average_attn_weights, out0, out1, out2, out3);
}

// aten::_native_decoder_only_multi_head_attention.out(Tensor query, Tensor key, Tensor value, int embed_dim, int num_head, Tensor qkv_weight, Tensor qkv_bias, Tensor proj_weight, Tensor proj_bias, Tensor? mask=None, Tensor? incr_key=None, Tensor? incr_value=None, bool need_weights=True, bool average_attn_weights=True, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!))
inline ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &,at::Tensor &> _native_decoder_only_multi_head_attention_outf(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 c10::optional<at::Tensor> & mask, const c10::optional<at::Tensor> & incr_key, const c10::optional<at::Tensor> & incr_value, bool need_weights, bool average_attn_weights, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3) {
    return at::_ops::_native_decoder_only_multi_head_attention_out::call(query, key, value, embed_dim, num_head, qkv_weight, qkv_bias, proj_weight, proj_bias, mask, incr_key, incr_value, need_weights, average_attn_weights, out0, out1, out2, out3);
}

}