#pragma once

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

#include <tuple>
#include <vector>

// Forward declarations of any types needed in the operator signatures.
// We can't directly include these classes because it will cause circular include dependencies.
// This file is included by TensorBody.h, which defines the Tensor class.
#include <ATen/core/ATen_fwd.h>

namespace at {
namespace _ops {


struct TORCH_API _native_decoder_only_multi_head_attention {
  using schema = ::std::tuple<at::Tensor,at::Tensor,at::Tensor,at::Tensor> (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, int64_t, const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const c10::optional<at::Tensor> &, const c10::optional<at::Tensor> &, const c10::optional<at::Tensor> &, bool, bool);
  using ptr_schema = schema*;
  // See Note [static constexpr char* members for windows NVCC]
  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_native_decoder_only_multi_head_attention")
  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_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)")
  static ::std::tuple<at::Tensor,at::Tensor,at::Tensor,at::Tensor> call(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);
  static ::std::tuple<at::Tensor,at::Tensor,at::Tensor,at::Tensor> redispatch(c10::DispatchKeySet dispatchKeySet, 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);
};

struct TORCH_API _native_decoder_only_multi_head_attention_out {
  using schema = ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &,at::Tensor &> (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, int64_t, const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const c10::optional<at::Tensor> &, const c10::optional<at::Tensor> &, const c10::optional<at::Tensor> &, bool, bool, at::Tensor &, at::Tensor &, at::Tensor &, at::Tensor &);
  using ptr_schema = schema*;
  // See Note [static constexpr char* members for windows NVCC]
  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_native_decoder_only_multi_head_attention")
  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_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!))")
  static ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &,at::Tensor &> call(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);
  static ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &,at::Tensor &> redispatch(c10::DispatchKeySet dispatchKeySet, 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);
};

}} // namespace at::_ops