#pragma once

// @generated by torchgen/gen.py from NativeFunction.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 <c10/core/QScheme.h>
#include <ATen/core/Reduction.h>
#include <ATen/core/Tensor.h>
#include <tuple>
#include <vector>


namespace at {
namespace native {
TORCH_API at::Tensor & batch_norm_backward_elemt_out(const at::Tensor & grad_out, const at::Tensor & input, const at::Tensor & mean, const at::Tensor & invstd, const c10::optional<at::Tensor> & weight, const at::Tensor & mean_dy, const at::Tensor & mean_dy_xmu, const at::Tensor & count, at::Tensor & out);
TORCH_API at::Tensor batch_norm_backward_elemt_cuda(const at::Tensor & grad_out, const at::Tensor & input, const at::Tensor & mean, const at::Tensor & invstd, const c10::optional<at::Tensor> & weight, const at::Tensor & mean_dy, const at::Tensor & mean_dy_xmu, const at::Tensor & count);
} // namespace native
} // namespace at