#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_elemt_cuda(const at::Tensor & input, const c10::optional<at::Tensor> & weight, const c10::optional<at::Tensor> & bias, const at::Tensor & mean, const at::Tensor & invstd, double eps);
TORCH_API at::Tensor & batch_norm_elemt_cuda_out(const at::Tensor & input, const c10::optional<at::Tensor> & weight, const c10::optional<at::Tensor> & bias, const at::Tensor & mean, const at::Tensor & invstd, double eps, at::Tensor & out);
} // namespace native
} // namespace at