#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 <optional>
#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 & quantize_per_tensor_out(const at::Tensor & self, double scale, int64_t zero_point, at::ScalarType dtype, at::Tensor & out);
TORCH_API at::Tensor quantize_per_tensor(const at::Tensor & self, double scale, int64_t zero_point, at::ScalarType dtype);
TORCH_API at::Tensor & quantize_per_tensor_tensor_qparams_out(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, at::ScalarType dtype, at::Tensor & out);
TORCH_API at::Tensor quantize_per_tensor_tensor_qparams(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, at::ScalarType dtype);
TORCH_API void quantize_per_tensor_tensors_out(at::TensorList tensors, const at::Tensor & scales, const at::Tensor & zero_points, at::ScalarType dtype, at::TensorList out);
TORCH_API ::std::vector<at::Tensor> quantize_per_tensor_list_cpu(at::TensorList tensors, const at::Tensor & scales, const at::Tensor & zero_points, at::ScalarType dtype);
} // namespace native
} // namespace at