// @generated by tools/codegen/gen.py from DispatchKeyFunctions.h

// NB: The implementing C++ file is RegisterDispatchKey.cpp

// TODO: tighten this include
#include <ATen/Functions.h>

namespace at {
namespace cpu {

TORCH_API Tensor & abs_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & abs_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & angle_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & angle_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor view_as_real(const Tensor & self);
TORCH_API Tensor view_as_complex(const Tensor & self);
TORCH_API Tensor & sgn_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & sgn_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & conj_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & conj_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & acos_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & acos_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & add_out(Tensor & out, const Tensor & self, const Tensor & other, Scalar alpha=1);
TORCH_API Tensor & add_outf(const Tensor & self, const Tensor & other, Scalar alpha, Tensor & out);
TORCH_API Tensor add(const Tensor & self, const Tensor & other, Scalar alpha=1);
TORCH_API Tensor & add_(Tensor & self, const Tensor & other, Scalar alpha=1);
TORCH_API Tensor _add_relu(const Tensor & self, const Tensor & other, Scalar alpha=1);
TORCH_API Tensor & _add_relu_(Tensor & self, const Tensor & other, Scalar alpha=1);
TORCH_API Tensor & _add_relu_out(Tensor & out, const Tensor & self, const Tensor & other, Scalar alpha=1);
TORCH_API Tensor & _add_relu_outf(const Tensor & self, const Tensor & other, Scalar alpha, Tensor & out);
TORCH_API Tensor addmv(const Tensor & self, const Tensor & mat, const Tensor & vec, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & addmv_(Tensor & self, const Tensor & mat, const Tensor & vec, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & addmv_out(Tensor & out, const Tensor & self, const Tensor & mat, const Tensor & vec, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & addmv_outf(const Tensor & self, const Tensor & mat, const Tensor & vec, Scalar beta, Scalar alpha, Tensor & out);
TORCH_API Tensor & _addmv_impl_(Tensor & self, const Tensor & self2, const Tensor & mat, const Tensor & vec, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor addr(const Tensor & self, const Tensor & vec1, const Tensor & vec2, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & addr_out(Tensor & out, const Tensor & self, const Tensor & vec1, const Tensor & vec2, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & addr_outf(const Tensor & self, const Tensor & vec1, const Tensor & vec2, Scalar beta, Scalar alpha, Tensor & out);
TORCH_API Tensor all(const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API Tensor & all_out(Tensor & out, const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API Tensor & all_outf(const Tensor & self, int64_t dim, bool keepdim, Tensor & out);
TORCH_API Tensor any(const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API Tensor & any_out(Tensor & out, const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API Tensor & any_outf(const Tensor & self, int64_t dim, bool keepdim, Tensor & out);
TORCH_API Tensor & arange_out(Tensor & out, Scalar start, Scalar end, Scalar step=1);
TORCH_API Tensor & arange_outf(Scalar start, Scalar end, Scalar step, Tensor & out);
TORCH_API Tensor argmax(const Tensor & self, c10::optional<int64_t> dim=c10::nullopt, bool keepdim=false);
TORCH_API Tensor & argmax_out(Tensor & out, const Tensor & self, c10::optional<int64_t> dim=c10::nullopt, bool keepdim=false);
TORCH_API Tensor & argmax_outf(const Tensor & self, c10::optional<int64_t> dim, bool keepdim, Tensor & out);
TORCH_API Tensor argmin(const Tensor & self, c10::optional<int64_t> dim=c10::nullopt, bool keepdim=false);
TORCH_API Tensor & argmin_out(Tensor & out, const Tensor & self, c10::optional<int64_t> dim=c10::nullopt, bool keepdim=false);
TORCH_API Tensor & argmin_outf(const Tensor & self, c10::optional<int64_t> dim, bool keepdim, Tensor & out);
TORCH_API Tensor & acosh_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & acosh_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & asinh_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & asinh_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & atanh_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & atanh_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor as_strided(const Tensor & self, IntArrayRef size, IntArrayRef stride, c10::optional<int64_t> storage_offset=c10::nullopt);
TORCH_API Tensor asin(const Tensor & self);
TORCH_API Tensor & asin_(Tensor & self);
TORCH_API Tensor & asin_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & asin_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & atan_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & atan_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor baddbmm(const Tensor & self, const Tensor & batch1, const Tensor & batch2, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & baddbmm_(Tensor & self, const Tensor & batch1, const Tensor & batch2, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & baddbmm_out(Tensor & out, const Tensor & self, const Tensor & batch1, const Tensor & batch2, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & baddbmm_outf(const Tensor & self, const Tensor & batch1, const Tensor & batch2, Scalar beta, Scalar alpha, Tensor & out);
TORCH_API Tensor & bernoulli_out(Tensor & out, const Tensor & self, c10::optional<Generator> generator=c10::nullopt);
TORCH_API Tensor & bernoulli_outf(const Tensor & self, c10::optional<Generator> generator, Tensor & out);
TORCH_API Tensor & bernoulli_(Tensor & self, const Tensor & p, c10::optional<Generator> generator=c10::nullopt);
TORCH_API Tensor & bernoulli_(Tensor & self, double p=0.5, c10::optional<Generator> generator=c10::nullopt);
TORCH_API Tensor binary_cross_entropy(const Tensor & self, const Tensor & target, const c10::optional<Tensor> & weight={}, int64_t reduction=at::Reduction::Mean);
TORCH_API Tensor & binary_cross_entropy_out(Tensor & out, const Tensor & self, const Tensor & target, const c10::optional<Tensor> & weight={}, int64_t reduction=at::Reduction::Mean);
TORCH_API Tensor & binary_cross_entropy_outf(const Tensor & self, const Tensor & target, const c10::optional<Tensor> & weight, int64_t reduction, Tensor & out);
TORCH_API Tensor binary_cross_entropy_backward(const Tensor & grad_output, const Tensor & self, const Tensor & target, const c10::optional<Tensor> & weight={}, int64_t reduction=at::Reduction::Mean);
TORCH_API Tensor & binary_cross_entropy_backward_out(Tensor & grad_input, const Tensor & grad_output, const Tensor & self, const Tensor & target, const c10::optional<Tensor> & weight={}, int64_t reduction=at::Reduction::Mean);
TORCH_API Tensor & binary_cross_entropy_backward_outf(const Tensor & grad_output, const Tensor & self, const Tensor & target, const c10::optional<Tensor> & weight, int64_t reduction, Tensor & grad_input);
TORCH_API Tensor bincount(const Tensor & self, const c10::optional<Tensor> & weights={}, int64_t minlength=0);
TORCH_API Tensor & bitwise_not_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & bitwise_not_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor copysign(const Tensor & self, const Tensor & other);
TORCH_API Tensor & copysign_(Tensor & self, const Tensor & other);
TORCH_API Tensor & copysign_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & copysign_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor copysign(const Tensor & self, Scalar other);
TORCH_API Tensor & copysign_(Tensor & self, Scalar other);
TORCH_API Tensor & logical_not_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & logical_not_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & logical_xor_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & logical_xor_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor & logical_and_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & logical_and_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor & logical_or_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & logical_or_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor bmm(const Tensor & self, const Tensor & mat2);
TORCH_API Tensor & bmm_out(Tensor & out, const Tensor & self, const Tensor & mat2);
TORCH_API Tensor & bmm_outf(const Tensor & self, const Tensor & mat2, Tensor & out);
TORCH_API Tensor & ceil_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & ceil_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor clamp(const Tensor & self, c10::optional<Scalar> min=c10::nullopt, c10::optional<Scalar> max=c10::nullopt);
TORCH_API Tensor & clamp_out(Tensor & out, const Tensor & self, c10::optional<Scalar> min=c10::nullopt, c10::optional<Scalar> max=c10::nullopt);
TORCH_API Tensor & clamp_outf(const Tensor & self, c10::optional<Scalar> min, c10::optional<Scalar> max, Tensor & out);
TORCH_API Tensor & clamp_max_out(Tensor & out, const Tensor & self, Scalar max);
TORCH_API Tensor & clamp_max_outf(const Tensor & self, Scalar max, Tensor & out);
TORCH_API Tensor & clamp_min_out(Tensor & out, const Tensor & self, Scalar min);
TORCH_API Tensor & clamp_min_outf(const Tensor & self, Scalar min, Tensor & out);
TORCH_API Tensor & complex_out(Tensor & out, const Tensor & real, const Tensor & imag);
TORCH_API Tensor & complex_outf(const Tensor & real, const Tensor & imag, Tensor & out);
TORCH_API Tensor & polar_out(Tensor & out, const Tensor & abs, const Tensor & angle);
TORCH_API Tensor & polar_outf(const Tensor & abs, const Tensor & angle, Tensor & out);
TORCH_API Tensor & cos_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & cos_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & cosh_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & cosh_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor count_nonzero(const Tensor & self, IntArrayRef dim);
TORCH_API void _cummax_helper(const Tensor & self, Tensor & values, Tensor & indices, int64_t dim);
TORCH_API void _cummin_helper(const Tensor & self, Tensor & values, Tensor & indices, int64_t dim);
TORCH_API std::tuple<Tensor,Tensor> _ctc_loss(const Tensor & log_probs, const Tensor & targets, IntArrayRef input_lengths, IntArrayRef target_lengths, int64_t blank=0, bool zero_infinity=false);
TORCH_API Tensor _ctc_loss_backward(const Tensor & grad, const Tensor & log_probs, const Tensor & targets, IntArrayRef input_lengths, IntArrayRef target_lengths, const Tensor & neg_log_likelihood, const Tensor & log_alpha, int64_t blank, bool zero_infinity=false);
TORCH_API Tensor div(const Tensor & self, const Tensor & other);
TORCH_API Tensor & div_(Tensor & self, const Tensor & other);
TORCH_API Tensor & div_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & div_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor div(const Tensor & self, const Tensor & other, std::string rounding_mode);
TORCH_API Tensor & div_(Tensor & self, const Tensor & other, std::string rounding_mode);
TORCH_API Tensor & div_out(Tensor & out, const Tensor & self, const Tensor & other, std::string rounding_mode);
TORCH_API Tensor & div_outf(const Tensor & self, const Tensor & other, std::string rounding_mode, Tensor & out);
TORCH_API Tensor dot(const Tensor & self, const Tensor & tensor);
TORCH_API Tensor vdot(const Tensor & self, const Tensor & other);
TORCH_API Tensor embedding_dense_backward(const Tensor & grad_output, const Tensor & indices, int64_t num_weights, int64_t padding_idx, bool scale_grad_by_freq);
TORCH_API Tensor & embedding_renorm_(Tensor & self, const Tensor & indices, double max_norm, double norm_type);
TORCH_API std::tuple<Tensor,Tensor,Tensor,Tensor> _embedding_bag_forward_only(const Tensor & weight, const Tensor & indices, const Tensor & offsets, bool scale_grad_by_freq=false, int64_t mode=0, bool sparse=false, const c10::optional<Tensor> & per_sample_weights={}, bool include_last_offset=false);
TORCH_API std::tuple<Tensor,Tensor,Tensor,Tensor> _embedding_bag(const Tensor & weight, const Tensor & indices, const Tensor & offsets, bool scale_grad_by_freq=false, int64_t mode=0, bool sparse=false, const c10::optional<Tensor> & per_sample_weights={}, bool include_last_offset=false);
TORCH_API Tensor _embedding_bag_dense_backward(const Tensor & grad, const Tensor & indices, const Tensor & offsets, const Tensor & offset2bag, const Tensor & bag_size, const Tensor & maximum_indices, int64_t num_weights, bool scale_grad_by_freq, int64_t mode, const c10::optional<Tensor> & per_sample_weights);
TORCH_API Tensor _embedding_bag_per_sample_weights_backward(const Tensor & grad, const Tensor & weight, const Tensor & indices, const Tensor & offsets, const Tensor & offset2bag, int64_t mode);
TORCH_API Tensor empty(IntArrayRef size, TensorOptions options={}, c10::optional<MemoryFormat> memory_format=c10::nullopt);
TORCH_API Tensor empty(IntArrayRef size, c10::optional<ScalarType> dtype, c10::optional<Layout> layout, c10::optional<Device> device, c10::optional<bool> pin_memory, c10::optional<MemoryFormat> memory_format);
TORCH_API Tensor _empty_affine_quantized(IntArrayRef size, TensorOptions options={}, double scale=1, int64_t zero_point=0, c10::optional<MemoryFormat> memory_format=MemoryFormat::Contiguous);
TORCH_API Tensor _empty_affine_quantized(IntArrayRef size, c10::optional<ScalarType> dtype, c10::optional<Layout> layout, c10::optional<Device> device, c10::optional<bool> pin_memory, double scale, int64_t zero_point, c10::optional<MemoryFormat> memory_format);
TORCH_API Tensor _empty_per_channel_affine_quantized(IntArrayRef size, const Tensor & scales, const Tensor & zero_points, int64_t axis, TensorOptions options={}, c10::optional<MemoryFormat> memory_format=MemoryFormat::Contiguous);
TORCH_API Tensor _empty_per_channel_affine_quantized(IntArrayRef size, const Tensor & scales, const Tensor & zero_points, int64_t axis, c10::optional<ScalarType> dtype, c10::optional<Layout> layout, c10::optional<Device> device, c10::optional<bool> pin_memory, c10::optional<MemoryFormat> memory_format);
TORCH_API Tensor & resize_(Tensor & self, IntArrayRef size, c10::optional<MemoryFormat> memory_format=c10::nullopt);
TORCH_API Tensor empty_strided(IntArrayRef size, IntArrayRef stride, TensorOptions options={});
TORCH_API Tensor empty_strided(IntArrayRef size, IntArrayRef stride, c10::optional<ScalarType> dtype, c10::optional<Layout> layout, c10::optional<Device> device, c10::optional<bool> pin_memory);
TORCH_API Tensor & erf_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & erf_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & erfc_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & erfc_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & exp_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & exp_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & exp2_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & exp2_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & expm1_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & expm1_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & eye_out(Tensor & out, int64_t n);
TORCH_API Tensor & eye_outf(int64_t n, Tensor & out);
TORCH_API Tensor & eye_out(Tensor & out, int64_t n, int64_t m);
TORCH_API Tensor & eye_outf(int64_t n, int64_t m, Tensor & out);
TORCH_API Tensor & floor_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & floor_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor floor_divide(const Tensor & self, const Tensor & other);
TORCH_API Tensor & floor_divide_(Tensor & self, const Tensor & other);
TORCH_API Tensor & floor_divide_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & floor_divide_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor & frac_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & frac_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor from_file(std::string filename, c10::optional<bool> shared=c10::nullopt, c10::optional<int64_t> size=0, TensorOptions options={});
TORCH_API Tensor from_file(std::string filename, c10::optional<bool> shared, c10::optional<int64_t> size, c10::optional<ScalarType> dtype, c10::optional<Layout> layout, c10::optional<Device> device, c10::optional<bool> pin_memory);
TORCH_API Tensor & gcd_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & gcd_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor & lcm_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & lcm_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor grid_sampler_2d(const Tensor & input, const Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners);
TORCH_API std::tuple<Tensor,Tensor> grid_sampler_2d_backward(const Tensor & grad_output, const Tensor & input, const Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners);
TORCH_API Tensor grid_sampler_3d(const Tensor & input, const Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners);
TORCH_API std::tuple<Tensor,Tensor> grid_sampler_3d_backward(const Tensor & grad_output, const Tensor & input, const Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners);
TORCH_API std::tuple<Tensor,Tensor,Tensor> native_group_norm(const Tensor & input, const c10::optional<Tensor> & weight, const c10::optional<Tensor> & bias, int64_t N, int64_t C, int64_t HxW, int64_t group, double eps);
TORCH_API std::tuple<Tensor,Tensor,Tensor> native_group_norm_backward(const Tensor & grad_out, const Tensor & input, const Tensor & mean, const Tensor & rstd, const c10::optional<Tensor> & weight, int64_t N, int64_t C, int64_t HxW, int64_t group, std::array<bool,3> output_mask);
TORCH_API Tensor _fft_r2c(const Tensor & self, IntArrayRef dim, int64_t normalization, bool onesided);
TORCH_API Tensor & _fft_r2c_out(Tensor & out, const Tensor & self, IntArrayRef dim, int64_t normalization, bool onesided);
TORCH_API Tensor & _fft_r2c_outf(const Tensor & self, IntArrayRef dim, int64_t normalization, bool onesided, Tensor & out);
TORCH_API Tensor _fft_c2r(const Tensor & self, IntArrayRef dim, int64_t normalization, int64_t last_dim_size);
TORCH_API Tensor & _fft_c2r_out(Tensor & out, const Tensor & self, IntArrayRef dim, int64_t normalization, int64_t last_dim_size);
TORCH_API Tensor & _fft_c2r_outf(const Tensor & self, IntArrayRef dim, int64_t normalization, int64_t last_dim_size, Tensor & out);
TORCH_API Tensor _fft_c2c(const Tensor & self, IntArrayRef dim, int64_t normalization, bool forward);
TORCH_API Tensor & _fft_c2c_out(Tensor & out, const Tensor & self, IntArrayRef dim, int64_t normalization, bool forward);
TORCH_API Tensor & _fft_c2c_outf(const Tensor & self, IntArrayRef dim, int64_t normalization, bool forward, Tensor & out);
TORCH_API Tensor index(const Tensor & self, const c10::List<c10::optional<Tensor>> & indices);
TORCH_API Tensor & _index_put_impl_(Tensor & self, const c10::List<c10::optional<Tensor>> & indices, const Tensor & values, bool accumulate=false, bool unsafe=false);
TORCH_API Tensor _inverse_helper(const Tensor & self);
TORCH_API Tensor isnan(const Tensor & self);
TORCH_API Tensor kl_div_backward(const Tensor & grad_output, const Tensor & self, const Tensor & target, int64_t reduction=at::Reduction::Mean, bool log_target=false);
TORCH_API std::tuple<Tensor &,Tensor &> kthvalue_out(Tensor & values, Tensor & indices, const Tensor & self, int64_t k, int64_t dim=-1, bool keepdim=false);
TORCH_API std::tuple<Tensor &,Tensor &> kthvalue_outf(const Tensor & self, int64_t k, int64_t dim, bool keepdim, Tensor & values, Tensor & indices);
TORCH_API std::tuple<Tensor,Tensor,Tensor> native_layer_norm(const Tensor & input, IntArrayRef normalized_shape, const c10::optional<Tensor> & weight, const c10::optional<Tensor> & bias, double eps);
TORCH_API std::tuple<Tensor,Tensor,Tensor> native_layer_norm_backward(const Tensor & grad_out, const Tensor & input, IntArrayRef normalized_shape, const Tensor & mean, const Tensor & rstd, const c10::optional<Tensor> & weight, const c10::optional<Tensor> & bias, std::array<bool,3> output_mask);
TORCH_API Tensor & linspace_out(Tensor & out, Scalar start, Scalar end, c10::optional<int64_t> steps=c10::nullopt);
TORCH_API Tensor & linspace_outf(Scalar start, Scalar end, c10::optional<int64_t> steps, Tensor & out);
TORCH_API Tensor & log_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & log_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & log10_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & log10_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor log1p(const Tensor & self);
TORCH_API Tensor & log1p_(Tensor & self);
TORCH_API Tensor & log1p_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & log1p_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & log2_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & log2_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & logaddexp_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & logaddexp_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor & logaddexp2_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & logaddexp2_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor xlogy(const Tensor & self, const Tensor & other);
TORCH_API Tensor & xlogy_(Tensor & self, const Tensor & other);
TORCH_API Tensor & xlogy_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & xlogy_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor xlogy(Scalar self, const Tensor & other);
TORCH_API Tensor & xlogy_out(Tensor & out, Scalar self, const Tensor & other);
TORCH_API Tensor & xlogy_outf(Scalar self, const Tensor & other, Tensor & out);
TORCH_API Tensor xlogy(const Tensor & self, Scalar other);
TORCH_API Tensor & xlogy_(Tensor & self, Scalar other);
TORCH_API Tensor & xlogy_out(Tensor & out, const Tensor & self, Scalar other);
TORCH_API Tensor & xlogy_outf(const Tensor & self, Scalar other, Tensor & out);
TORCH_API Tensor & logspace_out(Tensor & out, Scalar start, Scalar end, c10::optional<int64_t> steps=c10::nullopt, double base=10.0);
TORCH_API Tensor & logspace_outf(Scalar start, Scalar end, c10::optional<int64_t> steps, double base, Tensor & out);
TORCH_API Tensor _log_softmax(const Tensor & self, int64_t dim, bool half_to_float);
TORCH_API Tensor _log_softmax_backward_data(const Tensor & grad_output, const Tensor & output, int64_t dim, const Tensor & self);
TORCH_API Tensor _logcumsumexp(const Tensor & self, int64_t dim);
TORCH_API Tensor & _logcumsumexp_out(Tensor & out, const Tensor & self, int64_t dim);
TORCH_API Tensor & _logcumsumexp_outf(const Tensor & self, int64_t dim, Tensor & out);
TORCH_API Tensor matrix_exp(const Tensor & self);
TORCH_API std::tuple<Tensor,Tensor> _aminmax(const Tensor & self);
TORCH_API std::tuple<Tensor,Tensor> _aminmax(const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API Tensor _compute_linear_combination(const Tensor & input, const Tensor & coefficients);
TORCH_API Tensor & _compute_linear_combination_out(Tensor & out, const Tensor & input, const Tensor & coefficients);
TORCH_API Tensor & _compute_linear_combination_outf(const Tensor & input, const Tensor & coefficients, Tensor & out);
TORCH_API std::tuple<Tensor &,Tensor &> max_out(Tensor & max, Tensor & max_values, const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API std::tuple<Tensor &,Tensor &> max_outf(const Tensor & self, int64_t dim, bool keepdim, Tensor & max, Tensor & max_values);
TORCH_API Tensor & amax_out(Tensor & out, const Tensor & self, IntArrayRef dim={}, bool keepdim=false);
TORCH_API Tensor & amax_outf(const Tensor & self, IntArrayRef dim, bool keepdim, Tensor & out);
TORCH_API Tensor mean(const Tensor & self, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor mean(const Tensor & self, IntArrayRef dim, bool keepdim=false, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor & mean_out(Tensor & out, const Tensor & self, IntArrayRef dim, bool keepdim=false, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor & mean_outf(const Tensor & self, IntArrayRef dim, bool keepdim, c10::optional<ScalarType> dtype, Tensor & out);
TORCH_API Tensor median(const Tensor & self);
TORCH_API std::tuple<Tensor &,Tensor &> median_out(Tensor & values, Tensor & indices, const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API std::tuple<Tensor &,Tensor &> median_outf(const Tensor & self, int64_t dim, bool keepdim, Tensor & values, Tensor & indices);
TORCH_API Tensor nanmedian(const Tensor & self);
TORCH_API std::tuple<Tensor &,Tensor &> nanmedian_out(Tensor & values, Tensor & indices, const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API std::tuple<Tensor &,Tensor &> nanmedian_outf(const Tensor & self, int64_t dim, bool keepdim, Tensor & values, Tensor & indices);
TORCH_API std::tuple<Tensor &,Tensor &> min_out(Tensor & min, Tensor & min_indices, const Tensor & self, int64_t dim, bool keepdim=false);
TORCH_API std::tuple<Tensor &,Tensor &> min_outf(const Tensor & self, int64_t dim, bool keepdim, Tensor & min, Tensor & min_indices);
TORCH_API Tensor & amin_out(Tensor & out, const Tensor & self, IntArrayRef dim={}, bool keepdim=false);
TORCH_API Tensor & amin_outf(const Tensor & self, IntArrayRef dim, bool keepdim, Tensor & out);
TORCH_API Tensor mm(const Tensor & self, const Tensor & mat2);
TORCH_API Tensor & mm_out(Tensor & out, const Tensor & self, const Tensor & mat2);
TORCH_API Tensor & mm_outf(const Tensor & self, const Tensor & mat2, Tensor & out);
TORCH_API std::tuple<Tensor,Tensor> mode(const Tensor & self, int64_t dim=-1, bool keepdim=false);
TORCH_API Tensor mul(const Tensor & self, const Tensor & other);
TORCH_API Tensor & mul_(Tensor & self, const Tensor & other);
TORCH_API Tensor & mul_out(Tensor & out, const Tensor & self, const Tensor & other);
TORCH_API Tensor & mul_outf(const Tensor & self, const Tensor & other, Tensor & out);
TORCH_API Tensor mv(const Tensor & self, const Tensor & vec);
TORCH_API Tensor narrow_copy(const Tensor & self, int64_t dim, int64_t start, int64_t length);
TORCH_API Tensor & narrow_copy_out(Tensor & out, const Tensor & self, int64_t dim, int64_t start, int64_t length);
TORCH_API Tensor & narrow_copy_outf(const Tensor & self, int64_t dim, int64_t start, int64_t length, Tensor & out);
TORCH_API std::tuple<Tensor,Tensor,Tensor> native_batch_norm(const Tensor & input, const c10::optional<Tensor> & weight, const c10::optional<Tensor> & bias, const c10::optional<Tensor> & running_mean, const c10::optional<Tensor> & running_var, bool training, double momentum, double eps);
TORCH_API std::tuple<Tensor,Tensor,Tensor> native_batch_norm_backward(const Tensor & grad_out, const Tensor & input, const c10::optional<Tensor> & weight, const c10::optional<Tensor> & running_mean, const c10::optional<Tensor> & running_var, const c10::optional<Tensor> & save_mean, const c10::optional<Tensor> & save_invstd, bool train, double eps, std::array<bool,3> output_mask);
TORCH_API std::tuple<Tensor,Tensor> batch_norm_update_stats(const Tensor & input, const c10::optional<Tensor> & running_mean, const c10::optional<Tensor> & running_var, double momentum);
TORCH_API Tensor _cdist_forward(const Tensor & x1, const Tensor & x2, double p, c10::optional<int64_t> compute_mode);
TORCH_API Tensor _cdist_backward(const Tensor & grad, const Tensor & x1, const Tensor & x2, double p, const Tensor & cdist);
TORCH_API Tensor _pdist_forward(const Tensor & self, double p=2);
TORCH_API Tensor _pdist_backward(const Tensor & grad, const Tensor & self, double p, const Tensor & pdist);
TORCH_API Tensor channel_shuffle(const Tensor & self, int64_t groups);
TORCH_API Tensor & randperm_out(Tensor & out, int64_t n, c10::optional<Generator> generator);
TORCH_API Tensor & randperm_outf(int64_t n, c10::optional<Generator> generator, Tensor & out);
TORCH_API Tensor & range_out(Tensor & out, Scalar start, Scalar end, Scalar step=1);
TORCH_API Tensor & range_outf(Scalar start, Scalar end, Scalar step, Tensor & out);
TORCH_API Tensor & reciprocal_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & reciprocal_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & neg_(Tensor & self);
TORCH_API Tensor & neg_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & neg_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor repeat_interleave(const Tensor & repeats);
TORCH_API Tensor & round_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & round_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor relu(const Tensor & self);
TORCH_API Tensor & relu_(Tensor & self);
TORCH_API Tensor prelu(const Tensor & self, const Tensor & weight);
TORCH_API std::tuple<Tensor,Tensor> prelu_backward(const Tensor & grad_output, const Tensor & self, const Tensor & weight);
TORCH_API Tensor gelu(const Tensor & self);
TORCH_API Tensor gelu_backward(const Tensor & grad, const Tensor & self);
TORCH_API Tensor hardshrink(const Tensor & self, Scalar lambd=0.5);
TORCH_API Tensor hardshrink_backward(const Tensor & grad_out, const Tensor & self, Scalar lambd);
TORCH_API Tensor & rsqrt_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & rsqrt_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & silu_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & silu_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor silu_backward(const Tensor & grad_output, const Tensor & self);
TORCH_API Tensor sigmoid(const Tensor & self);
TORCH_API Tensor & sigmoid_(Tensor & self);
TORCH_API Tensor & sigmoid_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & sigmoid_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor logit(const Tensor & self, c10::optional<double> eps=c10::nullopt);
TORCH_API Tensor & logit_(Tensor & self, c10::optional<double> eps=c10::nullopt);
TORCH_API Tensor & logit_out(Tensor & out, const Tensor & self, c10::optional<double> eps=c10::nullopt);
TORCH_API Tensor & logit_outf(const Tensor & self, c10::optional<double> eps, Tensor & out);
TORCH_API Tensor & sin_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & sin_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & sinc_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & sinc_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor & sinh_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & sinh_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor _softmax(const Tensor & self, int64_t dim, bool half_to_float);
TORCH_API Tensor _softmax_backward_data(const Tensor & grad_output, const Tensor & output, int64_t dim, const Tensor & self);
TORCH_API Tensor & sspaddmm_out(Tensor & out, const Tensor & self, const Tensor & mat1, const Tensor & mat2, Scalar beta=1, Scalar alpha=1);
TORCH_API Tensor & sspaddmm_outf(const Tensor & self, const Tensor & mat1, const Tensor & mat2, Scalar beta, Scalar alpha, Tensor & out);
TORCH_API Tensor _stack(TensorList tensors, int64_t dim=0);
TORCH_API Tensor & _stack_out(Tensor & out, TensorList tensors, int64_t dim=0);
TORCH_API Tensor & _stack_outf(TensorList tensors, int64_t dim, Tensor & out);
TORCH_API Tensor sum(const Tensor & self, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor sum(const Tensor & self, IntArrayRef dim, bool keepdim=false, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor & sum_out(Tensor & out, const Tensor & self, IntArrayRef dim, bool keepdim=false, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor & sum_outf(const Tensor & self, IntArrayRef dim, bool keepdim, c10::optional<ScalarType> dtype, Tensor & out);
TORCH_API Tensor nansum(const Tensor & self, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor nansum(const Tensor & self, IntArrayRef dim, bool keepdim=false, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor & nansum_out(Tensor & out, const Tensor & self, IntArrayRef dim, bool keepdim=false, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor & nansum_outf(const Tensor & self, IntArrayRef dim, bool keepdim, c10::optional<ScalarType> dtype, Tensor & out);
TORCH_API Tensor sqrt(const Tensor & self);
TORCH_API Tensor & sqrt_(Tensor & self);
TORCH_API Tensor & sqrt_out(Tensor & out, const Tensor & self);
TORCH_API Tensor & sqrt_outf(const Tensor & self, Tensor & out);
TORCH_API Tensor std(const Tensor & self, bool unbiased=true);
TORCH_API Tensor std(const Tensor & self, IntArrayRef dim, bool unbiased=true, bool keepdim=false);
TORCH_API Tensor & std_out(Tensor & out, const Tensor & self, IntArrayRef dim, bool unbiased=true, bool keepdim=false);
TORCH_API Tensor & std_outf(const Tensor & self, IntArrayRef dim, bool unbiased, bool keepdim, Tensor & out);
TORCH_API std::tuple<Tensor,Tensor> std_mean(const Tensor & self, bool unbiased=true);
TORCH_API std::tuple<Tensor,Tensor> std_mean(const Tensor & self, IntArrayRef dim, bool unbiased=true, bool keepdim=false);
TORCH_API Tensor prod(const Tensor & self, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor prod(const Tensor & self, int64_t dim, bool keepdim=false, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor & prod_out(Tensor & out, const Tensor & self, int64_t dim, bool keepdim=false, c10::optional<ScalarType> dtype=c10::nullopt);
TORCH_API Tensor & prod_outf(const Tensor & self, int64_t dim, bool keepdim, c10::optional<ScalarType> dtype, Tensor & out);
TORCH_API Tensor & tan_out(Tensor & out, const Tensor & self);