// THIS FILE IS AUTOMATICALLY GENERATED, DO NOT EDIT BY HAND!

void atg___and__(tensor *, tensor self, scalar other);
void atg___and__tensor_(tensor *, tensor self, tensor other);
void atg___iand__(tensor *, tensor self, scalar other);
void atg___iand__tensor_(tensor *, tensor self, tensor other);
void atg___ilshift__(tensor *, tensor self, scalar other);
void atg___ilshift__tensor_(tensor *, tensor self, tensor other);
void atg___ior__(tensor *, tensor self, scalar other);
void atg___ior__tensor_(tensor *, tensor self, tensor other);
void atg___irshift__(tensor *, tensor self, scalar other);
void atg___irshift__tensor_(tensor *, tensor self, tensor other);
void atg___ixor__(tensor *, tensor self, scalar other);
void atg___ixor__tensor_(tensor *, tensor self, tensor other);
void atg___lshift__(tensor *, tensor self, scalar other);
void atg___lshift__tensor_(tensor *, tensor self, tensor other);
void atg___or__(tensor *, tensor self, scalar other);
void atg___or__tensor_(tensor *, tensor self, tensor other);
void atg___rshift__(tensor *, tensor self, scalar other);
void atg___rshift__tensor_(tensor *, tensor self, tensor other);
void atg___xor__(tensor *, tensor self, scalar other);
void atg___xor__tensor_(tensor *, tensor self, tensor other);
void atg__adaptive_avg_pool2d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg__adaptive_avg_pool2d_backward(tensor *, tensor grad_output, tensor self);
void atg__adaptive_avg_pool3d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg__adaptive_avg_pool3d_backward(tensor *, tensor grad_output, tensor self);
void atg__add_batch_dim(tensor *, tensor self, int64_t batch_dim, int64_t level);
void atg__add_relu(tensor *, tensor self, tensor other);
void atg__add_relu_(tensor *, tensor self, tensor other);
void atg__add_relu_out(tensor *, tensor out, tensor self, tensor other);
void atg__add_relu_scalar(tensor *, tensor self, scalar other);
void atg__add_relu_scalar_(tensor *, tensor self, scalar other);
void atg__aminmax(tensor *, tensor self);
void atg__aminmax_dim(tensor *, tensor self, int64_t dim, int keepdim);
void atg__amp_update_scale_(tensor *, tensor self, tensor growth_tracker, tensor found_inf, double scale_growth_factor, double scale_backoff_factor, int64_t growth_interval);
void atg__baddbmm_mkl_(tensor *, tensor self, tensor batch1, tensor batch2);
void atg__cast_byte(tensor *, tensor self, int non_blocking);
void atg__cast_char(tensor *, tensor self, int non_blocking);
void atg__cast_double(tensor *, tensor self, int non_blocking);
void atg__cast_float(tensor *, tensor self, int non_blocking);
void atg__cast_half(tensor *, tensor self, int non_blocking);
void atg__cast_int(tensor *, tensor self, int non_blocking);
void atg__cast_long(tensor *, tensor self, int non_blocking);
void atg__cast_short(tensor *, tensor self, int non_blocking);
void atg__cat(tensor *, tensor *tensors_data, int tensors_len, int64_t dim);
void atg__cat_out(tensor *, tensor out, tensor *tensors_data, int tensors_len, int64_t dim);
void atg__cdist_backward(tensor *, tensor grad, tensor x1, tensor x2, double p, tensor cdist);
void atg__cholesky_solve_helper(tensor *, tensor self, tensor A, int upper);
void atg__coalesce(tensor *, tensor self);
void atg__coalesced_(tensor *, tensor self, int coalesced);
void atg__compute_linear_combination(tensor *, tensor input, tensor coefficients);
void atg__compute_linear_combination_out(tensor *, tensor out, tensor input, tensor coefficients);
void atg__conj(tensor *, tensor self);
void atg__conj_physical(tensor *, tensor self);
void atg__conv_depthwise2d(tensor *, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len);
void atg__conv_depthwise2d_backward(tensor *, tensor grad_input, tensor grad_weight, tensor grad_output, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len);
void atg__conv_depthwise2d_out(tensor *, tensor out, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len);
void atg__convert_indices_from_coo_to_csr(tensor *, tensor self, int64_t size, int out_int32);
void atg__convert_indices_from_coo_to_csr_out(tensor *, tensor out, tensor self, int64_t size, int out_int32);
void atg__convolution(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int transposed, int64_t *output_padding_data, int output_padding_len, int64_t groups, int benchmark, int deterministic, int cudnn_enabled, int allow_tf32);
void atg__convolution_deprecated(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int transposed, int64_t *output_padding_data, int output_padding_len, int64_t groups, int benchmark, int deterministic, int cudnn_enabled);
void atg__convolution_mode(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, char* padding_ptr, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg__convolution_nogroup(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int transposed, int64_t *output_padding_data, int output_padding_len);
void atg__copy_from(tensor *, tensor self, tensor dst, int non_blocking);
void atg__copy_from_and_resize(tensor *, tensor self, tensor dst);
void atg__ctc_loss(tensor *, tensor log_probs, tensor targets, int64_t *input_lengths_data, int input_lengths_len, int64_t *target_lengths_data, int target_lengths_len, int64_t blank, int zero_infinity);
void atg__ctc_loss_backward(tensor *, tensor grad, tensor log_probs, tensor targets, int64_t *input_lengths_data, int input_lengths_len, int64_t *target_lengths_data, int target_lengths_len, tensor neg_log_likelihood, tensor log_alpha, int64_t blank, int zero_infinity);
void atg__cudnn_ctc_loss(tensor *, tensor log_probs, tensor targets, int64_t *input_lengths_data, int input_lengths_len, int64_t *target_lengths_data, int target_lengths_len, int64_t blank, int deterministic, int zero_infinity);
void atg__cudnn_init_dropout_state(tensor *, double dropout, int train, int64_t dropout_seed, int options_kind, int options_device);
void atg__cudnn_rnn(tensor *, tensor input, tensor *weight_data, int weight_len, int64_t weight_stride0, tensor weight_buf, tensor hx, tensor cx, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, int batch_first, double dropout, int train, int bidirectional, int64_t *batch_sizes_data, int batch_sizes_len, tensor dropout_state);
void atg__cudnn_rnn_flatten_weight(tensor *, tensor *weight_arr_data, int weight_arr_len, int64_t weight_stride0, int64_t input_size, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, int batch_first, int bidirectional);
int64_t atg__cufft_get_plan_cache_max_size(int64_t device_index);
int64_t atg__cufft_get_plan_cache_size(int64_t device_index);
int64_t atg__debug_has_internal_overlap(tensor self);
void atg__det_lu_based_helper(tensor *, tensor self);
void atg__det_lu_based_helper_backward_helper(tensor *, tensor det_grad, tensor det, tensor self, tensor lu, tensor pivs);
void atg__dim_arange(tensor *, tensor like, int64_t dim);
int64_t atg__dimi(tensor self);
int64_t atg__dimv(tensor self);
void atg__dirichlet_grad(tensor *, tensor x, tensor alpha, tensor total);
void atg__embedding_bag(tensor *, tensor weight, tensor indices, tensor offsets, int scale_grad_by_freq, int64_t mode, int sparse, tensor per_sample_weights, int include_last_offset, int64_t padding_idx);
void atg__embedding_bag_backward(tensor *, tensor grad, tensor indices, tensor offsets, tensor offset2bag, tensor bag_size, tensor maximum_indices, int64_t num_weights, int scale_grad_by_freq, int64_t mode, int sparse, tensor per_sample_weights, int64_t padding_idx);
void atg__embedding_bag_dense_backward(tensor *, tensor grad, tensor indices, tensor offset2bag, tensor bag_size, tensor maximum_indices, int64_t num_weights, int scale_grad_by_freq, int64_t mode, tensor per_sample_weights, int64_t padding_idx);
void atg__embedding_bag_forward_only(tensor *, tensor weight, tensor indices, tensor offsets, int scale_grad_by_freq, int64_t mode, int sparse, tensor per_sample_weights, int include_last_offset, int64_t padding_idx);
void atg__embedding_bag_per_sample_weights_backward(tensor *, tensor grad, tensor weight, tensor indices, tensor offsets, tensor offset2bag, int64_t mode, int64_t padding_idx);
void atg__embedding_bag_sparse_backward(tensor *, tensor grad, tensor indices, tensor offsets, tensor offset2bag, tensor bag_size, int64_t num_weights, int scale_grad_by_freq, int64_t mode, tensor per_sample_weights, int64_t padding_idx);
void atg__empty_affine_quantized(tensor *, int64_t *size_data, int size_len, int options_kind, int options_device, double scale, int64_t zero_point);
void atg__empty_per_channel_affine_quantized(tensor *, int64_t *size_data, int size_len, tensor scales, tensor zero_points, int64_t axis, int options_kind, int options_device);
void atg__euclidean_dist(tensor *, tensor x1, tensor x2);
void atg__fake_quantize_learnable_per_channel_affine(tensor *, tensor self, tensor scale, tensor zero_point, int64_t axis, int64_t quant_min, int64_t quant_max, double grad_factor);
void atg__fake_quantize_learnable_per_channel_affine_backward(tensor *, tensor grad, tensor self, tensor scale, tensor zero_point, int64_t axis, int64_t quant_min, int64_t quant_max, double grad_factor);
void atg__fake_quantize_learnable_per_tensor_affine(tensor *, tensor self, tensor scale, tensor zero_point, int64_t quant_min, int64_t quant_max, double grad_factor);
void atg__fake_quantize_learnable_per_tensor_affine_backward(tensor *, tensor grad, tensor self, tensor scale, tensor zero_point, int64_t quant_min, int64_t quant_max, double grad_factor);
void atg__fake_quantize_per_tensor_affine_cachemask_tensor_qparams(tensor *, tensor self, tensor scale, tensor zero_point, tensor fake_quant_enabled, int64_t quant_min, int64_t quant_max);
void atg__fft_c2c(tensor *, tensor self, int64_t *dim_data, int dim_len, int64_t normalization, int forward);
void atg__fft_c2c_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int64_t normalization, int forward);
void atg__fft_c2r(tensor *, tensor self, int64_t *dim_data, int dim_len, int64_t normalization, int64_t last_dim_size);
void atg__fft_c2r_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int64_t normalization, int64_t last_dim_size);
void atg__fft_r2c(tensor *, tensor self, int64_t *dim_data, int dim_len, int64_t normalization, int onesided);
void atg__fft_r2c_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int64_t normalization, int onesided);
void atg__fused_dropout(tensor *, tensor self, double p);
void atg__fused_moving_avg_obs_fq_helper(tensor *, tensor self, tensor observer_on, tensor fake_quant_on, tensor running_min, tensor running_max, tensor scale, tensor zero_point, double averaging_const, int64_t quant_min, int64_t quant_max, int64_t ch_axis, int per_row_fake_quant, int symmetric_quant);
void atg__fw_primal(tensor *, tensor self, int64_t level);
void atg__gather_sparse_backward(tensor *, tensor self, int64_t dim, tensor index, tensor grad);
void atg__grid_sampler_2d_cpu_fallback(tensor *, tensor input, tensor grid, int64_t interpolation_mode, int64_t padding_mode, int align_corners);
void atg__grid_sampler_2d_cpu_fallback_backward(tensor *, tensor grad_output, tensor input, tensor grid, int64_t interpolation_mode, int64_t padding_mode, int align_corners);
int atg__has_compatible_shallow_copy_type(tensor self, tensor from);
void atg__index_copy_(tensor *, tensor self, int64_t dim, tensor index, tensor source);
void atg__index_put_impl_(tensor *, tensor self, tensor *indices_data, int indices_len, tensor values, int accumulate, int unsafe);
void atg__indices(tensor *, tensor self);
void atg__inverse_helper(tensor *, tensor self);
void atg__linalg_inv_out_helper_(tensor *, tensor self, tensor infos_lu, tensor infos_getri);
void atg__linalg_qr_helper(tensor *, tensor self, char* mode_ptr, int mode_len);
void atg__log_softmax(tensor *, tensor self, int64_t dim, int half_to_float);
void atg__log_softmax_backward_data(tensor *, tensor grad_output, tensor output, int64_t dim, tensor self);
void atg__log_softmax_backward_data_out(tensor *, tensor out, tensor grad_output, tensor output, int64_t dim, tensor self);
void atg__log_softmax_out(tensor *, tensor out, tensor self, int64_t dim, int half_to_float);
void atg__logcumsumexp(tensor *, tensor self, int64_t dim);
void atg__logcumsumexp_out(tensor *, tensor out, tensor self, int64_t dim);
void atg__lu_with_info(tensor *, tensor self, int pivot, int check_errors);
void atg__make_dual(tensor *, tensor primal, tensor tangent, int64_t level);
void atg__make_per_channel_quantized_tensor(tensor *, tensor self, tensor scale, tensor zero_point, int64_t axis);
void atg__make_per_tensor_quantized_tensor(tensor *, tensor self, double scale, int64_t zero_point);
void atg__masked_scale(tensor *, tensor self, tensor mask, double scale);
void atg__mkldnn_reshape(tensor *, tensor self, int64_t *shape_data, int shape_len);
void atg__mkldnn_transpose(tensor *, tensor self, int64_t dim0, int64_t dim1);
void atg__mkldnn_transpose_(tensor *, tensor self, int64_t dim0, int64_t dim1);
void atg__neg_view(tensor *, tensor self);
int atg__nnpack_available();
void atg__nnpack_spatial_convolution(tensor *, tensor input, tensor weight, tensor bias, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg__nnpack_spatial_convolution_backward_input(tensor *, tensor input, tensor grad_output, tensor weight, int64_t *padding_data, int padding_len);
void atg__nnpack_spatial_convolution_backward_weight(tensor *, tensor input, int64_t *weightsize_data, int weightsize_len, tensor grad_output, int64_t *padding_data, int padding_len);
int64_t atg__nnz(tensor self);
void atg__pack_padded_sequence(tensor *, tensor input, tensor lengths, int batch_first);
void atg__pack_padded_sequence_backward(tensor *, tensor grad, int64_t *input_size_data, int input_size_len, tensor batch_sizes, int batch_first);
void atg__pad_packed_sequence(tensor *, tensor data, tensor batch_sizes, int batch_first, scalar padding_value, int64_t total_length);
void atg__pdist_backward(tensor *, tensor grad, tensor self, double p, tensor pdist);
void atg__pin_memory(tensor *, tensor self, int device);
void atg__remove_batch_dim(tensor *, tensor self, int64_t level, int64_t batch_size, int64_t out_dim);
void atg__reshape_alias(tensor *, tensor self, int64_t *size_data, int size_len, int64_t *stride_data, int stride_len);
void atg__reshape_from_tensor(tensor *, tensor self, tensor shape);
void atg__rowwise_prune(tensor *, tensor weight, tensor mask, int compressed_indices_dtype);
void atg__s_where(tensor *, tensor condition, tensor self, tensor other);
void atg__sample_dirichlet(tensor *, tensor self);
void atg__saturate_weight_to_fp16(tensor *, tensor weight);
void atg__segment_reduce_backward(tensor *, tensor grad, tensor output, tensor data, char* reduce_ptr, int reduce_len, tensor lengths, int64_t axis);
void atg__shape_as_tensor(tensor *, tensor self);
void atg__sobol_engine_draw(tensor *, tensor quasi, int64_t n, tensor sobolstate, int64_t dimension, int64_t num_generated, int dtype);
void atg__sobol_engine_ff_(tensor *, tensor self, int64_t n, tensor sobolstate, int64_t dimension, int64_t num_generated);
void atg__sobol_engine_initialize_state_(tensor *, tensor self, int64_t dimension);
void atg__sobol_engine_scramble_(tensor *, tensor self, tensor ltm, int64_t dimension);
void atg__softmax(tensor *, tensor self, int64_t dim, int half_to_float);
void atg__softmax_backward_data(tensor *, tensor grad_output, tensor output, int64_t dim, tensor self);
void atg__softmax_backward_data_out(tensor *, tensor grad_input, tensor grad_output, tensor output, int64_t dim, tensor self);
void atg__softmax_out(tensor *, tensor out, tensor self, int64_t dim, int half_to_float);
void atg__solve_helper(tensor *, tensor self, tensor A);
void atg__sparse_addmm(tensor *, tensor self, tensor sparse, tensor dense);
void atg__sparse_coo_tensor_unsafe(tensor *, tensor indices, tensor values, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg__sparse_coo_tensor_with_dims(tensor *, int64_t sparse_dim, int64_t dense_dim, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg__sparse_coo_tensor_with_dims_and_tensors(tensor *, int64_t sparse_dim, int64_t dense_dim, int64_t *size_data, int size_len, tensor indices, tensor values, int options_kind, int options_device);
void atg__sparse_csr_tensor_unsafe(tensor *, tensor crow_indices, tensor col_indices, tensor values, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg__sparse_log_softmax(tensor *, tensor self, int64_t dim, int half_to_float);
void atg__sparse_log_softmax_backward_data(tensor *, tensor grad_output, tensor output, int64_t dim, tensor self);
void atg__sparse_log_softmax_int(tensor *, tensor self, int64_t dim, int dtype);
void atg__sparse_mask_helper(tensor *, tensor t, tensor mask_indices);
void atg__sparse_mm(tensor *, tensor sparse, tensor dense);
void atg__sparse_softmax(tensor *, tensor self, int64_t dim, int half_to_float);
void atg__sparse_softmax_backward_data(tensor *, tensor grad_output, tensor output, int64_t dim, tensor self);
void atg__sparse_softmax_int(tensor *, tensor self, int64_t dim, int dtype);
void atg__sparse_sparse_matmul(tensor *, tensor self, tensor other);
void atg__sparse_sum(tensor *, tensor self);
void atg__sparse_sum_backward(tensor *, tensor grad, tensor self, int64_t *dim_data, int dim_len);
void atg__sparse_sum_dim(tensor *, tensor self, int64_t *dim_data, int dim_len);
void atg__sparse_sum_dim_dtype(tensor *, tensor self, int64_t *dim_data, int dim_len, int dtype);
void atg__sparse_sum_dtype(tensor *, tensor self, int dtype);
void atg__stack(tensor *, tensor *tensors_data, int tensors_len, int64_t dim);
void atg__stack_out(tensor *, tensor out, tensor *tensors_data, int tensors_len, int64_t dim);
void atg__standard_gamma(tensor *, tensor self);
void atg__standard_gamma_grad(tensor *, tensor self, tensor output);
void atg__svd_helper(tensor *, tensor self, int some, int compute_uv);
void atg__symeig_helper(tensor *, tensor self, int eigenvectors, int upper);
void atg__test_ambiguous_defaults(tensor *, tensor dummy, int64_t a, int64_t b);
void atg__test_ambiguous_defaults_b(tensor *, tensor dummy, int64_t a, char* b_ptr, int b_len);
void atg__test_optional_filled_intlist(tensor *, tensor values, int64_t *addends_data, int addends_len);
void atg__test_optional_floatlist(tensor *, tensor values, double *addends_data, int addends_len);
void atg__test_optional_intlist(tensor *, tensor values, int64_t *addends_data, int addends_len);
void atg__test_serialization_subcmul(tensor *, tensor self, tensor other);
void atg__test_string_default(tensor *, tensor dummy, char* a_ptr, int a_len, char* b_ptr, int b_len);
void atg__to_copy(tensor *, tensor self, int options_kind, int options_device, int non_blocking);
tensor *atg__to_cpu(tensor *tensors_data, int tensors_len);
void atg__trilinear(tensor *, tensor i1, tensor i2, tensor i3, int64_t *expand1_data, int expand1_len, int64_t *expand2_data, int expand2_len, int64_t *expand3_data, int expand3_len, int64_t *sumdim_data, int sumdim_len, int64_t unroll_dim);
void atg__unique(tensor *, tensor self, int sorted, int return_inverse);
void atg__unique2(tensor *, tensor self, int sorted, int return_inverse, int return_counts);
void atg__unpack_dual(tensor *, tensor dual, int64_t level);
void atg__unsafe_view(tensor *, tensor self, int64_t *size_data, int size_len);
int atg__use_cudnn_ctc_loss(tensor log_probs, tensor targets, int64_t *input_lengths_data, int input_lengths_len, int64_t *target_lengths_data, int target_lengths_len, int64_t blank);
int atg__use_cudnn_rnn_flatten_weight();
void atg__validate_sparse_csr_tensor_args(tensor crow_indices, tensor col_indices, tensor values, int64_t *size_data, int size_len);
void atg__values(tensor *, tensor self);
int64_t atg__version(tensor self);
void atg__weight_norm(tensor *, tensor v, tensor g, int64_t dim);
void atg__weight_norm_cuda_interface(tensor *, tensor v, tensor g, int64_t dim);
void atg__weight_norm_cuda_interface_backward(tensor *, tensor grad_w, tensor saved_v, tensor saved_g, tensor saved_norms, int64_t dim);
void atg__weight_norm_differentiable_backward(tensor *, tensor grad_w, tensor saved_v, tensor saved_g, tensor saved_norms, int64_t dim);
void atg_abs(tensor *, tensor self);
void atg_abs_(tensor *, tensor self);
void atg_abs_out(tensor *, tensor out, tensor self);
void atg_absolute(tensor *, tensor self);
void atg_absolute_(tensor *, tensor self);
void atg_absolute_out(tensor *, tensor out, tensor self);
void atg_acos(tensor *, tensor self);
void atg_acos_(tensor *, tensor self);
void atg_acos_out(tensor *, tensor out, tensor self);
void atg_acosh(tensor *, tensor self);
void atg_acosh_(tensor *, tensor self);
void atg_acosh_out(tensor *, tensor out, tensor self);
void atg_adaptive_avg_pool1d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_avg_pool2d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_avg_pool2d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_avg_pool3d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_avg_pool3d_backward(tensor *, tensor grad_input, tensor grad_output, tensor self);
void atg_adaptive_avg_pool3d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_max_pool1d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_max_pool2d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_max_pool2d_backward(tensor *, tensor grad_output, tensor self, tensor indices);
void atg_adaptive_max_pool2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor indices);
void atg_adaptive_max_pool2d_out(tensor *, tensor out, tensor indices, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_max_pool3d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg_adaptive_max_pool3d_backward(tensor *, tensor grad_output, tensor self, tensor indices);
void atg_adaptive_max_pool3d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor indices);
void atg_adaptive_max_pool3d_out(tensor *, tensor out, tensor indices, tensor self, int64_t *output_size_data, int output_size_len);
void atg_add(tensor *, tensor self, tensor other);
void atg_add_(tensor *, tensor self, tensor other);
void atg_add_out(tensor *, tensor out, tensor self, tensor other);
void atg_add_scalar(tensor *, tensor self, scalar other);
void atg_add_scalar_(tensor *, tensor self, scalar other);
void atg_addbmm(tensor *, tensor self, tensor batch1, tensor batch2);
void atg_addbmm_(tensor *, tensor self, tensor batch1, tensor batch2);
void atg_addbmm_out(tensor *, tensor out, tensor self, tensor batch1, tensor batch2);
void atg_addcdiv(tensor *, tensor self, tensor tensor1, tensor tensor2);
void atg_addcdiv_(tensor *, tensor self, tensor tensor1, tensor tensor2);
void atg_addcdiv_out(tensor *, tensor out, tensor self, tensor tensor1, tensor tensor2);
void atg_addcmul(tensor *, tensor self, tensor tensor1, tensor tensor2);
void atg_addcmul_(tensor *, tensor self, tensor tensor1, tensor tensor2);
void atg_addcmul_out(tensor *, tensor out, tensor self, tensor tensor1, tensor tensor2);
void atg_addmm(tensor *, tensor self, tensor mat1, tensor mat2);
void atg_addmm_(tensor *, tensor self, tensor mat1, tensor mat2);
void atg_addmm_out(tensor *, tensor out, tensor self, tensor mat1, tensor mat2);
void atg_addmv(tensor *, tensor self, tensor mat, tensor vec);
void atg_addmv_(tensor *, tensor self, tensor mat, tensor vec);
void atg_addmv_out(tensor *, tensor out, tensor self, tensor mat, tensor vec);
void atg_addr(tensor *, tensor self, tensor vec1, tensor vec2);
void atg_addr_(tensor *, tensor self, tensor vec1, tensor vec2);
void atg_addr_out(tensor *, tensor out, tensor self, tensor vec1, tensor vec2);
void atg_affine_grid_generator(tensor *, tensor theta, int64_t *size_data, int size_len, int align_corners);
void atg_affine_grid_generator_backward(tensor *, tensor grad, int64_t *size_data, int size_len, int align_corners);
void atg_alias(tensor *, tensor self);
void atg_align_as(tensor *, tensor self, tensor other);
tensor *atg_align_tensors(tensor *tensors_data, int tensors_len);
void atg_all(tensor *, tensor self);
void atg_all_all_out(tensor *, tensor out, tensor self);
void atg_all_dim(tensor *, tensor self, int64_t dim, int keepdim);
void atg_all_out(tensor *, tensor out, tensor self, int64_t dim, int keepdim);
int atg_allclose(tensor self, tensor other, double rtol, double atol, int equal_nan);
void atg_alpha_dropout(tensor *, tensor input, double p, int train);
void atg_alpha_dropout_(tensor *, tensor self, double p, int train);
void atg_amax(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_amax_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_amin(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_amin_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_aminmax(tensor *, tensor self, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_aminmax_out(tensor *, tensor min, tensor max, tensor self, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_angle(tensor *, tensor self);
void atg_angle_out(tensor *, tensor out, tensor self);
void atg_any(tensor *, tensor self);
void atg_any_all_out(tensor *, tensor out, tensor self);
void atg_any_dim(tensor *, tensor self, int64_t dim, int keepdim);
void atg_any_out(tensor *, tensor out, tensor self, int64_t dim, int keepdim);
void atg_arange(tensor *, scalar end, int options_kind, int options_device);
void atg_arange_out(tensor *, tensor out, scalar end);
void atg_arange_start(tensor *, scalar start, scalar end, int options_kind, int options_device);
void atg_arange_start_out(tensor *, tensor out, scalar start, scalar end);
void atg_arange_start_step(tensor *, scalar start, scalar end, scalar step, int options_kind, int options_device);
void atg_arccos(tensor *, tensor self);
void atg_arccos_(tensor *, tensor self);
void atg_arccos_out(tensor *, tensor out, tensor self);
void atg_arccosh(tensor *, tensor self);
void atg_arccosh_(tensor *, tensor self);
void atg_arccosh_out(tensor *, tensor out, tensor self);
void atg_arcsin(tensor *, tensor self);
void atg_arcsin_(tensor *, tensor self);
void atg_arcsin_out(tensor *, tensor out, tensor self);
void atg_arcsinh(tensor *, tensor self);
void atg_arcsinh_(tensor *, tensor self);
void atg_arcsinh_out(tensor *, tensor out, tensor self);
void atg_arctan(tensor *, tensor self);
void atg_arctan_(tensor *, tensor self);
void atg_arctan_out(tensor *, tensor out, tensor self);
void atg_arctanh(tensor *, tensor self);
void atg_arctanh_(tensor *, tensor self);
void atg_arctanh_out(tensor *, tensor out, tensor self);
void atg_argmax(tensor *, tensor self, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_argmax_out(tensor *, tensor out, tensor self, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_argmin(tensor *, tensor self, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_argmin_out(tensor *, tensor out, tensor self, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_argsort(tensor *, tensor self, int64_t dim, int descending);
void atg_as_strided(tensor *, tensor self, int64_t *size_data, int size_len, int64_t *stride_data, int stride_len, int64_t storage_offset_v, uint8_t storage_offset_null);
void atg_as_strided_(tensor *, tensor self, int64_t *size_data, int size_len, int64_t *stride_data, int stride_len, int64_t storage_offset_v, uint8_t storage_offset_null);
void atg_asin(tensor *, tensor self);
void atg_asin_(tensor *, tensor self);
void atg_asin_out(tensor *, tensor out, tensor self);
void atg_asinh(tensor *, tensor self);
void atg_asinh_(tensor *, tensor self);
void atg_asinh_out(tensor *, tensor out, tensor self);
void atg_atan(tensor *, tensor self);
void atg_atan2(tensor *, tensor self, tensor other);
void atg_atan2_(tensor *, tensor self, tensor other);
void atg_atan2_out(tensor *, tensor out, tensor self, tensor other);
void atg_atan_(tensor *, tensor self);
void atg_atan_out(tensor *, tensor out, tensor self);
void atg_atanh(tensor *, tensor self);
void atg_atanh_(tensor *, tensor self);
void atg_atanh_out(tensor *, tensor out, tensor self);
void atg_atleast_1d(tensor *, tensor self);
tensor *atg_atleast_1d_sequence(tensor *tensors_data, int tensors_len);
void atg_atleast_2d(tensor *, tensor self);
tensor *atg_atleast_2d_sequence(tensor *tensors_data, int tensors_len);
void atg_atleast_3d(tensor *, tensor self);
tensor *atg_atleast_3d_sequence(tensor *tensors_data, int tensors_len);
void atg_avg_pool1d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad);
void atg_avg_pool2d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad, int64_t divisor_override_v, uint8_t divisor_override_null);
void atg_avg_pool2d_backward(tensor *, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad, int64_t divisor_override_v, uint8_t divisor_override_null);
void atg_avg_pool2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad, int64_t divisor_override_v, uint8_t divisor_override_null);
void atg_avg_pool2d_out(tensor *, tensor out, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad, int64_t divisor_override_v, uint8_t divisor_override_null);
void atg_avg_pool3d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad, int64_t divisor_override_v, uint8_t divisor_override_null);
void atg_avg_pool3d_backward(tensor *, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad, int64_t divisor_override_v, uint8_t divisor_override_null);
void atg_avg_pool3d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad, int64_t divisor_override_v, uint8_t divisor_override_null);
void atg_avg_pool3d_out(tensor *, tensor out, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int ceil_mode, int count_include_pad, int64_t divisor_override_v, uint8_t divisor_override_null);
void atg_baddbmm(tensor *, tensor self, tensor batch1, tensor batch2);
void atg_baddbmm_(tensor *, tensor self, tensor batch1, tensor batch2);
void atg_baddbmm_out(tensor *, tensor out, tensor self, tensor batch1, tensor batch2);
void atg_bartlett_window(tensor *, int64_t window_length, int options_kind, int options_device);
void atg_bartlett_window_periodic(tensor *, int64_t window_length, int periodic, int options_kind, int options_device);
void atg_batch_norm(tensor *, tensor input, tensor weight, tensor bias, tensor running_mean, tensor running_var, int training, double momentum, double eps, int cudnn_enabled);
void atg_batch_norm_backward_elemt(tensor *, tensor grad_out, tensor input, tensor mean, tensor invstd, tensor weight, tensor mean_dy, tensor mean_dy_xmu, tensor count);
void atg_batch_norm_backward_reduce(tensor *, tensor grad_out, tensor input, tensor mean, tensor invstd, tensor weight, int input_g, int weight_g, int bias_g);
void atg_batch_norm_elemt(tensor *, tensor input, tensor weight, tensor bias, tensor mean, tensor invstd, double eps);
void atg_batch_norm_elemt_out(tensor *, tensor out, tensor input, tensor weight, tensor bias, tensor mean, tensor invstd, double eps);
void atg_batch_norm_gather_stats(tensor *, tensor input, tensor mean, tensor invstd, tensor running_mean, tensor running_var, double momentum, double eps, int64_t count);
void atg_batch_norm_gather_stats_with_counts(tensor *, tensor input, tensor mean, tensor invstd, tensor running_mean, tensor running_var, double momentum, double eps, tensor counts);
void atg_batch_norm_stats(tensor *, tensor input, double eps);
void atg_batch_norm_update_stats(tensor *, tensor input, tensor running_mean, tensor running_var, double momentum);
void atg_bernoulli(tensor *, tensor self);
void atg_bernoulli_(tensor *, tensor self, tensor p);
void atg_bernoulli_float_(tensor *, tensor self, double p);
void atg_bernoulli_out(tensor *, tensor out, tensor self);
void atg_bernoulli_p(tensor *, tensor self, double p);
void atg_bilinear(tensor *, tensor input1, tensor input2, tensor weight, tensor bias);
void atg_binary_cross_entropy(tensor *, tensor self, tensor target, tensor weight, int64_t reduction);
void atg_binary_cross_entropy_backward(tensor *, tensor grad_output, tensor self, tensor target, tensor weight, int64_t reduction);
void atg_binary_cross_entropy_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, tensor weight, int64_t reduction);
void atg_binary_cross_entropy_out(tensor *, tensor out, tensor self, tensor target, tensor weight, int64_t reduction);
void atg_binary_cross_entropy_with_logits(tensor *, tensor self, tensor target, tensor weight, tensor pos_weight, int64_t reduction);
void atg_binary_cross_entropy_with_logits_backward(tensor *, tensor grad_output, tensor self, tensor target, tensor weight, tensor pos_weight, int64_t reduction);
void atg_bincount(tensor *, tensor self, tensor weights, int64_t minlength);
void atg_binomial(tensor *, tensor count, tensor prob);
void atg_bitwise_and(tensor *, tensor self, scalar other);
void atg_bitwise_and_(tensor *, tensor self, scalar other);
void atg_bitwise_and_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_bitwise_and_tensor(tensor *, tensor self, tensor other);
void atg_bitwise_and_tensor_(tensor *, tensor self, tensor other);
void atg_bitwise_and_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_bitwise_left_shift(tensor *, tensor self, tensor other);
void atg_bitwise_left_shift_(tensor *, tensor self, tensor other);
void atg_bitwise_left_shift_scalar_tensor(tensor *, scalar self_scalar, tensor other);
void atg_bitwise_left_shift_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_bitwise_left_shift_tensor_scalar(tensor *, tensor self, scalar other);
void atg_bitwise_left_shift_tensor_scalar_(tensor *, tensor self, scalar other);
void atg_bitwise_left_shift_tensor_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_bitwise_not(tensor *, tensor self);
void atg_bitwise_not_(tensor *, tensor self);
void atg_bitwise_not_out(tensor *, tensor out, tensor self);
void atg_bitwise_or(tensor *, tensor self, scalar other);
void atg_bitwise_or_(tensor *, tensor self, scalar other);
void atg_bitwise_or_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_bitwise_or_tensor(tensor *, tensor self, tensor other);
void atg_bitwise_or_tensor_(tensor *, tensor self, tensor other);
void atg_bitwise_or_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_bitwise_right_shift(tensor *, tensor self, tensor other);
void atg_bitwise_right_shift_(tensor *, tensor self, tensor other);
void atg_bitwise_right_shift_scalar_tensor(tensor *, scalar self_scalar, tensor other);
void atg_bitwise_right_shift_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_bitwise_right_shift_tensor_scalar(tensor *, tensor self, scalar other);
void atg_bitwise_right_shift_tensor_scalar_(tensor *, tensor self, scalar other);
void atg_bitwise_right_shift_tensor_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_bitwise_xor(tensor *, tensor self, scalar other);
void atg_bitwise_xor_(tensor *, tensor self, scalar other);
void atg_bitwise_xor_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_bitwise_xor_tensor(tensor *, tensor self, tensor other);
void atg_bitwise_xor_tensor_(tensor *, tensor self, tensor other);
void atg_bitwise_xor_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_blackman_window(tensor *, int64_t window_length, int options_kind, int options_device);
void atg_blackman_window_periodic(tensor *, int64_t window_length, int periodic, int options_kind, int options_device);
void atg_block_diag(tensor *, tensor *tensors_data, int tensors_len);
void atg_bmm(tensor *, tensor self, tensor mat2);
void atg_bmm_out(tensor *, tensor out, tensor self, tensor mat2);
tensor *atg_broadcast_tensors(tensor *tensors_data, int tensors_len);
void atg_broadcast_to(tensor *, tensor self, int64_t *size_data, int size_len);
void atg_bucketize(tensor *, tensor self, tensor boundaries, int out_int32, int right);
void atg_bucketize_scalar(tensor *, scalar self_scalar, tensor boundaries, int out_int32, int right);
void atg_bucketize_tensor_out(tensor *, tensor out, tensor self, tensor boundaries, int out_int32, int right);
int atg_can_cast(int from, int to);
void atg_cartesian_prod(tensor *, tensor *tensors_data, int tensors_len);
void atg_cat(tensor *, tensor *tensors_data, int tensors_len, int64_t dim);
void atg_cat_out(tensor *, tensor out, tensor *tensors_data, int tensors_len, int64_t dim);
void atg_cauchy_(tensor *, tensor self, double median, double sigma);
void atg_cdist(tensor *, tensor x1, tensor x2, double p, int64_t compute_mode_v, uint8_t compute_mode_null);
void atg_ceil(tensor *, tensor self);
void atg_ceil_(tensor *, tensor self);
void atg_ceil_out(tensor *, tensor out, tensor self);
void atg_celu(tensor *, tensor self);
void atg_celu_(tensor *, tensor self);
void atg_chain_matmul(tensor *, tensor *matrices_data, int matrices_len);
void atg_chain_matmul_out(tensor *, tensor out, tensor *matrices_data, int matrices_len);
void atg_channel_shuffle(tensor *, tensor self, int64_t groups);
void atg_cholesky(tensor *, tensor self, int upper);
void atg_cholesky_inverse(tensor *, tensor self, int upper);
void atg_cholesky_inverse_out(tensor *, tensor out, tensor self, int upper);
void atg_cholesky_out(tensor *, tensor out, tensor self, int upper);
void atg_cholesky_solve(tensor *, tensor self, tensor input2, int upper);
void atg_cholesky_solve_out(tensor *, tensor out, tensor self, tensor input2, int upper);
void atg_choose_qparams_optimized(tensor *, tensor input, int64_t numel, int64_t n_bins, double ratio, int64_t bit_width);
tensor *atg_chunk(tensor self, int64_t chunks, int64_t dim);
void atg_clamp(tensor *, tensor self, scalar min, scalar max);
void atg_clamp_(tensor *, tensor self, scalar min, scalar max);
void atg_clamp_max(tensor *, tensor self, scalar max);
void atg_clamp_max_(tensor *, tensor self, scalar max);
void atg_clamp_max_out(tensor *, tensor out, tensor self, scalar max);
void atg_clamp_max_tensor(tensor *, tensor self, tensor max);
void atg_clamp_max_tensor_(tensor *, tensor self, tensor max);
void atg_clamp_max_tensor_out(tensor *, tensor out, tensor self, tensor max);
void atg_clamp_min(tensor *, tensor self, scalar min);
void atg_clamp_min_(tensor *, tensor self, scalar min);
void atg_clamp_min_out(tensor *, tensor out, tensor self, scalar min);
void atg_clamp_min_tensor(tensor *, tensor self, tensor min);
void atg_clamp_min_tensor_(tensor *, tensor self, tensor min);
void atg_clamp_min_tensor_out(tensor *, tensor out, tensor self, tensor min);
void atg_clamp_out(tensor *, tensor out, tensor self, scalar min, scalar max);
void atg_clamp_tensor(tensor *, tensor self, tensor min, tensor max);
void atg_clamp_tensor_(tensor *, tensor self, tensor min, tensor max);
void atg_clamp_tensor_out(tensor *, tensor out, tensor self, tensor min, tensor max);
void atg_clip(tensor *, tensor self, scalar min, scalar max);
void atg_clip_(tensor *, tensor self, scalar min, scalar max);
void atg_clip_out(tensor *, tensor out, tensor self, scalar min, scalar max);
void atg_clip_tensor(tensor *, tensor self, tensor min, tensor max);
void atg_clip_tensor_(tensor *, tensor self, tensor min, tensor max);
void atg_clip_tensor_out(tensor *, tensor out, tensor self, tensor min, tensor max);
void atg_coalesce(tensor *, tensor self);
void atg_col2im(tensor *, tensor self, int64_t *output_size_data, int output_size_len, int64_t *kernel_size_data, int kernel_size_len, int64_t *dilation_data, int dilation_len, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg_col2im_backward(tensor *, tensor grad_output, int64_t *kernel_size_data, int kernel_size_len, int64_t *dilation_data, int dilation_len, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg_col2im_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *kernel_size_data, int kernel_size_len, int64_t *dilation_data, int dilation_len, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg_col2im_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len, int64_t *kernel_size_data, int kernel_size_len, int64_t *dilation_data, int dilation_len, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg_col_indices(tensor *, tensor self);
void atg_column_stack(tensor *, tensor *tensors_data, int tensors_len);
void atg_column_stack_out(tensor *, tensor out, tensor *tensors_data, int tensors_len);
void atg_combinations(tensor *, tensor self, int64_t r, int with_replacement);
void atg_complex(tensor *, tensor real, tensor imag);
void atg_complex_out(tensor *, tensor out, tensor real, tensor imag);
void atg_concat(tensor *, tensor *tensors_data, int tensors_len, int64_t dim);
void atg_concat_out(tensor *, tensor out, tensor *tensors_data, int tensors_len, int64_t dim);
void atg_conj(tensor *, tensor self);
void atg_conj_physical(tensor *, tensor self);
void atg_conj_physical_(tensor *, tensor self);
void atg_conj_physical_out(tensor *, tensor out, tensor self);
void atg_constant_pad_nd(tensor *, tensor self, int64_t *pad_data, int pad_len);
void atg_contiguous(tensor *, tensor self);
void atg_conv1d(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_conv1d_padding(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, char* padding_ptr, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_conv2d(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_conv2d_padding(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, char* padding_ptr, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_conv3d(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_conv3d_padding(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, char* padding_ptr, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_conv_depthwise3d(tensor *, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len);
void atg_conv_depthwise3d_backward(tensor *, tensor grad_input, tensor grad_weight, tensor grad_bias, tensor grad_output, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len);
void atg_conv_tbc(tensor *, tensor self, tensor weight, tensor bias, int64_t pad);
void atg_conv_tbc_backward(tensor *, tensor self, tensor input, tensor weight, tensor bias, int64_t pad);
void atg_conv_transpose1d(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t groups, int64_t *dilation_data, int dilation_len);
void atg_conv_transpose2d(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t groups, int64_t *dilation_data, int dilation_len);
void atg_conv_transpose3d(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t groups, int64_t *dilation_data, int dilation_len);
void atg_convolution(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int transposed, int64_t *output_padding_data, int output_padding_len, int64_t groups);
void atg_convolution_overrideable(tensor *, tensor input, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int transposed, int64_t *output_padding_data, int output_padding_len, int64_t groups);
void atg_copy_sparse_to_sparse_(tensor *, tensor self, tensor src, int non_blocking);
void atg_copysign(tensor *, tensor self, tensor other);
void atg_copysign_(tensor *, tensor self, tensor other);
void atg_copysign_out(tensor *, tensor out, tensor self, tensor other);
void atg_copysign_scalar(tensor *, tensor self, scalar other);
void atg_copysign_scalar_(tensor *, tensor self, scalar other);
void atg_copysign_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_corrcoef(tensor *, tensor self);
void atg_cos(tensor *, tensor self);
void atg_cos_(tensor *, tensor self);
void atg_cos_out(tensor *, tensor out, tensor self);
void atg_cosh(tensor *, tensor self);
void atg_cosh_(tensor *, tensor self);
void atg_cosh_out(tensor *, tensor out, tensor self);
void atg_cosine_embedding_loss(tensor *, tensor input1, tensor input2, tensor target, double margin, int64_t reduction);
void atg_cosine_similarity(tensor *, tensor x1, tensor x2, int64_t dim, double eps);
void atg_count_nonzero(tensor *, tensor self, int64_t dim_v, uint8_t dim_null);
void atg_count_nonzero_dim_intlist(tensor *, tensor self, int64_t *dim_data, int dim_len);
void atg_cov(tensor *, tensor self, int64_t correction, tensor fweights, tensor aweights);
void atg_cross(tensor *, tensor self, tensor other, int64_t dim_v, uint8_t dim_null);
void atg_cross_entropy_loss(tensor *, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index, double label_smoothing);
void atg_cross_out(tensor *, tensor out, tensor self, tensor other, int64_t dim_v, uint8_t dim_null);
void atg_crow_indices(tensor *, tensor self);
void atg_ctc_loss(tensor *, tensor log_probs, tensor targets, int64_t *input_lengths_data, int input_lengths_len, int64_t *target_lengths_data, int target_lengths_len, int64_t blank, int64_t reduction, int zero_infinity);
void atg_ctc_loss_tensor(tensor *, tensor log_probs, tensor targets, tensor input_lengths, tensor target_lengths, int64_t blank, int64_t reduction, int zero_infinity);
void atg_cudnn_affine_grid_generator(tensor *, tensor theta, int64_t n, int64_t C, int64_t H, int64_t W);
void atg_cudnn_affine_grid_generator_backward(tensor *, tensor grad, int64_t n, int64_t C, int64_t H, int64_t W);
void atg_cudnn_batch_norm(tensor *, tensor input, tensor weight, tensor bias, tensor running_mean, tensor running_var, int training, double exponential_average_factor, double epsilon);
void atg_cudnn_batch_norm_backward(tensor *, tensor input, tensor grad_output, tensor weight, tensor running_mean, tensor running_var, tensor save_mean, tensor save_var, double epsilon, tensor reserveSpace);
void atg_cudnn_convolution(tensor *, tensor self, tensor weight, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic, int allow_tf32);
void atg_cudnn_convolution_add_relu(tensor *, tensor self, tensor weight, tensor z, scalar alpha, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_cudnn_convolution_backward_input(tensor *, int64_t *self_size_data, int self_size_len, tensor grad_output, tensor weight, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic, int allow_tf32);
void atg_cudnn_convolution_backward_weight(tensor *, int64_t *weight_size_data, int weight_size_len, tensor grad_output, tensor self, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic, int allow_tf32);
void atg_cudnn_convolution_deprecated(tensor *, tensor self, tensor weight, tensor bias, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_cudnn_convolution_deprecated2(tensor *, tensor self, tensor weight, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_cudnn_convolution_relu(tensor *, tensor self, tensor weight, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_cudnn_convolution_transpose(tensor *, tensor self, tensor weight, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic, int allow_tf32);
void atg_cudnn_convolution_transpose_backward_input(tensor *, tensor grad_output, tensor weight, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic, int allow_tf32);
void atg_cudnn_convolution_transpose_backward_weight(tensor *, int64_t *weight_size_data, int weight_size_len, tensor grad_output, tensor self, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic, int allow_tf32);
void atg_cudnn_convolution_transpose_deprecated(tensor *, tensor self, tensor weight, tensor bias, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_cudnn_convolution_transpose_deprecated2(tensor *, tensor self, tensor weight, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_cudnn_grid_sampler(tensor *, tensor self, tensor grid);
void atg_cudnn_grid_sampler_backward(tensor *, tensor self, tensor grid, tensor grad_output);
int atg_cudnn_is_acceptable(tensor self);
void atg_cummax(tensor *, tensor self, int64_t dim);
void atg_cummax_out(tensor *, tensor values, tensor indices, tensor self, int64_t dim);
void atg_cummaxmin_backward(tensor *, tensor grad, tensor input, tensor indices, int64_t dim);
void atg_cummin(tensor *, tensor self, int64_t dim);
void atg_cummin_out(tensor *, tensor values, tensor indices, tensor self, int64_t dim);
void atg_cumprod(tensor *, tensor self, int64_t dim, int dtype);
void atg_cumprod_(tensor *, tensor self, int64_t dim, int dtype);
void atg_cumprod_backward(tensor *, tensor grad, tensor input, int64_t dim, tensor output);
void atg_cumprod_out(tensor *, tensor out, tensor self, int64_t dim, int dtype);
void atg_cumsum(tensor *, tensor self, int64_t dim, int dtype);
void atg_cumsum_(tensor *, tensor self, int64_t dim, int dtype);
void atg_cumsum_out(tensor *, tensor out, tensor self, int64_t dim, int dtype);
void atg_cumulative_trapezoid(tensor *, tensor y, int64_t dim);
void atg_cumulative_trapezoid_x(tensor *, tensor y, tensor x, int64_t dim);
void atg_data(tensor *, tensor self);
void atg_deg2rad(tensor *, tensor self);
void atg_deg2rad_(tensor *, tensor self);
void atg_deg2rad_out(tensor *, tensor out, tensor self);
int64_t atg_dense_dim(tensor self);
void atg_dequantize(tensor *, tensor self);
tensor *atg_dequantize_tensors(tensor *tensors_data, int tensors_len);
void atg_det(tensor *, tensor self);
void atg_detach(tensor *, tensor self);
void atg_detach_(tensor *, tensor self);
void atg_diag(tensor *, tensor self, int64_t diagonal);
void atg_diag_backward(tensor *, tensor grad, int64_t *input_sizes_data, int input_sizes_len, int64_t diagonal);
void atg_diag_embed(tensor *, tensor self, int64_t offset, int64_t dim1, int64_t dim2);
void atg_diag_out(tensor *, tensor out, tensor self, int64_t diagonal);
void atg_diagflat(tensor *, tensor self, int64_t offset);
void atg_diagonal(tensor *, tensor self, int64_t offset, int64_t dim1, int64_t dim2);
void atg_diagonal_backward(tensor *, tensor grad_output, int64_t *input_sizes_data, int input_sizes_len, int64_t offset, int64_t dim1, int64_t dim2);
void atg_diff(tensor *, tensor self, int64_t n, int64_t dim, tensor prepend, tensor append);
void atg_diff_out(tensor *, tensor out, tensor self, int64_t n, int64_t dim, tensor prepend, tensor append);
void atg_digamma(tensor *, tensor self);
void atg_digamma_(tensor *, tensor self);
void atg_digamma_out(tensor *, tensor out, tensor self);
void atg_dist(tensor *, tensor self, tensor other);
void atg_div(tensor *, tensor self, tensor other);
void atg_div_(tensor *, tensor self, tensor other);
void atg_div_out(tensor *, tensor out, tensor self, tensor other);
void atg_div_out_mode(tensor *, tensor out, tensor self, tensor other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_div_scalar(tensor *, tensor self, scalar other);
void atg_div_scalar_(tensor *, tensor self, scalar other);
void atg_div_scalar_mode(tensor *, tensor self, scalar other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_div_scalar_mode_(tensor *, tensor self, scalar other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_div_tensor_mode(tensor *, tensor self, tensor other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_div_tensor_mode_(tensor *, tensor self, tensor other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_divide(tensor *, tensor self, tensor other);
void atg_divide_(tensor *, tensor self, tensor other);
void atg_divide_out(tensor *, tensor out, tensor self, tensor other);
void atg_divide_out_mode(tensor *, tensor out, tensor self, tensor other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_divide_scalar(tensor *, tensor self, scalar other);
void atg_divide_scalar_(tensor *, tensor self, scalar other);
void atg_divide_scalar_mode(tensor *, tensor self, scalar other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_divide_scalar_mode_(tensor *, tensor self, scalar other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_divide_tensor_mode(tensor *, tensor self, tensor other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_divide_tensor_mode_(tensor *, tensor self, tensor other, char* rounding_mode_ptr, int rounding_mode_len);
void atg_dot(tensor *, tensor self, tensor tensor);
void atg_dot_out(tensor *, tensor out, tensor self, tensor tensor);
void atg_dropout(tensor *, tensor input, double p, int train);
void atg_dropout_(tensor *, tensor self, double p, int train);
tensor *atg_dsplit(tensor self, int64_t sections);
tensor *atg_dsplit_array(tensor self, int64_t *indices_data, int indices_len);
void atg_dstack(tensor *, tensor *tensors_data, int tensors_len);
void atg_dstack_out(tensor *, tensor out, tensor *tensors_data, int tensors_len);
void atg_eig(tensor *, tensor self, int eigenvectors);
void atg_eig_e(tensor *, tensor e, tensor v, tensor self, int eigenvectors);
void atg_einsum(tensor *, char* equation_ptr, int equation_len, tensor *tensors_data, int tensors_len);
void atg_elu(tensor *, tensor self);
void atg_elu_(tensor *, tensor self);
void atg_elu_backward(tensor *, tensor grad_output, scalar alpha, scalar scale, scalar input_scale, int is_result, tensor self_or_result);
void atg_elu_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, scalar alpha, scalar scale, scalar input_scale, int is_result, tensor self_or_result);
void atg_elu_out(tensor *, tensor out, tensor self);
void atg_embedding(tensor *, tensor weight, tensor indices, int64_t padding_idx, int scale_grad_by_freq, int sparse);
void atg_embedding_backward(tensor *, tensor grad, tensor indices, int64_t num_weights, int64_t padding_idx, int scale_grad_by_freq, int sparse);
void atg_embedding_bag(tensor *, tensor weight, tensor indices, tensor offsets, int scale_grad_by_freq, int64_t mode, int sparse, tensor per_sample_weights, int include_last_offset);
void atg_embedding_bag_padding_idx(tensor *, tensor weight, tensor indices, tensor offsets, int scale_grad_by_freq, int64_t mode, int sparse, tensor per_sample_weights, int include_last_offset, int64_t padding_idx_v, uint8_t padding_idx_null);
void atg_embedding_dense_backward(tensor *, tensor grad_output, tensor indices, int64_t num_weights, int64_t padding_idx, int scale_grad_by_freq);
void atg_embedding_renorm_(tensor *, tensor self, tensor indices, double max_norm, double norm_type);
void atg_embedding_sparse_backward(tensor *, tensor grad, tensor indices, int64_t num_weights, int64_t padding_idx, int scale_grad_by_freq);
void atg_empty(tensor *, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_empty_like(tensor *, tensor self);
void atg_empty_out(tensor *, tensor out, int64_t *size_data, int size_len);
void atg_empty_quantized(tensor *, int64_t *size_data, int size_len, tensor qtensor, int options_kind, int options_device);
void atg_empty_strided(tensor *, int64_t *size_data, int size_len, int64_t *stride_data, int stride_len, int options_kind, int options_device);
void atg_eq(tensor *, tensor self, scalar other);
void atg_eq_(tensor *, tensor self, scalar other);
void atg_eq_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_eq_tensor(tensor *, tensor self, tensor other);
void atg_eq_tensor_(tensor *, tensor self, tensor other);
void atg_eq_tensor_out(tensor *, tensor out, tensor self, tensor other);
int atg_equal(tensor self, tensor other);
void atg_erf(tensor *, tensor self);
void atg_erf_(tensor *, tensor self);
void atg_erf_out(tensor *, tensor out, tensor self);
void atg_erfc(tensor *, tensor self);
void atg_erfc_(tensor *, tensor self);
void atg_erfc_out(tensor *, tensor out, tensor self);
void atg_erfinv(tensor *, tensor self);
void atg_erfinv_(tensor *, tensor self);
void atg_erfinv_out(tensor *, tensor out, tensor self);
void atg_exp(tensor *, tensor self);
void atg_exp2(tensor *, tensor self);
void atg_exp2_(tensor *, tensor self);
void atg_exp2_out(tensor *, tensor out, tensor self);
void atg_exp_(tensor *, tensor self);
void atg_exp_out(tensor *, tensor out, tensor self);
void atg_expand(tensor *, tensor self, int64_t *size_data, int size_len, int implicit);
void atg_expand_as(tensor *, tensor self, tensor other);
void atg_expm1(tensor *, tensor self);
void atg_expm1_(tensor *, tensor self);
void atg_expm1_out(tensor *, tensor out, tensor self);
void atg_exponential_(tensor *, tensor self, double lambd);
void atg_eye(tensor *, int64_t n, int options_kind, int options_device);
void atg_eye_m(tensor *, int64_t n, int64_t m, int options_kind, int options_device);
void atg_eye_m_out(tensor *, tensor out, int64_t n, int64_t m);
void atg_eye_out(tensor *, tensor out, int64_t n);
void atg_fake_quantize_per_channel_affine(tensor *, tensor self, tensor scale, tensor zero_point, int64_t axis, int64_t quant_min, int64_t quant_max);
void atg_fake_quantize_per_channel_affine_cachemask(tensor *, tensor self, tensor scale, tensor zero_point, int64_t axis, int64_t quant_min, int64_t quant_max);
void atg_fake_quantize_per_channel_affine_cachemask_backward(tensor *, tensor grad, tensor mask);
void atg_fake_quantize_per_tensor_affine(tensor *, tensor self, double scale, int64_t zero_point, int64_t quant_min, int64_t quant_max);
void atg_fake_quantize_per_tensor_affine_cachemask(tensor *, tensor self, double scale, int64_t zero_point, int64_t quant_min, int64_t quant_max);
void atg_fake_quantize_per_tensor_affine_cachemask_backward(tensor *, tensor grad, tensor mask);
void atg_fake_quantize_per_tensor_affine_tensor_qparams(tensor *, tensor self, tensor scale, tensor zero_point, int64_t quant_min, int64_t quant_max);
void atg_fbgemm_linear_fp16_weight(tensor *, tensor input, tensor packed_weight, tensor bias);
void atg_fbgemm_linear_fp16_weight_fp32_activation(tensor *, tensor input, tensor packed_weight, tensor bias);
void atg_fbgemm_linear_int8_weight(tensor *, tensor input, tensor weight, tensor packed, tensor col_offsets, scalar weight_scale, scalar weight_zero_point, tensor bias);
void atg_fbgemm_linear_int8_weight_fp32_activation(tensor *, tensor input, tensor weight, tensor packed, tensor col_offsets, scalar weight_scale, scalar weight_zero_point, tensor bias);
void atg_fbgemm_pack_gemm_matrix_fp16(tensor *, tensor input);
void atg_fbgemm_pack_quantized_matrix(tensor *, tensor input);
void atg_fbgemm_pack_quantized_matrix_kn(tensor *, tensor input, int64_t K, int64_t n);
void atg_feature_alpha_dropout(tensor *, tensor input, double p, int train);
void atg_feature_alpha_dropout_(tensor *, tensor self, double p, int train);
void atg_feature_dropout(tensor *, tensor input, double p, int train);
void atg_feature_dropout_(tensor *, tensor self, double p, int train);
void atg_fft_fft(tensor *, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_fft2(tensor *, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_fft2_out(tensor *, tensor out, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_fft_out(tensor *, tensor out, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_fftfreq(tensor *, int64_t n, double d, int options_kind, int options_device);
void atg_fft_fftfreq_out(tensor *, tensor out, int64_t n, double d);
void atg_fft_fftn(tensor *, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_fftn_out(tensor *, tensor out, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_fftshift(tensor *, tensor self, int64_t *dim_data, int dim_len);
void atg_fft_hfft(tensor *, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_hfft_out(tensor *, tensor out, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_ifft(tensor *, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_ifft2(tensor *, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_ifft2_out(tensor *, tensor out, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_ifft_out(tensor *, tensor out, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_ifftn(tensor *, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_ifftn_out(tensor *, tensor out, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_ifftshift(tensor *, tensor self, int64_t *dim_data, int dim_len);
void atg_fft_ihfft(tensor *, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_ihfft_out(tensor *, tensor out, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_irfft(tensor *, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_irfft2(tensor *, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_irfft2_out(tensor *, tensor out, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_irfft_out(tensor *, tensor out, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_irfftn(tensor *, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_irfftn_out(tensor *, tensor out, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_rfft(tensor *, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_rfft2(tensor *, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_rfft2_out(tensor *, tensor out, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_rfft_out(tensor *, tensor out, tensor self, int64_t n_v, uint8_t n_null, int64_t dim, char* norm_ptr, int norm_len);
void atg_fft_rfftfreq(tensor *, int64_t n, double d, int options_kind, int options_device);
void atg_fft_rfftfreq_out(tensor *, tensor out, int64_t n, double d);
void atg_fft_rfftn(tensor *, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fft_rfftn_out(tensor *, tensor out, tensor self, int64_t *s_data, int s_len, int64_t *dim_data, int dim_len, char* norm_ptr, int norm_len);
void atg_fill_(tensor *, tensor self, scalar value);
void atg_fill_diagonal_(tensor *, tensor self, scalar fill_value, int wrap);
void atg_fill_tensor_(tensor *, tensor self, tensor value);
void atg_fix(tensor *, tensor self);
void atg_fix_(tensor *, tensor self);
void atg_fix_out(tensor *, tensor out, tensor self);
void atg_flatten(tensor *, tensor self, int64_t start_dim, int64_t end_dim);
void atg_flatten_dense_tensors(tensor *, tensor *tensors_data, int tensors_len);
void atg_flip(tensor *, tensor self, int64_t *dims_data, int dims_len);
void atg_fliplr(tensor *, tensor self);
void atg_flipud(tensor *, tensor self);
void atg_float_power(tensor *, tensor self, tensor exponent);
void atg_float_power_(tensor *, tensor self, scalar exponent);
void atg_float_power_scalar(tensor *, scalar self_scalar, tensor exponent);
void atg_float_power_scalar_out(tensor *, tensor out, scalar self_scalar, tensor exponent);
void atg_float_power_tensor_(tensor *, tensor self, tensor exponent);
void atg_float_power_tensor_scalar(tensor *, tensor self, scalar exponent);
void atg_float_power_tensor_scalar_out(tensor *, tensor out, tensor self, scalar exponent);
void atg_float_power_tensor_tensor_out(tensor *, tensor out, tensor self, tensor exponent);
void atg_floor(tensor *, tensor self);
void atg_floor_(tensor *, tensor self);
void atg_floor_divide(tensor *, tensor self, tensor other);
void atg_floor_divide_(tensor *, tensor self, tensor other);
void atg_floor_divide_out(tensor *, tensor out, tensor self, tensor other);
void atg_floor_divide_scalar(tensor *, tensor self, scalar other);
void atg_floor_divide_scalar_(tensor *, tensor self, scalar other);
void atg_floor_out(tensor *, tensor out, tensor self);
void atg_fmax(tensor *, tensor self, tensor other);
void atg_fmax_out(tensor *, tensor out, tensor self, tensor other);
void atg_fmin(tensor *, tensor self, tensor other);
void atg_fmin_out(tensor *, tensor out, tensor self, tensor other);
void atg_fmod(tensor *, tensor self, scalar other);
void atg_fmod_(tensor *, tensor self, scalar other);
void atg_fmod_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_fmod_tensor(tensor *, tensor self, tensor other);
void atg_fmod_tensor_(tensor *, tensor self, tensor other);
void atg_fmod_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_frac(tensor *, tensor self);
void atg_frac_(tensor *, tensor self);
void atg_frac_out(tensor *, tensor out, tensor self);
void atg_fractional_max_pool2d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *output_size_data, int output_size_len, tensor random_samples);
void atg_fractional_max_pool2d_backward(tensor *, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *output_size_data, int output_size_len, tensor indices);
void atg_fractional_max_pool2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *output_size_data, int output_size_len, tensor indices);
void atg_fractional_max_pool2d_output(tensor *, tensor output, tensor indices, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *output_size_data, int output_size_len, tensor random_samples);
void atg_fractional_max_pool3d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *output_size_data, int output_size_len, tensor random_samples);
void atg_fractional_max_pool3d_backward(tensor *, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *output_size_data, int output_size_len, tensor indices);
void atg_fractional_max_pool3d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *output_size_data, int output_size_len, tensor indices);
void atg_fractional_max_pool3d_output(tensor *, tensor output, tensor indices, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *output_size_data, int output_size_len, tensor random_samples);
void atg_frexp(tensor *, tensor self);
void atg_frexp_tensor_out(tensor *, tensor mantissa, tensor exponent, tensor self);
void atg_frobenius_norm(tensor *, tensor self);
void atg_frobenius_norm_dim(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_frobenius_norm_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_from_file(tensor *, char* filename_ptr, int filename_len, int shared, int64_t size_v, uint8_t size_null, int options_kind, int options_device);
void atg_full(tensor *, int64_t *size_data, int size_len, scalar fill_value, int options_kind, int options_device);
void atg_full_like(tensor *, tensor self, scalar fill_value);
void atg_full_out(tensor *, tensor out, int64_t *size_data, int size_len, scalar fill_value);
void atg_fused_moving_avg_obs_fake_quant(tensor *, tensor self, tensor observer_on, tensor fake_quant_on, tensor running_min, tensor running_max, tensor scale, tensor zero_point, double averaging_const, int64_t quant_min, int64_t quant_max, int64_t ch_axis, int per_row_fake_quant, int symmetric_quant);
void atg_gather(tensor *, tensor self, int64_t dim, tensor index, int sparse_grad);
void atg_gather_backward(tensor *, tensor grad, tensor self, int64_t dim, tensor index, int sparse_grad);
void atg_gather_out(tensor *, tensor out, tensor self, int64_t dim, tensor index, int sparse_grad);
void atg_gcd(tensor *, tensor self, tensor other);
void atg_gcd_(tensor *, tensor self, tensor other);
void atg_gcd_out(tensor *, tensor out, tensor self, tensor other);
void atg_ge(tensor *, tensor self, scalar other);
void atg_ge_(tensor *, tensor self, scalar other);
void atg_ge_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_ge_tensor(tensor *, tensor self, tensor other);
void atg_ge_tensor_(tensor *, tensor self, tensor other);
void atg_ge_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_gelu(tensor *, tensor self);
void atg_gelu_backward(tensor *, tensor grad, tensor self);
void atg_gelu_backward_grad_input(tensor *, tensor grad_input, tensor grad, tensor self);
void atg_gelu_out(tensor *, tensor out, tensor self);
void atg_geometric_(tensor *, tensor self, double p);
void atg_geqrf(tensor *, tensor self);
void atg_geqrf_a(tensor *, tensor a, tensor tau, tensor self);
void atg_ger(tensor *, tensor self, tensor vec2);
void atg_ger_out(tensor *, tensor out, tensor self, tensor vec2);
void atg_glu(tensor *, tensor self, int64_t dim);
void atg_glu_backward(tensor *, tensor grad_output, tensor self, int64_t dim);
void atg_glu_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t dim);
void atg_glu_out(tensor *, tensor out, tensor self, int64_t dim);
void atg_grad(tensor *, tensor self);
void atg_greater(tensor *, tensor self, scalar other);
void atg_greater_(tensor *, tensor self, scalar other);
void atg_greater_equal(tensor *, tensor self, scalar other);
void atg_greater_equal_(tensor *, tensor self, scalar other);
void atg_greater_equal_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_greater_equal_tensor(tensor *, tensor self, tensor other);
void atg_greater_equal_tensor_(tensor *, tensor self, tensor other);
void atg_greater_equal_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_greater_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_greater_tensor(tensor *, tensor self, tensor other);
void atg_greater_tensor_(tensor *, tensor self, tensor other);
void atg_greater_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_grid_sampler(tensor *, tensor input, tensor grid, int64_t interpolation_mode, int64_t padding_mode, int align_corners);
void atg_grid_sampler_2d(tensor *, tensor input, tensor grid, int64_t interpolation_mode, int64_t padding_mode, int align_corners);
void atg_grid_sampler_2d_backward(tensor *, tensor grad_output, tensor input, tensor grid, int64_t interpolation_mode, int64_t padding_mode, int align_corners);
void atg_grid_sampler_3d(tensor *, tensor input, tensor grid, int64_t interpolation_mode, int64_t padding_mode, int align_corners);
void atg_grid_sampler_3d_backward(tensor *, tensor grad_output, tensor input, tensor grid, int64_t interpolation_mode, int64_t padding_mode, int align_corners);
void atg_group_norm(tensor *, tensor input, int64_t num_groups, tensor weight, tensor bias, double eps, int cudnn_enabled);
void atg_gru(tensor *, tensor input, tensor hx, tensor *params_data, int params_len, int has_biases, int64_t num_layers, double dropout, int train, int bidirectional, int batch_first);
void atg_gru_cell(tensor *, tensor input, tensor hx, tensor w_ih, tensor w_hh, tensor b_ih, tensor b_hh);
void atg_gru_data(tensor *, tensor data, tensor batch_sizes, tensor hx, tensor *params_data, int params_len, int has_biases, int64_t num_layers, double dropout, int train, int bidirectional);
void atg_gt(tensor *, tensor self, scalar other);
void atg_gt_(tensor *, tensor self, scalar other);
void atg_gt_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_gt_tensor(tensor *, tensor self, tensor other);
void atg_gt_tensor_(tensor *, tensor self, tensor other);
void atg_gt_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_hamming_window(tensor *, int64_t window_length, int options_kind, int options_device);
void atg_hamming_window_periodic(tensor *, int64_t window_length, int periodic, int options_kind, int options_device);
void atg_hamming_window_periodic_alpha(tensor *, int64_t window_length, int periodic, double alpha, int options_kind, int options_device);
void atg_hamming_window_periodic_alpha_beta(tensor *, int64_t window_length, int periodic, double alpha, double beta, int options_kind, int options_device);
void atg_hann_window(tensor *, int64_t window_length, int options_kind, int options_device);
void atg_hann_window_periodic(tensor *, int64_t window_length, int periodic, int options_kind, int options_device);
void atg_hardshrink(tensor *, tensor self);
void atg_hardshrink_backward(tensor *, tensor grad_out, tensor self, scalar lambd);
void atg_hardshrink_backward_grad_input(tensor *, tensor grad_input, tensor grad_out, tensor self, scalar lambd);
void atg_hardshrink_out(tensor *, tensor out, tensor self);
void atg_hardsigmoid(tensor *, tensor self);
void atg_hardsigmoid_(tensor *, tensor self);
void atg_hardsigmoid_backward(tensor *, tensor grad_output, tensor self);
void atg_hardsigmoid_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self);
void atg_hardsigmoid_out(tensor *, tensor out, tensor self);
void atg_hardswish(tensor *, tensor self);
void atg_hardswish_(tensor *, tensor self);
void atg_hardswish_backward(tensor *, tensor grad_output, tensor self);
void atg_hardswish_out(tensor *, tensor out, tensor self);
void atg_hardtanh(tensor *, tensor self);
void atg_hardtanh_(tensor *, tensor self);
void atg_hardtanh_backward(tensor *, tensor grad_output, tensor self, scalar min_val, scalar max_val);
void atg_hardtanh_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, scalar min_val, scalar max_val);
void atg_hardtanh_out(tensor *, tensor out, tensor self);
void atg_heaviside(tensor *, tensor self, tensor values);
void atg_heaviside_(tensor *, tensor self, tensor values);
void atg_heaviside_out(tensor *, tensor out, tensor self, tensor values);
void atg_hinge_embedding_loss(tensor *, tensor self, tensor target, double margin, int64_t reduction);
void atg_histc(tensor *, tensor self, int64_t bins);
void atg_histc_out(tensor *, tensor out, tensor self, int64_t bins);
void atg_histogram(tensor *, tensor self, tensor bins, tensor weight, int density);
void atg_histogram_bin_ct(tensor *, tensor self, int64_t bins, double *range_data, int range_len, tensor weight, int density);
void atg_histogram_bin_ct_out(tensor *, tensor hist, tensor bin_edges, tensor self, int64_t bins, double *range_data, int range_len, tensor weight, int density);
void atg_histogram_bins_tensor_out(tensor *, tensor hist, tensor bin_edges, tensor self, tensor bins, tensor weight, int density);
tensor *atg_hsplit(tensor self, int64_t sections);
tensor *atg_hsplit_array(tensor self, int64_t *indices_data, int indices_len);
void atg_hspmm(tensor *, tensor mat1, tensor mat2);
void atg_hspmm_out(tensor *, tensor out, tensor mat1, tensor mat2);
void atg_hstack(tensor *, tensor *tensors_data, int tensors_len);
void atg_hstack_out(tensor *, tensor out, tensor *tensors_data, int tensors_len);
void atg_huber_loss(tensor *, tensor self, tensor target, int64_t reduction, double delta);
void atg_huber_loss_backward(tensor *, tensor grad_output, tensor self, tensor target, int64_t reduction, double delta);
void atg_huber_loss_backward_out(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, int64_t reduction, double delta);
void atg_huber_loss_out(tensor *, tensor out, tensor self, tensor target, int64_t reduction, double delta);
void atg_hypot(tensor *, tensor self, tensor other);
void atg_hypot_(tensor *, tensor self, tensor other);
void atg_hypot_out(tensor *, tensor out, tensor self, tensor other);
void atg_i0(tensor *, tensor self);
void atg_i0_(tensor *, tensor self);
void atg_i0_out(tensor *, tensor out, tensor self);
void atg_igamma(tensor *, tensor self, tensor other);
void atg_igamma_(tensor *, tensor self, tensor other);
void atg_igamma_out(tensor *, tensor out, tensor self, tensor other);
void atg_igammac(tensor *, tensor self, tensor other);
void atg_igammac_(tensor *, tensor self, tensor other);
void atg_igammac_out(tensor *, tensor out, tensor self, tensor other);
void atg_im2col(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *dilation_data, int dilation_len, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg_im2col_backward(tensor *, tensor grad_output, int64_t *input_size_data, int input_size_len, int64_t *kernel_size_data, int kernel_size_len, int64_t *dilation_data, int dilation_len, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg_im2col_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *input_size_data, int input_size_len, int64_t *kernel_size_data, int kernel_size_len, int64_t *dilation_data, int dilation_len, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg_im2col_out(tensor *, tensor out, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *dilation_data, int dilation_len, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len);
void atg_imag(tensor *, tensor self);
void atg_index(tensor *, tensor self, tensor *indices_data, int indices_len);
void atg_index_add(tensor *, tensor self, int64_t dim, tensor index, tensor source);
void atg_index_add_(tensor *, tensor self, int64_t dim, tensor index, tensor source);
void atg_index_add_alpha(tensor *, tensor self, int64_t dim, tensor index, tensor source, scalar alpha);
void atg_index_add_alpha_(tensor *, tensor self, int64_t dim, tensor index, tensor source, scalar alpha);
void atg_index_copy(tensor *, tensor self, int64_t dim, tensor index, tensor source);
void atg_index_copy_(tensor *, tensor self, int64_t dim, tensor index, tensor source);
void atg_index_fill(tensor *, tensor self, int64_t dim, tensor index, scalar value);
void atg_index_fill_(tensor *, tensor self, int64_t dim, tensor index, scalar value);
void atg_index_fill_int_tensor(tensor *, tensor self, int64_t dim, tensor index, tensor value);
void atg_index_fill_int_tensor_(tensor *, tensor self, int64_t dim, tensor index, tensor value);
void atg_index_put(tensor *, tensor self, tensor *indices_data, int indices_len, tensor values, int accumulate);
void atg_index_put_(tensor *, tensor self, tensor *indices_data, int indices_len, tensor values, int accumulate);
void atg_index_select(tensor *, tensor self, int64_t dim, tensor index);
void atg_index_select_backward(tensor *, tensor grad, int64_t *self_sizes_data, int self_sizes_len, int64_t dim, tensor index);
void atg_index_select_out(tensor *, tensor out, tensor self, int64_t dim, tensor index);
void atg_indices(tensor *, tensor self);
void atg_infinitely_differentiable_gelu_backward(tensor *, tensor grad, tensor self);
void atg_inner(tensor *, tensor self, tensor other);
void atg_inner_out(tensor *, tensor out, tensor self, tensor other);
void atg_instance_norm(tensor *, tensor input, tensor weight, tensor bias, tensor running_mean, tensor running_var, int use_input_stats, double momentum, double eps, int cudnn_enabled);
void atg_int_repr(tensor *, tensor self);
void atg_inverse(tensor *, tensor self);
void atg_inverse_out(tensor *, tensor out, tensor self);
int atg_is_coalesced(tensor self);
int atg_is_complex(tensor self);
int atg_is_conj(tensor self);
int atg_is_distributed(tensor self);
int atg_is_floating_point(tensor self);
int atg_is_inference(tensor self);
int atg_is_leaf(tensor self);
int atg_is_neg(tensor self);
int atg_is_nonzero(tensor self);
int atg_is_pinned(tensor self, int device);
int atg_is_same_size(tensor self, tensor other);
int atg_is_set_to(tensor self, tensor tensor);
int atg_is_signed(tensor self);
int atg_is_vulkan_available();
void atg_isclose(tensor *, tensor self, tensor other, double rtol, double atol, int equal_nan);
void atg_isfinite(tensor *, tensor self);
void atg_isin(tensor *, tensor elements, tensor test_elements, int assume_unique, int invert);
void atg_isin_scalar_tensor(tensor *, scalar element, tensor test_elements, int assume_unique, int invert);
void atg_isin_scalar_tensor_out(tensor *, tensor out, scalar element, tensor test_elements, int assume_unique, int invert);
void atg_isin_tensor_scalar(tensor *, tensor elements, scalar test_element, int assume_unique, int invert);
void atg_isin_tensor_scalar_out(tensor *, tensor out, tensor elements, scalar test_element, int assume_unique, int invert);
void atg_isin_tensor_tensor_out(tensor *, tensor out, tensor elements, tensor test_elements, int assume_unique, int invert);
void atg_isinf(tensor *, tensor self);
void atg_isnan(tensor *, tensor self);
void atg_isneginf(tensor *, tensor self);
void atg_isneginf_out(tensor *, tensor out, tensor self);
void atg_isposinf(tensor *, tensor self);
void atg_isposinf_out(tensor *, tensor out, tensor self);
void atg_isreal(tensor *, tensor self);
void atg_istft(tensor *, tensor self, int64_t n_fft, int64_t hop_length_v, uint8_t hop_length_null, int64_t win_length_v, uint8_t win_length_null, tensor window, int center, int normalized, int onesided, int64_t length_v, uint8_t length_null, int return_complex);
void atg_kaiser_window(tensor *, int64_t window_length, int options_kind, int options_device);
void atg_kaiser_window_beta(tensor *, int64_t window_length, int periodic, double beta, int options_kind, int options_device);
void atg_kaiser_window_periodic(tensor *, int64_t window_length, int periodic, int options_kind, int options_device);
void atg_kl_div(tensor *, tensor self, tensor target, int64_t reduction, int log_target);
void atg_kl_div_backward(tensor *, tensor grad_output, tensor self, tensor target, int64_t reduction, int log_target);
void atg_kron(tensor *, tensor self, tensor other);
void atg_kron_out(tensor *, tensor out, tensor self, tensor other);
void atg_kthvalue(tensor *, tensor self, int64_t k, int64_t dim, int keepdim);
void atg_kthvalue_values(tensor *, tensor values, tensor indices, tensor self, int64_t k, int64_t dim, int keepdim);
void atg_l1_loss(tensor *, tensor self, tensor target, int64_t reduction);
void atg_l1_loss_backward(tensor *, tensor grad_output, tensor self, tensor target, int64_t reduction);
void atg_l1_loss_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, int64_t reduction);
void atg_l1_loss_out(tensor *, tensor out, tensor self, tensor target, int64_t reduction);
void atg_layer_norm(tensor *, tensor input, int64_t *normalized_shape_data, int normalized_shape_len, tensor weight, tensor bias, double eps, int cudnn_enable);
void atg_lcm(tensor *, tensor self, tensor other);
void atg_lcm_(tensor *, tensor self, tensor other);
void atg_lcm_out(tensor *, tensor out, tensor self, tensor other);
void atg_ldexp(tensor *, tensor self, tensor other);
void atg_ldexp_(tensor *, tensor self, tensor other);
void atg_ldexp_out(tensor *, tensor out, tensor self, tensor other);
void atg_le(tensor *, tensor self, scalar other);
void atg_le_(tensor *, tensor self, scalar other);
void atg_le_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_le_tensor(tensor *, tensor self, tensor other);
void atg_le_tensor_(tensor *, tensor self, tensor other);
void atg_le_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_leaky_relu(tensor *, tensor self);
void atg_leaky_relu_(tensor *, tensor self);
void atg_leaky_relu_backward(tensor *, tensor grad_output, tensor self, scalar negative_slope, int self_is_result);
void atg_leaky_relu_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, scalar negative_slope, int self_is_result);
void atg_leaky_relu_out(tensor *, tensor out, tensor self);
void atg_lerp(tensor *, tensor self, tensor end, scalar weight);
void atg_lerp_(tensor *, tensor self, tensor end, scalar weight);
void atg_lerp_scalar_out(tensor *, tensor out, tensor self, tensor end, scalar weight);
void atg_lerp_tensor(tensor *, tensor self, tensor end, tensor weight);
void atg_lerp_tensor_(tensor *, tensor self, tensor end, tensor weight);
void atg_lerp_tensor_out(tensor *, tensor out, tensor self, tensor end, tensor weight);
void atg_less(tensor *, tensor self, scalar other);
void atg_less_(tensor *, tensor self, scalar other);
void atg_less_equal(tensor *, tensor self, scalar other);
void atg_less_equal_(tensor *, tensor self, scalar other);
void atg_less_equal_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_less_equal_tensor(tensor *, tensor self, tensor other);
void atg_less_equal_tensor_(tensor *, tensor self, tensor other);
void atg_less_equal_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_less_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_less_tensor(tensor *, tensor self, tensor other);
void atg_less_tensor_(tensor *, tensor self, tensor other);
void atg_less_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_lgamma(tensor *, tensor self);
void atg_lgamma_(tensor *, tensor self);
void atg_lgamma_out(tensor *, tensor out, tensor self);
void atg_linalg_cholesky(tensor *, tensor self, int upper);
void atg_linalg_cholesky_ex(tensor *, tensor self, int upper, int check_errors);
void atg_linalg_cholesky_ex_l(tensor *, tensor L, tensor info, tensor self, int upper, int check_errors);
void atg_linalg_cholesky_out(tensor *, tensor out, tensor self, int upper);
void atg_linalg_cond(tensor *, tensor self, scalar p);
void atg_linalg_cond_out(tensor *, tensor out, tensor self, scalar p);
void atg_linalg_cond_p_str(tensor *, tensor self, char* p_ptr, int p_len);
void atg_linalg_cond_p_str_out(tensor *, tensor out, tensor self, char* p_ptr, int p_len);
void atg_linalg_det(tensor *, tensor self);
void atg_linalg_det_out(tensor *, tensor out, tensor self);
void atg_linalg_eig(tensor *, tensor self);
void atg_linalg_eig_out(tensor *, tensor eigenvalues, tensor eigenvectors, tensor self);
void atg_linalg_eigh(tensor *, tensor self, char* UPLO_ptr, int UPLO_len);
void atg_linalg_eigh_eigvals(tensor *, tensor eigvals, tensor eigvecs, tensor self, char* UPLO_ptr, int UPLO_len);
void atg_linalg_eigvals(tensor *, tensor self);
void atg_linalg_eigvals_out(tensor *, tensor out, tensor self);
void atg_linalg_eigvalsh(tensor *, tensor self, char* UPLO_ptr, int UPLO_len);
void atg_linalg_eigvalsh_out(tensor *, tensor out, tensor self, char* UPLO_ptr, int UPLO_len);
void atg_linalg_householder_product(tensor *, tensor input, tensor tau);
void atg_linalg_householder_product_out(tensor *, tensor out, tensor input, tensor tau);
void atg_linalg_inv(tensor *, tensor self);
void atg_linalg_inv_ex(tensor *, tensor self, int check_errors);
void atg_linalg_inv_ex_inverse(tensor *, tensor inverse, tensor info, tensor self, int check_errors);
void atg_linalg_inv_out(tensor *, tensor out, tensor self);
void atg_linalg_lstsq(tensor *, tensor self, tensor b, double rcond_v, uint8_t rcond_null, char* driver_ptr, int driver_len);
void atg_linalg_lstsq_out(tensor *, tensor solution, tensor residuals, tensor rank, tensor singular_values, tensor self, tensor b, double rcond_v, uint8_t rcond_null, char* driver_ptr, int driver_len);
void atg_linalg_matmul(tensor *, tensor self, tensor other);
void atg_linalg_matmul_out(tensor *, tensor out, tensor self, tensor other);
void atg_linalg_matrix_power(tensor *, tensor self, int64_t n);
void atg_linalg_matrix_power_out(tensor *, tensor out, tensor self, int64_t n);
void atg_linalg_matrix_rank(tensor *, tensor self, double tol_v, uint8_t tol_null, int hermitian);
void atg_linalg_matrix_rank_out(tensor *, tensor out, tensor self, double tol_v, uint8_t tol_null, int hermitian);
void atg_linalg_matrix_rank_out_tol_tensor(tensor *, tensor out, tensor input, tensor tol, int hermitian);
void atg_linalg_matrix_rank_tol_tensor(tensor *, tensor input, tensor tol, int hermitian);
void atg_linalg_multi_dot(tensor *, tensor *tensors_data, int tensors_len);
void atg_linalg_multi_dot_out(tensor *, tensor out, tensor *tensors_data, int tensors_len);
void atg_linalg_norm(tensor *, tensor self, scalar ord, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_linalg_norm_ord_str(tensor *, tensor self, char* ord_ptr, int ord_len, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_linalg_norm_ord_str_out(tensor *, tensor out, tensor self, char* ord_ptr, int ord_len, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_linalg_norm_out(tensor *, tensor out, tensor self, scalar ord, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_linalg_pinv(tensor *, tensor self, double rcond, int hermitian);
void atg_linalg_pinv_out(tensor *, tensor out, tensor self, double rcond, int hermitian);
void atg_linalg_pinv_out_rcond_tensor(tensor *, tensor out, tensor self, tensor rcond, int hermitian);
void atg_linalg_pinv_rcond_tensor(tensor *, tensor self, tensor rcond, int hermitian);
void atg_linalg_qr(tensor *, tensor self, char* mode_ptr, int mode_len);
void atg_linalg_qr_out(tensor *, tensor Q, tensor R, tensor self, char* mode_ptr, int mode_len);
void atg_linalg_slogdet(tensor *, tensor self);
void atg_linalg_slogdet_out(tensor *, tensor sign, tensor logabsdet, tensor self);
void atg_linalg_solve(tensor *, tensor input, tensor other);
void atg_linalg_solve_out(tensor *, tensor out, tensor input, tensor other);
void atg_linalg_svd(tensor *, tensor self, int full_matrices);
void atg_linalg_svd_u(tensor *, tensor U, tensor S, tensor Vh, tensor self, int full_matrices);
void atg_linalg_svdvals(tensor *, tensor input);
void atg_linalg_svdvals_out(tensor *, tensor out, tensor input);
void atg_linalg_tensorinv(tensor *, tensor self, int64_t ind);
void atg_linalg_tensorinv_out(tensor *, tensor out, tensor self, int64_t ind);
void atg_linalg_tensorsolve(tensor *, tensor self, tensor other, int64_t *dims_data, int dims_len);
void atg_linalg_tensorsolve_out(tensor *, tensor out, tensor self, tensor other, int64_t *dims_data, int dims_len);
void atg_linear(tensor *, tensor input, tensor weight, tensor bias);
void atg_linear_out(tensor *, tensor out, tensor input, tensor weight, tensor bias);
void atg_linspace(tensor *, scalar start, scalar end, int64_t steps_v, uint8_t steps_null, int options_kind, int options_device);
void atg_linspace_out(tensor *, tensor out, scalar start, scalar end, int64_t steps_v, uint8_t steps_null);
void atg_log(tensor *, tensor self);
void atg_log10(tensor *, tensor self);
void atg_log10_(tensor *, tensor self);
void atg_log10_out(tensor *, tensor out, tensor self);
void atg_log1p(tensor *, tensor self);
void atg_log1p_(tensor *, tensor self);
void atg_log1p_out(tensor *, tensor out, tensor self);
void atg_log2(tensor *, tensor self);
void atg_log2_(tensor *, tensor self);
void atg_log2_out(tensor *, tensor out, tensor self);
void atg_log_(tensor *, tensor self);
void atg_log_normal_(tensor *, tensor self, double mean, double std);
void atg_log_out(tensor *, tensor out, tensor self);
void atg_log_sigmoid(tensor *, tensor self);
void atg_log_sigmoid_backward(tensor *, tensor grad_output, tensor self, tensor buffer);
void atg_log_sigmoid_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor buffer);
void atg_log_sigmoid_out(tensor *, tensor out, tensor self);
void atg_log_softmax(tensor *, tensor self, int64_t dim, int dtype);
void atg_logaddexp(tensor *, tensor self, tensor other);
void atg_logaddexp2(tensor *, tensor self, tensor other);
void atg_logaddexp2_out(tensor *, tensor out, tensor self, tensor other);
void atg_logaddexp_out(tensor *, tensor out, tensor self, tensor other);
void atg_logcumsumexp(tensor *, tensor self, int64_t dim);
void atg_logcumsumexp_out(tensor *, tensor out, tensor self, int64_t dim);
void atg_logdet(tensor *, tensor self);
void atg_logical_and(tensor *, tensor self, tensor other);
void atg_logical_and_(tensor *, tensor self, tensor other);
void atg_logical_and_out(tensor *, tensor out, tensor self, tensor other);
void atg_logical_not(tensor *, tensor self);
void atg_logical_not_(tensor *, tensor self);
void atg_logical_not_out(tensor *, tensor out, tensor self);
void atg_logical_or(tensor *, tensor self, tensor other);
void atg_logical_or_(tensor *, tensor self, tensor other);
void atg_logical_or_out(tensor *, tensor out, tensor self, tensor other);
void atg_logical_xor(tensor *, tensor self, tensor other);
void atg_logical_xor_(tensor *, tensor self, tensor other);
void atg_logical_xor_out(tensor *, tensor out, tensor self, tensor other);
void atg_logit(tensor *, tensor self, double eps_v, uint8_t eps_null);
void atg_logit_(tensor *, tensor self, double eps_v, uint8_t eps_null);
void atg_logit_backward(tensor *, tensor grad_output, tensor self, double eps_v, uint8_t eps_null);
void atg_logit_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, double eps_v, uint8_t eps_null);
void atg_logit_out(tensor *, tensor out, tensor self, double eps_v, uint8_t eps_null);
void atg_logspace(tensor *, scalar start, scalar end, int64_t steps_v, uint8_t steps_null, double base, int options_kind, int options_device);
void atg_logspace_out(tensor *, tensor out, scalar start, scalar end, int64_t steps_v, uint8_t steps_null, double base);
void atg_logsumexp(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_logsumexp_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_lstm(tensor *, tensor input, tensor *hx_data, int hx_len, tensor *params_data, int params_len, int has_biases, int64_t num_layers, double dropout, int train, int bidirectional, int batch_first);
void atg_lstm_cell(tensor *, tensor input, tensor *hx_data, int hx_len, tensor w_ih, tensor w_hh, tensor b_ih, tensor b_hh);
void atg_lstm_data(tensor *, tensor data, tensor batch_sizes, tensor *hx_data, int hx_len, tensor *params_data, int params_len, int has_biases, int64_t num_layers, double dropout, int train, int bidirectional);
void atg_lstsq(tensor *, tensor self, tensor A);
void atg_lstsq_x(tensor *, tensor X, tensor qr, tensor self, tensor A);
void atg_lt(tensor *, tensor self, scalar other);
void atg_lt_(tensor *, tensor self, scalar other);
void atg_lt_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_lt_tensor(tensor *, tensor self, tensor other);
void atg_lt_tensor_(tensor *, tensor self, tensor other);
void atg_lt_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_lu_solve(tensor *, tensor self, tensor LU_data, tensor LU_pivots);
void atg_lu_solve_out(tensor *, tensor out, tensor self, tensor LU_data, tensor LU_pivots);
void atg_lu_unpack(tensor *, tensor LU_data, tensor LU_pivots, int unpack_data, int unpack_pivots);
void atg_lu_unpack_out(tensor *, tensor P, tensor L, tensor U, tensor LU_data, tensor LU_pivots, int unpack_data, int unpack_pivots);
void atg_margin_ranking_loss(tensor *, tensor input1, tensor input2, tensor target, double margin, int64_t reduction);
void atg_masked_fill(tensor *, tensor self, tensor mask, scalar value);
void atg_masked_fill_(tensor *, tensor self, tensor mask, scalar value);
void atg_masked_fill_tensor(tensor *, tensor self, tensor mask, tensor value);
void atg_masked_fill_tensor_(tensor *, tensor self, tensor mask, tensor value);
void atg_masked_scatter(tensor *, tensor self, tensor mask, tensor source);
void atg_masked_scatter_(tensor *, tensor self, tensor mask, tensor source);
void atg_masked_select(tensor *, tensor self, tensor mask);
void atg_masked_select_backward(tensor *, tensor grad, tensor input, tensor mask);
void atg_masked_select_out(tensor *, tensor out, tensor self, tensor mask);
void atg_matmul(tensor *, tensor self, tensor other);
void atg_matmul_out(tensor *, tensor out, tensor self, tensor other);
void atg_matrix_exp(tensor *, tensor self);
void atg_matrix_exp_backward(tensor *, tensor self, tensor grad);
void atg_matrix_power(tensor *, tensor self, int64_t n);
void atg_matrix_power_out(tensor *, tensor out, tensor self, int64_t n);
void atg_matrix_rank(tensor *, tensor self, int symmetric);
void atg_matrix_rank_tol(tensor *, tensor self, double tol, int symmetric);
void atg_max(tensor *, tensor self);
void atg_max_dim(tensor *, tensor self, int64_t dim, int keepdim);
void atg_max_dim_max(tensor *, tensor max, tensor max_values, tensor self, int64_t dim, int keepdim);
void atg_max_other(tensor *, tensor self, tensor other);
void atg_max_out(tensor *, tensor out, tensor self, tensor other);
void atg_max_pool1d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_max_pool1d_with_indices(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_max_pool2d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_max_pool2d_with_indices(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_max_pool2d_with_indices_backward(tensor *, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode, tensor indices);
void atg_max_pool2d_with_indices_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode, tensor indices);
void atg_max_pool2d_with_indices_out(tensor *, tensor out, tensor indices, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_max_pool3d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_max_pool3d_with_indices(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_max_pool3d_with_indices_backward(tensor *, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode, tensor indices);
void atg_max_pool3d_with_indices_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode, tensor indices);
void atg_max_pool3d_with_indices_out(tensor *, tensor out, tensor indices, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_max_unpool2d(tensor *, tensor self, tensor indices, int64_t *output_size_data, int output_size_len);
void atg_max_unpool2d_backward(tensor *, tensor grad_output, tensor self, tensor indices, int64_t *output_size_data, int output_size_len);
void atg_max_unpool2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor indices, int64_t *output_size_data, int output_size_len);
void atg_max_unpool2d_out(tensor *, tensor out, tensor self, tensor indices, int64_t *output_size_data, int output_size_len);
void atg_max_unpool3d(tensor *, tensor self, tensor indices, int64_t *output_size_data, int output_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len);
void atg_max_unpool3d_backward(tensor *, tensor grad_output, tensor self, tensor indices, int64_t *output_size_data, int output_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len);
void atg_max_unpool3d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor indices, int64_t *output_size_data, int output_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len);
void atg_max_unpool3d_out(tensor *, tensor out, tensor self, tensor indices, int64_t *output_size_data, int output_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len);
void atg_maximum(tensor *, tensor self, tensor other);
void atg_maximum_out(tensor *, tensor out, tensor self, tensor other);
void atg_mean(tensor *, tensor self, int dtype);
void atg_mean_dim(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_mean_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_median(tensor *, tensor self);
void atg_median_dim(tensor *, tensor self, int64_t dim, int keepdim);
void atg_median_dim_values(tensor *, tensor values, tensor indices, tensor self, int64_t dim, int keepdim);
tensor *atg_meshgrid(tensor *tensors_data, int tensors_len);
tensor *atg_meshgrid_indexing(tensor *tensors_data, int tensors_len, char* indexing_ptr, int indexing_len);
void atg_min(tensor *, tensor self);
void atg_min_dim(tensor *, tensor self, int64_t dim, int keepdim);
void atg_min_dim_min(tensor *, tensor min, tensor min_indices, tensor self, int64_t dim, int keepdim);
void atg_min_other(tensor *, tensor self, tensor other);
void atg_min_out(tensor *, tensor out, tensor self, tensor other);
void atg_minimum(tensor *, tensor self, tensor other);
void atg_minimum_out(tensor *, tensor out, tensor self, tensor other);
void atg_miopen_batch_norm(tensor *, tensor input, tensor weight, tensor bias, tensor running_mean, tensor running_var, int training, double exponential_average_factor, double epsilon);
void atg_miopen_batch_norm_backward(tensor *, tensor input, tensor grad_output, tensor weight, tensor running_mean, tensor running_var, tensor save_mean, tensor save_var, double epsilon);
void atg_miopen_convolution(tensor *, tensor self, tensor weight, tensor bias, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_convolution_backward_bias(tensor *, tensor grad_output);
void atg_miopen_convolution_backward_input(tensor *, int64_t *self_size_data, int self_size_len, tensor grad_output, tensor weight, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_convolution_backward_weight(tensor *, int64_t *weight_size_data, int weight_size_len, tensor grad_output, tensor self, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_convolution_transpose(tensor *, tensor self, tensor weight, tensor bias, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_convolution_transpose_backward_input(tensor *, tensor grad_output, tensor weight, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_convolution_transpose_backward_weight(tensor *, int64_t *weight_size_data, int weight_size_len, tensor grad_output, tensor self, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_depthwise_convolution(tensor *, tensor self, tensor weight, tensor bias, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_depthwise_convolution_backward_input(tensor *, int64_t *self_size_data, int self_size_len, tensor grad_output, tensor weight, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_depthwise_convolution_backward_weight(tensor *, int64_t *weight_size_data, int weight_size_len, tensor grad_output, tensor self, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int benchmark, int deterministic);
void atg_miopen_rnn(tensor *, tensor input, tensor *weight_data, int weight_len, int64_t weight_stride0, tensor hx, tensor cx, int64_t mode, int64_t hidden_size, int64_t num_layers, int batch_first, double dropout, int train, int bidirectional, int64_t *batch_sizes_data, int batch_sizes_len, tensor dropout_state);
void atg_mish(tensor *, tensor self);
void atg_mish_(tensor *, tensor self);
void atg_mish_backward(tensor *, tensor grad_output, tensor self);
void atg_mish_out(tensor *, tensor out, tensor self);
void atg_mkldnn_adaptive_avg_pool2d(tensor *, tensor self, int64_t *output_size_data, int output_size_len);
void atg_mkldnn_adaptive_avg_pool2d_backward(tensor *, tensor grad_output, tensor self);
void atg_mkldnn_convolution(tensor *, tensor self, tensor weight, tensor bias, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_mkldnn_convolution_backward_input(tensor *, int64_t *self_size_data, int self_size_len, tensor grad_output, tensor weight, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int bias_defined);
void atg_mkldnn_convolution_backward_weights(tensor *, int64_t *weight_size_data, int weight_size_len, tensor grad_output, tensor self, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups, int bias_defined);
void atg_mkldnn_linear(tensor *, tensor self, tensor weight, tensor bias);
void atg_mkldnn_linear_backward_input(tensor *, int64_t *input_size_data, int input_size_len, tensor grad_output, tensor weight);
void atg_mkldnn_linear_backward_weights(tensor *, tensor grad_output, tensor input, tensor weight, int bias_defined);
void atg_mkldnn_max_pool2d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_mkldnn_max_pool2d_backward(tensor *, tensor grad_output, tensor output, tensor input, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_mkldnn_max_pool3d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_mkldnn_max_pool3d_backward(tensor *, tensor grad_output, tensor output, tensor input, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_mkldnn_reorder_conv2d_weight(tensor *, tensor self, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_mkldnn_reorder_conv3d_weight(tensor *, tensor self, int64_t *padding_data, int padding_len, int64_t *stride_data, int stride_len, int64_t *dilation_data, int dilation_len, int64_t groups);
void atg_mm(tensor *, tensor self, tensor mat2);
void atg_mm_out(tensor *, tensor out, tensor self, tensor mat2);
void atg_mode(tensor *, tensor self, int64_t dim, int keepdim);
void atg_mode_values(tensor *, tensor values, tensor indices, tensor self, int64_t dim, int keepdim);
void atg_moveaxis(tensor *, tensor self, int64_t *source_data, int source_len, int64_t *destination_data, int destination_len);
void atg_moveaxis_int(tensor *, tensor self, int64_t source, int64_t destination);
void atg_movedim(tensor *, tensor self, int64_t *source_data, int source_len, int64_t *destination_data, int destination_len);
void atg_movedim_int(tensor *, tensor self, int64_t source, int64_t destination);
void atg_mse_loss(tensor *, tensor self, tensor target, int64_t reduction);
void atg_mse_loss_backward(tensor *, tensor grad_output, tensor self, tensor target, int64_t reduction);
void atg_mse_loss_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, int64_t reduction);
void atg_mse_loss_out(tensor *, tensor out, tensor self, tensor target, int64_t reduction);
void atg_msort(tensor *, tensor self);
void atg_msort_out(tensor *, tensor out, tensor self);
void atg_mul(tensor *, tensor self, tensor other);
void atg_mul_(tensor *, tensor self, tensor other);
void atg_mul_out(tensor *, tensor out, tensor self, tensor other);
void atg_mul_scalar(tensor *, tensor self, scalar other);
void atg_mul_scalar_(tensor *, tensor self, scalar other);
void atg_multi_margin_loss_backward(tensor *, tensor grad_output, tensor self, tensor target, scalar p, scalar margin, tensor weight, int64_t reduction);
void atg_multi_margin_loss_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, scalar p, scalar margin, tensor weight, int64_t reduction);
void atg_multilabel_margin_loss(tensor *, tensor self, tensor target, int64_t reduction);
void atg_multilabel_margin_loss_backward(tensor *, tensor grad_output, tensor self, tensor target, int64_t reduction, tensor is_target);
void atg_multilabel_margin_loss_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, int64_t reduction, tensor is_target);
void atg_multilabel_margin_loss_out(tensor *, tensor out, tensor self, tensor target, int64_t reduction);
void atg_multinomial(tensor *, tensor self, int64_t num_samples, int replacement);
void atg_multinomial_out(tensor *, tensor out, tensor self, int64_t num_samples, int replacement);
void atg_multiply(tensor *, tensor self, tensor other);
void atg_multiply_(tensor *, tensor self, tensor other);
void atg_multiply_out(tensor *, tensor out, tensor self, tensor other);
void atg_multiply_scalar(tensor *, tensor self, scalar other);
void atg_multiply_scalar_(tensor *, tensor self, scalar other);
void atg_mv(tensor *, tensor self, tensor vec);
void atg_mv_out(tensor *, tensor out, tensor self, tensor vec);
void atg_mvlgamma(tensor *, tensor self, int64_t p);
void atg_mvlgamma_(tensor *, tensor self, int64_t p);
void atg_mvlgamma_out(tensor *, tensor out, tensor self, int64_t p);
void atg_nan_to_num(tensor *, tensor self, double nan_v, uint8_t nan_null, double posinf_v, uint8_t posinf_null, double neginf_v, uint8_t neginf_null);
void atg_nan_to_num_(tensor *, tensor self, double nan_v, uint8_t nan_null, double posinf_v, uint8_t posinf_null, double neginf_v, uint8_t neginf_null);
void atg_nan_to_num_out(tensor *, tensor out, tensor self, double nan_v, uint8_t nan_null, double posinf_v, uint8_t posinf_null, double neginf_v, uint8_t neginf_null);
void atg_nanmean(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_nanmean_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_nanmedian(tensor *, tensor self);
void atg_nanmedian_dim(tensor *, tensor self, int64_t dim, int keepdim);
void atg_nanmedian_dim_values(tensor *, tensor values, tensor indices, tensor self, int64_t dim, int keepdim);
void atg_nanquantile(tensor *, tensor self, tensor q, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_nanquantile_new(tensor *, tensor self, tensor q, int64_t dim_v, uint8_t dim_null, int keepdim, char* interpolation_ptr, int interpolation_len);
void atg_nanquantile_new_out(tensor *, tensor out, tensor self, tensor q, int64_t dim_v, uint8_t dim_null, int keepdim, char* interpolation_ptr, int interpolation_len);
void atg_nanquantile_new_scalar(tensor *, tensor self, double q, int64_t dim_v, uint8_t dim_null, int keepdim, char* interpolation_ptr, int interpolation_len);
void atg_nanquantile_new_scalar_out(tensor *, tensor out, tensor self, double q, int64_t dim_v, uint8_t dim_null, int keepdim, char* interpolation_ptr, int interpolation_len);
void atg_nanquantile_out(tensor *, tensor out, tensor self, tensor q, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_nanquantile_scalar(tensor *, tensor self, double q, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_nanquantile_scalar_out(tensor *, tensor out, tensor self, double q, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_nansum(tensor *, tensor self, int dtype);
void atg_nansum_dim_intlist(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_nansum_intlist_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_narrow(tensor *, tensor self, int64_t dim, int64_t start, int64_t length);
void atg_narrow_copy(tensor *, tensor self, int64_t dim, int64_t start, int64_t length);
void atg_narrow_copy_out(tensor *, tensor out, tensor self, int64_t dim, int64_t start, int64_t length);
void atg_narrow_tensor(tensor *, tensor self, int64_t dim, tensor start, int64_t length);
void atg_native_batch_norm(tensor *, tensor input, tensor weight, tensor bias, tensor running_mean, tensor running_var, int training, double momentum, double eps);
void atg_native_batch_norm_out(tensor *, tensor out, tensor save_mean, tensor save_invstd, tensor input, tensor weight, tensor bias, tensor running_mean, tensor running_var, int training, double momentum, double eps);
void atg_native_group_norm(tensor *, tensor input, tensor weight, tensor bias, int64_t n, int64_t C, int64_t HxW, int64_t group, double eps);
void atg_native_layer_norm(tensor *, tensor input, int64_t *normalized_shape_data, int normalized_shape_len, tensor weight, tensor bias, double eps);
void atg_native_norm(tensor *, tensor self);
void atg_native_norm_scalaropt_dim_dtype(tensor *, tensor self, scalar p, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_ne(tensor *, tensor self, scalar other);
void atg_ne_(tensor *, tensor self, scalar other);
void atg_ne_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_ne_tensor(tensor *, tensor self, tensor other);
void atg_ne_tensor_(tensor *, tensor self, tensor other);
void atg_ne_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_neg(tensor *, tensor self);
void atg_neg_(tensor *, tensor self);
void atg_neg_out(tensor *, tensor out, tensor self);
void atg_negative(tensor *, tensor self);
void atg_negative_(tensor *, tensor self);
void atg_negative_out(tensor *, tensor out, tensor self);
void atg_new_empty(tensor *, tensor self, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_new_empty_strided(tensor *, tensor self, int64_t *size_data, int size_len, int64_t *stride_data, int stride_len, int options_kind, int options_device);
void atg_new_full(tensor *, tensor self, int64_t *size_data, int size_len, scalar fill_value, int options_kind, int options_device);
void atg_new_ones(tensor *, tensor self, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_new_zeros(tensor *, tensor self, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_nextafter(tensor *, tensor self, tensor other);
void atg_nextafter_(tensor *, tensor self, tensor other);
void atg_nextafter_out(tensor *, tensor out, tensor self, tensor other);
void atg_nll_loss(tensor *, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index);
void atg_nll_loss2d(tensor *, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index);
void atg_nll_loss2d_backward(tensor *, tensor grad_output, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index, tensor total_weight);
void atg_nll_loss2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index, tensor total_weight);
void atg_nll_loss2d_out(tensor *, tensor out, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index);
void atg_nll_loss_backward(tensor *, tensor grad_output, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index, tensor total_weight);
void atg_nll_loss_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index, tensor total_weight);
void atg_nll_loss_nd(tensor *, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index);
void atg_nll_loss_out(tensor *, tensor out, tensor self, tensor target, tensor weight, int64_t reduction, int64_t ignore_index);
void atg_nonzero(tensor *, tensor self);
tensor *atg_nonzero_numpy(tensor self);
void atg_nonzero_out(tensor *, tensor out, tensor self);
void atg_norm(tensor *, tensor self);
void atg_norm_dtype_out(tensor *, tensor out, tensor self, scalar p, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_norm_except_dim(tensor *, tensor v, int64_t pow, int64_t dim);
void atg_norm_out(tensor *, tensor out, tensor self, scalar p, int64_t *dim_data, int dim_len, int keepdim);
void atg_norm_scalaropt_dim(tensor *, tensor self, scalar p, int64_t *dim_data, int dim_len, int keepdim);
void atg_norm_scalaropt_dim_dtype(tensor *, tensor self, scalar p, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_norm_scalaropt_dtype(tensor *, tensor self, scalar p, int dtype);
void atg_normal(tensor *, tensor out, tensor mean, double std);
void atg_normal_(tensor *, tensor self, double mean, double std);
void atg_normal_float_float_out(tensor *, tensor out, double mean, double std, int64_t *size_data, int size_len);
void atg_normal_float_tensor_out(tensor *, tensor out, double mean, tensor std);
void atg_normal_tensor_tensor_out(tensor *, tensor out, tensor mean, tensor std);
void atg_not_equal(tensor *, tensor self, scalar other);
void atg_not_equal_(tensor *, tensor self, scalar other);
void atg_not_equal_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_not_equal_tensor(tensor *, tensor self, tensor other);
void atg_not_equal_tensor_(tensor *, tensor self, tensor other);
void atg_not_equal_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_nuclear_norm(tensor *, tensor self, int keepdim);
void atg_nuclear_norm_dim(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_nuclear_norm_dim_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_nuclear_norm_out(tensor *, tensor out, tensor self, int keepdim);
void atg_numpy_t(tensor *, tensor self);
void atg_one_hot(tensor *, tensor self, int64_t num_classes);
void atg_ones(tensor *, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_ones_like(tensor *, tensor self);
void atg_ones_out(tensor *, tensor out, int64_t *size_data, int size_len);
void atg_orgqr(tensor *, tensor self, tensor input2);
void atg_orgqr_out(tensor *, tensor out, tensor self, tensor input2);
void atg_ormqr(tensor *, tensor self, tensor input2, tensor input3, int left, int transpose);
void atg_ormqr_out(tensor *, tensor out, tensor self, tensor input2, tensor input3, int left, int transpose);
void atg_outer(tensor *, tensor self, tensor vec2);
void atg_outer_out(tensor *, tensor out, tensor self, tensor vec2);
int64_t atg_output_nr(tensor self);
void atg_pad_sequence(tensor *, tensor *sequences_data, int sequences_len, int batch_first, double padding_value);
void atg_pairwise_distance(tensor *, tensor x1, tensor x2, double p, double eps, int keepdim);
void atg_pdist(tensor *, tensor self, double p);
void atg_permute(tensor *, tensor self, int64_t *dims_data, int dims_len);
void atg_pin_memory(tensor *, tensor self, int device);
void atg_pinverse(tensor *, tensor self, double rcond);
void atg_pixel_shuffle(tensor *, tensor self, int64_t upscale_factor);
void atg_pixel_unshuffle(tensor *, tensor self, int64_t downscale_factor);
void atg_poisson(tensor *, tensor self);
void atg_poisson_nll_loss(tensor *, tensor input, tensor target, int log_input, int full, double eps, int64_t reduction);
void atg_polar(tensor *, tensor abs, tensor angle);
void atg_polar_out(tensor *, tensor out, tensor abs, tensor angle);
void atg_polygamma(tensor *, int64_t n, tensor self);
void atg_polygamma_(tensor *, tensor self, int64_t n);
void atg_polygamma_out(tensor *, tensor out, int64_t n, tensor self);
void atg_positive(tensor *, tensor self);
void atg_pow(tensor *, tensor self, tensor exponent);
void atg_pow_(tensor *, tensor self, scalar exponent);
void atg_pow_scalar(tensor *, scalar self_scalar, tensor exponent);
void atg_pow_scalar_out(tensor *, tensor out, scalar self_scalar, tensor exponent);
void atg_pow_tensor_(tensor *, tensor self, tensor exponent);
void atg_pow_tensor_scalar(tensor *, tensor self, scalar exponent);
void atg_pow_tensor_scalar_out(tensor *, tensor out, tensor self, scalar exponent);
void atg_pow_tensor_tensor_out(tensor *, tensor out, tensor self, tensor exponent);
void atg_prelu(tensor *, tensor self, tensor weight);
void atg_prelu_backward(tensor *, tensor grad_output, tensor self, tensor weight);
void atg_prod(tensor *, tensor self, int dtype);
void atg_prod_dim_int(tensor *, tensor self, int64_t dim, int keepdim, int dtype);
void atg_prod_int_out(tensor *, tensor out, tensor self, int64_t dim, int keepdim, int dtype);
void atg_put(tensor *, tensor self, tensor index, tensor source, int accumulate);
void atg_put_(tensor *, tensor self, tensor index, tensor source, int accumulate);
int64_t atg_q_per_channel_axis(tensor self);
void atg_q_per_channel_scales(tensor *, tensor self);
void atg_q_per_channel_zero_points(tensor *, tensor self);
double atg_q_scale(tensor self);
int64_t atg_q_zero_point(tensor self);
void atg_qr(tensor *, tensor self, int some);
void atg_qr_q(tensor *, tensor Q, tensor R, tensor self, int some);
void atg_quantile(tensor *, tensor self, tensor q, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_quantile_new(tensor *, tensor self, tensor q, int64_t dim_v, uint8_t dim_null, int keepdim, char* interpolation_ptr, int interpolation_len);
void atg_quantile_new_out(tensor *, tensor out, tensor self, tensor q, int64_t dim_v, uint8_t dim_null, int keepdim, char* interpolation_ptr, int interpolation_len);
void atg_quantile_new_scalar(tensor *, tensor self, double q, int64_t dim_v, uint8_t dim_null, int keepdim, char* interpolation_ptr, int interpolation_len);
void atg_quantile_new_scalar_out(tensor *, tensor out, tensor self, double q, int64_t dim_v, uint8_t dim_null, int keepdim, char* interpolation_ptr, int interpolation_len);
void atg_quantile_out(tensor *, tensor out, tensor self, tensor q, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_quantile_scalar(tensor *, tensor self, double q, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_quantile_scalar_out(tensor *, tensor out, tensor self, double q, int64_t dim_v, uint8_t dim_null, int keepdim);
void atg_quantize_per_channel(tensor *, tensor self, tensor scales, tensor zero_points, int64_t axis, int dtype);
void atg_quantize_per_tensor(tensor *, tensor self, double scale, int64_t zero_point, int dtype);
void atg_quantize_per_tensor_tensor_qparams(tensor *, tensor self, tensor scale, tensor zero_point, int dtype);
tensor *atg_quantize_per_tensor_tensors(tensor *tensors_data, int tensors_len, tensor scales, tensor zero_points, int dtype);
void atg_quantized_batch_norm(tensor *, tensor input, tensor weight, tensor bias, tensor mean, tensor var, double eps, double output_scale, int64_t output_zero_point);
void atg_quantized_gru_cell(tensor *, tensor input, tensor hx, tensor w_ih, tensor w_hh, tensor b_ih, tensor b_hh, tensor packed_ih, tensor packed_hh, tensor col_offsets_ih, tensor col_offsets_hh, scalar scale_ih, scalar scale_hh, scalar zero_point_ih, scalar zero_point_hh);
void atg_quantized_lstm_cell(tensor *, tensor input, tensor *hx_data, int hx_len, tensor w_ih, tensor w_hh, tensor b_ih, tensor b_hh, tensor packed_ih, tensor packed_hh, tensor col_offsets_ih, tensor col_offsets_hh, scalar scale_ih, scalar scale_hh, scalar zero_point_ih, scalar zero_point_hh);
void atg_quantized_max_pool1d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_quantized_max_pool2d(tensor *, tensor self, int64_t *kernel_size_data, int kernel_size_len, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len, int ceil_mode);
void atg_quantized_rnn_relu_cell(tensor *, tensor input, tensor hx, tensor w_ih, tensor w_hh, tensor b_ih, tensor b_hh, tensor packed_ih, tensor packed_hh, tensor col_offsets_ih, tensor col_offsets_hh, scalar scale_ih, scalar scale_hh, scalar zero_point_ih, scalar zero_point_hh);
void atg_quantized_rnn_tanh_cell(tensor *, tensor input, tensor hx, tensor w_ih, tensor w_hh, tensor b_ih, tensor b_hh, tensor packed_ih, tensor packed_hh, tensor col_offsets_ih, tensor col_offsets_hh, scalar scale_ih, scalar scale_hh, scalar zero_point_ih, scalar zero_point_hh);
void atg_rad2deg(tensor *, tensor self);
void atg_rad2deg_(tensor *, tensor self);
void atg_rad2deg_out(tensor *, tensor out, tensor self);
void atg_rand(tensor *, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_rand_like(tensor *, tensor self);
void atg_rand_out(tensor *, tensor out, int64_t *size_data, int size_len);
void atg_randint(tensor *, int64_t high, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_randint_like(tensor *, tensor self, int64_t high);
void atg_randint_like_low_dtype(tensor *, tensor self, int64_t low, int64_t high);
void atg_randint_low(tensor *, int64_t low, int64_t high, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_randint_low_out(tensor *, tensor out, int64_t low, int64_t high, int64_t *size_data, int size_len);
void atg_randint_out(tensor *, tensor out, int64_t high, int64_t *size_data, int size_len);
void atg_randn(tensor *, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_randn_like(tensor *, tensor self);
void atg_randn_out(tensor *, tensor out, int64_t *size_data, int size_len);
void atg_random_(tensor *, tensor self);
void atg_random_from_(tensor *, tensor self, int64_t from, int64_t to_v, uint8_t to_null);
void atg_random_to_(tensor *, tensor self, int64_t to);
void atg_randperm(tensor *, int64_t n, int options_kind, int options_device);
void atg_randperm_out(tensor *, tensor out, int64_t n);
void atg_range(tensor *, scalar start, scalar end, int options_kind, int options_device);
void atg_range_out(tensor *, tensor out, scalar start, scalar end);
void atg_range_step(tensor *, scalar start, scalar end, int options_kind, int options_device);
void atg_ravel(tensor *, tensor self);
void atg_real(tensor *, tensor self);
void atg_reciprocal(tensor *, tensor self);
void atg_reciprocal_(tensor *, tensor self);
void atg_reciprocal_out(tensor *, tensor out, tensor self);
void atg_reflection_pad1d(tensor *, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad1d_backward(tensor *, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad1d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad1d_out(tensor *, tensor out, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad2d(tensor *, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad2d_backward(tensor *, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad2d_out(tensor *, tensor out, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad3d(tensor *, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad3d_backward(tensor *, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad3d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_reflection_pad3d_out(tensor *, tensor out, tensor self, int64_t *padding_data, int padding_len);
void atg_relu(tensor *, tensor self);
void atg_relu6(tensor *, tensor self);
void atg_relu6_(tensor *, tensor self);
void atg_relu_(tensor *, tensor self);
void atg_remainder(tensor *, tensor self, scalar other);
void atg_remainder_(tensor *, tensor self, scalar other);
void atg_remainder_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_remainder_scalar_tensor(tensor *, scalar self_scalar, tensor other);
void atg_remainder_tensor(tensor *, tensor self, tensor other);
void atg_remainder_tensor_(tensor *, tensor self, tensor other);
void atg_remainder_tensor_out(tensor *, tensor out, tensor self, tensor other);
void atg_renorm(tensor *, tensor self, scalar p, int64_t dim, scalar maxnorm);
void atg_renorm_(tensor *, tensor self, scalar p, int64_t dim, scalar maxnorm);
void atg_renorm_out(tensor *, tensor out, tensor self, scalar p, int64_t dim, scalar maxnorm);
void atg_repeat(tensor *, tensor self, int64_t *repeats_data, int repeats_len);
void atg_repeat_interleave(tensor *, tensor repeats, int64_t output_size_v, uint8_t output_size_null);
void atg_repeat_interleave_self_int(tensor *, tensor self, int64_t repeats, int64_t dim_v, uint8_t dim_null, int64_t output_size_v, uint8_t output_size_null);
void atg_repeat_interleave_self_tensor(tensor *, tensor self, tensor repeats, int64_t dim_v, uint8_t dim_null, int64_t output_size_v, uint8_t output_size_null);
void atg_replication_pad1d(tensor *, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad1d_backward(tensor *, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad1d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad1d_out(tensor *, tensor out, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad2d(tensor *, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad2d_backward(tensor *, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad2d_out(tensor *, tensor out, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad3d(tensor *, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad3d_backward(tensor *, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad3d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, int64_t *padding_data, int padding_len);
void atg_replication_pad3d_out(tensor *, tensor out, tensor self, int64_t *padding_data, int padding_len);
void atg_requires_grad_(tensor *, tensor self, int requires_grad);
void atg_reshape(tensor *, tensor self, int64_t *shape_data, int shape_len);
void atg_reshape_as(tensor *, tensor self, tensor other);
void atg_resize_(tensor *, tensor self, int64_t *size_data, int size_len);
void atg_resize_as_(tensor *, tensor self, tensor the_template);
void atg_resize_as_sparse_(tensor *, tensor self, tensor the_template);
void atg_resolve_conj(tensor *, tensor self);
void atg_resolve_neg(tensor *, tensor self);
int atg_retains_grad(tensor self);
void atg_rnn_relu(tensor *, tensor input, tensor hx, tensor *params_data, int params_len, int has_biases, int64_t num_layers, double dropout, int train, int bidirectional, int batch_first);
void atg_rnn_relu_cell(tensor *, tensor input, tensor hx, tensor w_ih, tensor w_hh, tensor b_ih, tensor b_hh);
void atg_rnn_relu_data(tensor *, tensor data, tensor batch_sizes, tensor hx, tensor *params_data, int params_len, int has_biases, int64_t num_layers, double dropout, int train, int bidirectional);
void atg_rnn_tanh(tensor *, tensor input, tensor hx, tensor *params_data, int params_len, int has_biases, int64_t num_layers, double dropout, int train, int bidirectional, int batch_first);
void atg_rnn_tanh_cell(tensor *, tensor input, tensor hx, tensor w_ih, tensor w_hh, tensor b_ih, tensor b_hh);
void atg_rnn_tanh_data(tensor *, tensor data, tensor batch_sizes, tensor hx, tensor *params_data, int params_len, int has_biases, int64_t num_layers, double dropout, int train, int bidirectional);
void atg_roll(tensor *, tensor self, int64_t *shifts_data, int shifts_len, int64_t *dims_data, int dims_len);
void atg_rot90(tensor *, tensor self, int64_t k, int64_t *dims_data, int dims_len);
void atg_round(tensor *, tensor self);
void atg_round_(tensor *, tensor self);
void atg_round_out(tensor *, tensor out, tensor self);
void atg_row_stack(tensor *, tensor *tensors_data, int tensors_len);
void atg_row_stack_out(tensor *, tensor out, tensor *tensors_data, int tensors_len);
void atg_rrelu(tensor *, tensor self, int training);
void atg_rrelu_(tensor *, tensor self, int training);
void atg_rrelu_with_noise(tensor *, tensor self, tensor noise, int training);
void atg_rrelu_with_noise_(tensor *, tensor self, tensor noise, int training);
void atg_rrelu_with_noise_backward(tensor *, tensor grad_output, tensor self, tensor noise, scalar lower, scalar upper, int training, int self_is_result);
void atg_rrelu_with_noise_out(tensor *, tensor out, tensor self, tensor noise, int training);
void atg_rsqrt(tensor *, tensor self);
void atg_rsqrt_(tensor *, tensor self);
void atg_rsqrt_out(tensor *, tensor out, tensor self);
void atg_rsub(tensor *, tensor self, tensor other);
void atg_rsub_scalar(tensor *, tensor self, scalar other);
void atg_scalar_tensor(tensor *, scalar s, int options_kind, int options_device);
void atg_scatter(tensor *, tensor self, int64_t dim, tensor index, tensor src);
void atg_scatter_(tensor *, tensor self, int64_t dim, tensor index, tensor src);
void atg_scatter_add(tensor *, tensor self, int64_t dim, tensor index, tensor src);
void atg_scatter_add_(tensor *, tensor self, int64_t dim, tensor index, tensor src);
void atg_scatter_add_out(tensor *, tensor out, tensor self, int64_t dim, tensor index, tensor src);
void atg_scatter_reduce(tensor *, tensor self, int64_t dim, tensor index, tensor src, char* reduce_ptr, int reduce_len);
void atg_scatter_reduce_(tensor *, tensor self, int64_t dim, tensor index, tensor src, char* reduce_ptr, int reduce_len);
void atg_scatter_reduce_out(tensor *, tensor out, tensor self, int64_t dim, tensor index, tensor src, char* reduce_ptr, int reduce_len);
void atg_scatter_src_out(tensor *, tensor out, tensor self, int64_t dim, tensor index, tensor src);
void atg_scatter_value(tensor *, tensor self, int64_t dim, tensor index, scalar value);
void atg_scatter_value_(tensor *, tensor self, int64_t dim, tensor index, scalar value);
void atg_scatter_value_out(tensor *, tensor out, tensor self, int64_t dim, tensor index, scalar value);
void atg_scatter_value_reduce(tensor *, tensor self, int64_t dim, tensor index, scalar value, char* reduce_ptr, int reduce_len);
void atg_scatter_value_reduce_(tensor *, tensor self, int64_t dim, tensor index, scalar value, char* reduce_ptr, int reduce_len);
void atg_scatter_value_reduce_out(tensor *, tensor out, tensor self, int64_t dim, tensor index, scalar value, char* reduce_ptr, int reduce_len);
void atg_searchsorted(tensor *, tensor sorted_sequence, tensor self, int out_int32, int right);
void atg_searchsorted_scalar(tensor *, tensor sorted_sequence, scalar self_scalar, int out_int32, int right);
void atg_searchsorted_tensor_out(tensor *, tensor out, tensor sorted_sequence, tensor self, int out_int32, int right);
void atg_segment_reduce(tensor *, tensor data, char* reduce_ptr, int reduce_len, tensor lengths, tensor indices, int64_t axis, int unsafe, scalar initial);
void atg_select(tensor *, tensor self, int64_t dim, int64_t index);
void atg_select_backward(tensor *, tensor grad_output, int64_t *input_sizes_data, int input_sizes_len, int64_t dim, int64_t index);
void atg_selu(tensor *, tensor self);
void atg_selu_(tensor *, tensor self);
void atg_set_(tensor *, tensor self);
void atg_set_data(tensor self, tensor new_data);
void atg_set_requires_grad(tensor *, tensor self, int r);
void atg_set_source_tensor_(tensor *, tensor self, tensor source);
void atg_sgn(tensor *, tensor self);
void atg_sgn_(tensor *, tensor self);
void atg_sgn_out(tensor *, tensor out, tensor self);
void atg_sigmoid(tensor *, tensor self);
void atg_sigmoid_(tensor *, tensor self);
void atg_sigmoid_backward(tensor *, tensor grad_output, tensor output);
void atg_sigmoid_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor output);
void atg_sigmoid_out(tensor *, tensor out, tensor self);
void atg_sign(tensor *, tensor self);
void atg_sign_(tensor *, tensor self);
void atg_sign_out(tensor *, tensor out, tensor self);
void atg_signbit(tensor *, tensor self);
void atg_signbit_out(tensor *, tensor out, tensor self);
void atg_silu(tensor *, tensor self);
void atg_silu_(tensor *, tensor self);
void atg_silu_backward(tensor *, tensor grad_output, tensor self);
void atg_silu_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self);
void atg_silu_out(tensor *, tensor out, tensor self);
void atg_sin(tensor *, tensor self);
void atg_sin_(tensor *, tensor self);
void atg_sin_out(tensor *, tensor out, tensor self);
void atg_sinc(tensor *, tensor self);
void atg_sinc_(tensor *, tensor self);
void atg_sinc_out(tensor *, tensor out, tensor self);
void atg_sinh(tensor *, tensor self);
void atg_sinh_(tensor *, tensor self);
void atg_sinh_out(tensor *, tensor out, tensor self);
void atg_slice(tensor *, tensor self, int64_t dim, int64_t start_v, uint8_t start_null, int64_t end_v, uint8_t end_null, int64_t step);
void atg_slice_backward(tensor *, tensor grad_output, int64_t *input_sizes_data, int input_sizes_len, int64_t dim, int64_t start, int64_t end, int64_t step);
void atg_slogdet(tensor *, tensor self);
void atg_slow_conv3d(tensor *, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len);
void atg_slow_conv3d_out(tensor *, tensor out, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len);
void atg_slow_conv_dilated2d(tensor *, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len);
void atg_slow_conv_dilated3d(tensor *, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *dilation_data, int dilation_len);
void atg_slow_conv_transpose2d(tensor *, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t *dilation_data, int dilation_len);
void atg_slow_conv_transpose2d_out(tensor *, tensor out, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t *dilation_data, int dilation_len);
void atg_slow_conv_transpose3d(tensor *, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t *dilation_data, int dilation_len);
void atg_slow_conv_transpose3d_out(tensor *, tensor out, tensor self, tensor weight, int64_t *kernel_size_data, int kernel_size_len, tensor bias, int64_t *stride_data, int stride_len, int64_t *padding_data, int padding_len, int64_t *output_padding_data, int output_padding_len, int64_t *dilation_data, int dilation_len);
void atg_smm(tensor *, tensor self, tensor mat2);
void atg_smooth_l1_loss(tensor *, tensor self, tensor target, int64_t reduction, double beta);
void atg_smooth_l1_loss_backward(tensor *, tensor grad_output, tensor self, tensor target, int64_t reduction, double beta);
void atg_smooth_l1_loss_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, int64_t reduction, double beta);
void atg_smooth_l1_loss_out(tensor *, tensor out, tensor self, tensor target, int64_t reduction, double beta);
void atg_soft_margin_loss(tensor *, tensor self, tensor target, int64_t reduction);
void atg_soft_margin_loss_backward(tensor *, tensor grad_output, tensor self, tensor target, int64_t reduction);
void atg_soft_margin_loss_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, tensor target, int64_t reduction);
void atg_soft_margin_loss_out(tensor *, tensor out, tensor self, tensor target, int64_t reduction);
void atg_softmax(tensor *, tensor self, int64_t dim, int dtype);
void atg_softplus(tensor *, tensor self);
void atg_softplus_backward(tensor *, tensor grad_output, tensor self, scalar beta, scalar threshold, tensor output);
void atg_softplus_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, scalar beta, scalar threshold, tensor output);
void atg_softplus_out(tensor *, tensor out, tensor self);
void atg_softshrink(tensor *, tensor self);
void atg_softshrink_backward(tensor *, tensor grad_output, tensor self, scalar lambd);
void atg_softshrink_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, scalar lambd);
void atg_softshrink_out(tensor *, tensor out, tensor self);
void atg_solve(tensor *, tensor self, tensor A);
void atg_solve_solution(tensor *, tensor solution, tensor lu, tensor self, tensor A);
void atg_sort(tensor *, tensor self, int64_t dim, int descending);
void atg_sort_stable(tensor *, tensor self, int stable, int64_t dim, int descending);
void atg_sort_values(tensor *, tensor values, tensor indices, tensor self, int64_t dim, int descending);
void atg_sort_values_stable(tensor *, tensor values, tensor indices, tensor self, int stable, int64_t dim, int descending);
void atg_sparse_coo_tensor(tensor *, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_sparse_coo_tensor_indices(tensor *, tensor indices, tensor values, int options_kind, int options_device);
void atg_sparse_coo_tensor_indices_size(tensor *, tensor indices, tensor values, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_sparse_csr_tensor(tensor *, tensor crow_indices, tensor col_indices, tensor values, int options_kind, int options_device);
void atg_sparse_csr_tensor_crow_col_value_size(tensor *, tensor crow_indices, tensor col_indices, tensor values, int64_t *size_data, int size_len, int options_kind, int options_device);
int64_t atg_sparse_dim(tensor self);
void atg_sparse_mask(tensor *, tensor self, tensor mask);
void atg_sparse_resize_(tensor *, tensor self, int64_t *size_data, int size_len, int64_t sparse_dim, int64_t dense_dim);
void atg_sparse_resize_and_clear_(tensor *, tensor self, int64_t *size_data, int size_len, int64_t sparse_dim, int64_t dense_dim);
void atg_special_digamma(tensor *, tensor self);
void atg_special_digamma_out(tensor *, tensor out, tensor self);
void atg_special_entr(tensor *, tensor self);
void atg_special_entr_out(tensor *, tensor out, tensor self);
void atg_special_erf(tensor *, tensor self);
void atg_special_erf_out(tensor *, tensor out, tensor self);
void atg_special_erfc(tensor *, tensor self);
void atg_special_erfc_out(tensor *, tensor out, tensor self);
void atg_special_erfcx(tensor *, tensor self);
void atg_special_erfcx_out(tensor *, tensor out, tensor self);
void atg_special_erfinv(tensor *, tensor self);
void atg_special_erfinv_out(tensor *, tensor out, tensor self);
void atg_special_exp2(tensor *, tensor self);
void atg_special_exp2_out(tensor *, tensor out, tensor self);
void atg_special_expit(tensor *, tensor self);
void atg_special_expit_out(tensor *, tensor out, tensor self);
void atg_special_expm1(tensor *, tensor self);
void atg_special_expm1_out(tensor *, tensor out, tensor self);
void atg_special_gammainc(tensor *, tensor self, tensor other);
void atg_special_gammainc_out(tensor *, tensor out, tensor self, tensor other);
void atg_special_gammaincc(tensor *, tensor self, tensor other);
void atg_special_gammaincc_out(tensor *, tensor out, tensor self, tensor other);
void atg_special_gammaln(tensor *, tensor self);
void atg_special_gammaln_out(tensor *, tensor out, tensor self);
void atg_special_i0(tensor *, tensor self);
void atg_special_i0_out(tensor *, tensor out, tensor self);
void atg_special_i0e(tensor *, tensor self);
void atg_special_i0e_out(tensor *, tensor out, tensor self);
void atg_special_i1(tensor *, tensor self);
void atg_special_i1_out(tensor *, tensor out, tensor self);
void atg_special_i1e(tensor *, tensor self);
void atg_special_i1e_out(tensor *, tensor out, tensor self);
void atg_special_log1p(tensor *, tensor self);
void atg_special_log1p_out(tensor *, tensor out, tensor self);
void atg_special_log_softmax(tensor *, tensor self, int64_t dim, int dtype);
void atg_special_logit(tensor *, tensor self, double eps_v, uint8_t eps_null);
void atg_special_logit_out(tensor *, tensor out, tensor self, double eps_v, uint8_t eps_null);
void atg_special_logsumexp(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_special_logsumexp_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim);
void atg_special_multigammaln(tensor *, tensor self, int64_t p);
void atg_special_multigammaln_out(tensor *, tensor out, tensor self, int64_t p);
void atg_special_ndtr(tensor *, tensor self);
void atg_special_ndtr_out(tensor *, tensor out, tensor self);
void atg_special_ndtri(tensor *, tensor self);
void atg_special_ndtri_out(tensor *, tensor out, tensor self);
void atg_special_polygamma(tensor *, int64_t n, tensor self);
void atg_special_polygamma_out(tensor *, tensor out, int64_t n, tensor self);
void atg_special_psi(tensor *, tensor self);
void atg_special_psi_out(tensor *, tensor out, tensor self);
void atg_special_round(tensor *, tensor self);
void atg_special_round_out(tensor *, tensor out, tensor self);
void atg_special_sinc(tensor *, tensor self);
void atg_special_sinc_out(tensor *, tensor out, tensor self);
void atg_special_xlog1py(tensor *, tensor self, tensor other);
void atg_special_xlog1py_other_scalar(tensor *, tensor self, scalar other);
void atg_special_xlog1py_other_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_special_xlog1py_out(tensor *, tensor out, tensor self, tensor other);
void atg_special_xlog1py_self_scalar(tensor *, scalar self_scalar, tensor other);
void atg_special_xlog1py_self_scalar_out(tensor *, tensor out, scalar self_scalar, tensor other);
void atg_special_xlogy(tensor *, tensor self, tensor other);
void atg_special_xlogy_other_scalar(tensor *, tensor self, scalar other);
void atg_special_xlogy_other_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_special_xlogy_out(tensor *, tensor out, tensor self, tensor other);
void atg_special_xlogy_self_scalar(tensor *, scalar self_scalar, tensor other);
void atg_special_xlogy_self_scalar_out(tensor *, tensor out, scalar self_scalar, tensor other);
void atg_special_zeta(tensor *, tensor self, tensor other);
void atg_special_zeta_other_scalar(tensor *, tensor self, scalar other);
void atg_special_zeta_other_scalar_out(tensor *, tensor out, tensor self, scalar other);
void atg_special_zeta_out(tensor *, tensor out, tensor self, tensor other);
void atg_special_zeta_self_scalar(tensor *, scalar self_scalar, tensor other);
void atg_special_zeta_self_scalar_out(tensor *, tensor out, scalar self_scalar, tensor other);
tensor *atg_split(tensor self, int64_t split_size, int64_t dim);
tensor *atg_split_with_sizes(tensor self, int64_t *split_sizes_data, int split_sizes_len, int64_t dim);
void atg_sqrt(tensor *, tensor self);
void atg_sqrt_(tensor *, tensor self);
void atg_sqrt_out(tensor *, tensor out, tensor self);
void atg_square(tensor *, tensor self);
void atg_square_(tensor *, tensor self);
void atg_square_out(tensor *, tensor out, tensor self);
void atg_squeeze(tensor *, tensor self);
void atg_squeeze_(tensor *, tensor self);
void atg_squeeze_dim(tensor *, tensor self, int64_t dim);
void atg_squeeze_dim_(tensor *, tensor self, int64_t dim);
void atg_sspaddmm(tensor *, tensor self, tensor mat1, tensor mat2);
void atg_sspaddmm_out(tensor *, tensor out, tensor self, tensor mat1, tensor mat2);
void atg_stack(tensor *, tensor *tensors_data, int tensors_len, int64_t dim);
void atg_stack_out(tensor *, tensor out, tensor *tensors_data, int tensors_len, int64_t dim);
void atg_std(tensor *, tensor self, int unbiased);
void atg_std_correction(tensor *, tensor self, int64_t *dim_data, int dim_len, int64_t correction_v, uint8_t correction_null, int keepdim);
void atg_std_correction_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int64_t correction_v, uint8_t correction_null, int keepdim);
void atg_std_dim(tensor *, tensor self, int64_t *dim_data, int dim_len, int unbiased, int keepdim);
void atg_std_mean(tensor *, tensor self, int unbiased);
void atg_std_mean_correction(tensor *, tensor self, int64_t *dim_data, int dim_len, int64_t correction_v, uint8_t correction_null, int keepdim);
void atg_std_mean_dim(tensor *, tensor self, int64_t *dim_data, int dim_len, int unbiased, int keepdim);
void atg_std_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int unbiased, int keepdim);
void atg_stft(tensor *, tensor self, int64_t n_fft, int64_t hop_length_v, uint8_t hop_length_null, int64_t win_length_v, uint8_t win_length_null, tensor window, int normalized, int onesided, int return_complex);
void atg_sub(tensor *, tensor self, tensor other);
void atg_sub_(tensor *, tensor self, tensor other);
void atg_sub_out(tensor *, tensor out, tensor self, tensor other);
void atg_sub_scalar(tensor *, tensor self, scalar other);
void atg_sub_scalar_(tensor *, tensor self, scalar other);
void atg_subtract(tensor *, tensor self, tensor other);
void atg_subtract_(tensor *, tensor self, tensor other);
void atg_subtract_out(tensor *, tensor out, tensor self, tensor other);
void atg_subtract_scalar(tensor *, tensor self, scalar other);
void atg_subtract_scalar_(tensor *, tensor self, scalar other);
void atg_sum(tensor *, tensor self, int dtype);
void atg_sum_dim_intlist(tensor *, tensor self, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_sum_intlist_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int keepdim, int dtype);
void atg_sum_to_size(tensor *, tensor self, int64_t *size_data, int size_len);
void atg_svd(tensor *, tensor self, int some, int compute_uv);
void atg_svd_u(tensor *, tensor U, tensor S, tensor V, tensor self, int some, int compute_uv);
void atg_swapaxes(tensor *, tensor self, int64_t axis0, int64_t axis1);
void atg_swapaxes_(tensor *, tensor self, int64_t axis0, int64_t axis1);
void atg_swapdims(tensor *, tensor self, int64_t dim0, int64_t dim1);
void atg_swapdims_(tensor *, tensor self, int64_t dim0, int64_t dim1);
void atg_symeig(tensor *, tensor self, int eigenvectors, int upper);
void atg_symeig_e(tensor *, tensor e, tensor V, tensor self, int eigenvectors, int upper);
void atg_t(tensor *, tensor self);
void atg_t_(tensor *, tensor self);
void atg_take(tensor *, tensor self, tensor index);
void atg_take_along_dim(tensor *, tensor self, tensor indices, int64_t dim_v, uint8_t dim_null);
void atg_take_along_dim_out(tensor *, tensor out, tensor self, tensor indices, int64_t dim_v, uint8_t dim_null);
void atg_take_out(tensor *, tensor out, tensor self, tensor index);
void atg_tan(tensor *, tensor self);
void atg_tan_(tensor *, tensor self);
void atg_tan_out(tensor *, tensor out, tensor self);
void atg_tanh(tensor *, tensor self);
void atg_tanh_(tensor *, tensor self);
void atg_tanh_backward(tensor *, tensor grad_output, tensor output);
void atg_tanh_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor output);
void atg_tanh_out(tensor *, tensor out, tensor self);
tensor *atg_tensor_split(tensor self, int64_t sections, int64_t dim);
tensor *atg_tensor_split_indices(tensor self, int64_t *indices_data, int indices_len, int64_t dim);
tensor *atg_tensor_split_tensor_indices_or_sections(tensor self, tensor tensor_indices_or_sections, int64_t dim);
void atg_tensordot(tensor *, tensor self, tensor other, int64_t *dims_self_data, int dims_self_len, int64_t *dims_other_data, int dims_other_len);
void atg_tensordot_out(tensor *, tensor out, tensor self, tensor other, int64_t *dims_self_data, int dims_self_len, int64_t *dims_other_data, int dims_other_len);
void atg_threshold(tensor *, tensor self, scalar threshold, scalar value);
void atg_threshold_(tensor *, tensor self, scalar threshold, scalar value);
void atg_threshold_backward(tensor *, tensor grad_output, tensor self, scalar threshold);
void atg_threshold_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, tensor self, scalar threshold);
void atg_threshold_out(tensor *, tensor out, tensor self, scalar threshold, scalar value);
void atg_tile(tensor *, tensor self, int64_t *dims_data, int dims_len);
void atg_to(tensor *, tensor self, int device);
void atg_to_dense(tensor *, tensor self, int dtype);
void atg_to_dense_backward(tensor *, tensor grad, tensor input);
void atg_to_device(tensor *, tensor self, int device, int dtype, int non_blocking, int copy);
void atg_to_dtype(tensor *, tensor self, int dtype, int non_blocking, int copy);
void atg_to_dtype_layout(tensor *, tensor self, int options_kind, int options_device, int non_blocking, int copy);
void atg_to_mkldnn(tensor *, tensor self, int dtype);
void atg_to_mkldnn_backward(tensor *, tensor grad, tensor input);
void atg_to_other(tensor *, tensor self, tensor other, int non_blocking, int copy);
void atg_to_sparse(tensor *, tensor self);
void atg_to_sparse_sparse_dim(tensor *, tensor self, int64_t sparse_dim);
void atg_topk(tensor *, tensor self, int64_t k, int64_t dim, int largest, int sorted);
void atg_topk_values(tensor *, tensor values, tensor indices, tensor self, int64_t k, int64_t dim, int largest, int sorted);
void atg_totype(tensor *, tensor self, int scalar_type);
void atg_trace(tensor *, tensor self);
void atg_trace_backward(tensor *, tensor grad, int64_t *sizes_data, int sizes_len);
void atg_transpose(tensor *, tensor self, int64_t dim0, int64_t dim1);
void atg_transpose_(tensor *, tensor self, int64_t dim0, int64_t dim1);
void atg_trapezoid(tensor *, tensor y, int64_t dim);
void atg_trapezoid_x(tensor *, tensor y, tensor x, int64_t dim);
void atg_trapz(tensor *, tensor y, tensor x, int64_t dim);
void atg_trapz_dx(tensor *, tensor y, double dx, int64_t dim);
void atg_triangular_solve(tensor *, tensor self, tensor A, int upper, int transpose, int unitriangular);
void atg_triangular_solve_x(tensor *, tensor X, tensor M, tensor self, tensor A, int upper, int transpose, int unitriangular);
void atg_tril(tensor *, tensor self, int64_t diagonal);
void atg_tril_(tensor *, tensor self, int64_t diagonal);
void atg_tril_indices(tensor *, int64_t row, int64_t col, int64_t offset, int options_kind, int options_device);
void atg_tril_out(tensor *, tensor out, tensor self, int64_t diagonal);
void atg_triplet_margin_loss(tensor *, tensor anchor, tensor positive, tensor negative, double margin, double p, double eps, int swap, int64_t reduction);
void atg_triu(tensor *, tensor self, int64_t diagonal);
void atg_triu_(tensor *, tensor self, int64_t diagonal);
void atg_triu_indices(tensor *, int64_t row, int64_t col, int64_t offset, int options_kind, int options_device);
void atg_triu_out(tensor *, tensor out, tensor self, int64_t diagonal);
void atg_true_divide(tensor *, tensor self, tensor other);
void atg_true_divide_(tensor *, tensor self, tensor other);
void atg_true_divide_out(tensor *, tensor out, tensor self, tensor other);
void atg_true_divide_scalar(tensor *, tensor self, scalar other);
void atg_true_divide_scalar_(tensor *, tensor self, scalar other);
void atg_trunc(tensor *, tensor self);
void atg_trunc_(tensor *, tensor self);
void atg_trunc_out(tensor *, tensor out, tensor self);
void atg_type_as(tensor *, tensor self, tensor other);
tensor *atg_unbind(tensor self, int64_t dim);
void atg_unflatten(tensor *, tensor self, int64_t dim, int64_t *sizes_data, int sizes_len);
tensor *atg_unflatten_dense_tensors(tensor flat, tensor *tensors_data, int tensors_len);
void atg_unfold(tensor *, tensor self, int64_t dimension, int64_t size, int64_t step);
void atg_unfold_backward(tensor *, tensor grad_in, int64_t *input_sizes_data, int input_sizes_len, int64_t dim, int64_t size, int64_t step);
void atg_uniform_(tensor *, tensor self, double from, double to);
void atg_unique_consecutive(tensor *, tensor self, int return_inverse, int return_counts, int64_t dim_v, uint8_t dim_null);
void atg_unique_dim(tensor *, tensor self, int64_t dim, int sorted, int return_inverse, int return_counts);
void atg_unique_dim_consecutive(tensor *, tensor self, int64_t dim, int return_inverse, int return_counts);
tensor *atg_unsafe_chunk(tensor self, int64_t chunks, int64_t dim);
tensor *atg_unsafe_split(tensor self, int64_t split_size, int64_t dim);
tensor *atg_unsafe_split_with_sizes(tensor self, int64_t *split_sizes_data, int split_sizes_len, int64_t dim);
void atg_unsqueeze(tensor *, tensor self, int64_t dim);
void atg_unsqueeze_(tensor *, tensor self, int64_t dim);
void atg_upsample_bicubic2d(tensor *, tensor self, int64_t *output_size_data, int output_size_len, int align_corners, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_bicubic2d_backward(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_bicubic2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_bicubic2d_backward_vec(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double *scale_factors_data, int scale_factors_len);
void atg_upsample_bicubic2d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len, int align_corners, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_bicubic2d_vec(tensor *, tensor input, int64_t *output_size_data, int output_size_len, int align_corners, double *scale_factors_data, int scale_factors_len);
void atg_upsample_bilinear2d(tensor *, tensor self, int64_t *output_size_data, int output_size_len, int align_corners, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_bilinear2d_backward(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_bilinear2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_bilinear2d_backward_vec(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double *scale_factors_data, int scale_factors_len);
void atg_upsample_bilinear2d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len, int align_corners, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_bilinear2d_vec(tensor *, tensor input, int64_t *output_size_data, int output_size_len, int align_corners, double *scale_factors_data, int scale_factors_len);
void atg_upsample_linear1d(tensor *, tensor self, int64_t *output_size_data, int output_size_len, int align_corners, double scales_v, uint8_t scales_null);
void atg_upsample_linear1d_backward(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double scales_v, uint8_t scales_null);
void atg_upsample_linear1d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double scales_v, uint8_t scales_null);
void atg_upsample_linear1d_backward_vec(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double *scale_factors_data, int scale_factors_len);
void atg_upsample_linear1d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len, int align_corners, double scales_v, uint8_t scales_null);
void atg_upsample_linear1d_vec(tensor *, tensor input, int64_t *output_size_data, int output_size_len, int align_corners, double *scale_factors_data, int scale_factors_len);
void atg_upsample_nearest1d(tensor *, tensor self, int64_t *output_size_data, int output_size_len, double scales_v, uint8_t scales_null);
void atg_upsample_nearest1d_backward(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double scales_v, uint8_t scales_null);
void atg_upsample_nearest1d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double scales_v, uint8_t scales_null);
void atg_upsample_nearest1d_backward_vec(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double *scale_factors_data, int scale_factors_len);
void atg_upsample_nearest1d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len, double scales_v, uint8_t scales_null);
void atg_upsample_nearest1d_vec(tensor *, tensor input, int64_t *output_size_data, int output_size_len, double *scale_factors_data, int scale_factors_len);
void atg_upsample_nearest2d(tensor *, tensor self, int64_t *output_size_data, int output_size_len, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_nearest2d_backward(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_nearest2d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_nearest2d_backward_vec(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double *scale_factors_data, int scale_factors_len);
void atg_upsample_nearest2d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_nearest2d_vec(tensor *, tensor input, int64_t *output_size_data, int output_size_len, double *scale_factors_data, int scale_factors_len);
void atg_upsample_nearest3d(tensor *, tensor self, int64_t *output_size_data, int output_size_len, double scales_d_v, uint8_t scales_d_null, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_nearest3d_backward(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double scales_d_v, uint8_t scales_d_null, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_nearest3d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double scales_d_v, uint8_t scales_d_null, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_nearest3d_backward_vec(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, double *scale_factors_data, int scale_factors_len);
void atg_upsample_nearest3d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len, double scales_d_v, uint8_t scales_d_null, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_nearest3d_vec(tensor *, tensor input, int64_t *output_size_data, int output_size_len, double *scale_factors_data, int scale_factors_len);
void atg_upsample_trilinear3d(tensor *, tensor self, int64_t *output_size_data, int output_size_len, int align_corners, double scales_d_v, uint8_t scales_d_null, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_trilinear3d_backward(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double scales_d_v, uint8_t scales_d_null, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_trilinear3d_backward_grad_input(tensor *, tensor grad_input, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double scales_d_v, uint8_t scales_d_null, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_trilinear3d_backward_vec(tensor *, tensor grad_output, int64_t *output_size_data, int output_size_len, int64_t *input_size_data, int input_size_len, int align_corners, double *scale_factors_data, int scale_factors_len);
void atg_upsample_trilinear3d_out(tensor *, tensor out, tensor self, int64_t *output_size_data, int output_size_len, int align_corners, double scales_d_v, uint8_t scales_d_null, double scales_h_v, uint8_t scales_h_null, double scales_w_v, uint8_t scales_w_null);
void atg_upsample_trilinear3d_vec(tensor *, tensor input, int64_t *output_size_data, int output_size_len, int align_corners, double *scale_factors_data, int scale_factors_len);
void atg_value_selecting_reduction_backward(tensor *, tensor grad, int64_t dim, tensor indices, int64_t *sizes_data, int sizes_len, int keepdim);
void atg_values(tensor *, tensor self);
void atg_vander(tensor *, tensor x, int64_t n_v, uint8_t n_null, int increasing);
void atg_var(tensor *, tensor self, int unbiased);
void atg_var_correction(tensor *, tensor self, int64_t *dim_data, int dim_len, int64_t correction_v, uint8_t correction_null, int keepdim);
void atg_var_correction_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int64_t correction_v, uint8_t correction_null, int keepdim);
void atg_var_dim(tensor *, tensor self, int64_t *dim_data, int dim_len, int unbiased, int keepdim);
void atg_var_mean(tensor *, tensor self, int unbiased);
void atg_var_mean_correction(tensor *, tensor self, int64_t *dim_data, int dim_len, int64_t correction_v, uint8_t correction_null, int keepdim);
void atg_var_mean_dim(tensor *, tensor self, int64_t *dim_data, int dim_len, int unbiased, int keepdim);
void atg_var_out(tensor *, tensor out, tensor self, int64_t *dim_data, int dim_len, int unbiased, int keepdim);
void atg_vdot(tensor *, tensor self, tensor other);
void atg_vdot_out(tensor *, tensor out, tensor self, tensor other);
void atg_view(tensor *, tensor self, int64_t *size_data, int size_len);
void atg_view_as(tensor *, tensor self, tensor other);
void atg_view_as_complex(tensor *, tensor self);
void atg_view_as_real(tensor *, tensor self);
void atg_view_dtype(tensor *, tensor self, int dtype);
tensor *atg_vsplit(tensor self, int64_t sections);
tensor *atg_vsplit_array(tensor self, int64_t *indices_data, int indices_len);
void atg_vstack(tensor *, tensor *tensors_data, int tensors_len);
void atg_vstack_out(tensor *, tensor out, tensor *tensors_data, int tensors_len);
tensor *atg_where(tensor condition);
void atg_where_scalar(tensor *, tensor condition, scalar self_scalar, scalar other);
void atg_where_scalarother(tensor *, tensor condition, tensor self, scalar other);
void atg_where_scalarself(tensor *, tensor condition, scalar self_scalar, tensor other);
void atg_where_self(tensor *, tensor condition, tensor self, tensor other);
void atg_xlogy(tensor *, tensor self, tensor other);
void atg_xlogy_(tensor *, tensor self, tensor other);
void atg_xlogy_outscalar_other(tensor *, tensor out, tensor self, scalar other);
void atg_xlogy_outscalar_self(tensor *, tensor out, scalar self_scalar, tensor other);
void atg_xlogy_outtensor(tensor *, tensor out, tensor self, tensor other);
void atg_xlogy_scalar_other(tensor *, tensor self, scalar other);
void atg_xlogy_scalar_other_(tensor *, tensor self, scalar other);
void atg_xlogy_scalar_self(tensor *, scalar self_scalar, tensor other);
void atg_zero_(tensor *, tensor self);
void atg_zeros(tensor *, int64_t *size_data, int size_len, int options_kind, int options_device);
void atg_zeros_like(tensor *, tensor self);
void atg_zeros_out(tensor *, tensor out, int64_t *size_data, int size_len);