Add files using upload-large-folder tool

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_add_relu_meta_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace meta {
+
+TORCH_API at::Tensor & _add_relu_(at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha=1);
+TORCH_API at::Tensor & _add_relu_(at::Tensor & self, const at::Scalar & other, const at::Scalar & alpha=1);
+
+} // namespace meta
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Double.h

@@ -0,0 +1,30 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/_cast_Double_ops.h>
+
+namespace at {
+
+
+// aten::_cast_Double(Tensor self, bool non_blocking=False) -> Tensor
+inline at::Tensor _cast_Double(const at::Tensor & self, bool non_blocking=false) {
+    return at::_ops::_cast_Double::call(self, non_blocking);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_cosh_ops.h

@@ -0,0 +1,50 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Operator.h
+
+#include <tuple>
+#include <vector>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+namespace _ops {
+
+
+struct TORCH_API _foreach_cosh {
+  using schema = ::std::vector<at::Tensor> (at::TensorList);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_foreach_cosh")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_cosh(Tensor[] self) -> Tensor[]")
+  static ::std::vector<at::Tensor> call(at::TensorList self);
+  static ::std::vector<at::Tensor> redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList self);
+};
+
+struct TORCH_API _foreach_cosh_ {
+  using schema = void (at::TensorList);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_foreach_cosh_")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_cosh_(Tensor(a!)[] self) -> ()")
+  static void call(at::TensorList self);
+  static void redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList self);
+};
+
+struct TORCH_API _foreach_cosh_out {
+  using schema = void (at::TensorList, at::TensorList);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_foreach_cosh")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_cosh.out(Tensor[] self, *, Tensor(a!)[] out) -> ()")
+  static void call(at::TensorList self, at::TensorList out);
+  static void redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList self, at::TensorList out);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_sgd_cuda_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace cuda {
+
+TORCH_API void _fused_sgd_(at::TensorList self, at::TensorList grads, at::TensorList momentum_buffer_list, double weight_decay, double momentum, double lr, double dampening, bool nesterov, bool maximize, bool is_first_step, const ::std::optional<at::Tensor> & grad_scale={}, const ::std::optional<at::Tensor> & found_inf={});
+TORCH_API void _fused_sgd_(at::TensorList self, at::TensorList grads, at::TensorList momentum_buffer_list, double weight_decay, double momentum, const at::Tensor & lr, double dampening, bool nesterov, bool maximize, bool is_first_step, const ::std::optional<at::Tensor> & grad_scale={}, const ::std::optional<at::Tensor> & found_inf={});
+
+} // namespace cuda
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fw_primal.h

@@ -0,0 +1,26 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/_fw_primal_ops.h>
+
+namespace at {
+
+
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_bin_edges_compositeexplicitautograd_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeexplicitautograd {
+
+TORCH_API void _histogramdd_bin_edges_out(at::TensorList out, const at::Tensor & self, at::IntArrayRef bins, ::std::optional<at::ArrayRef<double>> range=::std::nullopt, const ::std::optional<at::Tensor> & weight={}, bool density=false);
+TORCH_API void _histogramdd_bin_edges_outf(const at::Tensor & self, at::IntArrayRef bins, ::std::optional<at::ArrayRef<double>> range, const ::std::optional<at::Tensor> & weight, bool density, at::TensorList out);
+
+} // namespace compositeexplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_tensors_cpu_dispatch.h

@@ -0,0 +1,23 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace cpu {
+
+TORCH_API at::Tensor _histogramdd_from_bin_tensors(const at::Tensor & self, at::TensorList bins, const ::std::optional<at::Tensor> & weight={}, bool density=false);
+
+} // namespace cpu
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_mask_left_aligned.h

@@ -0,0 +1,30 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/_nested_tensor_from_mask_left_aligned_ops.h>
+
+namespace at {
+
+
+// aten::_nested_tensor_from_mask_left_aligned(Tensor t, Tensor mask) -> bool
+inline bool _nested_tensor_from_mask_left_aligned(const at::Tensor & t, const at::Tensor & mask) {
+    return at::_ops::_nested_tensor_from_mask_left_aligned::call(t, mask);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_size_ops.h

@@ -0,0 +1,39 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Operator.h
+
+#include <tuple>
+#include <vector>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+namespace _ops {
+
+
+struct TORCH_API _nested_tensor_size {
+  using schema = at::Tensor (const at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_nested_tensor_size")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_nested_tensor_size(Tensor self) -> Tensor")
+  static at::Tensor call(const at::Tensor & self);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self);
+};
+
+struct TORCH_API _nested_tensor_size_out {
+  using schema = at::Tensor & (const at::Tensor &, at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_nested_tensor_size")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_nested_tensor_size.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pack_padded_sequence_compositeexplicitautograd_dispatch.h

@@ -0,0 +1,25 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeexplicitautograd {
+
+TORCH_API ::std::tuple<at::Tensor,at::Tensor> _pack_padded_sequence(const at::Tensor & input, const at::Tensor & lengths, bool batch_first);
+TORCH_API ::std::tuple<at::Tensor &,at::Tensor &> _pack_padded_sequence_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & input, const at::Tensor & lengths, bool batch_first);
+TORCH_API ::std::tuple<at::Tensor &,at::Tensor &> _pack_padded_sequence_outf(const at::Tensor & input, const at::Tensor & lengths, bool batch_first, at::Tensor & out0, at::Tensor & out1);
+
+} // namespace compositeexplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_packed_sequence_native.h

@@ -0,0 +1,21 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API ::std::tuple<at::Tensor,at::Tensor> _pad_packed_sequence(const at::Tensor & data, const at::Tensor & batch_sizes, bool batch_first, const at::Scalar & padding_value, int64_t total_length);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_propagate_xla_data.h

@@ -0,0 +1,30 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/_propagate_xla_data_ops.h>
+
+namespace at {
+
+
+// aten::_propagate_xla_data(Tensor input, Tensor output) -> ()
+inline void _propagate_xla_data(const at::Tensor & input, const at::Tensor & output) {
+    return at::_ops::_propagate_xla_data::call(input, output);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_segment_reduce_backward.h

@@ -0,0 +1,39 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/_segment_reduce_backward_ops.h>
+
+namespace at {
+
+
+// aten::_segment_reduce_backward(Tensor grad, Tensor output, Tensor data, str reduce, *, Tensor? lengths=None, Tensor? offsets=None, int axis=0, Scalar? initial=None) -> Tensor
+inline at::Tensor _segment_reduce_backward(const at::Tensor & grad, const at::Tensor & output, const at::Tensor & data, c10::string_view reduce, const ::std::optional<at::Tensor> & lengths={}, const ::std::optional<at::Tensor> & offsets={}, int64_t axis=0, const ::std::optional<at::Scalar> & initial=::std::nullopt) {
+    return at::_ops::_segment_reduce_backward::call(grad, output, data, reduce, lengths, offsets, axis, initial);
+}
+
+// aten::_segment_reduce_backward.out(Tensor grad, Tensor output, Tensor data, str reduce, *, Tensor? lengths=None, Tensor? offsets=None, int axis=0, Scalar? initial=None, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & _segment_reduce_backward_out(at::Tensor & out, const at::Tensor & grad, const at::Tensor & output, const at::Tensor & data, c10::string_view reduce, const ::std::optional<at::Tensor> & lengths={}, const ::std::optional<at::Tensor> & offsets={}, int64_t axis=0, const ::std::optional<at::Scalar> & initial=::std::nullopt) {
+    return at::_ops::_segment_reduce_backward_out::call(grad, output, data, reduce, lengths, offsets, axis, initial, out);
+}
+// aten::_segment_reduce_backward.out(Tensor grad, Tensor output, Tensor data, str reduce, *, Tensor? lengths=None, Tensor? offsets=None, int axis=0, Scalar? initial=None, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & _segment_reduce_backward_outf(const at::Tensor & grad, const at::Tensor & output, const at::Tensor & data, c10::string_view reduce, const ::std::optional<at::Tensor> & lengths, const ::std::optional<at::Tensor> & offsets, int64_t axis, const ::std::optional<at::Scalar> & initial, at::Tensor & out) {
+    return at::_ops::_segment_reduce_backward_out::call(grad, output, data, reduce, lengths, offsets, axis, initial, out);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_sparse_matmul_compositeexplicitautograd_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeexplicitautograd {
+
+TORCH_API at::Tensor & _sparse_sparse_matmul_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor & _sparse_sparse_matmul_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out);
+
+} // namespace compositeexplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_spsolve_native.h

@@ -0,0 +1,21 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API at::Tensor _sparse_csr_linear_solve(const at::Tensor & A, const at::Tensor & B, bool left=true);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_cpu_compositeimplicitautograd_dispatch.h

@@ -0,0 +1,23 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeimplicitautograd {
+
+TORCH_API ::std::vector<at::Tensor> _to_cpu(at::TensorList tensors);
+
+} // namespace compositeimplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csc_native.h

@@ -0,0 +1,24 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API at::Tensor & _to_sparse_csc_out(const at::Tensor & self, ::std::optional<int64_t> dense_dim, at::Tensor & out);
+TORCH_API at::Tensor dense_to_sparse_csc(const at::Tensor & self, ::std::optional<int64_t> dense_dim=::std::nullopt);
+TORCH_API at::Tensor coo_to_sparse_csc(const at::Tensor & self, ::std::optional<int64_t> dense_dim=::std::nullopt);
+TORCH_API at::Tensor sparse_compressed_to_sparse_csc(const at::Tensor & self, ::std::optional<int64_t> dense_dim=::std::nullopt);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_cuda_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace cuda {
+
+TORCH_API at::Tensor _to_sparse(const at::Tensor & self, int64_t sparse_dim);
+TORCH_API at::Tensor _to_sparse(const at::Tensor & self, ::std::optional<at::Layout> layout=::std::nullopt, at::OptionalIntArrayRef blocksize=::std::nullopt, ::std::optional<int64_t> dense_dim=::std::nullopt);
+
+} // namespace cuda
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_ctc_loss_cuda_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace cuda {
+
+TORCH_API bool _use_cudnn_ctc_loss(const at::Tensor & log_probs, const at::Tensor & targets, at::IntArrayRef input_lengths, at::IntArrayRef target_lengths, int64_t blank);
+TORCH_API bool _use_cudnn_ctc_loss(const at::Tensor & log_probs, const at::Tensor & targets, const at::Tensor & input_lengths, const at::Tensor & target_lengths, int64_t blank);
+
+} // namespace cuda
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_ops.h

@@ -0,0 +1,28 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Operator.h
+
+#include <tuple>
+#include <vector>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+namespace _ops {
+
+
+struct TORCH_API _weight_norm {
+  using schema = at::Tensor (const at::Tensor &, const at::Tensor &, int64_t);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_weight_norm")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_weight_norm(Tensor v, Tensor g, int dim=0) -> Tensor")
+  static at::Tensor call(const at::Tensor & v, const at::Tensor & g, int64_t dim);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & v, const at::Tensor & g, int64_t dim);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcmul_compositeexplicitautogradnonfunctional_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeexplicitautogradnonfunctional {
+
+TORCH_API at::Tensor addcmul(const at::Tensor & self, const at::Tensor & tensor1, const at::Tensor & tensor2, const at::Scalar & value=1);
+TORCH_API at::Tensor & addcmul_(at::Tensor & self, const at::Tensor & tensor1, const at::Tensor & tensor2, const at::Scalar & value=1);
+
+} // namespace compositeexplicitautogradnonfunctional
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/align_to_compositeimplicitautograd_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeimplicitautograd {
+
+TORCH_API at::Tensor align_to(const at::Tensor & self, at::DimnameList names);
+TORCH_API at::Tensor align_to(const at::Tensor & self, at::DimnameList order, int64_t ellipsis_idx);
+
+} // namespace compositeimplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/all_ops.h

@@ -0,0 +1,105 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Operator.h
+
+#include <tuple>
+#include <vector>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+namespace _ops {
+
+
+struct TORCH_API all_dim {
+  using schema = at::Tensor (const at::Tensor &, int64_t, bool);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::all")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dim")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "all.dim(Tensor self, int dim, bool keepdim=False) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, int64_t dim, bool keepdim);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dim, bool keepdim);
+};
+
+struct TORCH_API all_dims {
+  using schema = at::Tensor (const at::Tensor &, at::OptionalIntArrayRef, bool);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::all")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dims")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "all.dims(Tensor self, int[]? dim=None, bool keepdim=False) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim);
+};
+
+struct TORCH_API all_out {
+  using schema = at::Tensor & (const at::Tensor &, int64_t, bool, at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::all")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "all.out(Tensor self, int dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & out);
+};
+
+struct TORCH_API all_dims_out {
+  using schema = at::Tensor & (const at::Tensor &, at::OptionalIntArrayRef, bool, at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::all")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dims_out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "all.dims_out(Tensor self, int[]? dim=None, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, at::Tensor & out);
+};
+
+struct TORCH_API all_dimname {
+  using schema = at::Tensor (const at::Tensor &, at::Dimname, bool);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::all")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dimname")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "all.dimname(Tensor self, Dimname dim, bool keepdim=False) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, at::Dimname dim, bool keepdim);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Dimname dim, bool keepdim);
+};
+
+struct TORCH_API all_dimname_out {
+  using schema = at::Tensor & (const at::Tensor &, at::Dimname, bool, at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::all")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dimname_out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "all.dimname_out(Tensor self, Dimname dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, at::Dimname dim, bool keepdim, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Dimname dim, bool keepdim, at::Tensor & out);
+};
+
+struct TORCH_API all {
+  using schema = at::Tensor (const at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::all")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "all(Tensor self) -> Tensor")
+  static at::Tensor call(const at::Tensor & self);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self);
+};
+
+struct TORCH_API all_all_out {
+  using schema = at::Tensor & (const at::Tensor &, at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::all")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "all_out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "all.all_out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/asin_compositeexplicitautogradnonfunctional_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeexplicitautogradnonfunctional {
+
+TORCH_API at::Tensor asin(const at::Tensor & self);
+TORCH_API at::Tensor & asin_(at::Tensor & self);
+
+} // namespace compositeexplicitautogradnonfunctional
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2.h

@@ -0,0 +1,39 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/atan2_ops.h>
+
+namespace at {
+
+
+// aten::atan2.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & atan2_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) {
+    return at::_ops::atan2_out::call(self, other, out);
+}
+// aten::atan2.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & atan2_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) {
+    return at::_ops::atan2_out::call(self, other, out);
+}
+
+// aten::atan2(Tensor self, Tensor other) -> Tensor
+inline at::Tensor atan2(const at::Tensor & self, const at::Tensor & other) {
+    return at::_ops::atan2::call(self, other);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bernoulli_compositeexplicitautogradnonfunctional_dispatch.h

@@ -0,0 +1,23 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeexplicitautogradnonfunctional {
+
+TORCH_API at::Tensor bernoulli(const at::Tensor & self, double p, ::std::optional<at::Generator> generator=::std::nullopt);
+
+} // namespace compositeexplicitautogradnonfunctional
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_and_compositeexplicitautogradnonfunctional_dispatch.h

@@ -0,0 +1,24 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeexplicitautogradnonfunctional {
+
+TORCH_API at::Tensor bitwise_and(const at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor & bitwise_and_(at::Tensor & self, const at::Tensor & other);
+
+} // namespace compositeexplicitautogradnonfunctional
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_xor_meta.h

@@ -0,0 +1,27 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeMetaFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/TensorIterator.h>
+#include <ATen/TensorMeta.h>
+#include <tuple>
+#include <vector>
+
+namespace at {
+namespace meta {
+
+struct TORCH_API structured_bitwise_xor_Tensor : public TensorIteratorBase {
+    
+    
+    void meta(const at::Tensor & self, const at::Tensor & other);
+};
+
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ceil_meta.h

@@ -0,0 +1,27 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeMetaFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/TensorIterator.h>
+#include <ATen/TensorMeta.h>
+#include <tuple>
+#include <vector>
+
+namespace at {
+namespace meta {
+
+struct TORCH_API structured_ceil : public TensorIteratorBase {
+    
+    
+    void meta(const at::Tensor & self);
+};
+
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cholesky_inverse_cpu_dispatch.h

@@ -0,0 +1,25 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace cpu {
+
+TORCH_API at::Tensor cholesky_inverse(const at::Tensor & self, bool upper=false);
+TORCH_API at::Tensor & cholesky_inverse_out(at::Tensor & out, const at::Tensor & self, bool upper=false);
+TORCH_API at::Tensor & cholesky_inverse_outf(const at::Tensor & self, bool upper, at::Tensor & out);
+
+} // namespace cpu
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_ops.h

@@ -0,0 +1,83 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Operator.h
+
+#include <tuple>
+#include <vector>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+namespace _ops {
+
+
+struct TORCH_API clamp {
+  using schema = at::Tensor (const at::Tensor &, const ::std::optional<at::Scalar> &, const ::std::optional<at::Scalar> &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::clamp")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "clamp(Tensor self, Scalar? min=None, Scalar? max=None) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, const ::std::optional<at::Scalar> & min, const ::std::optional<at::Scalar> & max);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const ::std::optional<at::Scalar> & min, const ::std::optional<at::Scalar> & max);
+};
+
+struct TORCH_API clamp_Tensor {
+  using schema = at::Tensor (const at::Tensor &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::clamp")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "clamp.Tensor(Tensor self, Tensor? min=None, Tensor? max=None) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, const ::std::optional<at::Tensor> & min, const ::std::optional<at::Tensor> & max);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const ::std::optional<at::Tensor> & min, const ::std::optional<at::Tensor> & max);
+};
+
+struct TORCH_API clamp_ {
+  using schema = at::Tensor & (at::Tensor &, const ::std::optional<at::Scalar> &, const ::std::optional<at::Scalar> &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::clamp_")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "clamp_(Tensor(a!) self, Scalar? min=None, Scalar? max=None) -> Tensor(a!)")
+  static at::Tensor & call(at::Tensor & self, const ::std::optional<at::Scalar> & min, const ::std::optional<at::Scalar> & max);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const ::std::optional<at::Scalar> & min, const ::std::optional<at::Scalar> & max);
+};
+
+struct TORCH_API clamp__Tensor {
+  using schema = at::Tensor & (at::Tensor &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::clamp_")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "clamp_.Tensor(Tensor(a!) self, Tensor? min=None, Tensor? max=None) -> Tensor(a!)")
+  static at::Tensor & call(at::Tensor & self, const ::std::optional<at::Tensor> & min, const ::std::optional<at::Tensor> & max);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const ::std::optional<at::Tensor> & min, const ::std::optional<at::Tensor> & max);
+};
+
+struct TORCH_API clamp_out {
+  using schema = at::Tensor & (const at::Tensor &, const ::std::optional<at::Scalar> &, const ::std::optional<at::Scalar> &, at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::clamp")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "clamp.out(Tensor self, Scalar? min=None, Scalar? max=None, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, const ::std::optional<at::Scalar> & min, const ::std::optional<at::Scalar> & max, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const ::std::optional<at::Scalar> & min, const ::std::optional<at::Scalar> & max, at::Tensor & out);
+};
+
+struct TORCH_API clamp_Tensor_out {
+  using schema = at::Tensor & (const at::Tensor &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::clamp")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "clamp.Tensor_out(Tensor self, Tensor? min=None, Tensor? max=None, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, const ::std::optional<at::Tensor> & min, const ::std::optional<at::Tensor> & max, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const ::std::optional<at::Tensor> & min, const ::std::optional<at::Tensor> & max, at::Tensor & out);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_add_relu.h

@@ -0,0 +1,91 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/cudnn_convolution_add_relu_ops.h>
+
+namespace at {
+
+
+// aten::cudnn_convolution_add_relu(Tensor self, Tensor weight, Tensor z, Scalar? alpha, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, SymInt groups) -> Tensor
+inline at::Tensor cudnn_convolution_add_relu(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups) {
+    return at::_ops::cudnn_convolution_add_relu::call(self, weight, z, alpha, bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), groups);
+}
+namespace symint {
+  template <typename T, typename = std::enable_if_t<std::is_same<T, int64_t>::value>>
+  at::Tensor cudnn_convolution_add_relu(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups) {
+    return at::_ops::cudnn_convolution_add_relu::call(self, weight, z, alpha, bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), groups);
+  }
+}
+
+// aten::cudnn_convolution_add_relu(Tensor self, Tensor weight, Tensor z, Scalar? alpha, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, SymInt groups) -> Tensor
+inline at::Tensor cudnn_convolution_add_relu_symint(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups) {
+    return at::_ops::cudnn_convolution_add_relu::call(self, weight, z, alpha, bias, stride, padding, dilation, groups);
+}
+namespace symint {
+  template <typename T, typename = std::enable_if_t<std::is_same<T, c10::SymInt>::value>>
+  at::Tensor cudnn_convolution_add_relu(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups) {
+    return at::_ops::cudnn_convolution_add_relu::call(self, weight, z, alpha, bias, stride, padding, dilation, groups);
+  }
+}
+
+// aten::cudnn_convolution_add_relu.out(Tensor self, Tensor weight, Tensor z, Scalar? alpha, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & cudnn_convolution_add_relu_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups) {
+    return at::_ops::cudnn_convolution_add_relu_out::call(self, weight, z, alpha, bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), groups, out);
+}
+namespace symint {
+  template <typename T, typename = std::enable_if_t<std::is_same<T, int64_t>::value>>
+  at::Tensor & cudnn_convolution_add_relu_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups) {
+    return at::_ops::cudnn_convolution_add_relu_out::call(self, weight, z, alpha, bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), groups, out);
+  }
+}
+
+// aten::cudnn_convolution_add_relu.out(Tensor self, Tensor weight, Tensor z, Scalar? alpha, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & cudnn_convolution_add_relu_outf(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups, at::Tensor & out) {
+    return at::_ops::cudnn_convolution_add_relu_out::call(self, weight, z, alpha, bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), groups, out);
+}
+namespace symint {
+  template <typename T, typename = std::enable_if_t<std::is_same<T, int64_t>::value>>
+  at::Tensor & cudnn_convolution_add_relu_outf(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups, at::Tensor & out) {
+    return at::_ops::cudnn_convolution_add_relu_out::call(self, weight, z, alpha, bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), groups, out);
+  }
+}
+
+// aten::cudnn_convolution_add_relu.out(Tensor self, Tensor weight, Tensor z, Scalar? alpha, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & cudnn_convolution_add_relu_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups) {
+    return at::_ops::cudnn_convolution_add_relu_out::call(self, weight, z, alpha, bias, stride, padding, dilation, groups, out);
+}
+namespace symint {
+  template <typename T, typename = std::enable_if_t<std::is_same<T, c10::SymInt>::value>>
+  at::Tensor & cudnn_convolution_add_relu_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups) {
+    return at::_ops::cudnn_convolution_add_relu_out::call(self, weight, z, alpha, bias, stride, padding, dilation, groups, out);
+  }
+}
+
+// aten::cudnn_convolution_add_relu.out(Tensor self, Tensor weight, Tensor z, Scalar? alpha, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & cudnn_convolution_add_relu_symint_outf(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out) {
+    return at::_ops::cudnn_convolution_add_relu_out::call(self, weight, z, alpha, bias, stride, padding, dilation, groups, out);
+}
+namespace symint {
+  template <typename T, typename = std::enable_if_t<std::is_same<T, c10::SymInt>::value>>
+  at::Tensor & cudnn_convolution_add_relu_outf(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out) {
+    return at::_ops::cudnn_convolution_add_relu_out::call(self, weight, z, alpha, bias, stride, padding, dilation, groups, out);
+  }
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_add_relu_native.h

@@ -0,0 +1,22 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API at::Tensor & cudnn_convolution_add_relu_out_symint(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out);
+TORCH_API at::Tensor cudnn_convolution_add_relu(const at::Tensor & self, const at::Tensor & weight, const at::Tensor & z, const ::std::optional<at::Scalar> & alpha, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_native.h

@@ -0,0 +1,22 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API at::Tensor cudnn_convolution(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, bool benchmark, bool deterministic, bool allow_tf32);
+TORCH_API at::Tensor & cudnn_convolution_out(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, bool benchmark, bool deterministic, bool allow_tf32, at::Tensor & out);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummax_native.h

@@ -0,0 +1,24 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API ::std::tuple<at::Tensor,at::Tensor> cummax(const at::Tensor & self, int64_t dim);
+TORCH_API ::std::tuple<at::Tensor &,at::Tensor &> cummax_out(const at::Tensor & self, int64_t dim, at::Tensor & values, at::Tensor & indices);
+TORCH_API ::std::tuple<at::Tensor,at::Tensor> cummax(const at::Tensor & self, at::Dimname dim);
+TORCH_API ::std::tuple<at::Tensor &,at::Tensor &> cummax_out(const at::Tensor & self, at::Dimname dim, at::Tensor & values, at::Tensor & indices);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_pack_gemm_matrix_fp16.h

@@ -0,0 +1,30 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/fbgemm_pack_gemm_matrix_fp16_ops.h>
+
+namespace at {
+
+
+// aten::fbgemm_pack_gemm_matrix_fp16(Tensor input) -> Tensor
+inline at::Tensor fbgemm_pack_gemm_matrix_fp16(const at::Tensor & input) {
+    return at::_ops::fbgemm_pack_gemm_matrix_fp16::call(input);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_cuda_dispatch.h

@@ -0,0 +1,26 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace cuda {
+
+TORCH_API at::Tensor floor(const at::Tensor & self);
+TORCH_API at::Tensor & floor_out(at::Tensor & out, const at::Tensor & self);
+TORCH_API at::Tensor & floor_outf(const at::Tensor & self, at::Tensor & out);
+TORCH_API at::Tensor & floor_(at::Tensor & self);
+
+} // namespace cuda
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_divide_native.h

@@ -0,0 +1,29 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API at::Tensor floor_divide(const at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor & floor_divide_out(const at::Tensor & self, const at::Tensor & other, at::Tensor & out);
+TORCH_API at::Tensor & floor_divide_(at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor floor_divide_sparse(const at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor & floor_divide_out_sparse_zerodim(const at::Tensor & self, const at::Tensor & other, at::Tensor & out);
+TORCH_API at::Tensor & floor_divide_sparse_(at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor floor_divide(const at::Tensor & self, const at::Scalar & other);
+TORCH_API at::Tensor & floor_divide_Scalar_out(const at::Tensor & self, const at::Scalar & other, at::Tensor & out);
+TORCH_API at::Tensor & floor_divide_(at::Tensor & self, const at::Scalar & other);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ge_compositeexplicitautogradnonfunctional_dispatch.h

@@ -0,0 +1,26 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeexplicitautogradnonfunctional {
+
+TORCH_API at::Tensor ge(const at::Tensor & self, const at::Scalar & other);
+TORCH_API at::Tensor & ge_(at::Tensor & self, const at::Scalar & other);
+TORCH_API at::Tensor ge(const at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor & ge_(at::Tensor & self, const at::Tensor & other);
+
+} // namespace compositeexplicitautogradnonfunctional
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/group_norm_ops.h

@@ -0,0 +1,28 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Operator.h
+
+#include <tuple>
+#include <vector>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+namespace _ops {
+
+
+struct TORCH_API group_norm {
+  using schema = at::Tensor (const at::Tensor &, int64_t, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, double, bool);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::group_norm")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "group_norm(Tensor input, int num_groups, Tensor? weight=None, Tensor? bias=None, float eps=1e-05, bool cudnn_enabled=True) -> Tensor")
+  static at::Tensor call(const at::Tensor & input, int64_t num_groups, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & bias, double eps, bool cudnn_enabled);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, int64_t num_groups, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & bias, double eps, bool cudnn_enabled);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardshrink_ops.h

@@ -0,0 +1,39 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Operator.h
+
+#include <tuple>
+#include <vector>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+namespace _ops {
+
+
+struct TORCH_API hardshrink_out {
+  using schema = at::Tensor & (const at::Tensor &, const at::Scalar &, at::Tensor &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::hardshrink")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "hardshrink.out(Tensor self, Scalar lambd=0.5, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, const at::Scalar & lambd, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & lambd, at::Tensor & out);
+};
+
+struct TORCH_API hardshrink {
+  using schema = at::Tensor (const at::Tensor &, const at::Scalar &);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::hardshrink")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "hardshrink(Tensor self, Scalar lambd=0.5) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, const at::Scalar & lambd);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & lambd);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardsigmoid_backward_meta_dispatch.h

@@ -0,0 +1,25 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace meta {
+
+TORCH_API at::Tensor hardsigmoid_backward(const at::Tensor & grad_output, const at::Tensor & self);
+TORCH_API at::Tensor & hardsigmoid_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self);
+TORCH_API at::Tensor & hardsigmoid_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input);
+
+} // namespace meta
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hstack_compositeimplicitautograd_dispatch.h

@@ -0,0 +1,25 @@
+#pragma once
+// @generated by torchgen/gen.py from DispatchKeyFunction.h
+
+// NB: The implementing C++ file is RegisterDispatchKey.cpp
+
+// The only #includes we need are for custom classes that have defaults in the C++ API
+#include <c10/core/MemoryFormat.h>
+#include <c10/core/Scalar.h>
+#include <ATen/core/Reduction.h>
+
+// Forward declarations of any types needed in the operator signatures.
+// We can't directly include these classes because it will cause circular include dependencies.
+// This file is included by TensorBody.h, which defines the Tensor class.
+#include <ATen/core/ATen_fwd.h>
+
+namespace at {
+
+namespace compositeimplicitautograd {
+
+TORCH_API at::Tensor hstack(at::TensorList tensors);
+TORCH_API at::Tensor & hstack_out(at::Tensor & out, at::TensorList tensors);
+TORCH_API at::Tensor & hstack_outf(at::TensorList tensors, at::Tensor & out);
+
+} // namespace compositeimplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hstack_native.h

@@ -0,0 +1,22 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API at::Tensor hstack(at::TensorList tensors);
+TORCH_API at::Tensor & hstack_out(at::TensorList tensors, at::Tensor & out);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isneginf_native.h

@@ -0,0 +1,27 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+#include <ATen/ops/isneginf_meta.h>
+
+namespace at {
+namespace native {
+struct TORCH_API structured_isneginf_out : public at::meta::structured_isneginf {
+void impl(const at::Tensor & self, const at::Tensor & out);
+};
+TORCH_API at::Tensor isneginf_sparse(const at::Tensor & self);
+TORCH_API at::Tensor & isneginf_sparse_out(const at::Tensor & self, at::Tensor & out);
+TORCH_API at::Tensor isneginf_sparse_csr(const at::Tensor & self);
+TORCH_API at::Tensor & isneginf_sparse_csr_out(const at::Tensor & self, at::Tensor & out);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_backward.h

@@ -0,0 +1,39 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/leaky_relu_backward_ops.h>
+
+namespace at {
+
+
+// aten::leaky_relu_backward.grad_input(Tensor grad_output, Tensor self, Scalar negative_slope, bool self_is_result, *, Tensor(a!) grad_input) -> Tensor(a!)
+inline at::Tensor & leaky_relu_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & negative_slope, bool self_is_result) {
+    return at::_ops::leaky_relu_backward_grad_input::call(grad_output, self, negative_slope, self_is_result, grad_input);
+}
+// aten::leaky_relu_backward.grad_input(Tensor grad_output, Tensor self, Scalar negative_slope, bool self_is_result, *, Tensor(a!) grad_input) -> Tensor(a!)
+inline at::Tensor & leaky_relu_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & negative_slope, bool self_is_result, at::Tensor & grad_input) {
+    return at::_ops::leaky_relu_backward_grad_input::call(grad_output, self, negative_slope, self_is_result, grad_input);
+}
+
+// aten::leaky_relu_backward(Tensor grad_output, Tensor self, Scalar negative_slope, bool self_is_result) -> Tensor
+inline at::Tensor leaky_relu_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & negative_slope, bool self_is_result) {
+    return at::_ops::leaky_relu_backward::call(grad_output, self, negative_slope, self_is_result);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/less.h

@@ -0,0 +1,53 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/less_ops.h>
+
+namespace at {
+
+
+// aten::less.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & less_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other) {
+    return at::_ops::less_Scalar_out::call(self, other, out);
+}
+// aten::less.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & less_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out) {
+    return at::_ops::less_Scalar_out::call(self, other, out);
+}
+
+// aten::less.Scalar(Tensor self, Scalar other) -> Tensor
+inline at::Tensor less(const at::Tensor & self, const at::Scalar & other) {
+    return at::_ops::less_Scalar::call(self, other);
+}
+
+// aten::less.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & less_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) {
+    return at::_ops::less_Tensor_out::call(self, other, out);
+}
+// aten::less.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & less_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) {
+    return at::_ops::less_Tensor_out::call(self, other, out);
+}
+
+// aten::less.Tensor(Tensor self, Tensor other) -> Tensor
+inline at::Tensor less(const at::Tensor & self, const at::Tensor & other) {
+    return at::_ops::less_Tensor::call(self, other);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/less_equal.h

@@ -0,0 +1,53 @@
+#pragma once
+
+// @generated by torchgen/gen.py from Function.h
+
+#include <ATen/Context.h>
+#include <ATen/DeviceGuard.h>
+#include <ATen/TensorUtils.h>
+#include <ATen/TracerMode.h>
+#include <ATen/core/Generator.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+
+
+
+#include <ATen/ops/less_equal_ops.h>
+
+namespace at {
+
+
+// aten::less_equal.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & less_equal_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other) {
+    return at::_ops::less_equal_Scalar_out::call(self, other, out);
+}
+// aten::less_equal.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & less_equal_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out) {
+    return at::_ops::less_equal_Scalar_out::call(self, other, out);
+}
+
+// aten::less_equal.Scalar(Tensor self, Scalar other) -> Tensor
+inline at::Tensor less_equal(const at::Tensor & self, const at::Scalar & other) {
+    return at::_ops::less_equal_Scalar::call(self, other);
+}
+
+// aten::less_equal.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & less_equal_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) {
+    return at::_ops::less_equal_Tensor_out::call(self, other, out);
+}
+// aten::less_equal.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & less_equal_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) {
+    return at::_ops::less_equal_Tensor_out::call(self, other, out);
+}
+
+// aten::less_equal.Tensor(Tensor self, Tensor other) -> Tensor
+inline at::Tensor less_equal(const at::Tensor & self, const at::Tensor & other) {
+    return at::_ops::less_equal_Tensor::call(self, other);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_diagonal_native.h

@@ -0,0 +1,21 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/core/Tensor.h>
+#include <tuple>
+#include <vector>
+
+
+namespace at {
+namespace native {
+TORCH_API at::Tensor linalg_diagonal(const at::Tensor & A, int64_t offset=0, int64_t dim1=-2, int64_t dim2=-1);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_solve_meta.h

@@ -0,0 +1,27 @@
+#pragma once
+
+// @generated by torchgen/gen.py from NativeMetaFunction.h
+
+#include <c10/core/Scalar.h>
+#include <c10/core/Storage.h>
+#include <c10/core/TensorOptions.h>
+#include <c10/util/Deprecated.h>
+#include <optional>
+#include <c10/core/QScheme.h>
+#include <ATen/core/Reduction.h>
+#include <ATen/TensorIterator.h>
+#include <ATen/TensorMeta.h>
+#include <tuple>
+#include <vector>
+
+namespace at {
+namespace meta {
+
+struct TORCH_API structured_linalg_lu_solve : public at::impl::MetaBase {
+    
+    
+    void meta(const at::Tensor & LU, const at::Tensor & pivots, const at::Tensor & B, bool left, bool adjoint);
+};
+
+} // namespace native
+} // namespace at