Add files using upload-large-folder tool

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Int_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 _cast_Int {
+  using schema = at::Tensor (const at::Tensor &, bool);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_cast_Int")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cast_Int(Tensor self, bool non_blocking=False) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, bool non_blocking);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool non_blocking);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_coalesce_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 _coalesce {
+  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::_coalesce")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_coalesce(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 _coalesce_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::_coalesce")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_coalesce.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/_conj_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 _conj {
+  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::_conj")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_conj(Tensor(a) self) -> Tensor(a)")
+  static at::Tensor call(const at::Tensor & self);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_dirichlet_grad_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 _dirichlet_grad {
+  using schema = at::Tensor (const at::Tensor &, const 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::_dirichlet_grad")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_dirichlet_grad(Tensor x, Tensor alpha, Tensor total) -> Tensor")
+  static at::Tensor call(const at::Tensor & x, const at::Tensor & alpha, const at::Tensor & total);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x, const at::Tensor & alpha, const at::Tensor & total);
+};
+
+struct TORCH_API _dirichlet_grad_out {
+  using schema = at::Tensor & (const at::Tensor &, const 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::_dirichlet_grad")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_dirichlet_grad.out(Tensor x, Tensor alpha, Tensor total, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & x, const at::Tensor & alpha, const at::Tensor & total, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x, const at::Tensor & alpha, const at::Tensor & total, at::Tensor & out);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_empty_per_channel_affine_quantized_compositeexplicitautograd_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 compositeexplicitautograd {
+
+TORCH_API at::Tensor & _empty_per_channel_affine_quantized_out(at::Tensor & out, at::IntArrayRef size, const at::Tensor & scales, const at::Tensor & zero_points, int64_t axis, ::std::optional<at::MemoryFormat> memory_format=c10::MemoryFormat::Contiguous);
+TORCH_API at::Tensor & _empty_per_channel_affine_quantized_outf(at::IntArrayRef size, const at::Tensor & scales, const at::Tensor & zero_points, int64_t axis, ::std::optional<at::MemoryFormat> memory_format, at::Tensor & out);
+TORCH_API at::Tensor & _empty_per_channel_affine_quantized_symint_out(at::Tensor & out, c10::SymIntArrayRef size, const at::Tensor & scales, const at::Tensor & zero_points, int64_t axis, ::std::optional<at::MemoryFormat> memory_format=c10::MemoryFormat::Contiguous);
+TORCH_API at::Tensor & _empty_per_channel_affine_quantized_symint_outf(c10::SymIntArrayRef size, const at::Tensor & scales, const at::Tensor & zero_points, int64_t axis, ::std::optional<at::MemoryFormat> memory_format, at::Tensor & out);
+
+} // namespace compositeexplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fill_mem_eff_dropout_mask_cuda_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 cuda {
+
+TORCH_API at::Tensor & _fill_mem_eff_dropout_mask_(at::Tensor & self, double dropout_p, int64_t seed, int64_t offset);
+
+} // namespace cuda
+} // namespace at

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

@@ -0,0 +1,44 @@
+#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/_foreach_acos_ops.h>
+
+namespace at {
+
+
+// aten::_foreach_acos(Tensor[] self) -> Tensor[]
+inline ::std::vector<at::Tensor> _foreach_acos(at::TensorList self) {
+    return at::_ops::_foreach_acos::call(self);
+}
+
+// aten::_foreach_acos_(Tensor(a!)[] self) -> ()
+inline void _foreach_acos_(at::TensorList self) {
+    return at::_ops::_foreach_acos_::call(self);
+}
+
+// aten::_foreach_acos.out(Tensor[] self, *, Tensor(a!)[] out) -> ()
+inline void _foreach_acos_out(at::TensorList out, at::TensorList self) {
+    return at::_ops::_foreach_acos_out::call(self, out);
+}
+// aten::_foreach_acos.out(Tensor[] self, *, Tensor(a!)[] out) -> ()
+inline void _foreach_acos_outf(at::TensorList self, at::TensorList out) {
+    return at::_ops::_foreach_acos_out::call(self, out);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_ceil_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_ceil {
+  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_ceil")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_ceil(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_ceil_ {
+  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_ceil_")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_ceil_(Tensor(a!)[] self) -> ()")
+  static void call(at::TensorList self);
+  static void redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList self);
+};
+
+struct TORCH_API _foreach_ceil_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_ceil")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_ceil.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/_grid_sampler_2d_cpu_fallback_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 _grid_sampler_2d_cpu_fallback {
+  using schema = at::Tensor (const at::Tensor &, const at::Tensor &, int64_t, 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::_grid_sampler_2d_cpu_fallback")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_grid_sampler_2d_cpu_fallback(Tensor input, Tensor grid, int interpolation_mode, int padding_mode, bool align_corners) -> Tensor")
+  static at::Tensor call(const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners);
+};
+
+struct TORCH_API _grid_sampler_2d_cpu_fallback_out {
+  using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, int64_t, 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::_grid_sampler_2d_cpu_fallback")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_grid_sampler_2d_cpu_fallback.out(Tensor input, Tensor grid, int interpolation_mode, int padding_mode, bool align_corners, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, at::Tensor & out);
+};
+
+}} // namespace at::_ops

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

@@ -0,0 +1,23 @@
+#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 & _make_per_channel_quantized_tensor_out(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis, at::Tensor & out);
+TORCH_API at::Tensor make_per_channel_quantized_tensor_cpu(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis);
+TORCH_API at::Tensor make_per_channel_quantized_tensor_cuda(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_copy_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 _reshape_copy_symint(const at::Tensor & self, c10::SymIntArrayRef size);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_fused_attention_overrideable_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 _scaled_dot_product_fused_attention_overrideable {
+  using schema = ::std::tuple<at::Tensor,at::Tensor,at::Tensor,at::Tensor,c10::SymInt,c10::SymInt,at::Tensor,at::Tensor,at::Tensor> (const at::Tensor &, const at::Tensor &, const at::Tensor &, const ::std::optional<at::Tensor> &, double, bool, bool, ::std::optional<double>);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_scaled_dot_product_fused_attention_overrideable")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_scaled_dot_product_fused_attention_overrideable(Tensor query, Tensor key, Tensor value, Tensor? attn_bias=None, float dropout_p=0.0, bool is_causal=False, bool return_debug_mask=False, *, float? scale=None) -> (Tensor output, Tensor logsumexp, Tensor cum_seq_q, Tensor cum_seq_k, SymInt max_q, SymInt max_k, Tensor philox_seed, Tensor philox_offset, Tensor debug_attn_mask)")
+  static ::std::tuple<at::Tensor,at::Tensor,at::Tensor,at::Tensor,c10::SymInt,c10::SymInt,at::Tensor,at::Tensor,at::Tensor> call(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const ::std::optional<at::Tensor> & attn_bias, double dropout_p, bool is_causal, bool return_debug_mask, ::std::optional<double> scale);
+  static ::std::tuple<at::Tensor,at::Tensor,at::Tensor,at::Tensor,c10::SymInt,c10::SymInt,at::Tensor,at::Tensor,at::Tensor> redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const ::std::optional<at::Tensor> & attn_bias, double dropout_p, bool is_causal, bool return_debug_mask, ::std::optional<double> scale);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_forward_cuda_dispatch.h

@@ -0,0 +1,28 @@
+#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 _slow_conv2d_forward(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding);
+TORCH_API at::Tensor _slow_conv2d_forward_symint(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding);
+TORCH_API at::Tensor & _slow_conv2d_forward_out(at::Tensor & output, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding);
+TORCH_API at::Tensor & _slow_conv2d_forward_outf(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const ::std::optional<at::Tensor> & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & output);
+TORCH_API at::Tensor & _slow_conv2d_forward_symint_out(at::Tensor & output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding);
+TORCH_API at::Tensor & _slow_conv2d_forward_symint_outf(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const ::std::optional<at::Tensor> & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, at::Tensor & output);
+
+} // namespace cuda
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_optional_filled_intlist_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 & _test_optional_filled_intlist_out(const at::Tensor & values, at::OptionalIntArrayRef addends, at::Tensor & out);
+TORCH_API at::Tensor _test_optional_intlist(const at::Tensor & values, at::OptionalIntArrayRef addends);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_serialization_subcmul_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 at::Tensor _test_serialization_subcmul(const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha=1);
+
+} // namespace compositeimplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_index_put_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 _unsafe_index_put(const at::Tensor & self, const c10::List<::std::optional<at::Tensor>> & indices, const at::Tensor & values, bool accumulate=false);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact1d_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 _upsample_nearest_exact1d(const at::Tensor & self, at::IntArrayRef output_size, ::std::optional<double> scales=::std::nullopt);
+TORCH_API at::Tensor _upsample_nearest_exact1d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, ::std::optional<double> scales=::std::nullopt);
+
+} // namespace compositeexplicitautogradnonfunctional
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact1d_meta_dispatch.h

@@ -0,0 +1,28 @@
+#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 _upsample_nearest_exact1d(const at::Tensor & self, at::IntArrayRef output_size, ::std::optional<double> scales=::std::nullopt);
+TORCH_API at::Tensor _upsample_nearest_exact1d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, ::std::optional<double> scales=::std::nullopt);
+TORCH_API at::Tensor & _upsample_nearest_exact1d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, ::std::optional<double> scales=::std::nullopt);
+TORCH_API at::Tensor & _upsample_nearest_exact1d_outf(const at::Tensor & self, at::IntArrayRef output_size, ::std::optional<double> scales, at::Tensor & out);
+TORCH_API at::Tensor & _upsample_nearest_exact1d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, ::std::optional<double> scales=::std::nullopt);
+TORCH_API at::Tensor & _upsample_nearest_exact1d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, ::std::optional<double> scales, at::Tensor & out);
+
+} // namespace meta
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_cuda_dispatch.h

@@ -0,0 +1,28 @@
+#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 _upsample_nearest_exact3d(const at::Tensor & self, at::IntArrayRef output_size, ::std::optional<double> scales_d=::std::nullopt, ::std::optional<double> scales_h=::std::nullopt, ::std::optional<double> scales_w=::std::nullopt);
+TORCH_API at::Tensor _upsample_nearest_exact3d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, ::std::optional<double> scales_d=::std::nullopt, ::std::optional<double> scales_h=::std::nullopt, ::std::optional<double> scales_w=::std::nullopt);
+TORCH_API at::Tensor & _upsample_nearest_exact3d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, ::std::optional<double> scales_d=::std::nullopt, ::std::optional<double> scales_h=::std::nullopt, ::std::optional<double> scales_w=::std::nullopt);
+TORCH_API at::Tensor & _upsample_nearest_exact3d_outf(const at::Tensor & self, at::IntArrayRef output_size, ::std::optional<double> scales_d, ::std::optional<double> scales_h, ::std::optional<double> scales_w, at::Tensor & out);
+TORCH_API at::Tensor & _upsample_nearest_exact3d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, ::std::optional<double> scales_d=::std::nullopt, ::std::optional<double> scales_h=::std::nullopt, ::std::optional<double> scales_w=::std::nullopt);
+TORCH_API at::Tensor & _upsample_nearest_exact3d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, ::std::optional<double> scales_d, ::std::optional<double> scales_h, ::std::optional<double> scales_w, at::Tensor & out);
+
+} // namespace cuda
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/acos_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_acos : public TensorIteratorBase {
+    
+    
+    void meta(const at::Tensor & self);
+};
+
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_max_pool3d_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 ::std::tuple<at::Tensor,at::Tensor> adaptive_max_pool3d(const at::Tensor & self, at::IntArrayRef output_size);
+TORCH_API ::std::tuple<at::Tensor &,at::Tensor &> adaptive_max_pool3d_out(at::Tensor & out, at::Tensor & indices, const at::Tensor & self, at::IntArrayRef output_size);
+TORCH_API ::std::tuple<at::Tensor &,at::Tensor &> adaptive_max_pool3d_outf(const at::Tensor & self, at::IntArrayRef output_size, at::Tensor & out, at::Tensor & indices);
+
+} // namespace cpu
+} // namespace at

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

@@ -0,0 +1,29 @@
+#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 bitwise_and(const at::Tensor & self, const at::Scalar & other);
+TORCH_API at::Tensor & bitwise_and_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other);
+TORCH_API at::Tensor & bitwise_and_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out);
+TORCH_API at::Tensor & bitwise_and_(at::Tensor & self, const at::Scalar & other);
+TORCH_API at::Tensor bitwise_and(const at::Scalar & self, const at::Tensor & other);
+TORCH_API at::Tensor & bitwise_and_out(at::Tensor & out, const at::Scalar & self, const at::Tensor & other);
+TORCH_API at::Tensor & bitwise_and_outf(const at::Scalar & self, const at::Tensor & other, at::Tensor & out);
+
+} // namespace compositeexplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/col_indices_copy_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 col_indices_copy {
+  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::col_indices_copy")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "col_indices_copy(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 col_indices_copy_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::col_indices_copy")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "col_indices_copy.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/copysign_cpu_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 cpu {
+
+TORCH_API at::Tensor copysign(const at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor & copysign_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other);
+TORCH_API at::Tensor & copysign_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out);
+TORCH_API at::Tensor & copysign_(at::Tensor & self, const at::Tensor & other);
+
+} // namespace cpu
+} // namespace at

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

@@ -0,0 +1,35 @@
+#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/diagonal_ops.h>
+
+namespace at {
+
+
+// aten::diagonal(Tensor(a) self, int offset=0, int dim1=0, int dim2=1) -> Tensor(a)
+inline at::Tensor diagonal(const at::Tensor & self, int64_t offset=0, int64_t dim1=0, int64_t dim2=1) {
+    return at::_ops::diagonal::call(self, offset, dim1, dim2);
+}
+
+// aten::diagonal.Dimname(Tensor(a) self, *, Dimname outdim, Dimname dim1, Dimname dim2, int offset=0) -> Tensor(a)
+inline at::Tensor diagonal(const at::Tensor & self, at::Dimname outdim, at::Dimname dim1, at::Dimname dim2, int64_t offset=0) {
+    return at::_ops::diagonal_Dimname::call(self, outdim, dim1, dim2, offset);
+}
+
+}

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

@@ -0,0 +1,28 @@
+#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 diagonal_backward(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2);
+TORCH_API at::Tensor diagonal_backward_symint(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2);
+TORCH_API at::Tensor & diagonal_backward_out(at::Tensor & out, const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2);
+TORCH_API at::Tensor & diagonal_backward_outf(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2, at::Tensor & out);
+TORCH_API at::Tensor & diagonal_backward_symint_out(at::Tensor & out, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2);
+TORCH_API at::Tensor & diagonal_backward_symint_outf(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2, at::Tensor & out);
+
+} // namespace compositeexplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/embedding_renorm_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 & embedding_renorm_(at::Tensor & self, const at::Tensor & indices, double max_norm, double norm_type);
+
+} // namespace cpu
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/embedding_renorm_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 embedding_renorm(const at::Tensor & self, const at::Tensor & indices, double max_norm, double norm_type);
+TORCH_API at::Tensor & embedding_renorm_out(const at::Tensor & self, const at::Tensor & indices, double max_norm, double norm_type, at::Tensor & out);
+TORCH_API at::Tensor & embedding_renorm_cpu_(at::Tensor & self, const at::Tensor & indices, double max_norm, double norm_type);
+TORCH_API at::Tensor & embedding_renorm_cuda_(at::Tensor & self, const at::Tensor & indices, double max_norm, double norm_type);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_tensor_affine_cachemask_backward.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/fake_quantize_per_tensor_affine_cachemask_backward_ops.h>
+
+namespace at {
+
+
+// aten::fake_quantize_per_tensor_affine_cachemask_backward(Tensor grad, Tensor mask) -> Tensor
+inline at::Tensor fake_quantize_per_tensor_affine_cachemask_backward(const at::Tensor & grad, const at::Tensor & mask) {
+    return at::_ops::fake_quantize_per_tensor_affine_cachemask_backward::call(grad, mask);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ifftn_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 fft_ifftn_symint(const at::Tensor & self, at::OptionalSymIntArrayRef s=::std::nullopt, at::OptionalIntArrayRef dim=::std::nullopt, ::std::optional<c10::string_view> norm=::std::nullopt);
+TORCH_API at::Tensor & fft_ifftn_symint_out(const at::Tensor & self, at::OptionalSymIntArrayRef s, at::OptionalIntArrayRef dim, ::std::optional<c10::string_view> norm, at::Tensor & out);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fliplr_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 at::Tensor fliplr(const at::Tensor & self);
+
+} // namespace compositeimplicitautograd
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d_meta.h

@@ -0,0 +1,239 @@
+#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_fractional_max_pool3d : public at::impl::MetaBase {
+    
+                template <bool POOLSIZET = false, bool POOLSIZEH = false, bool POOLSIZEW = false, bool OUTPUTT = false, bool OUTPUTH = false, bool OUTPUTW = false, bool NUMBATCH = false, bool NUMPLANES = false, bool INPUTT = false, bool INPUTH = false, bool INPUTW = false>
+                struct TORCH_API precompute_out {
+                    
+                    precompute_out<true, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> set_poolSizeT(int64_t value) {
+                        static_assert(POOLSIZET == false, "poolSizeT already set");
+                        precompute_out<true, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> ret;
+ret.poolSizeT = value;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, true, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> set_poolSizeH(int64_t value) {
+                        static_assert(POOLSIZEH == false, "poolSizeH already set");
+                        precompute_out<POOLSIZET, true, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = value;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, true, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> set_poolSizeW(int64_t value) {
+                        static_assert(POOLSIZEW == false, "poolSizeW already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, true, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = value;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, true, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> set_outputT(int64_t value) {
+                        static_assert(OUTPUTT == false, "outputT already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, true, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = value;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, true, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> set_outputH(int64_t value) {
+                        static_assert(OUTPUTH == false, "outputH already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, true, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = value;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, true, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> set_outputW(int64_t value) {
+                        static_assert(OUTPUTW == false, "outputW already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, true, NUMBATCH, NUMPLANES, INPUTT, INPUTH, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = value;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, true, NUMPLANES, INPUTT, INPUTH, INPUTW> set_numBatch(int64_t value) {
+                        static_assert(NUMBATCH == false, "numBatch already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, true, NUMPLANES, INPUTT, INPUTH, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = value;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, true, INPUTT, INPUTH, INPUTW> set_numPlanes(int64_t value) {
+                        static_assert(NUMPLANES == false, "numPlanes already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, true, INPUTT, INPUTH, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = value;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, true, INPUTH, INPUTW> set_inputT(int64_t value) {
+                        static_assert(INPUTT == false, "inputT already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, true, INPUTH, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = value;
+ret.inputH = this->inputH;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, true, INPUTW> set_inputH(int64_t value) {
+                        static_assert(INPUTH == false, "inputH already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, true, INPUTW> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = value;
+ret.inputW = this->inputW;
+return ret;
+                    }
+                
+
+                    precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, true> set_inputW(int64_t value) {
+                        static_assert(INPUTW == false, "inputW already set");
+                        precompute_out<POOLSIZET, POOLSIZEH, POOLSIZEW, OUTPUTT, OUTPUTH, OUTPUTW, NUMBATCH, NUMPLANES, INPUTT, INPUTH, true> ret;
+ret.poolSizeT = this->poolSizeT;
+ret.poolSizeH = this->poolSizeH;
+ret.poolSizeW = this->poolSizeW;
+ret.outputT = this->outputT;
+ret.outputH = this->outputH;
+ret.outputW = this->outputW;
+ret.numBatch = this->numBatch;
+ret.numPlanes = this->numPlanes;
+ret.inputT = this->inputT;
+ret.inputH = this->inputH;
+ret.inputW = value;
+return ret;
+                    }
+                
+                    int64_t poolSizeT;
+int64_t poolSizeH;
+int64_t poolSizeW;
+int64_t outputT;
+int64_t outputH;
+int64_t outputW;
+int64_t numBatch;
+int64_t numPlanes;
+int64_t inputT;
+int64_t inputH;
+int64_t inputW;
+            };
+    using meta_return_ty = precompute_out <true, true, true, true, true, true, true, true, true, true, true>;
+    meta_return_ty meta(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples);
+};
+
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gelu_cpu_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 cpu {
+
+TORCH_API at::Tensor gelu(const at::Tensor & self, c10::string_view approximate="none");
+TORCH_API at::Tensor & gelu_out(at::Tensor & out, const at::Tensor & self, c10::string_view approximate="none");
+TORCH_API at::Tensor & gelu_outf(const at::Tensor & self, c10::string_view approximate, at::Tensor & out);
+TORCH_API at::Tensor & gelu_(at::Tensor & self, c10::string_view approximate="none");
+
+} // namespace cpu
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_2d_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 grid_sampler_2d(const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners);
+
+} // namespace cpu
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/i0_meta_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 meta {
+
+TORCH_API at::Tensor i0(const at::Tensor & self);
+TORCH_API at::Tensor & i0_out(at::Tensor & out, const at::Tensor & self);
+TORCH_API at::Tensor & i0_outf(const at::Tensor & self, at::Tensor & out);
+TORCH_API at::Tensor & i0_(at::Tensor & self);
+
+} // namespace meta
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_fill_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 & index_fill_(at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Scalar & value);
+TORCH_API at::Tensor & index_fill_(at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & value);
+
+} // namespace meta
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/item.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/item_ops.h>
+
+namespace at {
+
+
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lcm_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 lcm_out {
+  using schema = at::Tensor & (const 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::lcm")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lcm.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, const at::Tensor & other, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other, at::Tensor & out);
+};
+
+struct TORCH_API lcm {
+  using schema = at::Tensor (const 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::lcm")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lcm(Tensor self, Tensor other) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, const at::Tensor & other);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other);
+};
+
+struct TORCH_API lcm_ {
+  using schema = at::Tensor & (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::lcm_")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lcm_(Tensor(a!) self, Tensor other) -> Tensor(a!)")
+  static at::Tensor & call(at::Tensor & self, const at::Tensor & other);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Tensor & other);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_cpu_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 cpu {
+
+TORCH_API at::Tensor leaky_relu(const at::Tensor & self, const at::Scalar & negative_slope=0.01);
+TORCH_API at::Tensor & leaky_relu_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & negative_slope=0.01);
+TORCH_API at::Tensor & leaky_relu_outf(const at::Tensor & self, const at::Scalar & negative_slope, at::Tensor & out);
+TORCH_API at::Tensor & leaky_relu_(at::Tensor & self, const at::Scalar & negative_slope=0.01);
+
+} // namespace cpu
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cholesky_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 linalg_cholesky(const at::Tensor & self, bool upper=false);
+TORCH_API at::Tensor & linalg_cholesky_out(const at::Tensor & self, bool upper, at::Tensor & out);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_svdvals_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 linalg_svdvals(const at::Tensor & A, ::std::optional<c10::string_view> driver=::std::nullopt);
+TORCH_API at::Tensor & linalg_svdvals_out(const at::Tensor & A, ::std::optional<c10::string_view> driver, at::Tensor & out);
+} // namespace native
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_backward_cuda_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 cuda {
+
+TORCH_API at::Tensor max_pool2d_with_indices_backward(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices);
+TORCH_API at::Tensor & max_pool2d_with_indices_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices);
+TORCH_API at::Tensor & max_pool2d_with_indices_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices, at::Tensor & grad_input);
+
+} // namespace cuda
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_convolution_add_relu_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 miopen_convolution_add_relu {
+  using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, const ::std::optional<at::Scalar> &, const ::std::optional<at::Tensor> &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymInt);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::miopen_convolution_add_relu")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "miopen_convolution_add_relu(Tensor self, Tensor weight, Tensor z, Scalar? alpha, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, SymInt groups) -> Tensor")
+  static at::Tensor call(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);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, 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);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mish_cpu_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 cpu {
+
+TORCH_API at::Tensor mish(const at::Tensor & self);
+TORCH_API at::Tensor & mish_out(at::Tensor & out, const at::Tensor & self);
+TORCH_API at::Tensor & mish_outf(const at::Tensor & self, at::Tensor & out);
+TORCH_API at::Tensor & mish_(at::Tensor & self);
+
+} // namespace cpu
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool3d_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/mkldnn_max_pool3d_backward_ops.h>
+
+namespace at {
+
+
+// aten::mkldnn_max_pool3d_backward(Tensor grad_output, Tensor output, Tensor input, int[3] kernel_size, int[3] stride=[], int[3] padding=0, int[3] dilation=1, bool ceil_mode=False) -> Tensor
+inline at::Tensor mkldnn_max_pool3d_backward(const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & input, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false) {
+    return at::_ops::mkldnn_max_pool3d_backward::call(grad_output, output, input, kernel_size, stride, padding, dilation, ceil_mode);
+}
+
+// aten::mkldnn_max_pool3d_backward.out(Tensor grad_output, Tensor output, Tensor input, int[3] kernel_size, int[3] stride=[], int[3] padding=0, int[3] dilation=1, bool ceil_mode=False, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & mkldnn_max_pool3d_backward_out(at::Tensor & out, const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & input, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false) {
+    return at::_ops::mkldnn_max_pool3d_backward_out::call(grad_output, output, input, kernel_size, stride, padding, dilation, ceil_mode, out);
+}
+// aten::mkldnn_max_pool3d_backward.out(Tensor grad_output, Tensor output, Tensor input, int[3] kernel_size, int[3] stride=[], int[3] padding=0, int[3] dilation=1, bool ceil_mode=False, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & mkldnn_max_pool3d_backward_outf(const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & input, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out) {
+    return at::_ops::mkldnn_max_pool3d_backward_out::call(grad_output, output, input, kernel_size, stride, padding, dilation, ceil_mode, out);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mv_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 mv {
+  using schema = at::Tensor (const 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::mv")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mv(Tensor self, Tensor vec) -> Tensor")
+  static at::Tensor call(const at::Tensor & self, const at::Tensor & vec);
+  static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & vec);
+};
+
+struct TORCH_API mv_out {
+  using schema = at::Tensor & (const 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::mv")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mv.out(Tensor self, Tensor vec, *, Tensor(a!) out) -> Tensor(a!)")
+  static at::Tensor & call(const at::Tensor & self, const at::Tensor & vec, at::Tensor & out);
+  static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & vec, at::Tensor & out);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_batch_norm_backward_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 native_batch_norm_backward {
+  using schema = ::std::tuple<at::Tensor,at::Tensor,at::Tensor> (const at::Tensor &, const at::Tensor &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, bool, double, ::std::array<bool,3>);
+  using ptr_schema = schema*;
+  // See Note [static constexpr char* members for windows NVCC]
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::native_batch_norm_backward")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "native_batch_norm_backward(Tensor grad_out, Tensor input, Tensor? weight, Tensor? running_mean, Tensor? running_var, Tensor? save_mean, Tensor? save_invstd, bool train, float eps, bool[3] output_mask) -> (Tensor, Tensor, Tensor)")
+  static ::std::tuple<at::Tensor,at::Tensor,at::Tensor> call(const at::Tensor & grad_out, const at::Tensor & input, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & running_mean, const ::std::optional<at::Tensor> & running_var, const ::std::optional<at::Tensor> & save_mean, const ::std::optional<at::Tensor> & save_invstd, bool train, double eps, ::std::array<bool,3> output_mask);
+  static ::std::tuple<at::Tensor,at::Tensor,at::Tensor> redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_out, const at::Tensor & input, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & running_mean, const ::std::optional<at::Tensor> & running_var, const ::std::optional<at::Tensor> & save_mean, const ::std::optional<at::Tensor> & save_invstd, bool train, double eps, ::std::array<bool,3> output_mask);
+};
+
+struct TORCH_API native_batch_norm_backward_out {
+  using schema = ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &> (const at::Tensor &, const at::Tensor &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, const ::std::optional<at::Tensor> &, bool, double, ::std::array<bool,3>, at::Tensor &, 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::native_batch_norm_backward")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out")
+  STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "native_batch_norm_backward.out(Tensor grad_out, Tensor input, Tensor? weight, Tensor? running_mean, Tensor? running_var, Tensor? save_mean, Tensor? save_invstd, bool train, float eps, bool[3] output_mask, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2) -> (Tensor(a!), Tensor(b!), Tensor(c!))")
+  static ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &> call(const at::Tensor & grad_out, const at::Tensor & input, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & running_mean, const ::std::optional<at::Tensor> & running_var, const ::std::optional<at::Tensor> & save_mean, const ::std::optional<at::Tensor> & save_invstd, bool train, double eps, ::std::array<bool,3> output_mask, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2);
+  static ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &> redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_out, const at::Tensor & input, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & running_mean, const ::std::optional<at::Tensor> & running_var, const ::std::optional<at::Tensor> & save_mean, const ::std::optional<at::Tensor> & save_invstd, bool train, double eps, ::std::array<bool,3> output_mask, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2);
+};
+
+}} // namespace at::_ops

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_batch_norm_cuda_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 cuda {
+
+TORCH_API ::std::tuple<at::Tensor,at::Tensor,at::Tensor> native_batch_norm(const at::Tensor & input, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & bias, const ::std::optional<at::Tensor> & running_mean, const ::std::optional<at::Tensor> & running_var, bool training, double momentum, double eps);
+TORCH_API ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &> native_batch_norm_out(at::Tensor & out, at::Tensor & save_mean, at::Tensor & save_invstd, const at::Tensor & input, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & bias, const ::std::optional<at::Tensor> & running_mean, const ::std::optional<at::Tensor> & running_var, bool training, double momentum, double eps);
+TORCH_API ::std::tuple<at::Tensor &,at::Tensor &,at::Tensor &> native_batch_norm_outf(const at::Tensor & input, const ::std::optional<at::Tensor> & weight, const ::std::optional<at::Tensor> & bias, const ::std::optional<at::Tensor> & running_mean, const ::std::optional<at::Tensor> & running_var, bool training, double momentum, double eps, at::Tensor & out, at::Tensor & save_mean, at::Tensor & save_invstd);
+
+} // namespace cuda
+} // namespace at

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/permute.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/permute_ops.h>
+
+namespace at {
+
+
+// aten::permute(Tensor(a) self, int[] dims) -> Tensor(a)
+inline at::Tensor permute(const at::Tensor & self, at::IntArrayRef dims) {
+    return at::_ops::permute::call(self, dims);
+}
+
+}

.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pixel_shuffle.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/pixel_shuffle_ops.h>
+
+namespace at {
+
+
+// aten::pixel_shuffle(Tensor self, int upscale_factor) -> Tensor
+inline at::Tensor pixel_shuffle(const at::Tensor & self, int64_t upscale_factor) {
+    return at::_ops::pixel_shuffle::call(self, upscale_factor);
+}
+
+// aten::pixel_shuffle.out(Tensor self, int upscale_factor, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & pixel_shuffle_out(at::Tensor & out, const at::Tensor & self, int64_t upscale_factor) {
+    return at::_ops::pixel_shuffle_out::call(self, upscale_factor, out);
+}
+// aten::pixel_shuffle.out(Tensor self, int upscale_factor, *, Tensor(a!) out) -> Tensor(a!)
+inline at::Tensor & pixel_shuffle_outf(const at::Tensor & self, int64_t upscale_factor, at::Tensor & out) {
+    return at::_ops::pixel_shuffle_out::call(self, upscale_factor, out);
+}
+
+}