diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_adaptive_avg_pool3d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_adaptive_avg_pool3d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5ec299d29b0884e4ba3b5db3e0fa9876fc851140 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_adaptive_avg_pool3d_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API _adaptive_avg_pool3d { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_adaptive_avg_pool3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_adaptive_avg_pool3d(Tensor self, SymInt[3] output_size) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef output_size); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef output_size); +}; + +struct TORCH_API _adaptive_avg_pool3d_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymIntArrayRef, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_adaptive_avg_pool3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_adaptive_avg_pool3d.out(Tensor self, SymInt[3] output_size, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::SymIntArrayRef output_size, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef output_size, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cummax_helper_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cummax_helper_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..64db1f76c08e21e67a590c1f3c93cc73a524a2ac --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cummax_helper_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 +#include +#include + +// 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 + +namespace at { + +namespace cpu { + +TORCH_API void _cummax_helper(const at::Tensor & self, at::Tensor & values, at::Tensor & indices, int64_t dim); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_learnable_per_tensor_affine_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_learnable_per_tensor_affine_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..e78a05dd3a2d7e0642ede3f7a1b863b9817bea3a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_learnable_per_tensor_affine_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API _fake_quantize_learnable_per_tensor_affine { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, int64_t, double); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_fake_quantize_learnable_per_tensor_affine") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_fake_quantize_learnable_per_tensor_affine(Tensor self, Tensor scale, Tensor zero_point, int quant_min, int quant_max, float grad_factor=1.0) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t quant_min, int64_t quant_max, double grad_factor); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t quant_min, int64_t quant_max, double grad_factor); +}; + +struct TORCH_API _fake_quantize_learnable_per_tensor_affine_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, int64_t, double, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_fake_quantize_learnable_per_tensor_affine") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_fake_quantize_learnable_per_tensor_affine.out(Tensor self, Tensor scale, Tensor zero_point, int quant_min, int quant_max, float grad_factor=1.0, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t quant_min, int64_t quant_max, double grad_factor, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t quant_min, int64_t quant_max, double grad_factor, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_asin.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_asin.h new file mode 100644 index 0000000000000000000000000000000000000000..3b4a0adb20a0fa3a5daa757cc3d84df97ae95653 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_asin.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_foreach_asin(Tensor[] self) -> Tensor[] +inline ::std::vector _foreach_asin(at::TensorList self) { + return at::_ops::_foreach_asin::call(self); +} + +// aten::_foreach_asin_(Tensor(a!)[] self) -> () +inline void _foreach_asin_(at::TensorList self) { + return at::_ops::_foreach_asin_::call(self); +} + +// aten::_foreach_asin.out(Tensor[] self, *, Tensor(a!)[] out) -> () +inline void _foreach_asin_out(at::TensorList out, at::TensorList self) { + return at::_ops::_foreach_asin_out::call(self, out); +} +// aten::_foreach_asin.out(Tensor[] self, *, Tensor(a!)[] out) -> () +inline void _foreach_asin_outf(at::TensorList self, at::TensorList out) { + return at::_ops::_foreach_asin_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_frac_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_frac_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..be2715382e60a5ef9e942bdf1932e524d7276299 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_frac_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API ::std::vector _foreach_frac(at::TensorList self); +TORCH_API void _foreach_frac_(at::TensorList self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log2_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log2_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ea6cd9a690771fbf690e9e97cf28af4d2b296d61 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log2_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API void _foreach_log2_out(at::TensorList out, at::TensorList self); +TORCH_API void _foreach_log2_outf(at::TensorList self, at::TensorList out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt.h new file mode 100644 index 0000000000000000000000000000000000000000..84400e1dd4cb00304502d931c31f67358ee2e0aa --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_foreach_sqrt(Tensor[] self) -> Tensor[] +inline ::std::vector _foreach_sqrt(at::TensorList self) { + return at::_ops::_foreach_sqrt::call(self); +} + +// aten::_foreach_sqrt_(Tensor(a!)[] self) -> () +inline void _foreach_sqrt_(at::TensorList self) { + return at::_ops::_foreach_sqrt_::call(self); +} + +// aten::_foreach_sqrt.out(Tensor[] self, *, Tensor(a!)[] out) -> () +inline void _foreach_sqrt_out(at::TensorList out, at::TensorList self) { + return at::_ops::_foreach_sqrt_out::call(self, out); +} +// aten::_foreach_sqrt.out(Tensor[] self, *, Tensor(a!)[] out) -> () +inline void _foreach_sqrt_outf(at::TensorList self, at::TensorList out) { + return at::_ops::_foreach_sqrt_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_mask_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_mask_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cbbdcbd019121541d352e98b4936e0099c9dad54 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor _nested_tensor_from_mask(const at::Tensor & t, const at::Tensor & mask, bool mask_check=true); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_tensor_list_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_tensor_list_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4a4b019d6267307307b9e95d5e1b2508384e6d23 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_tensor_list_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor _nested_tensor_from_tensor_list(at::TensorList list, c10::optional dtype=c10::nullopt, c10::optional layout=c10::nullopt, c10::optional device=c10::nullopt, c10::optional pin_memory=c10::nullopt); +TORCH_API at::Tensor & _nested_tensor_from_tensor_list_out(at::Tensor & out, at::TensorList list, c10::optional dtype=c10::nullopt, c10::optional layout=c10::nullopt, c10::optional device=c10::nullopt, c10::optional pin_memory=c10::nullopt); +TORCH_API at::Tensor & _nested_tensor_from_tensor_list_outf(at::TensorList list, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_copy_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_copy_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3e821e42b1d1babf4976f8eb415c4e659987dbf5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_copy_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & _nested_view_from_jagged_copy_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & offsets, const at::Tensor & dummy, const c10::optional & lengths={}, int64_t ragged_idx=1); +TORCH_API at::Tensor & _nested_view_from_jagged_copy_outf(const at::Tensor & self, const at::Tensor & offsets, const at::Tensor & dummy, const c10::optional & lengths, int64_t ragged_idx, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_propagate_xla_data_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_propagate_xla_data_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..8a00740618fe20ea073354ac1ee433cd86810bd0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_propagate_xla_data_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API _propagate_xla_data { + using schema = void (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::_propagate_xla_data") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_propagate_xla_data(Tensor input, Tensor output) -> ()") + static void call(const at::Tensor & input, const at::Tensor & output); + static void redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const at::Tensor & output); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_efficient_attention_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_efficient_attention_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..28eec721e84b0a1355ec708aee24e680a50b5797 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_efficient_attention_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API ::std::tuple _scaled_dot_product_efficient_attention(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const c10::optional & attn_bias, bool compute_log_sumexp, double dropout_p=0.0, bool is_causal=false, c10::optional scale=c10::nullopt); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_coo_tensor_with_dims.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_coo_tensor_with_dims.h new file mode 100644 index 0000000000000000000000000000000000000000..209eb3ccef96f290164785c736c4dde47c14618d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_coo_tensor_with_dims.h @@ -0,0 +1,43 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_sparse_coo_tensor_with_dims(int sparse_dim, int dense_dim, int[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=False) -> Tensor +inline at::Tensor _sparse_coo_tensor_with_dims(int64_t sparse_dim, int64_t dense_dim, at::IntArrayRef size, at::TensorOptions options) { + return at::_ops::_sparse_coo_tensor_with_dims::call(sparse_dim, dense_dim, size, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +// aten::_sparse_coo_tensor_with_dims(int sparse_dim, int dense_dim, int[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=False) -> Tensor +inline at::Tensor _sparse_coo_tensor_with_dims(int64_t sparse_dim, int64_t dense_dim, at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::_sparse_coo_tensor_with_dims::call(sparse_dim, dense_dim, size, dtype, layout, device, pin_memory); +} + +// aten::_sparse_coo_tensor_with_dims.out(int sparse_dim, int dense_dim, int[] size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _sparse_coo_tensor_with_dims_out(at::Tensor & out, int64_t sparse_dim, int64_t dense_dim, at::IntArrayRef size) { + return at::_ops::_sparse_coo_tensor_with_dims_out::call(sparse_dim, dense_dim, size, out); +} +// aten::_sparse_coo_tensor_with_dims.out(int sparse_dim, int dense_dim, int[] size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _sparse_coo_tensor_with_dims_outf(int64_t sparse_dim, int64_t dense_dim, at::IntArrayRef size, at::Tensor & out) { + return at::_ops::_sparse_coo_tensor_with_dims_out::call(sparse_dim, dense_dim, size, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_sparse_matmul_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_sparse_matmul_native.h new file mode 100644 index 0000000000000000000000000000000000000000..594af3b59ccfb046cafa0bed42972d3998c1c6d2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_sparse_matmul_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor & _sparse_sparse_matmul_out(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor sparse_sparse_matmul_cpu(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor sparse_sparse_matmul_cuda(const at::Tensor & self, const at::Tensor & other); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..55be257872606a14eb4dfa16639dce066b3e6aac --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple _thnn_differentiable_gru_cell_backward(const at::Tensor & grad_hy, const at::Tensor & input_gates, const at::Tensor & hidden_gates, const at::Tensor & hx, const c10::optional & input_bias, const c10::optional & hidden_bias); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_semi_structured_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_semi_structured_native.h new file mode 100644 index 0000000000000000000000000000000000000000..a40b83487868746413074479be59a95ab4547014 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_semi_structured_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple _to_sparse_semi_structured(const at::Tensor & dense); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa.h new file mode 100644 index 0000000000000000000000000000000000000000..239adc042e957e59a236d3c02daf358381f64c0e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa.h @@ -0,0 +1,113 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_upsample_bilinear2d_aa.vec(Tensor input, SymInt[]? output_size, bool align_corners, float[]? scale_factors) -> Tensor +inline at::Tensor _upsample_bilinear2d_aa(const at::Tensor & input, at::OptionalIntArrayRef output_size, bool align_corners, c10::optional> scale_factors) { + return at::_ops::_upsample_bilinear2d_aa_vec::call(input, output_size.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*output_size)) : c10::nullopt, align_corners, scale_factors); +} +namespace symint { + template ::value>> + at::Tensor _upsample_bilinear2d_aa(const at::Tensor & input, at::OptionalIntArrayRef output_size, bool align_corners, c10::optional> scale_factors) { + return at::_ops::_upsample_bilinear2d_aa_vec::call(input, output_size.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*output_size)) : c10::nullopt, align_corners, scale_factors); + } +} + +// aten::_upsample_bilinear2d_aa.vec(Tensor input, SymInt[]? output_size, bool align_corners, float[]? scale_factors) -> Tensor +inline at::Tensor _upsample_bilinear2d_aa_symint(const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors) { + return at::_ops::_upsample_bilinear2d_aa_vec::call(input, output_size, align_corners, scale_factors); +} +namespace symint { + template ::value>> + at::Tensor _upsample_bilinear2d_aa(const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors) { + return at::_ops::_upsample_bilinear2d_aa_vec::call(input, output_size, align_corners, scale_factors); + } +} + +// aten::_upsample_bilinear2d_aa.out(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _upsample_bilinear2d_aa_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::_upsample_bilinear2d_aa_out::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_h, scales_w, out); +} +namespace symint { + template ::value>> + at::Tensor & _upsample_bilinear2d_aa_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::_upsample_bilinear2d_aa_out::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_h, scales_w, out); + } +} + +// aten::_upsample_bilinear2d_aa.out(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _upsample_bilinear2d_aa_outf(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w, at::Tensor & out) { + return at::_ops::_upsample_bilinear2d_aa_out::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_h, scales_w, out); +} +namespace symint { + template ::value>> + at::Tensor & _upsample_bilinear2d_aa_outf(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w, at::Tensor & out) { + return at::_ops::_upsample_bilinear2d_aa_out::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_h, scales_w, out); + } +} + +// aten::_upsample_bilinear2d_aa.out(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _upsample_bilinear2d_aa_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::_upsample_bilinear2d_aa_out::call(self, output_size, align_corners, scales_h, scales_w, out); +} +namespace symint { + template ::value>> + at::Tensor & _upsample_bilinear2d_aa_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::_upsample_bilinear2d_aa_out::call(self, output_size, align_corners, scales_h, scales_w, out); + } +} + +// aten::_upsample_bilinear2d_aa.out(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _upsample_bilinear2d_aa_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w, at::Tensor & out) { + return at::_ops::_upsample_bilinear2d_aa_out::call(self, output_size, align_corners, scales_h, scales_w, out); +} +namespace symint { + template ::value>> + at::Tensor & _upsample_bilinear2d_aa_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w, at::Tensor & out) { + return at::_ops::_upsample_bilinear2d_aa_out::call(self, output_size, align_corners, scales_h, scales_w, out); + } +} + +// aten::_upsample_bilinear2d_aa(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None) -> Tensor +inline at::Tensor _upsample_bilinear2d_aa(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::_upsample_bilinear2d_aa::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_h, scales_w); +} +namespace symint { + template ::value>> + at::Tensor _upsample_bilinear2d_aa(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::_upsample_bilinear2d_aa::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_h, scales_w); + } +} + +// aten::_upsample_bilinear2d_aa(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None) -> Tensor +inline at::Tensor _upsample_bilinear2d_aa_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::_upsample_bilinear2d_aa::call(self, output_size, align_corners, scales_h, scales_w); +} +namespace symint { + template ::value>> + at::Tensor _upsample_bilinear2d_aa(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::_upsample_bilinear2d_aa::call(self, output_size, align_corners, scales_h, scales_w); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addr.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addr.h new file mode 100644 index 0000000000000000000000000000000000000000..4d28c4de3f7fb3242f947d13773ff17baef9ad23 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addr.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::addr(Tensor self, Tensor vec1, Tensor vec2, *, Scalar beta=1, Scalar alpha=1) -> Tensor +inline at::Tensor addr(const at::Tensor & self, const at::Tensor & vec1, const at::Tensor & vec2, const at::Scalar & beta=1, const at::Scalar & alpha=1) { + return at::_ops::addr::call(self, vec1, vec2, beta, alpha); +} + +// aten::addr.out(Tensor self, Tensor vec1, Tensor vec2, *, Scalar beta=1, Scalar alpha=1, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & addr_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & vec1, const at::Tensor & vec2, const at::Scalar & beta=1, const at::Scalar & alpha=1) { + return at::_ops::addr_out::call(self, vec1, vec2, beta, alpha, out); +} +// aten::addr.out(Tensor self, Tensor vec1, Tensor vec2, *, Scalar beta=1, Scalar alpha=1, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & addr_outf(const at::Tensor & self, const at::Tensor & vec1, const at::Tensor & vec2, const at::Scalar & beta, const at::Scalar & alpha, at::Tensor & out) { + return at::_ops::addr_out::call(self, vec1, vec2, beta, alpha, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/all_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/all_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d1e71888d22493972849fedf700d9fbdae737cd3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/all_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor all(const at::Tensor & self, at::Dimname dim, bool keepdim=false); +TORCH_API at::Tensor & all_out(at::Tensor & out, const at::Tensor & self, at::Dimname dim, bool keepdim=false); +TORCH_API at::Tensor & all_outf(const at::Tensor & self, at::Dimname dim, bool keepdim, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atanh_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atanh_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..401c0f867307016cbcc059646523bfb116459357 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atanh_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor atanh(const at::Tensor & self); +TORCH_API at::Tensor & atanh_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & atanh_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & atanh_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bartlett_window_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bartlett_window_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..05f8e3fb21f21825abad1674ea2aebef79db4c43 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bartlett_window_ops.h @@ -0,0 +1,61 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API bartlett_window { + using schema = at::Tensor (int64_t, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::bartlett_window") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bartlett_window(int window_length, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(int64_t window_length, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, int64_t window_length, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API bartlett_window_periodic { + using schema = at::Tensor (int64_t, bool, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::bartlett_window") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "periodic") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bartlett_window.periodic(int window_length, bool periodic, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(int64_t window_length, bool periodic, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, int64_t window_length, bool periodic, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API bartlett_window_out { + using schema = at::Tensor & (int64_t, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::bartlett_window") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bartlett_window.out(int window_length, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(int64_t window_length, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, int64_t window_length, at::Tensor & out); +}; + +struct TORCH_API bartlett_window_periodic_out { + using schema = 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::bartlett_window") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "periodic_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bartlett_window.periodic_out(int window_length, bool periodic, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(int64_t window_length, bool periodic, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, int64_t window_length, bool periodic, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_gather_stats_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_gather_stats_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..eaddf3f88a2d9f6346a7f6d3229bf59d4533c437 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_gather_stats_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API batch_norm_gather_stats { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, const c10::optional &, const c10::optional &, double, double, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::batch_norm_gather_stats") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "batch_norm_gather_stats(Tensor input, Tensor mean, Tensor invstd, Tensor? running_mean, Tensor? running_var, float momentum, float eps, int count) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & input, const at::Tensor & mean, const at::Tensor & invstd, const c10::optional & running_mean, const c10::optional & running_var, double momentum, double eps, int64_t count); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const at::Tensor & mean, const at::Tensor & invstd, const c10::optional & running_mean, const c10::optional & running_var, double momentum, double eps, int64_t count); +}; + +struct TORCH_API batch_norm_gather_stats_out { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, const c10::optional &, const c10::optional &, double, double, int64_t, 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::batch_norm_gather_stats") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "batch_norm_gather_stats.out(Tensor input, Tensor mean, Tensor invstd, Tensor? running_mean, Tensor? running_var, float momentum, float eps, int count, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!))") + static ::std::tuple call(const at::Tensor & input, const at::Tensor & mean, const at::Tensor & invstd, const c10::optional & running_mean, const c10::optional & running_var, double momentum, double eps, int64_t count, at::Tensor & out0, at::Tensor & out1); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const at::Tensor & mean, const at::Tensor & invstd, const c10::optional & running_mean, const c10::optional & running_var, double momentum, double eps, int64_t count, at::Tensor & out0, at::Tensor & out1); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_and_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_and_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..af66882c390b5aed1ad14bff4b0cce3692b18de0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_and_ops.h @@ -0,0 +1,105 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API bitwise_and_Tensor_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::bitwise_and") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bitwise_and.Tensor_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 bitwise_and_Scalar_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::bitwise_and") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bitwise_and.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +}; + +struct TORCH_API bitwise_and_Scalar { + 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::bitwise_and") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bitwise_and.Scalar(Tensor self, Scalar other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Scalar & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API bitwise_and_Scalar_Tensor { + using schema = at::Tensor (const at::Scalar &, 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::bitwise_and") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bitwise_and.Scalar_Tensor(Scalar self, Tensor other) -> Tensor") + static at::Tensor call(const at::Scalar & self, const at::Tensor & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & self, const at::Tensor & other); +}; + +struct TORCH_API bitwise_and_Tensor { + 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::bitwise_and") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bitwise_and.Tensor(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 bitwise_and__Scalar { + using schema = at::Tensor & (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::bitwise_and_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bitwise_and_.Scalar(Tensor(a!) self, Scalar other) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Scalar & other); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API bitwise_and__Tensor { + 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::bitwise_and_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bitwise_and_.Tensor(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); +}; + +struct TORCH_API bitwise_and_Scalar_Tensor_out { + using schema = at::Tensor & (const at::Scalar &, 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::bitwise_and") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Tensor_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bitwise_and.Scalar_Tensor_out(Scalar self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Scalar & self, const at::Tensor & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & self, const at::Tensor & other, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..5733f2659d9b6989746203c9dbf372a53f02c823 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_bitwise_left_shift_Tensor : public TensorIteratorBase { + + + void meta(const at::Tensor & self, const at::Tensor & other); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bucketize_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bucketize_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..f3be8c9b37e4670f3bab27a318a70bf52536a0e9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bucketize_ops.h @@ -0,0 +1,61 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API bucketize_Tensor { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, bool, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::bucketize") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bucketize.Tensor(Tensor self, Tensor boundaries, *, bool out_int32=False, bool right=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & boundaries, bool out_int32, bool right); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & boundaries, bool out_int32, bool right); +}; + +struct TORCH_API bucketize_Tensor_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, bool, 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::bucketize") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bucketize.Tensor_out(Tensor self, Tensor boundaries, *, bool out_int32=False, bool right=False, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & boundaries, bool out_int32, bool right, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & boundaries, bool out_int32, bool right, at::Tensor & out); +}; + +struct TORCH_API bucketize_Scalar { + using schema = at::Tensor (const at::Scalar &, const at::Tensor &, bool, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::bucketize") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bucketize.Scalar(Scalar self, Tensor boundaries, *, bool out_int32=False, bool right=False) -> Tensor") + static at::Tensor call(const at::Scalar & self, const at::Tensor & boundaries, bool out_int32, bool right); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & self, const at::Tensor & boundaries, bool out_int32, bool right); +}; + +struct TORCH_API bucketize_Scalar_out { + using schema = at::Tensor & (const at::Scalar &, const at::Tensor &, bool, 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::bucketize") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bucketize.Scalar_out(Scalar self, Tensor boundaries, *, bool out_int32=False, bool right=False, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Scalar & self, const at::Tensor & boundaries, bool out_int32, bool right, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & self, const at::Tensor & boundaries, bool out_int32, bool right, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cdist_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cdist_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..9ed688fee794747e93e232b5c32d59d20c9acf20 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cdist_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API cdist { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, double, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cdist") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cdist(Tensor x1, Tensor x2, float p=2, int? compute_mode=None) -> Tensor") + static at::Tensor call(const at::Tensor & x1, const at::Tensor & x2, double p, c10::optional compute_mode); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x1, const at::Tensor & x2, double p, c10::optional compute_mode); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/col_indices_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/col_indices_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..536cf3af66c2d33d5bec95449491fe75fec28f52 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/col_indices_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API col_indices { + 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") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "col_indices(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 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diag.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diag.h new file mode 100644 index 0000000000000000000000000000000000000000..743e10ccdbddbf0e9de78265e31672d8d4dcc5e0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diag.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::diag.out(Tensor self, int diagonal=0, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & diag_out(at::Tensor & out, const at::Tensor & self, int64_t diagonal=0) { + return at::_ops::diag_out::call(self, diagonal, out); +} +// aten::diag.out(Tensor self, int diagonal=0, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & diag_outf(const at::Tensor & self, int64_t diagonal, at::Tensor & out) { + return at::_ops::diag_out::call(self, diagonal, out); +} + +// aten::diag(Tensor self, int diagonal=0) -> Tensor +inline at::Tensor diag(const at::Tensor & self, int64_t diagonal=0) { + return at::_ops::diag::call(self, diagonal); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_copy_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_copy_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..46489889de9e731e487078f8ea0742bc58d12a24 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_copy_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & diagonal_copy_out(at::Tensor & out, const at::Tensor & self, int64_t offset=0, int64_t dim1=0, int64_t dim2=1); +TORCH_API at::Tensor & diagonal_copy_outf(const at::Tensor & self, int64_t offset, int64_t dim1, int64_t dim2, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/elu_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/elu_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7614c28971d57ad6ef15181805dbe18eec45e09b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/elu_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API elu_backward_grad_input { + using schema = at::Tensor & (const at::Tensor &, const at::Scalar &, const at::Scalar &, const at::Scalar &, bool, 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::elu_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "grad_input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "elu_backward.grad_input(Tensor grad_output, Scalar alpha, Scalar scale, Scalar input_scale, bool is_result, Tensor self_or_result, *, Tensor(a!) grad_input) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Scalar & alpha, const at::Scalar & scale, const at::Scalar & input_scale, bool is_result, const at::Tensor & self_or_result, at::Tensor & grad_input); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Scalar & alpha, const at::Scalar & scale, const at::Scalar & input_scale, bool is_result, const at::Tensor & self_or_result, at::Tensor & grad_input); +}; + +struct TORCH_API elu_backward { + using schema = at::Tensor (const at::Tensor &, const at::Scalar &, const at::Scalar &, const at::Scalar &, bool, 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::elu_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "elu_backward(Tensor grad_output, Scalar alpha, Scalar scale, Scalar input_scale, bool is_result, Tensor self_or_result) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Scalar & alpha, const at::Scalar & scale, const at::Scalar & input_scale, bool is_result, const at::Tensor & self_or_result); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Scalar & alpha, const at::Scalar & scale, const at::Scalar & input_scale, bool is_result, const at::Tensor & self_or_result); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/eye_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/eye_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..38f15587a8ef70fb221392d51d220192b0ed50f6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/eye_meta_dispatch.h @@ -0,0 +1,30 @@ +#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 +#include +#include + +// 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 + +namespace at { + +namespace meta { + +TORCH_API at::Tensor & eye_out(at::Tensor & out, int64_t n); +TORCH_API at::Tensor & eye_outf(int64_t n, at::Tensor & out); +TORCH_API at::Tensor & eye_symint_out(at::Tensor & out, c10::SymInt n); +TORCH_API at::Tensor & eye_symint_outf(c10::SymInt n, at::Tensor & out); +TORCH_API at::Tensor & eye_out(at::Tensor & out, int64_t n, int64_t m); +TORCH_API at::Tensor & eye_outf(int64_t n, int64_t m, at::Tensor & out); +TORCH_API at::Tensor & eye_symint_out(at::Tensor & out, c10::SymInt n, c10::SymInt m); +TORCH_API at::Tensor & eye_symint_outf(c10::SymInt n, c10::SymInt m, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_fft2_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_fft2_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..44d85e18e43149bda00a588ee76da97e11734f94 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_fft2_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API fft_fft2 { + using schema = at::Tensor (const at::Tensor &, at::OptionalSymIntArrayRef, at::IntArrayRef, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::fft_fft2") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fft_fft2(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm); +}; + +struct TORCH_API fft_fft2_out { + using schema = at::Tensor & (const at::Tensor &, at::OptionalSymIntArrayRef, at::IntArrayRef, c10::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::fft_fft2") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fft_fft2.out(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igammac_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igammac_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..fa16a552675b499c3c2295b09f8f085a807e4803 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igammac_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_igammac : public TensorIteratorBase { + + + void meta(const at::Tensor & self, const at::Tensor & other); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_coalesced_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_coalesced_native.h new file mode 100644 index 0000000000000000000000000000000000000000..4698de0b1d4da3a745a6a1bfc1d11d93da8b7a42 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_coalesced_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API bool is_coalesced_default(const at::Tensor & self); +TORCH_API bool is_coalesced_sparse(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_norm_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_norm_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3684c2dde5e902f7cfd6c09844e66c4eebcce5fd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_norm_compositeimplicitautograd_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor linalg_norm(const at::Tensor & self, const c10::optional & ord=c10::nullopt, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & linalg_norm_out(at::Tensor & out, const at::Tensor & self, const c10::optional & ord=c10::nullopt, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & linalg_norm_outf(const at::Tensor & self, const c10::optional & ord, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype, at::Tensor & out); +TORCH_API at::Tensor linalg_norm(const at::Tensor & self, c10::string_view ord, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & linalg_norm_out(at::Tensor & out, const at::Tensor & self, c10::string_view ord, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & linalg_norm_outf(const at::Tensor & self, c10::string_view ord, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lt_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lt_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..dce5c55d8f7891f3aeef763d7b5e78339a82b305 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lt_ops.h @@ -0,0 +1,83 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API lt_Scalar_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::lt") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lt.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +}; + +struct TORCH_API lt_Scalar { + 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::lt") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lt.Scalar(Tensor self, Scalar other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Scalar & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API lt_Tensor_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::lt") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lt.Tensor_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 lt_Tensor { + 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::lt") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lt.Tensor(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 lt__Scalar { + using schema = at::Tensor & (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::lt_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lt_.Scalar(Tensor(a!) self, Scalar other) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Scalar & other); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API lt__Tensor { + 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::lt_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lt_.Tensor(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 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..d9ea382ff78ccc5770288d1b949cc464cb3a3db6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API masked_scatter_ { + using schema = at::Tensor & (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::masked_scatter_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "masked_scatter_(Tensor(a!) self, Tensor mask, Tensor source) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Tensor & mask, const at::Tensor & source); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Tensor & mask, const at::Tensor & source); +}; + +struct TORCH_API masked_scatter { + 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::masked_scatter") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "masked_scatter(Tensor self, Tensor mask, Tensor source) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & mask, const at::Tensor & source); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & mask, const at::Tensor & source); +}; + +struct TORCH_API masked_scatter_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::masked_scatter") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "masked_scatter.out(Tensor self, Tensor mask, Tensor source, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & mask, const at::Tensor & source, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & mask, const at::Tensor & source, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c06dee8eb07a091054df33e776d9b1046efbf621 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_compositeimplicitautograd_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API ::std::tuple max(const at::Tensor & self, at::Dimname dim, bool keepdim=false); +TORCH_API ::std::tuple max_out(at::Tensor & max, at::Tensor & max_values, const at::Tensor & self, at::Dimname dim, bool keepdim=false); +TORCH_API ::std::tuple max_outf(const at::Tensor & self, at::Dimname dim, bool keepdim, at::Tensor & max, at::Tensor & max_values); +TORCH_API at::Tensor max(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & max_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & max_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..181d07fe0b6c14146025bc53aba090d3862a4cbb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor max_unpool2d(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size); +TORCH_API at::Tensor max_unpool2d_symint(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size); +TORCH_API at::Tensor & max_unpool2d_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size); +TORCH_API at::Tensor & max_unpool2d_outf(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::Tensor & out); +TORCH_API at::Tensor & max_unpool2d_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size); +TORCH_API at::Tensor & max_unpool2d_symint_outf(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..8255fc7c95260d71f74c4aed976127ce57609d7f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_native.h @@ -0,0 +1,24 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor max_unpooling2d_forward_cpu(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size); +TORCH_API at::Tensor & max_unpooling2d_forward_out_cpu(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::Tensor & out); +TORCH_API at::Tensor max_unpooling2d_forward_cuda(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size); +TORCH_API at::Tensor & max_unpooling2d_forward_out_cuda(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_batch_norm_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_batch_norm_native.h new file mode 100644 index 0000000000000000000000000000000000000000..0eebfdbab373ff676f78cebd322af811c45de5f9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_batch_norm_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple miopen_batch_norm_out(const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, const c10::optional & running_mean, const c10::optional & running_var, bool training, double exponential_average_factor, double epsilon, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); +TORCH_API ::std::tuple miopen_batch_norm(const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, const c10::optional & running_mean, const c10::optional & running_var, bool training, double exponential_average_factor, double epsilon); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_adaptive_avg_pool2d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_adaptive_avg_pool2d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..2ed1d1f8a48c2d5aaa5603c8261c8342793d45f3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_adaptive_avg_pool2d_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API mkldnn_adaptive_avg_pool2d { + using schema = at::Tensor (const at::Tensor &, at::IntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::mkldnn_adaptive_avg_pool2d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mkldnn_adaptive_avg_pool2d(Tensor self, int[2] output_size) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::IntArrayRef output_size); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef output_size); +}; + +struct TORCH_API mkldnn_adaptive_avg_pool2d_out { + using schema = at::Tensor & (const at::Tensor &, at::IntArrayRef, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::mkldnn_adaptive_avg_pool2d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mkldnn_adaptive_avg_pool2d.out(Tensor self, int[2] output_size, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::IntArrayRef output_size, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef output_size, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/msort_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/msort_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ffa025ccad40952c4c798d6fcb6464274d986dcc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/msort_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor msort(const at::Tensor & self); +TORCH_API at::Tensor & msort_out(const at::Tensor & self, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nan_to_num_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nan_to_num_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f9d12033fc87e73a6f6417df56bdf446093fe812 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nan_to_num_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor nan_to_num(const at::Tensor & self, c10::optional nan=c10::nullopt, c10::optional posinf=c10::nullopt, c10::optional neginf=c10::nullopt); +TORCH_API at::Tensor & nan_to_num_(at::Tensor & self, c10::optional nan=c10::nullopt, c10::optional posinf=c10::nullopt, c10::optional neginf=c10::nullopt); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/negative.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/negative.h new file mode 100644 index 0000000000000000000000000000000000000000..9ba0394665d5e06b3b4fc3e319eef7ddcacff4ab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/negative.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::negative(Tensor self) -> Tensor +inline at::Tensor negative(const at::Tensor & self) { + return at::_ops::negative::call(self); +} + +// aten::negative_(Tensor(a!) self) -> Tensor(a!) +inline at::Tensor & negative_(at::Tensor & self) { + return at::_ops::negative_::call(self); +} + +// aten::negative.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & negative_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::negative_out::call(self, out); +} +// aten::negative.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & negative_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::negative_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/new_empty_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/new_empty_native.h new file mode 100644 index 0000000000000000000000000000000000000000..448142a4dfae0486de6071cf83dbe3c071c7864c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/new_empty_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor new_empty_symint(const at::Tensor & self, c10::SymIntArrayRef size, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +TORCH_API at::Tensor & new_empty_out_symint(const at::Tensor & self, c10::SymIntArrayRef size, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/prod_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/prod_native.h new file mode 100644 index 0000000000000000000000000000000000000000..fc0af66d5d8e574fab688e13ade6e84c76ff2590 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/prod_native.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +TORCH_API at::Tensor & prod_out(const at::Tensor & self, c10::optional dtype, at::Tensor & out); +TORCH_API at::Tensor prod(const at::Tensor & self, c10::optional dtype=c10::nullopt); +struct TORCH_API structured_prod_out : public at::meta::structured_prod_dim_int { +void impl(const at::Tensor & self, int64_t dim, bool keepdim, c10::optional dtype, const at::Tensor & out); +}; +TORCH_API at::Tensor prod(const at::Tensor & self, at::Dimname dim, bool keepdim=false, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & prod_out(const at::Tensor & self, at::Dimname dim, bool keepdim, c10::optional dtype, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/put_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/put_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d52570b662c012d4b85b2ed292d7ba1abe029f41 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/put_meta_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 +#include +#include + +// 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 + +namespace at { + +namespace meta { + +TORCH_API at::Tensor & put_(at::Tensor & self, const at::Tensor & index, const at::Tensor & source, bool accumulate=false); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/quantized_max_pool2d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/quantized_max_pool2d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..69089ab49000a80b5012e8a0f0153d50254019b9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/quantized_max_pool2d_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API quantized_max_pool2d { + using schema = at::Tensor (const at::Tensor &, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::quantized_max_pool2d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "quantized_max_pool2d(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=0, int[2] dilation=1, bool ceil_mode=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode); +}; + +struct TORCH_API quantized_max_pool2d_out { + using schema = at::Tensor & (const at::Tensor &, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, 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::quantized_max_pool2d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "quantized_max_pool2d.out(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=0, int[2] dilation=1, bool ceil_mode=False, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/real_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/real_native.h new file mode 100644 index 0000000000000000000000000000000000000000..75b20319e2da6e700ec529d77e70bb6e57173c41 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/real_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor real(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad1d_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad1d_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e16a3d92e05fb9ab64fa472274a8fa86132560bb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad1d_cpu_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 +#include +#include + +// 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 + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor replication_pad1d(const at::Tensor & self, at::IntArrayRef padding); +TORCH_API at::Tensor replication_pad1d_symint(const at::Tensor & self, c10::SymIntArrayRef padding); +TORCH_API at::Tensor & replication_pad1d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef padding); +TORCH_API at::Tensor & replication_pad1d_outf(const at::Tensor & self, at::IntArrayRef padding, at::Tensor & out); +TORCH_API at::Tensor & replication_pad1d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef padding); +TORCH_API at::Tensor & replication_pad1d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef padding, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/row_indices_copy_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/row_indices_copy_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..6f21aa45924283f0ecf042b226317b9830237f7a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/row_indices_copy_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor row_indices_copy(const at::Tensor & self); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rrelu_with_noise.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rrelu_with_noise.h new file mode 100644 index 0000000000000000000000000000000000000000..f6da561fce188ce2c5b0bddab716b17fe5f6fa01 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rrelu_with_noise.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::rrelu_with_noise.out(Tensor self, Tensor noise, Scalar lower=0.125, Scalar upper=0.3333333333333333, bool training=False, Generator? generator=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & rrelu_with_noise_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & noise, const at::Scalar & lower=0.125, const at::Scalar & upper=0.3333333333333333, bool training=false, c10::optional generator=c10::nullopt) { + return at::_ops::rrelu_with_noise_out::call(self, noise, lower, upper, training, generator, out); +} +// aten::rrelu_with_noise.out(Tensor self, Tensor noise, Scalar lower=0.125, Scalar upper=0.3333333333333333, bool training=False, Generator? generator=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & rrelu_with_noise_outf(const at::Tensor & self, const at::Tensor & noise, const at::Scalar & lower, const at::Scalar & upper, bool training, c10::optional generator, at::Tensor & out) { + return at::_ops::rrelu_with_noise_out::call(self, noise, lower, upper, training, generator, out); +} + +// aten::rrelu_with_noise(Tensor self, Tensor noise, Scalar lower=0.125, Scalar upper=0.3333333333333333, bool training=False, Generator? generator=None) -> Tensor +inline at::Tensor rrelu_with_noise(const at::Tensor & self, const at::Tensor & noise, const at::Scalar & lower=0.125, const at::Scalar & upper=0.3333333333333333, bool training=false, c10::optional generator=c10::nullopt) { + return at::_ops::rrelu_with_noise::call(self, noise, lower, upper, training, generator); +} + +// aten::rrelu_with_noise_(Tensor(a!) self, Tensor noise, Scalar lower=0.125, Scalar upper=0.3333333333333333, bool training=False, Generator? generator=None) -> Tensor(a!) +inline at::Tensor & rrelu_with_noise_(at::Tensor & self, const at::Tensor & noise, const at::Scalar & lower=0.125, const at::Scalar & upper=0.3333333333333333, bool training=false, c10::optional generator=c10::nullopt) { + return at::_ops::rrelu_with_noise_::call(self, noise, lower, upper, training, generator); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_reduce_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_reduce_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2add648340654ab66e33c3e5775ee3e6a080966b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_reduce_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor scatter_reduce(const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & src, c10::string_view reduce, bool include_self=true); +TORCH_API at::Tensor & scatter_reduce_out(at::Tensor & out, const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & src, c10::string_view reduce, bool include_self=true); +TORCH_API at::Tensor & scatter_reduce_outf(const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & src, c10::string_view reduce, bool include_self, at::Tensor & out); +TORCH_API at::Tensor & scatter_reduce_(at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & src, c10::string_view reduce, bool include_self=true); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/select_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/select_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..be51f278ca681417c5f9eee0acbd5b3401855105 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/select_backward.h @@ -0,0 +1,91 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::select_backward(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt index) -> Tensor +inline at::Tensor select_backward(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t index) { + return at::_ops::select_backward::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, index); +} +namespace symint { + template ::value>> + at::Tensor select_backward(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t index) { + return at::_ops::select_backward::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, index); + } +} + +// aten::select_backward(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt index) -> Tensor +inline at::Tensor select_backward_symint(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt index) { + return at::_ops::select_backward::call(grad_output, input_sizes, dim, index); +} +namespace symint { + template ::value>> + at::Tensor select_backward(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt index) { + return at::_ops::select_backward::call(grad_output, input_sizes, dim, index); + } +} + +// aten::select_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt index, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & select_backward_out(at::Tensor & out, const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t index) { + return at::_ops::select_backward_out::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, index, out); +} +namespace symint { + template ::value>> + at::Tensor & select_backward_out(at::Tensor & out, const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t index) { + return at::_ops::select_backward_out::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, index, out); + } +} + +// aten::select_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt index, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & select_backward_outf(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t index, at::Tensor & out) { + return at::_ops::select_backward_out::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, index, out); +} +namespace symint { + template ::value>> + at::Tensor & select_backward_outf(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t index, at::Tensor & out) { + return at::_ops::select_backward_out::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, index, out); + } +} + +// aten::select_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt index, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & select_backward_symint_out(at::Tensor & out, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt index) { + return at::_ops::select_backward_out::call(grad_output, input_sizes, dim, index, out); +} +namespace symint { + template ::value>> + at::Tensor & select_backward_out(at::Tensor & out, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt index) { + return at::_ops::select_backward_out::call(grad_output, input_sizes, dim, index, out); + } +} + +// aten::select_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt index, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & select_backward_symint_outf(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt index, at::Tensor & out) { + return at::_ops::select_backward_out::call(grad_output, input_sizes, dim, index, out); +} +namespace symint { + template ::value>> + at::Tensor & select_backward_outf(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt index, at::Tensor & out) { + return at::_ops::select_backward_out::call(grad_output, input_sizes, dim, index, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..eb7daf678380c9f3efa3a3c1e3b7b938fbbf2e2d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_cuda_dispatch.h @@ -0,0 +1,27 @@ +#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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor & set_(at::Tensor & self, at::Storage source); +TORCH_API at::Tensor & set_(at::Tensor & self, at::Storage source, int64_t storage_offset, at::IntArrayRef size, at::IntArrayRef stride={}); +TORCH_API at::Tensor & set__symint(at::Tensor & self, at::Storage source, c10::SymInt storage_offset, c10::SymIntArrayRef size, c10::SymIntArrayRef stride={}); +TORCH_API at::Tensor & set_(at::Tensor & self, const at::Tensor & source); +TORCH_API at::Tensor & set_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..9f734516fc449a327784cc677c8e64f39ef13744 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smm_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API smm { + 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::smm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "smm(Tensor self, Tensor mat2) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & mat2); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & mat2); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softplus_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softplus_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..76674116588fd5dd0d9488cbe83fb08199b479e6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softplus_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor softplus(const at::Tensor & self, const at::Scalar & beta=1, const at::Scalar & threshold=20); +TORCH_API at::Tensor & softplus_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & beta=1, const at::Scalar & threshold=20); +TORCH_API at::Tensor & softplus_outf(const at::Tensor & self, const at::Scalar & beta, const at::Scalar & threshold, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..46752d2c17034617d6c46f3767e9a1b47d088d1a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_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 +#include +#include + +// 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 + +namespace at { + +namespace meta { + +TORCH_API at::Tensor softshrink(const at::Tensor & self, const at::Scalar & lambd=0.5); +TORCH_API at::Tensor & softshrink_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & lambd=0.5); +TORCH_API at::Tensor & softshrink_outf(const at::Tensor & self, const at::Scalar & lambd, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_resize.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_resize.h new file mode 100644 index 0000000000000000000000000000000000000000..84b9eccd266df12f8b8f0f6dd14f94a40274ff40 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_resize.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::sparse_resize.out(Tensor self, int[] size, int sparse_dim, int dense_dim, *, Tensor(a!) out) -> Tensor(a!) +inline const at::Tensor & sparse_resize_out(const at::Tensor & out, const at::Tensor & self, at::IntArrayRef size, int64_t sparse_dim, int64_t dense_dim) { + return at::_ops::sparse_resize_out::call(self, size, sparse_dim, dense_dim, out); +} +// aten::sparse_resize.out(Tensor self, int[] size, int sparse_dim, int dense_dim, *, Tensor(a!) out) -> Tensor(a!) +inline const at::Tensor & sparse_resize_outf(const at::Tensor & self, at::IntArrayRef size, int64_t sparse_dim, int64_t dense_dim, const at::Tensor & out) { + return at::_ops::sparse_resize_out::call(self, size, sparse_dim, dense_dim, out); +} + +// aten::sparse_resize(Tensor self, int[] size, int sparse_dim, int dense_dim) -> Tensor +inline at::Tensor sparse_resize(const at::Tensor & self, at::IntArrayRef size, int64_t sparse_dim, int64_t dense_dim) { + return at::_ops::sparse_resize::call(self, size, sparse_dim, dense_dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_y0_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_y0_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..70f7758ce1882bc3cf8a46f328c0b796293dd086 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_y0_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor special_bessel_y0(const at::Tensor & self); +TORCH_API at::Tensor & special_bessel_y0_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & special_bessel_y0_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_y0_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_y0_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..55e11d5a9bdb8706d75c9e9f5d07ec913645ef3b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_y0_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// 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 + +namespace at { +namespace _ops { + + +struct TORCH_API special_bessel_y0 { + 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::special_bessel_y0") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_bessel_y0(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 special_bessel_y0_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::special_bessel_y0") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_bessel_y0.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 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..02389dcff33a02635f2db0ca97214b801c0e35d4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_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 +#include +#include + +// 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 + +namespace at { + +namespace meta { + +TORCH_API at::Tensor special_chebyshev_polynomial_v(const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_v_out(at::Tensor & out, const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_v_outf(const at::Tensor & x, const at::Tensor & n, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_native.h new file mode 100644 index 0000000000000000000000000000000000000000..407ac798b58b395bc2c407c61b2bb34d666a843a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_native.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_special_chebyshev_polynomial_v_out : public at::meta::structured_special_chebyshev_polynomial_v { +void impl(const at::Tensor & x, const at::Tensor & n, const at::Tensor & out); +}; +TORCH_API at::Tensor special_chebyshev_polynomial_v(const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_v_out(const at::Scalar & x, const at::Tensor & n, at::Tensor & out); +TORCH_API at::Tensor special_chebyshev_polynomial_v(const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_v_out(const at::Tensor & x, const at::Scalar & n, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_he_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_he_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..34814ebc4a250a89cd7a3798c94e5891cf3d5c6d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_he_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor special_hermite_polynomial_he(const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_hermite_polynomial_he_out(at::Tensor & out, const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_hermite_polynomial_he_outf(const at::Tensor & x, const at::Tensor & n, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i1_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i1_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..178225d062c9cde23f22d4c53cbe47d889924228 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i1_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor special_modified_bessel_i1(const at::Tensor & self); +TORCH_API at::Tensor & special_modified_bessel_i1_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & special_modified_bessel_i1_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k1_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k1_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e40ed94c353a457eedcfcc5cc2b77ecc87cfbf19 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k1_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 +#include +#include + +// 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 + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor special_scaled_modified_bessel_k1(const at::Tensor & x); +TORCH_API at::Tensor & special_scaled_modified_bessel_k1_out(at::Tensor & out, const at::Tensor & x); +TORCH_API at::Tensor & special_scaled_modified_bessel_k1_outf(const at::Tensor & x, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_t_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_t_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..1de0dad4f3a1508a194fdb35e2ea068e3850a7db --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_t_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_special_shifted_chebyshev_polynomial_t : public TensorIteratorBase { + + + void meta(const at::Tensor & x, const at::Tensor & n); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/split_copy_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/split_copy_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3c5b8b5fa81b9aeddcc134e21adbe11fa11d2f8e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/split_copy_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 +#include +#include + +// 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 + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API ::std::vector split_copy(const at::Tensor & self, int64_t split_size, int64_t dim=0); +TORCH_API ::std::vector split_copy_symint(const at::Tensor & self, c10::SymInt split_size, int64_t dim=0); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..bbd0e4502aa39ac5c9f4c5ae6658c01610973f2e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_backward_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_tanh_backward_out : public at::meta::structured_tanh_backward { +void impl(const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & grad_input); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_native.h new file mode 100644 index 0000000000000000000000000000000000000000..1eea477a5ca8ca84dba9c1fac836444c34a42250 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor unfold(const at::Tensor & self, int64_t dimension, int64_t size, int64_t step); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest1d_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest1d_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..d0479060dc334daff669f4995a17275d4a4b05da --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest1d_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_upsample_nearest1d : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, at::ArrayRef output_size, c10::optional scales); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest2d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest2d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..3b35319b6b3a9eed962f1b5adc3e1a6845a18f17 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest2d_native.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +TORCH_API at::Tensor upsample_nearest2d(const at::Tensor & input, at::OptionalIntArrayRef output_size, c10::optional> scale_factors); +struct TORCH_API structured_upsample_nearest2d_out_cpu : public at::meta::structured_upsample_nearest2d { +void impl(const at::Tensor & self, at::ArrayRef output_size, c10::optional scales_h, c10::optional scales_w, const at::Tensor & out); +}; +struct TORCH_API structured_upsample_nearest2d_out_cuda : public at::meta::structured_upsample_nearest2d { +void impl(const at::Tensor & self, at::ArrayRef output_size, c10::optional scales_h, c10::optional scales_w, const at::Tensor & out); +}; +TORCH_API at::Tensor upsample_nearest2d_quantized_cpu(const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..dae7711ba7a43506d4db9fec94a932baf302dd6f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_upsample_trilinear3d : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, at::ArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a03452aa9fd2a975250c202e431fe0f21012f286 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_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 +#include +#include + +// 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 + +namespace at { + +namespace meta { + +TORCH_API at::Tensor view(const at::Tensor & self, at::IntArrayRef size); +TORCH_API at::Tensor view_symint(const at::Tensor & self, c10::SymIntArrayRef size); + +} // namespace meta +} // namespace at