diff --git a/.gitattributes b/.gitattributes index fce1c027d856d579e817839d16dc38665c89bf00..ff2c318650b390823be45406c68e34225f104c9e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -83,3 +83,7 @@ tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/_ tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/parallel/__pycache__/distributed.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/linalg/__pycache__/__init__.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/__pycache__/functional.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text +tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/__pycache__/loss.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text +tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_refs/__pycache__/__init__.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text +tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/__pycache__/module.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text +tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/scheduler.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/scheduler.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/scheduler.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2997c1720bdc6e6f93c329288f874608731e505e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/scheduler.cpython-311.pyc @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b43be7e1d098c1666039dc2fc8e25fb23eed582cb4c24fb4d664a2f55345c1 +size 146053 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_refs/__pycache__/__init__.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_refs/__pycache__/__init__.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2db3bc96a853d98b1d290aede677f369d977746a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_refs/__pycache__/__init__.cpython-311.pyc @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdeee77be80297ccf1467a937e3262b937304e5f5619bb0feabf763162ad45a5 +size 283057 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_native.h new file mode 100644 index 0000000000000000000000000000000000000000..e2eb0e9cf8e875ad4c91adbf66cb1a868334dfc4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_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 void _assert_scalar(const at::Scalar & self, c10::string_view assert_msg); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Double_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Double_native.h new file mode 100644 index 0000000000000000000000000000000000000000..30851adfca3dd02fada1706b62f57136fd144ddb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Double_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 _cast_Double(const at::Tensor & self, bool non_blocking=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b607e83c528a8f5eada4b0aa043a6674866f75b1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_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 _conj(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_per_tensor_affine_cachemask_tensor_qparams_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_per_tensor_affine_cachemask_tensor_qparams_native.h new file mode 100644 index 0000000000000000000000000000000000000000..78a7d691f8be0798858413b5cf469f8ef51bbe9f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_per_tensor_affine_cachemask_tensor_qparams_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 _fake_quantize_per_tensor_affine_cachemask_tensor_qparams_out(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, const at::Tensor & fake_quant_enabled, int64_t quant_min, int64_t quant_max, at::Tensor & out0, at::Tensor & out1); +TORCH_API ::std::tuple _fake_quantize_per_tensor_affine_cachemask_tensor_qparams(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, const at::Tensor & fake_quant_enabled, int64_t quant_min, int64_t quant_max); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_acos_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_acos_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..da40225787c7f246a0a1ee18aee17f4fc4bcf0a6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_acos_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_acos_out(at::TensorList out, at::TensorList self); +TORCH_API void _foreach_acos_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_clamp_min.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_min.h new file mode 100644 index 0000000000000000000000000000000000000000..883754a68fd9105cfea5fca164e6ece430bc4cf5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_min.h @@ -0,0 +1,82 @@ +#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_clamp_min.Scalar(Tensor[] self, Scalar scalar) -> Tensor[] +inline ::std::vector _foreach_clamp_min(at::TensorList self, const at::Scalar & scalar) { + return at::_ops::_foreach_clamp_min_Scalar::call(self, scalar); +} + +// aten::_foreach_clamp_min_.Scalar(Tensor(a!)[] self, Scalar scalar) -> () +inline void _foreach_clamp_min_(at::TensorList self, const at::Scalar & scalar) { + return at::_ops::_foreach_clamp_min__Scalar::call(self, scalar); +} + +// aten::_foreach_clamp_min.List(Tensor[] self, Tensor[] other) -> Tensor[] +inline ::std::vector _foreach_clamp_min(at::TensorList self, at::TensorList other) { + return at::_ops::_foreach_clamp_min_List::call(self, other); +} + +// aten::_foreach_clamp_min_.List(Tensor(a!)[] self, Tensor[] other) -> () +inline void _foreach_clamp_min_(at::TensorList self, at::TensorList other) { + return at::_ops::_foreach_clamp_min__List::call(self, other); +} + +// aten::_foreach_clamp_min.ScalarList(Tensor[] self, Scalar[] scalars) -> Tensor[] +inline ::std::vector _foreach_clamp_min(at::TensorList self, at::ArrayRef scalars) { + return at::_ops::_foreach_clamp_min_ScalarList::call(self, scalars); +} + +// aten::_foreach_clamp_min_.ScalarList(Tensor(a!)[] self, Scalar[] scalars) -> () +inline void _foreach_clamp_min_(at::TensorList self, at::ArrayRef scalars) { + return at::_ops::_foreach_clamp_min__ScalarList::call(self, scalars); +} + +// aten::_foreach_clamp_min.Scalar_out(Tensor[] self, Scalar scalar, *, Tensor(a!)[] out) -> () +inline void _foreach_clamp_min_out(at::TensorList out, at::TensorList self, const at::Scalar & scalar) { + return at::_ops::_foreach_clamp_min_Scalar_out::call(self, scalar, out); +} +// aten::_foreach_clamp_min.Scalar_out(Tensor[] self, Scalar scalar, *, Tensor(a!)[] out) -> () +inline void _foreach_clamp_min_outf(at::TensorList self, const at::Scalar & scalar, at::TensorList out) { + return at::_ops::_foreach_clamp_min_Scalar_out::call(self, scalar, out); +} + +// aten::_foreach_clamp_min.List_out(Tensor[] self, Tensor[] other, *, Tensor(a!)[] out) -> () +inline void _foreach_clamp_min_out(at::TensorList out, at::TensorList self, at::TensorList other) { + return at::_ops::_foreach_clamp_min_List_out::call(self, other, out); +} +// aten::_foreach_clamp_min.List_out(Tensor[] self, Tensor[] other, *, Tensor(a!)[] out) -> () +inline void _foreach_clamp_min_outf(at::TensorList self, at::TensorList other, at::TensorList out) { + return at::_ops::_foreach_clamp_min_List_out::call(self, other, out); +} + +// aten::_foreach_clamp_min.ScalarList_out(Tensor[] self, Scalar[] scalars, *, Tensor(a!)[] out) -> () +inline void _foreach_clamp_min_out(at::TensorList out, at::TensorList self, at::ArrayRef scalars) { + return at::_ops::_foreach_clamp_min_ScalarList_out::call(self, scalars, out); +} +// aten::_foreach_clamp_min.ScalarList_out(Tensor[] self, Scalar[] scalars, *, Tensor(a!)[] out) -> () +inline void _foreach_clamp_min_outf(at::TensorList self, at::ArrayRef scalars, at::TensorList out) { + return at::_ops::_foreach_clamp_min_ScalarList_out::call(self, scalars, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_min_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_min_native.h new file mode 100644 index 0000000000000000000000000000000000000000..02e3e40f993af792de8684d256f391160ec134f4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_min_native.h @@ -0,0 +1,35 @@ +#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 void _foreach_clamp_min_Scalar_out(at::TensorList self, const at::Scalar & scalar, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_clamp_min_scalar_kernel_slow(at::TensorList self, const at::Scalar & scalar); +TORCH_API void foreach_tensor_clamp_min_scalar_kernel_slow_(at::TensorList self, const at::Scalar & scalar); +TORCH_API ::std::vector foreach_tensor_clamp_min_scalar_kernel_cuda(at::TensorList self, const at::Scalar & scalar); +TORCH_API void foreach_tensor_clamp_min_scalar_kernel_cuda_(at::TensorList self, const at::Scalar & scalar); +TORCH_API void _foreach_clamp_min_List_out(at::TensorList self, at::TensorList other, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_clamp_min_list_kernel_slow(at::TensorList self, at::TensorList other); +TORCH_API void foreach_tensor_clamp_min_list_kernel_slow_(at::TensorList self, at::TensorList other); +TORCH_API ::std::vector foreach_tensor_clamp_min_list_kernel_cuda(at::TensorList self, at::TensorList other); +TORCH_API void foreach_tensor_clamp_min_list_kernel_cuda_(at::TensorList self, at::TensorList other); +TORCH_API void _foreach_clamp_min_ScalarList_out(at::TensorList self, at::ArrayRef scalars, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_clamp_min_scalarlist_kernel_slow(at::TensorList self, at::ArrayRef scalars); +TORCH_API void foreach_tensor_clamp_min_scalarlist_kernel_slow_(at::TensorList self, at::ArrayRef scalars); +TORCH_API ::std::vector foreach_tensor_clamp_min_scalarlist_kernel_cuda(at::TensorList self, at::ArrayRef scalars); +TORCH_API void foreach_tensor_clamp_min_scalarlist_kernel_cuda_(at::TensorList self, at::ArrayRef scalars); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_tensors.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_tensors.h new file mode 100644 index 0000000000000000000000000000000000000000..c66865367984f923f42dad260ac58845b95ae372 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_tensors.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::_histogramdd_from_bin_tensors(Tensor self, Tensor[] bins, *, Tensor? weight=None, bool density=False) -> Tensor +inline at::Tensor _histogramdd_from_bin_tensors(const at::Tensor & self, at::TensorList bins, const c10::optional & weight={}, bool density=false) { + return at::_ops::_histogramdd_from_bin_tensors::call(self, bins, weight, density); +} + +// aten::_histogramdd_from_bin_tensors.out(Tensor self, Tensor[] bins, *, Tensor? weight=None, bool density=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _histogramdd_from_bin_tensors_out(at::Tensor & out, const at::Tensor & self, at::TensorList bins, const c10::optional & weight={}, bool density=false) { + return at::_ops::_histogramdd_from_bin_tensors_out::call(self, bins, weight, density, out); +} +// aten::_histogramdd_from_bin_tensors.out(Tensor self, Tensor[] bins, *, Tensor? weight=None, bool density=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _histogramdd_from_bin_tensors_outf(const at::Tensor & self, at::TensorList bins, const c10::optional & weight, bool density, at::Tensor & out) { + return at::_ops::_histogramdd_from_bin_tensors_out::call(self, bins, weight, density, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_batch_norm_legit.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_batch_norm_legit.h new file mode 100644 index 0000000000000000000000000000000000000000..d467c2a7507ef6694652bf8f4797a6a83c3ed169 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_batch_norm_legit.h @@ -0,0 +1,58 @@ +#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::_native_batch_norm_legit(Tensor input, Tensor? weight, Tensor? bias, Tensor(a!) running_mean, Tensor(b!) running_var, bool training, float momentum, float eps) -> (Tensor, Tensor, Tensor) +inline ::std::tuple _native_batch_norm_legit(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, at::Tensor & running_mean, at::Tensor & running_var, bool training, double momentum, double eps) { + return at::_ops::_native_batch_norm_legit::call(input, weight, bias, running_mean, running_var, training, momentum, eps); +} + +// aten::_native_batch_norm_legit.out(Tensor input, Tensor? weight, Tensor? bias, Tensor(a!) running_mean, Tensor(b!) running_var, bool training, float momentum, float eps, *, Tensor(d!) out, Tensor(e!) save_mean, Tensor(f!) save_invstd) -> (Tensor(d!), Tensor(e!), Tensor(f!)) +inline ::std::tuple _native_batch_norm_legit_out(at::Tensor & out, at::Tensor & save_mean, at::Tensor & save_invstd, const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, at::Tensor & running_mean, at::Tensor & running_var, bool training, double momentum, double eps) { + return at::_ops::_native_batch_norm_legit_out::call(input, weight, bias, running_mean, running_var, training, momentum, eps, out, save_mean, save_invstd); +} +// aten::_native_batch_norm_legit.out(Tensor input, Tensor? weight, Tensor? bias, Tensor(a!) running_mean, Tensor(b!) running_var, bool training, float momentum, float eps, *, Tensor(d!) out, Tensor(e!) save_mean, Tensor(f!) save_invstd) -> (Tensor(d!), Tensor(e!), Tensor(f!)) +inline ::std::tuple _native_batch_norm_legit_outf(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, at::Tensor & running_mean, at::Tensor & running_var, bool training, double momentum, double eps, at::Tensor & out, at::Tensor & save_mean, at::Tensor & save_invstd) { + return at::_ops::_native_batch_norm_legit_out::call(input, weight, bias, running_mean, running_var, training, momentum, eps, out, save_mean, save_invstd); +} + +// aten::_native_batch_norm_legit.no_stats(Tensor input, Tensor? weight, Tensor? bias, bool training, float momentum, float eps) -> (Tensor, Tensor, Tensor) +inline ::std::tuple _native_batch_norm_legit(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, bool training, double momentum, double eps) { + return at::_ops::_native_batch_norm_legit_no_stats::call(input, weight, bias, training, momentum, eps); +} + +// aten::_native_batch_norm_legit.no_stats_out(Tensor input, Tensor? weight, Tensor? bias, bool training, float momentum, float eps, *, Tensor(a!) out, Tensor(b!) save_mean, Tensor(c!) save_invstd) -> (Tensor(a!), Tensor(b!), Tensor(c!)) +inline ::std::tuple _native_batch_norm_legit_out(at::Tensor & out, at::Tensor & save_mean, at::Tensor & save_invstd, const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, bool training, double momentum, double eps) { + return at::_ops::_native_batch_norm_legit_no_stats_out::call(input, weight, bias, training, momentum, eps, out, save_mean, save_invstd); +} +// aten::_native_batch_norm_legit.no_stats_out(Tensor input, Tensor? weight, Tensor? bias, bool training, float momentum, float eps, *, Tensor(a!) out, Tensor(b!) save_mean, Tensor(c!) save_invstd) -> (Tensor(a!), Tensor(b!), Tensor(c!)) +inline ::std::tuple _native_batch_norm_legit_outf(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, bool training, double momentum, double eps, at::Tensor & out, at::Tensor & save_mean, at::Tensor & save_invstd) { + return at::_ops::_native_batch_norm_legit_no_stats_out::call(input, weight, bias, training, momentum, eps, out, save_mean, save_invstd); +} + +// aten::_native_batch_norm_legit_functional(Tensor input, Tensor? weight, Tensor? bias, Tensor running_mean, Tensor running_var, bool training, float momentum, float eps) -> (Tensor, Tensor, Tensor, Tensor running_mean_out, Tensor running_var_out) +inline ::std::tuple _native_batch_norm_legit_functional(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, const at::Tensor & running_mean, const at::Tensor & running_var, bool training, double momentum, double eps) { + return at::_ops::_native_batch_norm_legit_functional::call(input, weight, bias, running_mean, running_var, training, momentum, eps); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sample_dirichlet_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sample_dirichlet_native.h new file mode 100644 index 0000000000000000000000000000000000000000..822f4c7f14570404fe7ec9b0dde091adc23317ca --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sample_dirichlet_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 & _sample_dirichlet_out(const at::Tensor & self, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor _s_dirichlet_cpu(const at::Tensor & self, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor _s_dirichlet_cuda(const at::Tensor & self, c10::optional generator=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d98bc55c6105bff07b3ae9232de3ba1e3033d72e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_backward_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 ::std::tuple _slow_conv2d_backward_out(at::Tensor & grad_input, at::Tensor & grad_weight, at::Tensor & grad_bias, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API ::std::tuple _slow_conv2d_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & grad_input, at::Tensor & grad_weight, at::Tensor & grad_bias); +TORCH_API ::std::tuple _slow_conv2d_backward_symint_out(at::Tensor & grad_input, at::Tensor & grad_weight, at::Tensor & grad_bias, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding); +TORCH_API ::std::tuple _slow_conv2d_backward_symint_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, at::Tensor & grad_input, at::Tensor & grad_weight, at::Tensor & grad_bias); +TORCH_API ::std::tuple _slow_conv2d_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, ::std::array output_mask); +TORCH_API ::std::tuple _slow_conv2d_backward_symint(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, ::std::array output_mask); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..e1bb0c47150bc56c5345fd83e49b8cf4ff0cf251 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_backward.h @@ -0,0 +1,30 @@ +#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::_thnn_fused_lstm_cell_backward(Tensor? grad_hy, Tensor? grad_cy, Tensor cx, Tensor cy, Tensor workspace, bool has_bias) -> (Tensor, Tensor, Tensor, Tensor, Tensor) +inline ::std::tuple _thnn_fused_lstm_cell_backward(const c10::optional & grad_hy, const c10::optional & grad_cy, const at::Tensor & cx, const at::Tensor & cy, const at::Tensor & workspace, bool has_bias) { + return at::_ops::_thnn_fused_lstm_cell_backward::call(grad_hy, grad_cy, cx, cy, workspace, has_bias); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_view_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_view_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..532036cb8e7370371ba20b2b5bbf9997b5c926e8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_view_compositeexplicitautograd_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 _unsafe_view(const at::Tensor & self, at::IntArrayRef size); +TORCH_API at::Tensor _unsafe_view_symint(const at::Tensor & self, c10::SymIntArrayRef size); +TORCH_API at::Tensor & _unsafe_view_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef size); +TORCH_API at::Tensor & _unsafe_view_outf(const at::Tensor & self, at::IntArrayRef size, at::Tensor & out); +TORCH_API at::Tensor & _unsafe_view_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef size); +TORCH_API at::Tensor & _unsafe_view_symint_outf(const at::Tensor & self, c10::SymIntArrayRef size, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact1d_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact1d_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..75c3ff97ef48782c016460d009b4386445c5cfd4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact1d_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::_upsample_nearest_exact1d_backward.grad_input(Tensor grad_output, SymInt[1] output_size, SymInt[3] input_size, float? scales=None, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & _upsample_nearest_exact1d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales=c10::nullopt) { + return at::_ops::_upsample_nearest_exact1d_backward_grad_input::call(grad_output, c10::fromIntArrayRefSlow(output_size), c10::fromIntArrayRefSlow(input_size), scales, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & _upsample_nearest_exact1d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales=c10::nullopt) { + return at::_ops::_upsample_nearest_exact1d_backward_grad_input::call(grad_output, c10::fromIntArrayRefSlow(output_size), c10::fromIntArrayRefSlow(input_size), scales, grad_input); + } +} + +// aten::_upsample_nearest_exact1d_backward.grad_input(Tensor grad_output, SymInt[1] output_size, SymInt[3] input_size, float? scales=None, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & _upsample_nearest_exact1d_backward_outf(const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales, at::Tensor & grad_input) { + return at::_ops::_upsample_nearest_exact1d_backward_grad_input::call(grad_output, c10::fromIntArrayRefSlow(output_size), c10::fromIntArrayRefSlow(input_size), scales, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & _upsample_nearest_exact1d_backward_outf(const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales, at::Tensor & grad_input) { + return at::_ops::_upsample_nearest_exact1d_backward_grad_input::call(grad_output, c10::fromIntArrayRefSlow(output_size), c10::fromIntArrayRefSlow(input_size), scales, grad_input); + } +} + +// aten::_upsample_nearest_exact1d_backward.grad_input(Tensor grad_output, SymInt[1] output_size, SymInt[3] input_size, float? scales=None, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & _upsample_nearest_exact1d_backward_symint_out(at::Tensor & grad_input, const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales=c10::nullopt) { + return at::_ops::_upsample_nearest_exact1d_backward_grad_input::call(grad_output, output_size, input_size, scales, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & _upsample_nearest_exact1d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales=c10::nullopt) { + return at::_ops::_upsample_nearest_exact1d_backward_grad_input::call(grad_output, output_size, input_size, scales, grad_input); + } +} + +// aten::_upsample_nearest_exact1d_backward.grad_input(Tensor grad_output, SymInt[1] output_size, SymInt[3] input_size, float? scales=None, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & _upsample_nearest_exact1d_backward_symint_outf(const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales, at::Tensor & grad_input) { + return at::_ops::_upsample_nearest_exact1d_backward_grad_input::call(grad_output, output_size, input_size, scales, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & _upsample_nearest_exact1d_backward_outf(const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales, at::Tensor & grad_input) { + return at::_ops::_upsample_nearest_exact1d_backward_grad_input::call(grad_output, output_size, input_size, scales, grad_input); + } +} + +// aten::_upsample_nearest_exact1d_backward(Tensor grad_output, SymInt[1] output_size, SymInt[3] input_size, float? scales=None) -> Tensor +inline at::Tensor _upsample_nearest_exact1d_backward(const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales=c10::nullopt) { + return at::_ops::_upsample_nearest_exact1d_backward::call(grad_output, c10::fromIntArrayRefSlow(output_size), c10::fromIntArrayRefSlow(input_size), scales); +} +namespace symint { + template ::value>> + at::Tensor _upsample_nearest_exact1d_backward(const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales=c10::nullopt) { + return at::_ops::_upsample_nearest_exact1d_backward::call(grad_output, c10::fromIntArrayRefSlow(output_size), c10::fromIntArrayRefSlow(input_size), scales); + } +} + +// aten::_upsample_nearest_exact1d_backward(Tensor grad_output, SymInt[1] output_size, SymInt[3] input_size, float? scales=None) -> Tensor +inline at::Tensor _upsample_nearest_exact1d_backward_symint(const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales=c10::nullopt) { + return at::_ops::_upsample_nearest_exact1d_backward::call(grad_output, output_size, input_size, scales); +} +namespace symint { + template ::value>> + at::Tensor _upsample_nearest_exact1d_backward(const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales=c10::nullopt) { + return at::_ops::_upsample_nearest_exact1d_backward::call(grad_output, output_size, input_size, scales); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_interface.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_interface.h new file mode 100644 index 0000000000000000000000000000000000000000..f64c6ff2844685285187c0904ae29ee5e5774fdc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_interface.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::_weight_norm_interface(Tensor v, Tensor g, int dim=0) -> (Tensor, Tensor) +inline ::std::tuple _weight_norm_interface(const at::Tensor & v, const at::Tensor & g, int64_t dim=0) { + return at::_ops::_weight_norm_interface::call(v, g, dim); +} + +// aten::_weight_norm_interface.out(Tensor v, Tensor g, int dim=0, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple _weight_norm_interface_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & v, const at::Tensor & g, int64_t dim=0) { + return at::_ops::_weight_norm_interface_out::call(v, g, dim, out0, out1); +} +// aten::_weight_norm_interface.out(Tensor v, Tensor g, int dim=0, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple _weight_norm_interface_outf(const at::Tensor & v, const at::Tensor & g, int64_t dim, at::Tensor & out0, at::Tensor & out1) { + return at::_ops::_weight_norm_interface_out::call(v, g, dim, out0, out1); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcdiv_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcdiv_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5126018e0a0d21e11f418cde969253e7b66ce5c7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcdiv_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 at::Tensor addcdiv(const at::Tensor & self, const at::Tensor & tensor1, const at::Tensor & tensor2, const at::Scalar & value=1); +TORCH_API at::Tensor & addcdiv_(at::Tensor & self, const at::Tensor & tensor1, const at::Tensor & tensor2, const at::Scalar & value=1); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/affine_grid_generator_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/affine_grid_generator_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8697f34aa0623c0c39fc44b9d6e9df50f209a14a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/affine_grid_generator_backward_compositeimplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 affine_grid_generator_backward(const at::Tensor & grad, at::IntArrayRef size, bool align_corners); +TORCH_API at::Tensor affine_grid_generator_backward_symint(const at::Tensor & grad, c10::SymIntArrayRef size, bool align_corners); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argmax_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argmax_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f32dea5fbc8c4bd8f2c0505c7877fd8aa0bea743 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argmax_cpu_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 argmax(const at::Tensor & self, c10::optional dim=c10::nullopt, bool keepdim=false); +TORCH_API at::Tensor & argmax_out(at::Tensor & out, const at::Tensor & self, c10::optional dim=c10::nullopt, bool keepdim=false); +TORCH_API at::Tensor & argmax_outf(const at::Tensor & self, c10::optional dim, bool keepdim, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/asinh_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/asinh_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ea63344ece063bd1fb05e03f00bb19fc5ced2ec3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/asinh_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 asinh(const at::Tensor & self); +TORCH_API at::Tensor & asinh_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & asinh_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & asinh_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/avg_pool2d_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/avg_pool2d_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..297c0c1338524fc091bb303869cf52fc4b776a61 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/avg_pool2d_backward_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 avg_pool2d_backward(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, bool ceil_mode, bool count_include_pad, c10::optional divisor_override); +TORCH_API at::Tensor & avg_pool2d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, bool ceil_mode, bool count_include_pad, c10::optional divisor_override); +TORCH_API at::Tensor & avg_pool2d_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, bool ceil_mode, bool count_include_pad, c10::optional divisor_override, at::Tensor & grad_input); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_not_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_not_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5d78bf5906c610635664f99c8ec8e9c94c6c0811 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_not_meta_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 bitwise_not(const at::Tensor & self); +TORCH_API at::Tensor & bitwise_not_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & bitwise_not_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & bitwise_not_(at::Tensor & self); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..f8072f6ef1f26bfb0964d2327fce34bf56221562 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_meta.h @@ -0,0 +1,114 @@ +#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_cat : public at::impl::MetaBase { + + template + struct TORCH_API precompute_out { + + precompute_out set_dim(int64_t value) { + static_assert(DIM == false, "dim already set"); + precompute_out ret; +ret.dim = value; +ret.valid = this->valid; +ret.all_contiguous = this->all_contiguous; +ret.all_same_dtype = this->all_same_dtype; +ret.all_same_sizes_and_stride = this->all_same_sizes_and_stride; +ret.memory_format = this->memory_format; +return ret; + } + + + precompute_out set_valid(int64_t value) { + static_assert(VALID == false, "valid already set"); + precompute_out ret; +ret.dim = this->dim; +ret.valid = value; +ret.all_contiguous = this->all_contiguous; +ret.all_same_dtype = this->all_same_dtype; +ret.all_same_sizes_and_stride = this->all_same_sizes_and_stride; +ret.memory_format = this->memory_format; +return ret; + } + + + precompute_out set_all_contiguous(bool value) { + static_assert(ALL_CONTIGUOUS == false, "all_contiguous already set"); + precompute_out ret; +ret.dim = this->dim; +ret.valid = this->valid; +ret.all_contiguous = value; +ret.all_same_dtype = this->all_same_dtype; +ret.all_same_sizes_and_stride = this->all_same_sizes_and_stride; +ret.memory_format = this->memory_format; +return ret; + } + + + precompute_out set_all_same_dtype(bool value) { + static_assert(ALL_SAME_DTYPE == false, "all_same_dtype already set"); + precompute_out ret; +ret.dim = this->dim; +ret.valid = this->valid; +ret.all_contiguous = this->all_contiguous; +ret.all_same_dtype = value; +ret.all_same_sizes_and_stride = this->all_same_sizes_and_stride; +ret.memory_format = this->memory_format; +return ret; + } + + + precompute_out set_all_same_sizes_and_stride(bool value) { + static_assert(ALL_SAME_SIZES_AND_STRIDE == false, "all_same_sizes_and_stride already set"); + precompute_out ret; +ret.dim = this->dim; +ret.valid = this->valid; +ret.all_contiguous = this->all_contiguous; +ret.all_same_dtype = this->all_same_dtype; +ret.all_same_sizes_and_stride = value; +ret.memory_format = this->memory_format; +return ret; + } + + + precompute_out set_memory_format(at::MemoryFormat value) { + static_assert(MEMORY_FORMAT == false, "memory_format already set"); + precompute_out ret; +ret.dim = this->dim; +ret.valid = this->valid; +ret.all_contiguous = this->all_contiguous; +ret.all_same_dtype = this->all_same_dtype; +ret.all_same_sizes_and_stride = this->all_same_sizes_and_stride; +ret.memory_format = value; +return ret; + } + + int64_t dim; +int64_t valid; +bool all_contiguous; +bool all_same_dtype; +bool all_same_sizes_and_stride; +at::MemoryFormat memory_format; + }; + using meta_return_ty = precompute_out ; + meta_return_ty meta(const at::ITensorListRef & tensors, int64_t dim); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8911f1a55a557dbe900e271ae81be57999b1cf65 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_cuda_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 cuda { + +TORCH_API at::Tensor clamp(const at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor & clamp_out(at::Tensor & out, const at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor & clamp_outf(const at::Tensor & self, const c10::optional & min, const c10::optional & max, at::Tensor & out); +TORCH_API at::Tensor & clamp_(at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor clamp(const at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); +TORCH_API at::Tensor & clamp_out(at::Tensor & out, const at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); +TORCH_API at::Tensor & clamp_outf(const at::Tensor & self, const c10::optional & min, const c10::optional & max, at::Tensor & out); +TORCH_API at::Tensor & clamp_(at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_max_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_max_native.h new file mode 100644 index 0000000000000000000000000000000000000000..deb235f3906890896614a5b4d77caa0275c85f21 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_max_native.h @@ -0,0 +1,26 @@ +#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_clamp_max_out : public at::meta::structured_clamp_max { +void impl(const at::Tensor & self, const at::Scalar & max, const at::Tensor & out); +}; +struct TORCH_API structured_clamp_max_Tensor_out : public at::meta::structured_clamp_max_Tensor { +void impl(const at::Tensor & self, const at::Tensor & max, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conj.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conj.h new file mode 100644 index 0000000000000000000000000000000000000000..6a80689ab9a78b36864e3aa42a4224e6810fcdf3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conj.h @@ -0,0 +1,30 @@ +#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::conj(Tensor(a) self) -> Tensor(a) +inline at::Tensor __dispatch_conj(const at::Tensor & self) { + return at::_ops::conj::call(self); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_batch_norm_backward_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_batch_norm_backward_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7bd97e00e862992f3018f88cd97d93bdc140a4ae --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_batch_norm_backward_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 ::std::tuple cudnn_batch_norm_backward_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, const at::Tensor & input, const at::Tensor & grad_output, const at::Tensor & weight, const c10::optional & running_mean, const c10::optional & running_var, const c10::optional & save_mean, const c10::optional & save_var, double epsilon, const at::Tensor & reserveSpace); +TORCH_API ::std::tuple cudnn_batch_norm_backward_outf(const at::Tensor & input, const at::Tensor & grad_output, const at::Tensor & weight, const c10::optional & running_mean, const c10::optional & running_var, const c10::optional & save_mean, const c10::optional & save_var, double epsilon, const at::Tensor & reserveSpace, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/det_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/det_native.h new file mode 100644 index 0000000000000000000000000000000000000000..90a1707dc4ce0e5dd4072c79bae32da07a30b79a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/det_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 det(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d684303921e016a651b764c5ee22db18be1e53d2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_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 empty(at::IntArrayRef size, at::TensorOptions options={}, c10::optional memory_format=c10::nullopt); +TORCH_API at::Tensor empty(at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); +TORCH_API at::Tensor empty_symint(c10::SymIntArrayRef size, at::TensorOptions options={}, c10::optional memory_format=c10::nullopt); +TORCH_API at::Tensor empty_symint(c10::SymIntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1a7139b4ea8a50acde3f4808cfac4aabfe61a8f0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_cpu_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 expm1(const at::Tensor & self); +TORCH_API at::Tensor & expm1_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & expm1_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & expm1_(at::Tensor & self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_fp16_weight_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_fp16_weight_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8c145586f9822f499a95baaf52082c2dfa410921 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_fp16_weight_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 fbgemm_linear_fp16_weight(const at::Tensor & input, const at::Tensor & packed_weight, const at::Tensor & bias); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_fp16_weight_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_fp16_weight_native.h new file mode 100644 index 0000000000000000000000000000000000000000..1b07d848873d3a4a58cbbb2a7cb002c3311012d5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_fp16_weight_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 fbgemm_linear_fp16_weight(const at::Tensor & input, const at::Tensor & packed_weight, const at::Tensor & bias); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_int8_weight_fp32_activation.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_int8_weight_fp32_activation.h new file mode 100644 index 0000000000000000000000000000000000000000..70a5a750ac0a4820100ecc1299a52bf01edc5a95 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_int8_weight_fp32_activation.h @@ -0,0 +1,30 @@ +#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::fbgemm_linear_int8_weight_fp32_activation(Tensor input, Tensor weight, Tensor packed, Tensor col_offsets, Scalar weight_scale, Scalar weight_zero_point, Tensor bias) -> Tensor +inline at::Tensor fbgemm_linear_int8_weight_fp32_activation(const at::Tensor & input, const at::Tensor & weight, const at::Tensor & packed, const at::Tensor & col_offsets, const at::Scalar & weight_scale, const at::Scalar & weight_zero_point, const at::Tensor & bias) { + return at::_ops::fbgemm_linear_int8_weight_fp32_activation::call(input, weight, packed, col_offsets, weight_scale, weight_zero_point, bias); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_fft_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_fft_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..44752e3fd6a70a2c2eda0e91da6cf00bd443ea70 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_fft_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 fft_fft(const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor fft_fft_symint(const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_fft_out(at::Tensor & out, const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_fft_outf(const at::Tensor & self, c10::optional n, int64_t dim, c10::optional norm, at::Tensor & out); +TORCH_API at::Tensor & fft_fft_symint_out(at::Tensor & out, const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_fft_symint_outf(const at::Tensor & self, c10::optional n, int64_t dim, c10::optional norm, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_divide_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_divide_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..73aa1ed5a954297106af6832677d047638b5b990 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_divide_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 & floor_divide_(at::Tensor & self, const at::Tensor & other); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/greater.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/greater.h new file mode 100644 index 0000000000000000000000000000000000000000..f34a7708892ff3f9824851b28df8ca76f9ddcfa2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/greater.h @@ -0,0 +1,53 @@ +#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::greater.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & greater_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other) { + return at::_ops::greater_Scalar_out::call(self, other, out); +} +// aten::greater.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & greater_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out) { + return at::_ops::greater_Scalar_out::call(self, other, out); +} + +// aten::greater.Scalar(Tensor self, Scalar other) -> Tensor +inline at::Tensor greater(const at::Tensor & self, const at::Scalar & other) { + return at::_ops::greater_Scalar::call(self, other); +} + +// aten::greater.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & greater_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::greater_Tensor_out::call(self, other, out); +} +// aten::greater.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & greater_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::greater_Tensor_out::call(self, other, out); +} + +// aten::greater.Tensor(Tensor self, Tensor other) -> Tensor +inline at::Tensor greater(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::greater_Tensor::call(self, other); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f8e33ad7e71615b649ca8f813500299b74e26cce --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 grid_sampler(const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/group_norm_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/group_norm_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cc86fcea7422f130b2fe9a101b017823f30e659c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/group_norm_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 group_norm(const at::Tensor & input, int64_t num_groups, const c10::optional & weight={}, const c10::optional & bias={}, double eps=1e-05, bool cudnn_enabled=true); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardsigmoid_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardsigmoid_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..2fd7fdf669a692c8d9acac45290302a7476fc77f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardsigmoid_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 hardsigmoid_backward_grad_input { + 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::hardsigmoid_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "grad_input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "hardsigmoid_backward.grad_input(Tensor grad_output, Tensor self, *, Tensor(a!) grad_input) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input); +}; + +struct TORCH_API hardsigmoid_backward { + 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::hardsigmoid_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "hardsigmoid_backward(Tensor grad_output, Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogram.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogram.h new file mode 100644 index 0000000000000000000000000000000000000000..d240d8510e5064db0cddc9d0a75797ba3caac4ec --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogram.h @@ -0,0 +1,53 @@ +#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::histogram.bins_tensor_out(Tensor self, Tensor bins, *, Tensor? weight=None, bool density=False, Tensor(a!) hist, Tensor(b!) bin_edges) -> (Tensor(a!) hist, Tensor(b!) bin_edges) +inline ::std::tuple histogram_out(at::Tensor & hist, at::Tensor & bin_edges, const at::Tensor & self, const at::Tensor & bins, const c10::optional & weight={}, bool density=false) { + return at::_ops::histogram_bins_tensor_out::call(self, bins, weight, density, hist, bin_edges); +} +// aten::histogram.bins_tensor_out(Tensor self, Tensor bins, *, Tensor? weight=None, bool density=False, Tensor(a!) hist, Tensor(b!) bin_edges) -> (Tensor(a!) hist, Tensor(b!) bin_edges) +inline ::std::tuple histogram_outf(const at::Tensor & self, const at::Tensor & bins, const c10::optional & weight, bool density, at::Tensor & hist, at::Tensor & bin_edges) { + return at::_ops::histogram_bins_tensor_out::call(self, bins, weight, density, hist, bin_edges); +} + +// aten::histogram.bins_tensor(Tensor self, Tensor bins, *, Tensor? weight=None, bool density=False) -> (Tensor hist, Tensor bin_edges) +inline ::std::tuple histogram(const at::Tensor & self, const at::Tensor & bins, const c10::optional & weight={}, bool density=false) { + return at::_ops::histogram_bins_tensor::call(self, bins, weight, density); +} + +// aten::histogram.bin_ct_out(Tensor self, int bins=100, *, float[]? range=None, Tensor? weight=None, bool density=False, Tensor(a!) hist, Tensor(b!) bin_edges) -> (Tensor(a!) hist, Tensor(b!) bin_edges) +inline ::std::tuple histogram_out(at::Tensor & hist, at::Tensor & bin_edges, const at::Tensor & self, int64_t bins=100, c10::optional> range=c10::nullopt, const c10::optional & weight={}, bool density=false) { + return at::_ops::histogram_bin_ct_out::call(self, bins, range, weight, density, hist, bin_edges); +} +// aten::histogram.bin_ct_out(Tensor self, int bins=100, *, float[]? range=None, Tensor? weight=None, bool density=False, Tensor(a!) hist, Tensor(b!) bin_edges) -> (Tensor(a!) hist, Tensor(b!) bin_edges) +inline ::std::tuple histogram_outf(const at::Tensor & self, int64_t bins, c10::optional> range, const c10::optional & weight, bool density, at::Tensor & hist, at::Tensor & bin_edges) { + return at::_ops::histogram_bin_ct_out::call(self, bins, range, weight, density, hist, bin_edges); +} + +// aten::histogram.bin_ct(Tensor self, int bins=100, *, float[]? range=None, Tensor? weight=None, bool density=False) -> (Tensor hist, Tensor bin_edges) +inline ::std::tuple histogram(const at::Tensor & self, int64_t bins=100, c10::optional> range=c10::nullopt, const c10::optional & weight={}, bool density=false) { + return at::_ops::histogram_bin_ct::call(self, bins, range, weight, density); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_reduce.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_reduce.h new file mode 100644 index 0000000000000000000000000000000000000000..096df260c47151873ba140ee9eb0a41403d1e6d7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_reduce.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::index_reduce.out(Tensor self, int dim, Tensor index, Tensor source, str reduce, *, bool include_self=True, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & index_reduce_out(at::Tensor & out, const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source, c10::string_view reduce, bool include_self=true) { + return at::_ops::index_reduce_out::call(self, dim, index, source, reduce, include_self, out); +} +// aten::index_reduce.out(Tensor self, int dim, Tensor index, Tensor source, str reduce, *, bool include_self=True, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & index_reduce_outf(const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source, c10::string_view reduce, bool include_self, at::Tensor & out) { + return at::_ops::index_reduce_out::call(self, dim, index, source, reduce, include_self, out); +} + +// aten::index_reduce(Tensor self, int dim, Tensor index, Tensor source, str reduce, *, bool include_self=True) -> Tensor +inline at::Tensor index_reduce(const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source, c10::string_view reduce, bool include_self=true) { + return at::_ops::index_reduce::call(self, dim, index, source, reduce, include_self); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_floating_point_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_floating_point_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7985002a7a2a17264da404c596cdec3d4ec93a71 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_floating_point_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 is_floating_point { + using schema = 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::is_floating_point") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "is_floating_point(Tensor self) -> bool") + static bool call(const at::Tensor & self); + static bool 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/is_same_size_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_same_size_native.h new file mode 100644 index 0000000000000000000000000000000000000000..16a1354bd69d23c69894a311381460d96d579d51 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_same_size_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_same_size(const at::Tensor & self, const at::Tensor & other); +TORCH_API bool nested_is_same_size(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/less_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/less_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1787471c9f44c97f73334aefb426695c30091f5d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/less_compositeimplicitautograd_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 compositeimplicitautograd { + +TORCH_API at::Tensor less(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & less_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & less_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +TORCH_API at::Tensor & less_(at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor less(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & less_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & less_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & less_(at::Tensor & self, const at::Tensor & other); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cross_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cross_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..fea8090dbaea3f9be8d5592cd2cb91ac7ac1d1b4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cross_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_linalg_cross : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, const at::Tensor & other, int64_t dim); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_pinv_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_pinv_native.h new file mode 100644 index 0000000000000000000000000000000000000000..346dd90b8d52afcaf6dba6061ad7255b87c780db --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_pinv_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 + + +namespace at { +namespace native { +TORCH_API at::Tensor & linalg_pinv_out(const at::Tensor & self, const c10::optional & atol, const c10::optional & rtol, bool hermitian, at::Tensor & out); +TORCH_API at::Tensor linalg_pinv(const at::Tensor & self, const c10::optional & atol={}, const c10::optional & rtol={}, bool hermitian=false); +TORCH_API at::Tensor linalg_pinv(const at::Tensor & self, c10::optional atol=c10::nullopt, c10::optional rtol=c10::nullopt, bool hermitian=false); +TORCH_API at::Tensor & linalg_pinv_out(const at::Tensor & self, c10::optional atol, c10::optional rtol, bool hermitian, at::Tensor & out); +TORCH_API at::Tensor linalg_pinv(const at::Tensor & self, double rcond, bool hermitian=false); +TORCH_API at::Tensor & linalg_pinv_out(const at::Tensor & self, double rcond, bool hermitian, at::Tensor & out); +TORCH_API at::Tensor linalg_pinv(const at::Tensor & self, const at::Tensor & rcond, bool hermitian=false); +TORCH_API at::Tensor & linalg_pinv_out(const at::Tensor & self, const at::Tensor & rcond, bool hermitian, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lu_unpack_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lu_unpack_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..33a48f21e220762c6041677d52a654dffef51ad9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lu_unpack_cpu_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 ::std::tuple lu_unpack(const at::Tensor & LU_data, const at::Tensor & LU_pivots, bool unpack_data=true, bool unpack_pivots=true); +TORCH_API ::std::tuple lu_unpack_out(at::Tensor & P, at::Tensor & L, at::Tensor & U, const at::Tensor & LU_data, const at::Tensor & LU_pivots, bool unpack_data=true, bool unpack_pivots=true); +TORCH_API ::std::tuple lu_unpack_outf(const at::Tensor & LU_data, const at::Tensor & LU_pivots, bool unpack_data, bool unpack_pivots, at::Tensor & P, at::Tensor & L, at::Tensor & U); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lu_unpack_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lu_unpack_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..2b6e917eb0f5b7d1732057be27b08c03e7aff98a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lu_unpack_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_lu_unpack : public at::impl::MetaBase { + + + void meta(const at::Tensor & LU_data, const at::Tensor & LU_pivots, bool unpack_data, bool unpack_pivots); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_native.h new file mode 100644 index 0000000000000000000000000000000000000000..c3abb1a8e640d501394db45eff6ed4bd91b57e1b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_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 masked_scatter(const at::Tensor & self, const at::Tensor & mask, const at::Tensor & source); +TORCH_API at::Tensor & masked_scatter_out(const at::Tensor & self, const at::Tensor & mask, const at::Tensor & source, at::Tensor & out); +TORCH_API at::Tensor & masked_scatter__cpu(at::Tensor & self, const at::Tensor & mask, const at::Tensor & source); +TORCH_API at::Tensor & masked_scatter__cuda(at::Tensor & self, const at::Tensor & mask, const at::Tensor & source); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mean_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mean_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..9aab4991fb2641ffef0b4e3f37218bbc77a20107 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mean_ops.h @@ -0,0 +1,72 @@ +#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 mean { + using schema = at::Tensor (const at::Tensor &, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::mean") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mean(Tensor self, *, ScalarType? dtype=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::optional dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::optional dtype); +}; + +struct TORCH_API mean_dim { + using schema = at::Tensor (const at::Tensor &, at::OptionalIntArrayRef, bool, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::mean") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dim") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mean.dim(Tensor self, int[1]? dim, bool keepdim=False, *, ScalarType? dtype=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype); +}; + +struct TORCH_API mean_out { + using schema = at::Tensor & (const at::Tensor &, at::OptionalIntArrayRef, bool, 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::mean") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mean.out(Tensor self, int[1]? dim, bool keepdim=False, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype, at::Tensor & out); +}; + +struct TORCH_API mean_names_dim { + using schema = at::Tensor (const at::Tensor &, at::DimnameList, bool, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::mean") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names_dim") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mean.names_dim(Tensor self, Dimname[1] dim, bool keepdim=False, *, ScalarType? dtype=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::DimnameList dim, bool keepdim, c10::optional dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::DimnameList dim, bool keepdim, c10::optional dtype); +}; + +struct TORCH_API mean_names_out { + using schema = at::Tensor & (const at::Tensor &, at::DimnameList, bool, 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::mean") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mean.names_out(Tensor self, Dimname[1] dim, bool keepdim=False, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::DimnameList dim, bool keepdim, c10::optional dtype, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::DimnameList dim, bool keepdim, c10::optional dtype, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_linear_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_linear_native.h new file mode 100644 index 0000000000000000000000000000000000000000..be62a413cc163ddd7d66ab3b72ac0915bafba504 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_linear_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 & mkldnn_linear_out(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::Tensor & out); +TORCH_API at::Tensor mkldnn_linear(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias={}); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..6af961bf25b378abc75e8707b0ca2bc5d2af20a3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mm_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 mm { + 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::mm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mm(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); +}; + +struct TORCH_API mm_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::mm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "mm.out(Tensor self, Tensor mat2, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & mat2, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & mat2, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_group_norm_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_group_norm_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..315e8fe61a3220ca6a66b607fc5000e1c78c9e24 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_group_norm_compositeexplicitautograd_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 ::std::tuple native_group_norm(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, int64_t N, int64_t C, int64_t HxW, int64_t group, double eps); +TORCH_API ::std::tuple native_group_norm_symint(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, c10::SymInt N, c10::SymInt C, c10::SymInt HxW, int64_t group, double eps); +TORCH_API ::std::tuple native_group_norm_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, int64_t N, int64_t C, int64_t HxW, int64_t group, double eps); +TORCH_API ::std::tuple native_group_norm_outf(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, int64_t N, int64_t C, int64_t HxW, int64_t group, double eps, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); +TORCH_API ::std::tuple native_group_norm_symint_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, c10::SymInt N, c10::SymInt C, c10::SymInt HxW, int64_t group, double eps); +TORCH_API ::std::tuple native_group_norm_symint_outf(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, c10::SymInt N, c10::SymInt C, c10::SymInt HxW, int64_t group, double eps, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad.h new file mode 100644 index 0000000000000000000000000000000000000000..2d6bb6e9e4bb1d2b91650df93c384e9d117509df --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad.h @@ -0,0 +1,47 @@ +#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::pad(Tensor self, SymInt[] pad, str mode="constant", float? value=None) -> Tensor +inline at::Tensor pad(const at::Tensor & self, at::IntArrayRef pad, c10::string_view mode="constant", c10::optional value=c10::nullopt) { + return at::_ops::pad::call(self, c10::fromIntArrayRefSlow(pad), mode, value); +} +namespace symint { + template ::value>> + at::Tensor pad(const at::Tensor & self, at::IntArrayRef pad, c10::string_view mode="constant", c10::optional value=c10::nullopt) { + return at::_ops::pad::call(self, c10::fromIntArrayRefSlow(pad), mode, value); + } +} + +// aten::pad(Tensor self, SymInt[] pad, str mode="constant", float? value=None) -> Tensor +inline at::Tensor pad_symint(const at::Tensor & self, c10::SymIntArrayRef pad, c10::string_view mode="constant", c10::optional value=c10::nullopt) { + return at::_ops::pad::call(self, pad, mode, value); +} +namespace symint { + template ::value>> + at::Tensor pad(const at::Tensor & self, c10::SymIntArrayRef pad, c10::string_view mode="constant", c10::optional value=c10::nullopt) { + return at::_ops::pad::call(self, pad, mode, value); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad_sequence.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad_sequence.h new file mode 100644 index 0000000000000000000000000000000000000000..9981f845733ee67046ab8067500f69e46a03d725 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad_sequence.h @@ -0,0 +1,30 @@ +#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::pad_sequence(Tensor[] sequences, bool batch_first=False, float padding_value=0.0) -> Tensor +inline at::Tensor pad_sequence(at::TensorList sequences, bool batch_first=false, double padding_value=0.0) { + return at::_ops::pad_sequence::call(sequences, batch_first, padding_value); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/qscheme_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/qscheme_native.h new file mode 100644 index 0000000000000000000000000000000000000000..dd3531f9f8db845f2dc37c5b70b1de17c6ecf929 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/qscheme_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::QScheme qscheme_quant(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rad2deg_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rad2deg_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a7c3fe4b15bb393d83404b468a2f5b0571d28712 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rad2deg_compositeexplicitautograd_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 rad2deg(const at::Tensor & self); +TORCH_API at::Tensor & rad2deg_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & rad2deg_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & rad2deg_(at::Tensor & self); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9ca3e1ffa90e2ae830644b69c8c6fef7f4e4e2ec --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_compositeimplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 scatter(const at::Tensor & self, at::Dimname dim, const at::Tensor & index, const at::Tensor & src); +TORCH_API at::Tensor scatter(const at::Tensor & self, at::Dimname dim, const at::Tensor & index, const at::Scalar & value); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sigmoid_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sigmoid_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..2048840db34c15a10054107ce94296f5c94023dd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sigmoid_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_sigmoid : public TensorIteratorBase { + + + void meta(const at::Tensor & self); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sign_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sign_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a1ea09f5b7ab748eaf490155a5e0dc97fc8e2e68 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sign_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 at::Tensor sign(const at::Tensor & self); +TORCH_API at::Tensor & sign_(at::Tensor & self); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sin_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sin_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b38bdb546022fd0aa72dd89cd460c2d9fdf6fab5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sin_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 sin(const at::Tensor & self); +TORCH_API at::Tensor & sin_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & sin_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & sin_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b5a00b6e375d645ce3f53b4f148efc99c44d0f4e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_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 smooth_l1_loss_backward_grad_input { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const at::Tensor &, 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::smooth_l1_loss_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "grad_input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "smooth_l1_loss_backward.grad_input(Tensor grad_output, Tensor self, Tensor target, int reduction, float beta, *, Tensor(a!) grad_input) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double beta, at::Tensor & grad_input); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double beta, at::Tensor & grad_input); +}; + +struct TORCH_API smooth_l1_loss_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, 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::smooth_l1_loss_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "smooth_l1_loss_backward(Tensor grad_output, Tensor self, Tensor target, int reduction, float beta) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double beta); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double beta); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softplus_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softplus_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7378f288894ebe7be61f5a0854fde530604862e9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softplus_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 softplus_backward_grad_input { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const at::Scalar &, 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::softplus_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "grad_input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "softplus_backward.grad_input(Tensor grad_output, Tensor self, Scalar beta, Scalar threshold, *, Tensor(a!) grad_input) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & beta, const at::Scalar & threshold, at::Tensor & grad_input); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & beta, const at::Scalar & threshold, at::Tensor & grad_input); +}; + +struct TORCH_API softplus_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Scalar &, 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::softplus_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "softplus_backward(Tensor grad_output, Tensor self, Scalar beta, Scalar threshold) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & beta, const at::Scalar & threshold); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & beta, const at::Scalar & threshold); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_backward_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_backward_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..08059cd739556de5621adbd6df5c04a11c290d83 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_backward_cpu_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 softshrink_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd); +TORCH_API at::Tensor & softshrink_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd); +TORCH_API at::Tensor & softshrink_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd, at::Tensor & grad_input); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..483f0d5eafde24f9d8b42075df81b846f0d3786c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_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 special_entr(const at::Tensor & self); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfc_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfc_native.h new file mode 100644 index 0000000000000000000000000000000000000000..464e8b2a83f2d67ee74937d996c8e1f88cba5614 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfc_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 special_erfc(const at::Tensor & self); +TORCH_API at::Tensor & special_erfc_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/special_modified_bessel_i0_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i0_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..da22683ca6c330bb7a8b9c030671075e5f7071e8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i0_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_modified_bessel_i0 : public TensorIteratorBase { + + + void meta(const at::Tensor & self); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_u_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_u_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..8ffcc363904171c64541de187caec1d712283825 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_u_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_u : 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/special_shifted_chebyshev_polynomial_v_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_v_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..da19a90b7eba8590435e29ca396873f1c3e009de --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_v_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_v : 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/std_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/std_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0e223e76a9a0651eaaed8453ff2759006b04623c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/std_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 std(const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, const c10::optional & correction=c10::nullopt, bool keepdim=false); +TORCH_API at::Tensor & std_out(at::Tensor & out, const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, const c10::optional & correction=c10::nullopt, bool keepdim=false); +TORCH_API at::Tensor & std_outf(const at::Tensor & self, at::OptionalIntArrayRef dim, const c10::optional & correction, bool keepdim, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8f230420071450eb235c6eddbcd093f09f8f739f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_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 at::Tensor upsample_bilinear2d(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor upsample_bilinear2d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest3d_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest3d_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..2f5e8085958f00e1bfc7d6c908b2e9bfc279d4e5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest3d_backward_native.h @@ -0,0 +1,26 @@ +#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_upsample_nearest3d_backward_out_cpu : public at::meta::structured_upsample_nearest3d_backward { +void impl(const at::Tensor & grad_output, at::ArrayRef output_size, at::ArrayRef input_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & grad_input); +}; +struct TORCH_API structured_upsample_nearest3d_backward_out_cuda : public at::meta::structured_upsample_nearest3d_backward { +void impl(const at::Tensor & grad_output, at::ArrayRef output_size, at::ArrayRef input_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, 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/vander.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/vander.h new file mode 100644 index 0000000000000000000000000000000000000000..a9ad0421b69082c667156284190d21a6a83a1a24 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/vander.h @@ -0,0 +1,30 @@ +#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::vander(Tensor x, int? N=None, bool increasing=False) -> Tensor +inline at::Tensor vander(const at::Tensor & x, c10::optional N=c10::nullopt, bool increasing=false) { + return at::_ops::vander::call(x, N, increasing); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..0547319778f01264a924783f72fad970d45c0136 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_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 view_as_complex { + 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::view_as_complex") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "view_as_complex(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/vstack_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/vstack_native.h new file mode 100644 index 0000000000000000000000000000000000000000..bf7b6a464aa6c2e9842baa1d1e0459f7f73ee90b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/vstack_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 vstack(at::TensorList tensors); +TORCH_API at::Tensor & vstack_out(at::TensorList tensors, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/xor_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/xor_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..35bff7a8d8d0961b5abddb41ab5f8cd914066518 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/xor_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 __xor___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::__xor__") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "__xor__.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 __xor___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::__xor__") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "__xor__.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 __ixor___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::__ixor__") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "__ixor__.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 __ixor___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::__ixor__") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "__ixor__.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/nn/modules/__pycache__/loss.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/__pycache__/loss.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..342ff6b3c1b4a6c0139c32b0bdb56f4ad03c5fbf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/__pycache__/loss.cpython-311.pyc @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecddf5719c13f08ab50ac0715c85c66f020a50a14e0f7828472e84279c894a88 +size 104698 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/__pycache__/module.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/__pycache__/module.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ee186d522f9ad1d3b4807a0133a2271e39336485 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/__pycache__/module.cpython-311.pyc @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6298d8f5564b74144277b76c203f1ffedb3d3b8b22ba1e7898cd6ab406132632 +size 129565