diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_aminmax_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_aminmax_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b2760bff6b9b44a045ee857fd07d1bd526ed6cc9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_aminmax_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 ::std::tuple _aminmax_out(const at::Tensor & self, at::Tensor & out0, at::Tensor & out1); +TORCH_API ::std::tuple _aminmax_all(const at::Tensor & self); +TORCH_API ::std::tuple _aminmax_dim_out(const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & out0, at::Tensor & out1); +TORCH_API ::std::tuple _aminmax(const at::Tensor & self, int64_t dim, bool keepdim=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_async.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_async.h new file mode 100644 index 0000000000000000000000000000000000000000..3bb927b8c574c342ee7c7bfa968331a0b107f807 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_async.h @@ -0,0 +1,35 @@ +#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::_assert_async(Tensor self) -> () +inline void _assert_async(const at::Tensor & self) { + return at::_ops::_assert_async::call(self); +} + +// aten::_assert_async.msg(Tensor self, str assert_msg) -> () +inline void _assert_async(const at::Tensor & self, c10::string_view assert_msg) { + return at::_ops::_assert_async_msg::call(self, assert_msg); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..07012a5b9d7026c4f7b2cb0e8568c20b640bce42 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_backward.h @@ -0,0 +1,26 @@ +#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 { + + + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7fe191bf0037a7db4435ac2356e1255f73e5fb1a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_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 _convolution(const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool transposed, at::IntArrayRef output_padding, int64_t groups, bool benchmark, bool deterministic, bool cudnn_enabled); +TORCH_API at::Tensor _convolution_symint(const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, bool transposed, at::IntArrayRef output_padding, c10::SymInt groups, bool benchmark, bool deterministic, bool cudnn_enabled); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ed70977835f4549fb593ec4e04f6f0a362f11c8c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_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 ::std::tuple _embedding_bag_forward_only_out(const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, bool scale_grad_by_freq, int64_t mode, bool sparse, const c10::optional & per_sample_weights, bool include_last_offset, int64_t padding_idx, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3); +TORCH_API ::std::tuple _embedding_bag_forward_only_cpu(const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, bool scale_grad_by_freq=false, int64_t mode=0, bool sparse=false, const c10::optional & per_sample_weights={}, bool include_last_offset=false, int64_t padding_idx=-1); +TORCH_API ::std::tuple _embedding_bag_forward_only_cuda(const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, bool scale_grad_by_freq=false, int64_t mode=0, bool sparse=false, const c10::optional & per_sample_weights={}, bool include_last_offset=false, int64_t padding_idx=-1); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_per_sample_weights_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_per_sample_weights_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d19c516775ba49979eef39a20b36e0a22d18751c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_per_sample_weights_backward_cuda_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor _embedding_bag_per_sample_weights_backward(const at::Tensor & grad, const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, const at::Tensor & offset2bag, int64_t mode, int64_t padding_idx=-1); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_cosh_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_cosh_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ed494719f4fbbe1cf69ea634f42b6e9d7503cdb7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_cosh_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_cosh_out(at::TensorList out, at::TensorList self); +TORCH_API void _foreach_cosh_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_erf_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_erf_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1da6b839e7a5ff54aa1e92aa11c91f9e067c26c6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_erf_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_erf_out(at::TensorList out, at::TensorList self); +TORCH_API void _foreach_erf_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_erf_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_erf_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9b81a69870a4a9c05f8e07445de08c69686107c4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_erf_cuda_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::vector _foreach_erf(at::TensorList self); +TORCH_API void _foreach_erf_(at::TensorList self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_neg_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_neg_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2712134847d4fea3c58c91f02a0251ba627f2eb5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_neg_cuda_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::vector _foreach_neg(at::TensorList self); +TORCH_API void _foreach_neg_(at::TensorList self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_norm_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_norm_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9d34b7718c758821257a9b62f5746099d803d41c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_norm_cpu_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API ::std::vector _foreach_norm(at::TensorList self, const at::Scalar & ord=2); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_adam.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_adam.h new file mode 100644 index 0000000000000000000000000000000000000000..09a067936d524f0a6fdbd4263c0e935fb346c560 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_adam.h @@ -0,0 +1,63 @@ +#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::_fused_adam_(Tensor(a!)[] self, Tensor(b!)[] grads, Tensor(c!)[] exp_avgs, Tensor(d!)[] exp_avg_sqs, Tensor(e!)[] max_exp_avg_sqs, Tensor[] state_steps, *, float lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None) -> () +inline void _fused_adam_(at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, double lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const c10::optional & grad_scale={}, const c10::optional & found_inf={}) { + return at::_ops::_fused_adam_::call(self, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, lr, beta1, beta2, weight_decay, eps, amsgrad, maximize, grad_scale, found_inf); +} + +// aten::_fused_adam_.tensor_lr(Tensor(a!)[] self, Tensor(b!)[] grads, Tensor(c!)[] exp_avgs, Tensor(d!)[] exp_avg_sqs, Tensor(e!)[] max_exp_avg_sqs, Tensor[] state_steps, *, Tensor lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None) -> () +inline void _fused_adam_(at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, const at::Tensor & lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const c10::optional & grad_scale={}, const c10::optional & found_inf={}) { + return at::_ops::_fused_adam__tensor_lr::call(self, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, lr, beta1, beta2, weight_decay, eps, amsgrad, maximize, grad_scale, found_inf); +} + +// aten::_fused_adam.out(Tensor[] self, Tensor(b!)[] grads, Tensor(c!)[] exp_avgs, Tensor(d!)[] exp_avg_sqs, Tensor(e!)[] max_exp_avg_sqs, Tensor[] state_steps, *, float lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None, Tensor(a!)[] out) -> () +inline void _fused_adam_out(at::TensorList out, at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, double lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const c10::optional & grad_scale={}, const c10::optional & found_inf={}) { + return at::_ops::_fused_adam_out::call(self, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, lr, beta1, beta2, weight_decay, eps, amsgrad, maximize, grad_scale, found_inf, out); +} +// aten::_fused_adam.out(Tensor[] self, Tensor(b!)[] grads, Tensor(c!)[] exp_avgs, Tensor(d!)[] exp_avg_sqs, Tensor(e!)[] max_exp_avg_sqs, Tensor[] state_steps, *, float lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None, Tensor(a!)[] out) -> () +inline void _fused_adam_outf(at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, double lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const c10::optional & grad_scale, const c10::optional & found_inf, at::TensorList out) { + return at::_ops::_fused_adam_out::call(self, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, lr, beta1, beta2, weight_decay, eps, amsgrad, maximize, grad_scale, found_inf, out); +} + +// aten::_fused_adam(Tensor[] self, Tensor[] grads, Tensor[] exp_avgs, Tensor[] exp_avg_sqs, Tensor[] max_exp_avg_sqs, Tensor[] state_steps, *, float lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None) -> (Tensor[] self_out, Tensor[] grads_out, Tensor[] exp_avgs_out, Tensor[] exp_avg_sqs_out, Tensor[] max_exp_avg_sqs_out) +inline ::std::tuple<::std::vector,::std::vector,::std::vector,::std::vector,::std::vector> _fused_adam(at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, double lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const c10::optional & grad_scale={}, const c10::optional & found_inf={}) { + return at::_ops::_fused_adam::call(self, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, lr, beta1, beta2, weight_decay, eps, amsgrad, maximize, grad_scale, found_inf); +} + +// aten::_fused_adam.tensor_lr_out(Tensor[] self, Tensor(b!)[] grads, Tensor(c!)[] exp_avgs, Tensor(d!)[] exp_avg_sqs, Tensor(e!)[] max_exp_avg_sqs, Tensor[] state_steps, *, Tensor lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None, Tensor(a!)[] out) -> () +inline void _fused_adam_out(at::TensorList out, at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, const at::Tensor & lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const c10::optional & grad_scale={}, const c10::optional & found_inf={}) { + return at::_ops::_fused_adam_tensor_lr_out::call(self, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, lr, beta1, beta2, weight_decay, eps, amsgrad, maximize, grad_scale, found_inf, out); +} +// aten::_fused_adam.tensor_lr_out(Tensor[] self, Tensor(b!)[] grads, Tensor(c!)[] exp_avgs, Tensor(d!)[] exp_avg_sqs, Tensor(e!)[] max_exp_avg_sqs, Tensor[] state_steps, *, Tensor lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None, Tensor(a!)[] out) -> () +inline void _fused_adam_outf(at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, const at::Tensor & lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const c10::optional & grad_scale, const c10::optional & found_inf, at::TensorList out) { + return at::_ops::_fused_adam_tensor_lr_out::call(self, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, lr, beta1, beta2, weight_decay, eps, amsgrad, maximize, grad_scale, found_inf, out); +} + +// aten::_fused_adam.tensor_lr(Tensor[] self, Tensor[] grads, Tensor[] exp_avgs, Tensor[] exp_avg_sqs, Tensor[] max_exp_avg_sqs, Tensor[] state_steps, *, Tensor lr, float beta1, float beta2, float weight_decay, float eps, bool amsgrad, bool maximize, Tensor? grad_scale=None, Tensor? found_inf=None) -> (Tensor[] self_out, Tensor[] grads_out, Tensor[] exp_avgs_out, Tensor[] exp_avg_sqs_out, Tensor[] max_exp_avg_sqs_out) +inline ::std::tuple<::std::vector,::std::vector,::std::vector,::std::vector,::std::vector> _fused_adam(at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, const at::Tensor & lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const c10::optional & grad_scale={}, const c10::optional & found_inf={}) { + return at::_ops::_fused_adam_tensor_lr::call(self, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, lr, beta1, beta2, weight_decay, eps, amsgrad, maximize, grad_scale, found_inf); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_index_put_impl_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_index_put_impl_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..26fda5429170da1dca9013576a10092eab376b71 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_index_put_impl_compositeexplicitautograd_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor _index_put_impl(const at::Tensor & self, const c10::List> & indices, const at::Tensor & values, bool accumulate=false, bool unsafe=false); +TORCH_API at::Tensor & _index_put_impl_out(at::Tensor & out, const at::Tensor & self, const c10::List> & indices, const at::Tensor & values, bool accumulate=false, bool unsafe=false); +TORCH_API at::Tensor & _index_put_impl_outf(const at::Tensor & self, const c10::List> & indices, const at::Tensor & values, bool accumulate, bool unsafe, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mixed_dtypes_linear_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mixed_dtypes_linear_native.h new file mode 100644 index 0000000000000000000000000000000000000000..2d85eed9b0873a13e775973fdcff7a4ac04be929 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mixed_dtypes_linear_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 _mixed_dtypes_linear(const at::Tensor & input, const at::Tensor & weight, const at::Tensor & scale, const c10::optional & bias={}, c10::optional activation=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution.h new file mode 100644 index 0000000000000000000000000000000000000000..8da065897796de72743b9262787f4e0691231a44 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution.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::_mps_convolution(Tensor self, Tensor weight, Tensor? bias, SymInt[] padding, SymInt[] stride, SymInt[] dilation, SymInt groups) -> Tensor +inline at::Tensor _mps_convolution(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups) { + return at::_ops::_mps_convolution::call(self, weight, bias, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups); +} +namespace symint { + template ::value>> + at::Tensor _mps_convolution(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups) { + return at::_ops::_mps_convolution::call(self, weight, bias, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups); + } +} + +// aten::_mps_convolution(Tensor self, Tensor weight, Tensor? bias, SymInt[] padding, SymInt[] stride, SymInt[] dilation, SymInt groups) -> Tensor +inline at::Tensor _mps_convolution_symint(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups) { + return at::_ops::_mps_convolution::call(self, weight, bias, padding, stride, dilation, groups); +} +namespace symint { + template ::value>> + at::Tensor _mps_convolution(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups) { + return at::_ops::_mps_convolution::call(self, weight, bias, padding, stride, dilation, groups); + } +} + +// aten::_mps_convolution.out(Tensor self, Tensor weight, Tensor? bias, SymInt[] padding, SymInt[] stride, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _mps_convolution_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups) { + return at::_ops::_mps_convolution_out::call(self, weight, bias, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups, out); +} +namespace symint { + template ::value>> + at::Tensor & _mps_convolution_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups) { + return at::_ops::_mps_convolution_out::call(self, weight, bias, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups, out); + } +} + +// aten::_mps_convolution.out(Tensor self, Tensor weight, Tensor? bias, SymInt[] padding, SymInt[] stride, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _mps_convolution_outf(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, at::Tensor & out) { + return at::_ops::_mps_convolution_out::call(self, weight, bias, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups, out); +} +namespace symint { + template ::value>> + at::Tensor & _mps_convolution_outf(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, at::Tensor & out) { + return at::_ops::_mps_convolution_out::call(self, weight, bias, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups, out); + } +} + +// aten::_mps_convolution.out(Tensor self, Tensor weight, Tensor? bias, SymInt[] padding, SymInt[] stride, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _mps_convolution_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups) { + return at::_ops::_mps_convolution_out::call(self, weight, bias, padding, stride, dilation, groups, out); +} +namespace symint { + template ::value>> + at::Tensor & _mps_convolution_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups) { + return at::_ops::_mps_convolution_out::call(self, weight, bias, padding, stride, dilation, groups, out); + } +} + +// aten::_mps_convolution.out(Tensor self, Tensor weight, Tensor? bias, SymInt[] padding, SymInt[] stride, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _mps_convolution_symint_outf(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out) { + return at::_ops::_mps_convolution_out::call(self, weight, bias, padding, stride, dilation, groups, out); +} +namespace symint { + template ::value>> + at::Tensor & _mps_convolution_outf(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out) { + return at::_ops::_mps_convolution_out::call(self, weight, bias, padding, stride, dilation, groups, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_batch_norm_legit_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_batch_norm_legit_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9721681c5294a31a144db41d87cc35cf383016c2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_batch_norm_legit_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 _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); +TORCH_API ::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); +TORCH_API ::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); +TORCH_API ::std::tuple _native_batch_norm_legit(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, bool training, double momentum, double eps); +TORCH_API ::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); +TORCH_API ::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); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pdist_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pdist_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..f0d4c7c650f7e5cef22da1c9e7d163c8434e5db8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pdist_backward_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 & _pdist_backward_out(const at::Tensor & grad, const at::Tensor & self, double p, const at::Tensor & pdist, at::Tensor & out); +TORCH_API at::Tensor _pdist_backward(const at::Tensor & grad, const at::Tensor & self, double p, const at::Tensor & pdist); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pdist_forward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pdist_forward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..80ddaa57d7f9e0647c10c06c1a2233e0d5aa282c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pdist_forward_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 & _pdist_forward_out(const at::Tensor & self, double p, at::Tensor & out); +TORCH_API at::Tensor _pdist_forward(const at::Tensor & self, double p=2); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_alias_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_alias_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..2b1d0e0e22698dae8fdf34caf80137660bfcbd06 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_alias_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 _reshape_alias { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_reshape_alias") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_reshape_alias(Tensor(a) self, SymInt[] size, SymInt[] stride) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef size, c10::SymIntArrayRef stride); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef size, c10::SymIntArrayRef stride); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_forward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_forward.h new file mode 100644 index 0000000000000000000000000000000000000000..3a40f38247b4381fbf221acff87f6f36c5c9b150 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_forward.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::_slow_conv2d_forward.output(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, *, Tensor(a!) output) -> Tensor(a!) +inline at::Tensor & _slow_conv2d_forward_out(at::Tensor & output, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::_slow_conv2d_forward_output::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), output); +} +namespace symint { + template ::value>> + at::Tensor & _slow_conv2d_forward_out(at::Tensor & output, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::_slow_conv2d_forward_output::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), output); + } +} + +// aten::_slow_conv2d_forward.output(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, *, Tensor(a!) output) -> Tensor(a!) +inline at::Tensor & _slow_conv2d_forward_outf(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & output) { + return at::_ops::_slow_conv2d_forward_output::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), output); +} +namespace symint { + template ::value>> + at::Tensor & _slow_conv2d_forward_outf(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & output) { + return at::_ops::_slow_conv2d_forward_output::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), output); + } +} + +// aten::_slow_conv2d_forward.output(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, *, Tensor(a!) output) -> Tensor(a!) +inline at::Tensor & _slow_conv2d_forward_symint_out(at::Tensor & output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding) { + return at::_ops::_slow_conv2d_forward_output::call(self, weight, kernel_size, bias, stride, padding, output); +} +namespace symint { + template ::value>> + at::Tensor & _slow_conv2d_forward_out(at::Tensor & output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding) { + return at::_ops::_slow_conv2d_forward_output::call(self, weight, kernel_size, bias, stride, padding, output); + } +} + +// aten::_slow_conv2d_forward.output(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, *, Tensor(a!) output) -> Tensor(a!) +inline at::Tensor & _slow_conv2d_forward_symint_outf(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, at::Tensor & output) { + return at::_ops::_slow_conv2d_forward_output::call(self, weight, kernel_size, bias, stride, padding, output); +} +namespace symint { + template ::value>> + at::Tensor & _slow_conv2d_forward_outf(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, at::Tensor & output) { + return at::_ops::_slow_conv2d_forward_output::call(self, weight, kernel_size, bias, stride, padding, output); + } +} + +// aten::_slow_conv2d_forward(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding) -> Tensor +inline at::Tensor _slow_conv2d_forward(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::_slow_conv2d_forward::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding)); +} +namespace symint { + template ::value>> + at::Tensor _slow_conv2d_forward(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::_slow_conv2d_forward::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding)); + } +} + +// aten::_slow_conv2d_forward(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding) -> Tensor +inline at::Tensor _slow_conv2d_forward_symint(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding) { + return at::_ops::_slow_conv2d_forward::call(self, weight, kernel_size, bias, stride, padding); +} +namespace symint { + template ::value>> + at::Tensor _slow_conv2d_forward(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding) { + return at::_ops::_slow_conv2d_forward::call(self, weight, kernel_size, bias, stride, padding); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_scramble_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_scramble_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..41dd474ad41359d693b3337c24222998c57f91f2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_scramble_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 _sobol_engine_scramble_ { + using schema = at::Tensor & (at::Tensor &, const at::Tensor &, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_sobol_engine_scramble_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_sobol_engine_scramble_(Tensor(a!) self, Tensor ltm, int dimension) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Tensor & ltm, int64_t dimension); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Tensor & ltm, int64_t dimension); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_copy_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_copy_native.h new file mode 100644 index 0000000000000000000000000000000000000000..df5e4b9fa36fa653524f485a3199725840a4ebc2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_copy_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 _to_copy(const at::Tensor & self, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}, bool non_blocking=false, c10::optional memory_format=c10::nullopt); +TORCH_API at::Tensor & _to_copy_out(const at::Tensor & self, bool non_blocking, c10::optional memory_format, at::Tensor & out); +TORCH_API at::Tensor _to_copy_nested(const at::Tensor & self, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}, bool non_blocking=false, c10::optional memory_format=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..27037ce7a445c3d0ea3f75710ce062758165e839 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _upsample_bilinear2d_aa_vec { + using schema = at::Tensor (const at::Tensor &, at::OptionalSymIntArrayRef, 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::_upsample_bilinear2d_aa") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "vec") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_upsample_bilinear2d_aa.vec(Tensor input, SymInt[]? output_size, bool align_corners, float[]? scale_factors) -> Tensor") + static at::Tensor call(const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); +}; + +struct TORCH_API _upsample_bilinear2d_aa_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymIntArrayRef, bool, c10::optional, 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::_upsample_bilinear2d_aa") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_upsample_bilinear2d_aa.out(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w, at::Tensor & out); +}; + +struct TORCH_API _upsample_bilinear2d_aa { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef, bool, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_upsample_bilinear2d_aa") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_upsample_bilinear2d_aa(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_differentiable_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_differentiable_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7c8c7e406cc8b1c91e22166e32a99001a777e99e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_differentiable_backward_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 ::std::tuple _weight_norm_differentiable_backward(const at::Tensor & grad_w, const at::Tensor & saved_v, const at::Tensor & saved_g, const at::Tensor & saved_norms, int64_t dim); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_differentiable_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_differentiable_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..51b61dda1b5d60c9fcba96ec544ed7d1be16c649 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_differentiable_backward_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 _weight_norm_differentiable_backward { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_weight_norm_differentiable_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_weight_norm_differentiable_backward(Tensor grad_w, Tensor saved_v, Tensor saved_g, Tensor saved_norms, int dim) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & grad_w, const at::Tensor & saved_v, const at::Tensor & saved_g, const at::Tensor & saved_norms, int64_t dim); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_w, const at::Tensor & saved_v, const at::Tensor & saved_g, const at::Tensor & saved_norms, int64_t dim); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_max_pool2d_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_max_pool2d_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d2464ca09e1416b25cd3beec54c4533c7d3451d5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_max_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 adaptive_max_pool2d_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & indices); +TORCH_API at::Tensor & adaptive_max_pool2d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & indices); +TORCH_API at::Tensor & adaptive_max_pool2d_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & indices, at::Tensor & grad_input); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_elemt_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_elemt_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f750d87abae951267a775c1adf3cfff629b8542e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_elemt_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 batch_norm_elemt(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, const at::Tensor & mean, const at::Tensor & invstd, double eps); +TORCH_API at::Tensor & batch_norm_elemt_out(at::Tensor & out, const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, const at::Tensor & mean, const at::Tensor & invstd, double eps); +TORCH_API at::Tensor & batch_norm_elemt_outf(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, const at::Tensor & mean, const at::Tensor & invstd, double eps, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/binary_cross_entropy_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/binary_cross_entropy_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..a103684b51adad393e222bd0a11fc9be04e8dd7a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/binary_cross_entropy_backward_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 binary_cross_entropy_backward_cpu(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean); +TORCH_API at::Tensor & binary_cross_entropy_backward_out_cpu(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, at::Tensor & grad_input); +TORCH_API at::Tensor binary_cross_entropy_backward_cuda(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean); +TORCH_API at::Tensor & binary_cross_entropy_backward_out_cuda(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, at::Tensor & grad_input); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bincount_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bincount_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cbd582bd3ae4c0f38c4ab3c019d053cf665f61f1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bincount_cpu_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor bincount(const at::Tensor & self, const c10::optional & weights={}, int64_t minlength=0); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/can_cast_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/can_cast_native.h new file mode 100644 index 0000000000000000000000000000000000000000..67b819cb64695188978d55db7df49c6141e7102b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/can_cast_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 bool can_cast(at::ScalarType from, at::ScalarType to); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chain_matmul_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chain_matmul_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..9354c948a10f649e7456946726e343bff5a644b4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chain_matmul_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 chain_matmul { + using schema = at::Tensor (at::TensorList); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::chain_matmul") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "chain_matmul(Tensor[] matrices) -> Tensor") + static at::Tensor call(at::TensorList matrices); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList matrices); +}; + +struct TORCH_API chain_matmul_out { + using schema = at::Tensor & (at::TensorList, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::chain_matmul") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "chain_matmul.out(Tensor[] matrices, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(at::TensorList matrices, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList matrices, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cross_entropy_loss_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cross_entropy_loss_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8204742aebc1ce9d60fe0faa027da9afd332fdbc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cross_entropy_loss_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 cross_entropy_loss(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean, int64_t ignore_index=-100, double label_smoothing=0.0); +TORCH_API at::Tensor cross_entropy_loss_symint(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean, c10::SymInt ignore_index=-100, double label_smoothing=0.0); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumprod_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumprod_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..283d3bcaddc2d3c96216c02da2cb1d1d9af07caf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumprod_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::cumprod_backward(Tensor grad, Tensor input, int dim, Tensor output) -> Tensor +inline at::Tensor cumprod_backward(const at::Tensor & grad, const at::Tensor & input, int64_t dim, const at::Tensor & output) { + return at::_ops::cumprod_backward::call(grad, input, dim, output); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumprod_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumprod_native.h new file mode 100644 index 0000000000000000000000000000000000000000..2270c63e5d028429a7bb03fb3db8717d129ebae8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumprod_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_cumprod_out : public at::meta::structured_cumprod { +void impl(const at::Tensor & self, int64_t dim, c10::optional dtype, const at::Tensor & out); +}; +TORCH_API at::Tensor cumprod(const at::Tensor & self, at::Dimname dim, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & cumprod_out(const at::Tensor & self, at::Dimname dim, c10::optional dtype, at::Tensor & out); +TORCH_API at::Tensor & cumprod_(at::Tensor & self, at::Dimname dim, c10::optional dtype=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/data_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/data_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8dee6aef370181014cf43e5e303114cece2930d0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/data_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 data(const at::Tensor & self); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dot_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dot_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..2d34c2dc0bf3fc4af4cf44f1557433f0763a2f3d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dot_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 dot { + 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::dot") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "dot(Tensor self, Tensor tensor) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & tensor); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & tensor); +}; + +struct TORCH_API dot_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::dot") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "dot.out(Tensor self, Tensor tensor, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & tensor, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & tensor, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_like_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_like_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4a1312e034a8ac42b8548d8812c46b0fac71b532 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_like_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 empty_like(const at::Tensor & self, at::TensorOptions options={}, c10::optional memory_format=c10::nullopt); +TORCH_API at::Tensor empty_like(const at::Tensor & self, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); +TORCH_API at::Tensor & empty_like_out(at::Tensor & out, const at::Tensor & self, c10::optional memory_format=c10::nullopt); +TORCH_API at::Tensor & empty_like_outf(const at::Tensor & self, c10::optional memory_format, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ihfft2_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ihfft2_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5b1d4206b2a7cc1bf849c40a884c3eff5042a3c5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ihfft2_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API fft_ihfft2 { + using schema = at::Tensor (const at::Tensor &, at::OptionalSymIntArrayRef, at::IntArrayRef, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::fft_ihfft2") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fft_ihfft2(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm); +}; + +struct TORCH_API fft_ihfft2_out { + using schema = const at::Tensor & (const at::Tensor &, at::OptionalSymIntArrayRef, at::IntArrayRef, c10::optional, 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::fft_ihfft2") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fft_ihfft2.out(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None, *, Tensor(a!) out) -> Tensor(a!)") + static const at::Tensor & call(const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm, const at::Tensor & out); + static const at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm, const at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ea620c6449484f5a7e4697f2e4837579a8011434 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_backward_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 glu_backward_cpu(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim); +TORCH_API at::Tensor & glu_backward_cpu_out(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim, at::Tensor & grad_input); +TORCH_API at::Tensor glu_backward_cuda(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim); +TORCH_API at::Tensor & glu_backward_cuda_out(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim, at::Tensor & grad_input); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..b3e63d53610c179e2cf61ed81accce26e1914372 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_backward.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::grid_sampler_3d_backward(Tensor grad_output, Tensor input, Tensor grid, int interpolation_mode, int padding_mode, bool align_corners, bool[2] output_mask) -> (Tensor, Tensor) +inline ::std::tuple grid_sampler_3d_backward(const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask) { + return at::_ops::grid_sampler_3d_backward::call(grad_output, input, grid, interpolation_mode, padding_mode, align_corners, output_mask); +} + +// aten::grid_sampler_3d_backward.out(Tensor grad_output, Tensor input, Tensor grid, int interpolation_mode, int padding_mode, bool align_corners, bool[2] output_mask, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple grid_sampler_3d_backward_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask) { + return at::_ops::grid_sampler_3d_backward_out::call(grad_output, input, grid, interpolation_mode, padding_mode, align_corners, output_mask, out0, out1); +} +// aten::grid_sampler_3d_backward.out(Tensor grad_output, Tensor input, Tensor grid, int interpolation_mode, int padding_mode, bool align_corners, bool[2] output_mask, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple grid_sampler_3d_backward_outf(const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1) { + return at::_ops::grid_sampler_3d_backward_out::call(grad_output, input, grid, interpolation_mode, padding_mode, align_corners, output_mask, out0, out1); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hamming_window.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hamming_window.h new file mode 100644 index 0000000000000000000000000000000000000000..947b6012b1365854d2d55d28ba88882be9a213ae --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hamming_window.h @@ -0,0 +1,97 @@ +#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::hamming_window(int window_length, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor hamming_window(int64_t window_length, at::TensorOptions options={}) { + return at::_ops::hamming_window::call(window_length, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +// aten::hamming_window(int window_length, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor hamming_window(int64_t window_length, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::hamming_window::call(window_length, dtype, layout, device, pin_memory); +} + +// aten::hamming_window.periodic(int window_length, bool periodic, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor hamming_window(int64_t window_length, bool periodic, at::TensorOptions options={}) { + return at::_ops::hamming_window_periodic::call(window_length, periodic, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +// aten::hamming_window.periodic(int window_length, bool periodic, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor hamming_window(int64_t window_length, bool periodic, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::hamming_window_periodic::call(window_length, periodic, dtype, layout, device, pin_memory); +} + +// aten::hamming_window.periodic_alpha(int window_length, bool periodic, float alpha, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor hamming_window(int64_t window_length, bool periodic, double alpha, at::TensorOptions options={}) { + return at::_ops::hamming_window_periodic_alpha::call(window_length, periodic, alpha, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +// aten::hamming_window.periodic_alpha(int window_length, bool periodic, float alpha, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor hamming_window(int64_t window_length, bool periodic, double alpha, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::hamming_window_periodic_alpha::call(window_length, periodic, alpha, dtype, layout, device, pin_memory); +} + +// aten::hamming_window.periodic_alpha_beta(int window_length, bool periodic, float alpha, float beta, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor hamming_window(int64_t window_length, bool periodic, double alpha, double beta, at::TensorOptions options={}) { + return at::_ops::hamming_window_periodic_alpha_beta::call(window_length, periodic, alpha, beta, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +// aten::hamming_window.periodic_alpha_beta(int window_length, bool periodic, float alpha, float beta, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor hamming_window(int64_t window_length, bool periodic, double alpha, double beta, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::hamming_window_periodic_alpha_beta::call(window_length, periodic, alpha, beta, dtype, layout, device, pin_memory); +} + +// aten::hamming_window.out(int window_length, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hamming_window_out(at::Tensor & out, int64_t window_length) { + return at::_ops::hamming_window_out::call(window_length, out); +} +// aten::hamming_window.out(int window_length, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hamming_window_outf(int64_t window_length, at::Tensor & out) { + return at::_ops::hamming_window_out::call(window_length, out); +} + +// aten::hamming_window.periodic_out(int window_length, bool periodic, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hamming_window_out(at::Tensor & out, int64_t window_length, bool periodic) { + return at::_ops::hamming_window_periodic_out::call(window_length, periodic, out); +} +// aten::hamming_window.periodic_out(int window_length, bool periodic, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hamming_window_outf(int64_t window_length, bool periodic, at::Tensor & out) { + return at::_ops::hamming_window_periodic_out::call(window_length, periodic, out); +} + +// aten::hamming_window.periodic_alpha_out(int window_length, bool periodic, float alpha, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hamming_window_out(at::Tensor & out, int64_t window_length, bool periodic, double alpha) { + return at::_ops::hamming_window_periodic_alpha_out::call(window_length, periodic, alpha, out); +} +// aten::hamming_window.periodic_alpha_out(int window_length, bool periodic, float alpha, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hamming_window_outf(int64_t window_length, bool periodic, double alpha, at::Tensor & out) { + return at::_ops::hamming_window_periodic_alpha_out::call(window_length, periodic, alpha, out); +} + +// aten::hamming_window.periodic_alpha_beta_out(int window_length, bool periodic, float alpha, float beta, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hamming_window_out(at::Tensor & out, int64_t window_length, bool periodic, double alpha, double beta) { + return at::_ops::hamming_window_periodic_alpha_beta_out::call(window_length, periodic, alpha, beta, out); +} +// aten::hamming_window.periodic_alpha_beta_out(int window_length, bool periodic, float alpha, float beta, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hamming_window_outf(int64_t window_length, bool periodic, double alpha, double beta, at::Tensor & out) { + return at::_ops::hamming_window_periodic_alpha_beta_out::call(window_length, periodic, alpha, beta, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_inference_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_inference_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..519b18dc7c7f6d15a70bbc1203402f0481044d18 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_inference_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_inference { + 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_inference") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "is_inference(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/kthvalue_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/kthvalue_native.h new file mode 100644 index 0000000000000000000000000000000000000000..05784c0c16064a03280f2381af66e13f4faf07a8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/kthvalue_native.h @@ -0,0 +1,25 @@ +#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 kthvalue(const at::Tensor & self, int64_t k, int64_t dim=-1, bool keepdim=false); +TORCH_API ::std::tuple kthvalue_out_cpu(const at::Tensor & self, int64_t k, int64_t dim, bool keepdim, at::Tensor & values, at::Tensor & indices); +TORCH_API ::std::tuple kthvalue_out_cuda(const at::Tensor & self, int64_t k, int64_t dim, bool keepdim, at::Tensor & values, at::Tensor & indices); +TORCH_API ::std::tuple kthvalue(const at::Tensor & self, int64_t k, at::Dimname dim, bool keepdim=false); +TORCH_API ::std::tuple kthvalue_out(const at::Tensor & self, int64_t k, at::Dimname dim, bool keepdim, at::Tensor & values, at::Tensor & indices); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp.h new file mode 100644 index 0000000000000000000000000000000000000000..1ed59c0b34e5734acc67601f12d550d26818604c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp.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::lerp.Scalar_out(Tensor self, Tensor end, Scalar weight, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & lerp_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & end, const at::Scalar & weight) { + return at::_ops::lerp_Scalar_out::call(self, end, weight, out); +} +// aten::lerp.Scalar_out(Tensor self, Tensor end, Scalar weight, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & lerp_outf(const at::Tensor & self, const at::Tensor & end, const at::Scalar & weight, at::Tensor & out) { + return at::_ops::lerp_Scalar_out::call(self, end, weight, out); +} + +// aten::lerp.Tensor_out(Tensor self, Tensor end, Tensor weight, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & lerp_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & end, const at::Tensor & weight) { + return at::_ops::lerp_Tensor_out::call(self, end, weight, out); +} +// aten::lerp.Tensor_out(Tensor self, Tensor end, Tensor weight, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & lerp_outf(const at::Tensor & self, const at::Tensor & end, const at::Tensor & weight, at::Tensor & out) { + return at::_ops::lerp_Tensor_out::call(self, end, weight, out); +} + +// aten::lerp.Scalar(Tensor self, Tensor end, Scalar weight) -> Tensor +inline at::Tensor lerp(const at::Tensor & self, const at::Tensor & end, const at::Scalar & weight) { + return at::_ops::lerp_Scalar::call(self, end, weight); +} + +// aten::lerp.Tensor(Tensor self, Tensor end, Tensor weight) -> Tensor +inline at::Tensor lerp(const at::Tensor & self, const at::Tensor & end, const at::Tensor & weight) { + return at::_ops::lerp_Tensor::call(self, end, weight); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cond.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cond.h new file mode 100644 index 0000000000000000000000000000000000000000..e9b3618b7a3e2c1fa2e1b9df2b728789e397d5cd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cond.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::linalg_cond(Tensor self, Scalar? p=None) -> Tensor +inline at::Tensor linalg_cond(const at::Tensor & self, const c10::optional & p=c10::nullopt) { + return at::_ops::linalg_cond::call(self, p); +} + +// aten::linalg_cond.out(Tensor self, Scalar? p=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_cond_out(at::Tensor & out, const at::Tensor & self, const c10::optional & p=c10::nullopt) { + return at::_ops::linalg_cond_out::call(self, p, out); +} +// aten::linalg_cond.out(Tensor self, Scalar? p=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_cond_outf(const at::Tensor & self, const c10::optional & p, at::Tensor & out) { + return at::_ops::linalg_cond_out::call(self, p, out); +} + +// aten::linalg_cond.p_str(Tensor self, str p) -> Tensor +inline at::Tensor linalg_cond(const at::Tensor & self, c10::string_view p) { + return at::_ops::linalg_cond_p_str::call(self, p); +} + +// aten::linalg_cond.p_str_out(Tensor self, str p, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_cond_out(at::Tensor & out, const at::Tensor & self, c10::string_view p) { + return at::_ops::linalg_cond_p_str_out::call(self, p, out); +} +// aten::linalg_cond.p_str_out(Tensor self, str p, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_cond_outf(const at::Tensor & self, c10::string_view p, at::Tensor & out) { + return at::_ops::linalg_cond_p_str_out::call(self, p, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_factor_ex_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_factor_ex_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..253e3d0b5039420d2d7905110cc48f9736b037e2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_factor_ex_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API ::std::tuple linalg_ldl_factor_ex(const at::Tensor & self, bool hermitian=false, bool check_errors=false); +TORCH_API ::std::tuple linalg_ldl_factor_ex_out(at::Tensor & LD, at::Tensor & pivots, at::Tensor & info, const at::Tensor & self, bool hermitian=false, bool check_errors=false); +TORCH_API ::std::tuple linalg_ldl_factor_ex_outf(const at::Tensor & self, bool hermitian, bool check_errors, at::Tensor & LD, at::Tensor & pivots, at::Tensor & info); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_ex_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_ex_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..ee0da01cebf4f2177455359ee13a47f256730fae --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_ex_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 linalg_lu_factor_ex { + using schema = ::std::tuple (const at::Tensor &, bool, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::linalg_lu_factor_ex") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "linalg_lu_factor_ex(Tensor A, *, bool pivot=True, bool check_errors=False) -> (Tensor LU, Tensor pivots, Tensor info)") + static ::std::tuple call(const at::Tensor & A, bool pivot, bool check_errors); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & A, bool pivot, bool check_errors); +}; + +struct TORCH_API linalg_lu_factor_ex_out { + using schema = ::std::tuple (const at::Tensor &, bool, bool, at::Tensor &, at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::linalg_lu_factor_ex") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "linalg_lu_factor_ex.out(Tensor A, *, bool pivot=True, bool check_errors=False, Tensor(a!) LU, Tensor(b!) pivots, Tensor(c!) info) -> (Tensor(a!) LU, Tensor(b!) pivots, Tensor(c!) info)") + static ::std::tuple call(const at::Tensor & A, bool pivot, bool check_errors, at::Tensor & LU, at::Tensor & pivots, at::Tensor & info); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & A, bool pivot, bool check_errors, at::Tensor & LU, at::Tensor & pivots, at::Tensor & info); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1bc9b581a0a6d19e3523246a6a11aaa72bdeb416 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_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 log(const at::Tensor & self); +TORCH_API at::Tensor & log_(at::Tensor & self); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..bb0330b29f83c29c60e350fcbcbc14550df96c0f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_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 log(const at::Tensor & self); +TORCH_API at::Tensor & log_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & log_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & log_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_cell_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_cell_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..d2b8eac109b20804ffb200e3322910ceb4e080d4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_cell_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 lstm_cell { + using schema = ::std::tuple (const at::Tensor &, at::TensorList, const at::Tensor &, const at::Tensor &, const c10::optional &, const c10::optional &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::lstm_cell") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "lstm_cell(Tensor input, Tensor[] hx, Tensor w_ih, Tensor w_hh, Tensor? b_ih=None, Tensor? b_hh=None) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & input, at::TensorList hx, const at::Tensor & w_ih, const at::Tensor & w_hh, const c10::optional & b_ih, const c10::optional & b_hh); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, at::TensorList hx, const at::Tensor & w_ih, const at::Tensor & w_hh, const c10::optional & b_ih, const c10::optional & b_hh); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_backward_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_backward_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0c660362710ed9c5cb929ef3c466e4e1b49ac105 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_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 at::Tensor masked_scatter_backward(const at::Tensor & grad_output, const at::Tensor & mask, at::IntArrayRef sizes); +TORCH_API at::Tensor masked_scatter_backward_symint(const at::Tensor & grad_output, const at::Tensor & mask, c10::SymIntArrayRef sizes); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3430d0a8e58e6d22121550952e31be8044795c37 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_cpu_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor & masked_scatter_(at::Tensor & self, const at::Tensor & mask, const at::Tensor & source); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matmul_backward_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matmul_backward_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ec96e4a1b913da103868f80c282137e744e61981 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matmul_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 matmul_backward_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & grad, const at::Tensor & self, const at::Tensor & other, ::std::array mask); +TORCH_API ::std::tuple matmul_backward_outf(const at::Tensor & grad, const at::Tensor & self, const at::Tensor & other, ::std::array mask, at::Tensor & out0, at::Tensor & out1); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..04ea12298a75b2eef1df0122bbbdd74cb3dbdf69 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_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 max_pool2d_with_indices(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false); +TORCH_API ::std::tuple max_pool2d_with_indices_out(at::Tensor & out, at::Tensor & indices, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false); +TORCH_API ::std::tuple max_pool2d_with_indices_outf(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out, at::Tensor & indices); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..01ceefbd3db9ec7f34e689c4fc42c31e4962f583 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_native.h @@ -0,0 +1,24 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor max_unpooling3d_forward_cpu(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API at::Tensor & max_unpooling3d_forward_out_cpu(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out); +TORCH_API at::Tensor max_unpooling3d_forward_cuda(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API at::Tensor & max_unpooling3d_forward_out_cuda(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mse_loss_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mse_loss_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..93b0f165b1e19d592b7e57bd841686cf8d562386 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mse_loss_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 mse_loss_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction); +TORCH_API at::Tensor & mse_loss_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction); +TORCH_API at::Tensor & mse_loss_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, at::Tensor & grad_input); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanquantile_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanquantile_native.h new file mode 100644 index 0000000000000000000000000000000000000000..eddb0ca705f51c3d168f22f3e4cdad48a97c1129 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanquantile_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 nanquantile(const at::Tensor & self, const at::Tensor & q, c10::optional dim=c10::nullopt, bool keepdim=false, c10::string_view interpolation="linear"); +TORCH_API at::Tensor & nanquantile_out(const at::Tensor & self, const at::Tensor & q, c10::optional dim, bool keepdim, c10::string_view interpolation, at::Tensor & out); +TORCH_API at::Tensor nanquantile(const at::Tensor & self, double q, c10::optional dim=c10::nullopt, bool keepdim=false, c10::string_view interpolation="linear"); +TORCH_API at::Tensor & nanquantile_out(const at::Tensor & self, double q, c10::optional dim, bool keepdim, c10::string_view interpolation, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss2d_forward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss2d_forward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f1bd8a52c26ac071349e90e63a0d44a82ce9bfaf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss2d_forward_cuda_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 nll_loss2d_forward(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index); +TORCH_API ::std::tuple nll_loss2d_forward_symint(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index); +TORCH_API ::std::tuple nll_loss2d_forward_out(at::Tensor & output, at::Tensor & total_weight, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index); +TORCH_API ::std::tuple nll_loss2d_forward_outf(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index, at::Tensor & output, at::Tensor & total_weight); +TORCH_API ::std::tuple nll_loss2d_forward_symint_out(at::Tensor & output, at::Tensor & total_weight, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index); +TORCH_API ::std::tuple nll_loss2d_forward_symint_outf(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index, at::Tensor & output, at::Tensor & total_weight); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_except_dim.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_except_dim.h new file mode 100644 index 0000000000000000000000000000000000000000..b577796739b183ed46d08ca2c9a2dc12e219fd36 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_except_dim.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::norm_except_dim(Tensor v, int pow=2, int dim=0) -> Tensor +inline at::Tensor norm_except_dim(const at::Tensor & v, int64_t pow=2, int64_t dim=0) { + return at::_ops::norm_except_dim::call(v, pow, dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/polar_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/polar_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b2803f6083b6a493c068dfee89e59c2e7d79bafe --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/polar_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 polar { + 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::polar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "polar(Tensor abs, Tensor angle) -> Tensor") + static at::Tensor call(const at::Tensor & abs, const at::Tensor & angle); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & abs, const at::Tensor & angle); +}; + +struct TORCH_API polar_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::polar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "polar.out(Tensor abs, Tensor angle, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & abs, const at::Tensor & angle, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & abs, const at::Tensor & angle, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..f4e55a8894f0cb8dcd46461fc47d5810a295bd3b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_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_replication_pad3d_out_cpu : public at::meta::structured_replication_pad3d { +void impl(const at::Tensor & self, at::ArrayRef padding, const at::Tensor & out); +}; +struct TORCH_API structured_replication_pad3d_out_cuda : public at::meta::structured_replication_pad3d { +void impl(const at::Tensor & self, at::ArrayRef padding, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rnn_tanh_cell_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rnn_tanh_cell_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b0ee702e895eb6dc0fd65b446511f7ca0f72732f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rnn_tanh_cell_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 rnn_tanh_cell(const at::Tensor & input, const at::Tensor & hx, const at::Tensor & w_ih, const at::Tensor & w_hh, const c10::optional & b_ih={}, const c10::optional & b_hh={}); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_csc_tensor_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_csc_tensor_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5857a620b802fee09cf49216dfa7afd1a9c70d09 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_csc_tensor_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 sparse_csc_tensor_ccol_row_value_size { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, at::IntArrayRef, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::sparse_csc_tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "ccol_row_value_size") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "sparse_csc_tensor.ccol_row_value_size(Tensor ccol_indices, Tensor row_indices, Tensor values, int[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=False) -> Tensor") + static at::Tensor call(const at::Tensor & ccol_indices, const at::Tensor & row_indices, const at::Tensor & values, at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & ccol_indices, const at::Tensor & row_indices, const at::Tensor & values, at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API sparse_csc_tensor_ccol_row_value { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::sparse_csc_tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "ccol_row_value") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "sparse_csc_tensor.ccol_row_value(Tensor ccol_indices, Tensor row_indices, Tensor values, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=False) -> Tensor") + static at::Tensor call(const at::Tensor & ccol_indices, const at::Tensor & row_indices, const at::Tensor & values, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & ccol_indices, const at::Tensor & row_indices, const at::Tensor & values, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_resize_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_resize_native.h new file mode 100644 index 0000000000000000000000000000000000000000..e8d7e18873105ef19de4c8b78908f8121c1a3fa3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_resize_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor sparse_resize(const at::Tensor & self, at::IntArrayRef size, int64_t sparse_dim, int64_t dense_dim); +TORCH_API const at::Tensor & sparse_resize_out(const at::Tensor & self, at::IntArrayRef size, int64_t sparse_dim, int64_t dense_dim, const at::Tensor & out); +TORCH_API const at::Tensor & sparse_resize_(const at::Tensor & self, at::IntArrayRef size, int64_t sparse_dim, int64_t dense_dim); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9701de88f63ddf403f675a559fbf8867b802bae1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_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 special_bessel_j0(const at::Tensor & self); +TORCH_API at::Tensor & special_bessel_j0_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & special_bessel_j0_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..0cc31f797435a5750487a6820a84833e8da951cf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_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_bessel_j0 : 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_entr_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..01e0b2c9c547a43f14ecd56a622222f6bdd0109b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API special_entr { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_entr") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_entr(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API special_entr_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_entr") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_entr.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i0_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i0_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..670661c053004e8c4ea9f332ba6f48f22d5d41f5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i0_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API special_modified_bessel_i0 { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_modified_bessel_i0") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_modified_bessel_i0(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API special_modified_bessel_i0_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_modified_bessel_i0") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_modified_bessel_i0.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_psi_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_psi_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8933a587ec92fac30742fd3a3586c83dc2aa13bd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_psi_compositeimplicitautograd_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor special_psi(const at::Tensor & self); +TORCH_API at::Tensor & special_psi_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & special_psi_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k0_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k0_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..d09b43f24e252c7f8efdf43dbea70069b47ecaa2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k0_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_scaled_modified_bessel_k0 : public TensorIteratorBase { + + + void meta(const at::Tensor & x); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tensor_split_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tensor_split_native.h new file mode 100644 index 0000000000000000000000000000000000000000..81d46f23cfd8c687436760df35e770de0dd4ebc5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tensor_split_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 ::std::vector tensor_split_sections_symint(const at::Tensor & self, c10::SymInt sections, int64_t dim=0); +TORCH_API ::std::vector tensor_split_indices_symint(const at::Tensor & self, c10::SymIntArrayRef indices, int64_t dim=0); +TORCH_API ::std::vector tensor_split(const at::Tensor & self, const at::Tensor & tensor_indices_or_sections, int64_t dim=0); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..72e37ccd2b5ca05e96d857585f13b3789e4be55f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_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 threshold(const at::Tensor & self, const at::Scalar & threshold, const at::Scalar & value); +TORCH_API at::Tensor & threshold_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & threshold, const at::Scalar & value); +TORCH_API at::Tensor & threshold_outf(const at::Tensor & self, const at::Scalar & threshold, const at::Scalar & value, at::Tensor & out); +TORCH_API at::Tensor & threshold_(at::Tensor & self, const at::Scalar & threshold, const at::Scalar & value); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense_native.h new file mode 100644 index 0000000000000000000000000000000000000000..644abdaed5d93aba30c8e947fb41851753024473 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense_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 to_dense(const at::Tensor & self, c10::optional dtype=c10::nullopt, c10::optional masked_grad=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest1d_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest1d_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c65c70a11d6248c378901e2540ae04c93b20cbab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest1d_meta_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#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 upsample_nearest1d(const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales=c10::nullopt); +TORCH_API at::Tensor upsample_nearest1d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, c10::optional scales=c10::nullopt); +TORCH_API at::Tensor & upsample_nearest1d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales=c10::nullopt); +TORCH_API at::Tensor & upsample_nearest1d_outf(const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales, at::Tensor & out); +TORCH_API at::Tensor & upsample_nearest1d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, c10::optional scales=c10::nullopt); +TORCH_API at::Tensor & upsample_nearest1d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, c10::optional scales, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_copy_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_copy_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3dff7c7ed2585fba4bd29eed5312e1cabd813734 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_copy_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 view_copy { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::view_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "view_copy(Tensor self, SymInt[] size) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef size); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef size); +}; + +struct TORCH_API view_copy_dtype { + using schema = at::Tensor (const at::Tensor &, at::ScalarType); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::view_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dtype") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "view_copy.dtype(Tensor self, ScalarType dtype) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::ScalarType dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::ScalarType dtype); +}; + +struct TORCH_API view_copy_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymIntArrayRef, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::view_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "view_copy.out(Tensor self, SymInt[] size, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::SymIntArrayRef size, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef size, at::Tensor & out); +}; + +struct TORCH_API view_copy_dtype_out { + using schema = at::Tensor & (const at::Tensor &, at::ScalarType, 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_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dtype_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "view_copy.dtype_out(Tensor self, ScalarType dtype, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::ScalarType dtype, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::ScalarType dtype, at::Tensor & out); +}; + +}} // namespace at::_ops