diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_adaptive_avg_pool3d_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_adaptive_avg_pool3d_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..2d978e6e54168c488dfd4b120b465229c7f3ee8a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_adaptive_avg_pool3d_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _adaptive_avg_pool3d_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_adaptive_avg_pool3d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_adaptive_avg_pool3d_backward(Tensor grad_output, Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self); +}; + +struct TORCH_API _adaptive_avg_pool3d_backward_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::_adaptive_avg_pool3d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_adaptive_avg_pool3d_backward.out(Tensor grad_output, Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, 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/_assert_async_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_async_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..cfdf4be4fa4dead18edb85e332dc3b67a9c09031 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_async_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 _assert_async { + using schema = void (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::_assert_async") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_assert_async(Tensor self) -> ()") + static void call(const at::Tensor & self); + static void redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API _assert_async_msg { + using schema = void (const at::Tensor &, c10::string_view); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_assert_async") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "msg") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_assert_async.msg(Tensor self, str assert_msg) -> ()") + static void call(const at::Tensor & self, c10::string_view assert_msg); + static void redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::string_view assert_msg); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Char_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Char_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7ecde69c246125ec003dbe6910f1815281289bab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Char_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 _cast_Char { + using schema = at::Tensor (const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_cast_Char") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cast_Char(Tensor self, bool non_blocking=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, bool non_blocking); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool non_blocking); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cholesky_solve_helper_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cholesky_solve_helper_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3707cf7fdc8adede0719fa9b8ac490a1c8fe10bb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cholesky_solve_helper_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 _cholesky_solve_helper { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_cholesky_solve_helper") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cholesky_solve_helper(Tensor self, Tensor A, bool upper) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & A, bool upper); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & A, bool upper); +}; + +struct TORCH_API _cholesky_solve_helper_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, bool, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_cholesky_solve_helper") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cholesky_solve_helper.out(Tensor self, Tensor A, bool upper, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & A, bool upper, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & A, bool upper, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_indices_from_coo_to_csr.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_indices_from_coo_to_csr.h new file mode 100644 index 0000000000000000000000000000000000000000..58d64bcb4324c86a235ff4b506376314b32eec17 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_indices_from_coo_to_csr.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::_convert_indices_from_coo_to_csr(Tensor self, int size, *, bool out_int32=False) -> Tensor +inline at::Tensor _convert_indices_from_coo_to_csr(const at::Tensor & self, int64_t size, bool out_int32=false) { + return at::_ops::_convert_indices_from_coo_to_csr::call(self, size, out_int32); +} + +// aten::_convert_indices_from_coo_to_csr.out(Tensor self, int size, *, bool out_int32=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _convert_indices_from_coo_to_csr_out(at::Tensor & out, const at::Tensor & self, int64_t size, bool out_int32=false) { + return at::_ops::_convert_indices_from_coo_to_csr_out::call(self, size, out_int32, out); +} +// aten::_convert_indices_from_coo_to_csr.out(Tensor self, int size, *, bool out_int32=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _convert_indices_from_coo_to_csr_outf(const at::Tensor & self, int64_t size, bool out_int32, at::Tensor & out) { + return at::_ops::_convert_indices_from_coo_to_csr_out::call(self, size, out_int32, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..077b8a4c0201b0dea8408721ad478b9e649ab18b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_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 _convolution { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const c10::optional &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, bool, c10::SymIntArrayRef, c10::SymInt, bool, bool, bool, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_convolution") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_convolution(Tensor input, Tensor weight, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, bool transposed, SymInt[] output_padding, SymInt groups, bool benchmark, bool deterministic, bool cudnn_enabled, bool allow_tf32) -> Tensor") + static at::Tensor call(const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, bool transposed, c10::SymIntArrayRef output_padding, c10::SymInt groups, bool benchmark, bool deterministic, bool cudnn_enabled, bool allow_tf32); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, bool transposed, c10::SymIntArrayRef output_padding, c10::SymInt groups, bool benchmark, bool deterministic, bool cudnn_enabled, bool allow_tf32); +}; + +struct TORCH_API _convolution_deprecated { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const c10::optional &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, bool, at::IntArrayRef, c10::SymInt, bool, bool, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_convolution") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "deprecated") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_convolution.deprecated(Tensor input, Tensor weight, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, bool transposed, int[] output_padding, SymInt groups, bool benchmark, bool deterministic, bool cudnn_enabled) -> Tensor") + static at::Tensor call(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); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, 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); +}; + +struct TORCH_API _convolution_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const c10::optional &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, bool, c10::SymIntArrayRef, c10::SymInt, bool, bool, bool, bool, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_convolution") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_convolution.out(Tensor input, Tensor weight, Tensor? bias, SymInt[] stride, SymInt[] padding, SymInt[] dilation, bool transposed, SymInt[] output_padding, SymInt groups, bool benchmark, bool deterministic, bool cudnn_enabled, bool allow_tf32, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, bool transposed, c10::SymIntArrayRef output_padding, c10::SymInt groups, bool benchmark, bool deterministic, bool cudnn_enabled, bool allow_tf32, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, bool transposed, c10::SymIntArrayRef output_padding, c10::SymInt groups, bool benchmark, bool deterministic, bool cudnn_enabled, bool allow_tf32, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cufft_get_plan_cache_max_size.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cufft_get_plan_cache_max_size.h new file mode 100644 index 0000000000000000000000000000000000000000..b006fbc6445fae58ff324afc6ca8e84de182987c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cufft_get_plan_cache_max_size.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::_cufft_get_plan_cache_max_size(DeviceIndex device_index) -> int +inline int64_t _cufft_get_plan_cache_max_size(at::DeviceIndex device_index) { + return at::_ops::_cufft_get_plan_cache_max_size::call(device_index); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fft_c2c_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fft_c2c_native.h new file mode 100644 index 0000000000000000000000000000000000000000..38d293f0eb45c27f232262ab64187b74003ed226 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fft_c2c_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 _fft_c2c_mkl(const at::Tensor & self, at::IntArrayRef dim, int64_t normalization, bool forward); +TORCH_API at::Tensor & _fft_c2c_mkl_out(const at::Tensor & self, at::IntArrayRef dim, int64_t normalization, bool forward, at::Tensor & out); +TORCH_API at::Tensor _fft_c2c_cufft(const at::Tensor & self, at::IntArrayRef dim, int64_t normalization, bool forward); +TORCH_API at::Tensor & _fft_c2c_cufft_out(const at::Tensor & self, at::IntArrayRef dim, int64_t normalization, bool forward, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_frac_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_frac_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7d4d93896e1483122dc673ef0e37f4b9e750fc02 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_frac_cpu_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 cpu { + +TORCH_API ::std::vector _foreach_frac(at::TensorList self); +TORCH_API void _foreach_frac_(at::TensorList self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt_native.h new file mode 100644 index 0000000000000000000000000000000000000000..7a8e1dfa477a81dfec37f07e4b97d66607c51f0d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt_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 void _foreach_sqrt_out(at::TensorList self, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_sqrt_slow(at::TensorList self); +TORCH_API void foreach_tensor_sqrt_slow_(at::TensorList self); +TORCH_API ::std::vector foreach_tensor_sqrt_cuda(at::TensorList self); +TORCH_API void foreach_tensor_sqrt_cuda_(at::TensorList self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_zero_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_zero_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..035a0c9c7956bcf29f5a8fe6c0a121a568a390de --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_zero_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 _foreach_zero_ { + using schema = void (at::TensorList); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_foreach_zero_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_zero_(Tensor(a!)[] self) -> ()") + static void call(at::TensorList self); + static void redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList self); +}; + +struct TORCH_API _foreach_zero_out { + using schema = void (at::TensorList, at::TensorList); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_foreach_zero") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_zero.out(Tensor[] self, *, Tensor(a!)[] out) -> ()") + static void call(at::TensorList self, at::TensorList out); + static void redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList self, at::TensorList out); +}; + +struct TORCH_API _foreach_zero { + using schema = ::std::vector (at::TensorList); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_foreach_zero") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_foreach_zero(Tensor[] self) -> Tensor[] self_out") + static ::std::vector call(at::TensorList self); + static ::std::vector redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList self); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_bin_edges_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_bin_edges_native.h new file mode 100644 index 0000000000000000000000000000000000000000..0a03f50ccf20b2fefcc7f3b6172a1b477240fc67 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_bin_edges_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 void _histogramdd_bin_edges_out(const at::Tensor & self, at::IntArrayRef bins, c10::optional> range, const c10::optional & weight, bool density, at::TensorList out); +TORCH_API ::std::vector histogramdd_bin_edges(const at::Tensor & self, at::IntArrayRef bins, c10::optional> range=c10::nullopt, const c10::optional & weight={}, bool density=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_make_dual_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_make_dual_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..188e5b4769cc53829bf3e13f85ee2ee51dd1fb55 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_make_dual_compositeexplicitautograd_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 compositeexplicitautograd { + +TORCH_API at::Tensor _make_dual(const at::Tensor & primal, const at::Tensor & tangent, int64_t level); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_multi_head_attention_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_multi_head_attention_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b9a19951274dc858e3062b0da5e8fdf975d4b71e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_native_multi_head_attention_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 _native_multi_head_attention_out(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, int64_t embed_dim, int64_t num_head, const at::Tensor & qkv_weight, const at::Tensor & qkv_bias, const at::Tensor & proj_weight, const at::Tensor & proj_bias, const c10::optional & mask, bool need_weights, bool average_attn_weights, c10::optional mask_type, at::Tensor & out0, at::Tensor & out1); +TORCH_API ::std::tuple native_multi_head_attention_cpu(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, int64_t embed_dim, int64_t num_head, const at::Tensor & qkv_weight, const at::Tensor & qkv_bias, const at::Tensor & proj_weight, const at::Tensor & proj_bias, const c10::optional & mask={}, bool need_weights=true, bool average_attn_weights=true, c10::optional mask_type=c10::nullopt); +TORCH_API ::std::tuple native_multi_head_attention_cuda(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, int64_t embed_dim, int64_t num_head, const at::Tensor & qkv_weight, const at::Tensor & qkv_bias, const at::Tensor & proj_weight, const at::Tensor & proj_bias, const c10::optional & mask={}, bool need_weights=true, bool average_attn_weights=true, c10::optional mask_type=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_flash_attention.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_flash_attention.h new file mode 100644 index 0000000000000000000000000000000000000000..295f1aa87d42469f3e61e6f696e941ae5b206f48 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_flash_attention.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::_scaled_dot_product_flash_attention(Tensor query, Tensor key, Tensor value, float dropout_p=0.0, bool is_causal=False, bool return_debug_mask=False, *, float? scale=None) -> (Tensor output, Tensor logsumexp, Tensor cum_seq_q, Tensor cum_seq_k, SymInt max_q, SymInt max_k, Tensor philox_seed, Tensor philox_offset, Tensor debug_attn_mask) +inline ::std::tuple _scaled_dot_product_flash_attention(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, double dropout_p=0.0, bool is_causal=false, bool return_debug_mask=false, c10::optional scale=c10::nullopt) { + return at::_ops::_scaled_dot_product_flash_attention::call(query, key, value, dropout_p, is_causal, return_debug_mask, scale); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_mm_reduce_impl_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_mm_reduce_impl_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..35b767ae3379a59b5f3dc76e512bb43df1344c16 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_mm_reduce_impl_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::_sparse_mm_reduce_impl_backward(Tensor self, Tensor grad_out, Tensor weight, str reduce, Tensor arg_out, bool[2] output_mask) -> (Tensor, Tensor) +inline ::std::tuple _sparse_mm_reduce_impl_backward(const at::Tensor & self, const at::Tensor & grad_out, const at::Tensor & weight, c10::string_view reduce, const at::Tensor & arg_out, ::std::array output_mask) { + return at::_ops::_sparse_mm_reduce_impl_backward::call(self, grad_out, weight, reduce, arg_out, output_mask); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_check_tensor_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_check_tensor_native.h new file mode 100644 index 0000000000000000000000000000000000000000..8c2078e5a9c44223082be7984efda7d2194c5297 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_check_tensor_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 _test_check_tensor(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_warn_in_autograd.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_warn_in_autograd.h new file mode 100644 index 0000000000000000000000000000000000000000..c0066582f803cd5d609c6481f16056cf2a4ca9b1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_warn_in_autograd.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::_test_warn_in_autograd(Tensor self) -> Tensor +inline at::Tensor _test_warn_in_autograd(const at::Tensor & self) { + return at::_ops::_test_warn_in_autograd::call(self); +} + +// aten::_test_warn_in_autograd.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _test_warn_in_autograd_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::_test_warn_in_autograd_out::call(self, out); +} +// aten::_test_warn_in_autograd.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _test_warn_in_autograd_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::_test_warn_in_autograd_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_view.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_view.h new file mode 100644 index 0000000000000000000000000000000000000000..32c11a99de4030f4c0347f9313b665f43cdfad22 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_view.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::_unsafe_view(Tensor self, SymInt[] size) -> Tensor +inline at::Tensor _unsafe_view(const at::Tensor & self, at::IntArrayRef size) { + return at::_ops::_unsafe_view::call(self, c10::fromIntArrayRefSlow(size)); +} +namespace symint { + template ::value>> + at::Tensor _unsafe_view(const at::Tensor & self, at::IntArrayRef size) { + return at::_ops::_unsafe_view::call(self, c10::fromIntArrayRefSlow(size)); + } +} + +// aten::_unsafe_view(Tensor self, SymInt[] size) -> Tensor +inline at::Tensor _unsafe_view_symint(const at::Tensor & self, c10::SymIntArrayRef size) { + return at::_ops::_unsafe_view::call(self, size); +} +namespace symint { + template ::value>> + at::Tensor _unsafe_view(const at::Tensor & self, c10::SymIntArrayRef size) { + return at::_ops::_unsafe_view::call(self, size); + } +} + +// aten::_unsafe_view.out(Tensor self, SymInt[] size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _unsafe_view_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef size) { + return at::_ops::_unsafe_view_out::call(self, c10::fromIntArrayRefSlow(size), out); +} +namespace symint { + template ::value>> + at::Tensor & _unsafe_view_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef size) { + return at::_ops::_unsafe_view_out::call(self, c10::fromIntArrayRefSlow(size), out); + } +} + +// aten::_unsafe_view.out(Tensor self, SymInt[] size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _unsafe_view_outf(const at::Tensor & self, at::IntArrayRef size, at::Tensor & out) { + return at::_ops::_unsafe_view_out::call(self, c10::fromIntArrayRefSlow(size), out); +} +namespace symint { + template ::value>> + at::Tensor & _unsafe_view_outf(const at::Tensor & self, at::IntArrayRef size, at::Tensor & out) { + return at::_ops::_unsafe_view_out::call(self, c10::fromIntArrayRefSlow(size), out); + } +} + +// aten::_unsafe_view.out(Tensor self, SymInt[] size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _unsafe_view_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef size) { + return at::_ops::_unsafe_view_out::call(self, size, out); +} +namespace symint { + template ::value>> + at::Tensor & _unsafe_view_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef size) { + return at::_ops::_unsafe_view_out::call(self, size, out); + } +} + +// aten::_unsafe_view.out(Tensor self, SymInt[] size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _unsafe_view_symint_outf(const at::Tensor & self, c10::SymIntArrayRef size, at::Tensor & out) { + return at::_ops::_unsafe_view_out::call(self, size, out); +} +namespace symint { + template ::value>> + at::Tensor & _unsafe_view_outf(const at::Tensor & self, c10::SymIntArrayRef size, at::Tensor & out) { + return at::_ops::_unsafe_view_out::call(self, size, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_values_copy_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_values_copy_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5ea7e87e7f3238853b048c222fcd8164ebbc6dc4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_values_copy_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 _values_copy { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_values_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_values_copy(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API _values_copy_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_values_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_values_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_interface_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_interface_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4d0f12a3d040af148407c30630901ca4f5742ad4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_norm_interface_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 ::std::tuple _weight_norm_interface_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 cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_max_pool2d_backward_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_max_pool2d_backward_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8bc988555d4df387f3c54e96f577e88c87f38ac0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_max_pool2d_backward_compositeexplicitautogradnonfunctional_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor adaptive_max_pool2d_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & indices); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c952a1ba1ae6ae7547b6fd202321777a1862d3d7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_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 bitwise_left_shift(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_left_shift_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_left_shift_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & bitwise_left_shift_(at::Tensor & self, const at::Tensor & other); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a932f8ef0efeb98ec395ba59ced02b0c00b726fc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift_meta_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor bitwise_left_shift(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_left_shift_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_left_shift_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & bitwise_left_shift_(at::Tensor & self, const at::Tensor & other); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bmm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bmm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7dfabe75ec355ebe0fcd2c32063466b337ac1349 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bmm_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 bmm { + 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::bmm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bmm(Tensor self, Tensor mat2) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & mat2); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & mat2); +}; + +struct TORCH_API bmm_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::bmm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "bmm.out(Tensor self, Tensor mat2, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & mat2, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & mat2, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cholesky_inverse_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cholesky_inverse_native.h new file mode 100644 index 0000000000000000000000000000000000000000..6d0337bf987d535595aa1eea84fd1ae14475612a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cholesky_inverse_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 cholesky_inverse(const at::Tensor & self, bool upper=false); +TORCH_API at::Tensor & cholesky_inverse_out(const at::Tensor & self, bool upper, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..eb671173d21101742e86a95d36dc90dc2c2e2ee1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_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 cosh { + 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::cosh") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cosh(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 cosh_ { + using schema = 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::cosh_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cosh_(Tensor(a!) self) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self); +}; + +struct TORCH_API cosh_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::cosh") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cosh.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/dot_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dot_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e447c990cd7a3d8b37a2d8a0fca5f04ab54f083c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dot_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 dot(const at::Tensor & self, const at::Tensor & tensor); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dropout_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dropout_native.h new file mode 100644 index 0000000000000000000000000000000000000000..fdc59661fafaa00a81f1ac6b692e56f5c89e0823 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dropout_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 dropout(const at::Tensor & input, double p, bool train); +TORCH_API at::Tensor & dropout_(at::Tensor & self, double p, bool train); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/elu_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/elu_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..5fc1d7845bd88ce0a4fdf78d27bc3f8f6eb8dfcc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/elu_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_elu : public TensorIteratorBase { + + + void meta(const at::Tensor & self, const at::Scalar & alpha, const at::Scalar & scale, const at::Scalar & input_scale); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expand_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expand_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..caee23e50b40484c91aab65ea8ccce0db45bd305 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expand_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 expand(const at::Tensor & self, at::IntArrayRef size, bool implicit=false); +TORCH_API at::Tensor expand_symint(const at::Tensor & self, c10::SymIntArrayRef size, bool implicit=false); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..28e4c5e78074c36cc1e317110732569edabebf69 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_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 at::Tensor fake_quantize_per_channel_affine_cachemask_backward(const at::Tensor & grad, const at::Tensor & mask); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5de31e13b13a9de84316a42b3d0533246cecd019 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API fake_quantize_per_channel_affine_cachemask { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, int64_t, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::fake_quantize_per_channel_affine_cachemask") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fake_quantize_per_channel_affine_cachemask(Tensor self, Tensor scale, Tensor zero_point, int axis, int quant_min, int quant_max) -> (Tensor output, Tensor mask)") + static ::std::tuple call(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis, int64_t quant_min, int64_t quant_max); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis, int64_t quant_min, int64_t quant_max); +}; + +struct TORCH_API fake_quantize_per_channel_affine_cachemask_out { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, int64_t, int64_t, at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::fake_quantize_per_channel_affine_cachemask") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fake_quantize_per_channel_affine_cachemask.out(Tensor self, Tensor scale, Tensor zero_point, int axis, int quant_min, int quant_max, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!))") + static ::std::tuple call(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis, int64_t quant_min, int64_t quant_max, at::Tensor & out0, at::Tensor & out1); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis, int64_t quant_min, int64_t quant_max, at::Tensor & out0, at::Tensor & out1); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ifft_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ifft_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ebad60dec6402dc014e118e83432eb34582205be --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ifft_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 fft_ifft_symint(const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_ifft_symint_out(const at::Tensor & self, c10::optional n, int64_t dim, c10::optional norm, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gelu_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gelu_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..1892e3f3f46a26e95fbac5a92be04526349ad25a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gelu_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_gelu : public TensorIteratorBase { + + + void meta(const at::Tensor & self, c10::string_view approximate); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isnan.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isnan.h new file mode 100644 index 0000000000000000000000000000000000000000..4222f80d1a3525edc2ee5cf55fb287c0d63f3ab0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isnan.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::isnan(Tensor self) -> Tensor +inline at::Tensor isnan(const at::Tensor & self) { + return at::_ops::isnan::call(self); +} + +// aten::isnan.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isnan_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::isnan_out::call(self, out); +} +// aten::isnan.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isnan_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::isnan_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_matrix_power.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_matrix_power.h new file mode 100644 index 0000000000000000000000000000000000000000..f0059452be84cba674780292dea71aa0701f1d06 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_matrix_power.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::linalg_matrix_power(Tensor self, int n) -> Tensor +inline at::Tensor linalg_matrix_power(const at::Tensor & self, int64_t n) { + return at::_ops::linalg_matrix_power::call(self, n); +} + +// aten::linalg_matrix_power.out(Tensor self, int n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_matrix_power_out(at::Tensor & out, const at::Tensor & self, int64_t n) { + return at::_ops::linalg_matrix_power_out::call(self, n, out); +} +// aten::linalg_matrix_power.out(Tensor self, int n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_matrix_power_outf(const at::Tensor & self, int64_t n, at::Tensor & out) { + return at::_ops::linalg_matrix_power_out::call(self, n, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log2.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log2.h new file mode 100644 index 0000000000000000000000000000000000000000..26f1356fb5ec992b25d159d3ec2f77980e4b0463 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log2.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::log2(Tensor self) -> Tensor +inline at::Tensor log2(const at::Tensor & self) { + return at::_ops::log2::call(self); +} + +// aten::log2_(Tensor(a!) self) -> Tensor(a!) +inline at::Tensor & log2_(at::Tensor & self) { + return at::_ops::log2_::call(self); +} + +// aten::log2.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & log2_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::log2_out::call(self, out); +} +// aten::log2.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & log2_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::log2_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3741e1fcc10dc6bae759a6ddc1e950c2f79a7123 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_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 max(const at::Tensor & self, int64_t dim, bool keepdim=false); +TORCH_API ::std::tuple max_out(at::Tensor & max, at::Tensor & max_values, const at::Tensor & self, int64_t dim, bool keepdim=false); +TORCH_API ::std::tuple max_outf(const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & max, at::Tensor & max_values); +TORCH_API at::Tensor max(const at::Tensor & self); +TORCH_API at::Tensor & max_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & max_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/maximum_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/maximum_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..092c13d6725fba99cc11050758197e988f318a2c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/maximum_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 maximum { + 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::maximum") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "maximum(Tensor self, Tensor other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other); +}; + +struct TORCH_API maximum_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::maximum") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "maximum.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/median_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/median_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5e22f2ee64d953a68b442a3fc2129edad574f5ea --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/median_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 ::std::tuple median(const at::Tensor & self, at::Dimname dim, bool keepdim=false); +TORCH_API ::std::tuple median_out(at::Tensor & values, at::Tensor & indices, const at::Tensor & self, at::Dimname dim, bool keepdim=false); +TORCH_API ::std::tuple median_outf(const at::Tensor & self, at::Dimname dim, bool keepdim, at::Tensor & values, at::Tensor & indices); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_rnn_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_rnn_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..af7bb9dde5b148e01e75cba9afd41094b2d7ed3a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_rnn_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 void miopen_rnn_backward_out(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const at::Tensor & weight_buf, const at::Tensor & hx, const c10::optional & cx, const at::Tensor & output, const c10::optional & grad_output, const c10::optional & grad_hy, const c10::optional & grad_cy, int64_t mode, int64_t hidden_size, int64_t num_layers, bool batch_first, double dropout, bool train, bool bidirectional, at::IntArrayRef batch_sizes, const c10::optional & dropout_state, const at::Tensor & reserve, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::TensorList out3); +TORCH_API ::std::tuple> miopen_rnn_backward(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const at::Tensor & weight_buf, const at::Tensor & hx, const c10::optional & cx, const at::Tensor & output, const c10::optional & grad_output, const c10::optional & grad_hy, const c10::optional & grad_cy, int64_t mode, int64_t hidden_size, int64_t num_layers, bool batch_first, double dropout, bool train, bool bidirectional, at::IntArrayRef batch_sizes, const c10::optional & dropout_state, const at::Tensor & reserve, ::std::array output_mask); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_backward_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_backward_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..524be7c0cce029725d9783d3d9d3023099944f88 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_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 & mkldnn_max_pool2d_backward_out(at::Tensor & out, const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & input, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false); +TORCH_API at::Tensor & mkldnn_max_pool2d_backward_outf(const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & input, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..9b72584abe9c4c4ce17c78d504d813f79c581212 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_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 & mkldnn_max_pool2d_backward_out(const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & input, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out); +TORCH_API at::Tensor mkldnn_max_pool2d_backward(const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & input, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_reorder_conv3d_weight_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_reorder_conv3d_weight_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b8dd905d4e6c78b6e325fd78ece08832c4ff0ea3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_reorder_conv3d_weight_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 & mkldnn_reorder_conv3d_weight_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef padding=0, at::IntArrayRef stride=1, at::IntArrayRef dilation=1, int64_t groups=1); +TORCH_API at::Tensor & mkldnn_reorder_conv3d_weight_outf(const at::Tensor & self, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, at::Tensor & out); +TORCH_API at::Tensor & mkldnn_reorder_conv3d_weight_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef padding=c10::SymInt(0), c10::SymIntArrayRef stride=c10::SymInt(1), c10::SymIntArrayRef dilation=c10::SymInt(1), c10::SymInt groups=1); +TORCH_API at::Tensor & mkldnn_reorder_conv3d_weight_symint_outf(const at::Tensor & self, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mul_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mul_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..ad03e09cc7dc201fc7a82d99a0aee0122a4b12fd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mul_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_mul_Tensor : public TensorIteratorBase { + + + void meta(const at::Tensor & self, const at::Tensor & other); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_dropout_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_dropout_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..87ec256922fa90e5bfaae39f3a3c0f6c151b3ce3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_dropout_cuda_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::tuple native_dropout(const at::Tensor & input, double p, c10::optional train); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ne_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ne_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5f0e862ed4ee8faac90f623ec429c4ba6121f184 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ne_meta_dispatch.h @@ -0,0 +1,30 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor ne(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & ne_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & ne_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +TORCH_API at::Tensor & ne_(at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor ne(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & ne_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & ne_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & ne_(at::Tensor & self, const at::Tensor & other); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_nd.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_nd.h new file mode 100644 index 0000000000000000000000000000000000000000..152564027803e09cccdf4917684957a4a5de6803 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_nd.h @@ -0,0 +1,47 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::nll_loss_nd(Tensor self, Tensor target, Tensor? weight=None, int reduction=Mean, SymInt ignore_index=-100) -> Tensor +inline at::Tensor nll_loss_nd(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean, int64_t ignore_index=-100) { + return at::_ops::nll_loss_nd::call(self, target, weight, reduction, ignore_index); +} +namespace symint { + template ::value>> + at::Tensor nll_loss_nd(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean, int64_t ignore_index=-100) { + return at::_ops::nll_loss_nd::call(self, target, weight, reduction, ignore_index); + } +} + +// aten::nll_loss_nd(Tensor self, Tensor target, Tensor? weight=None, int reduction=Mean, SymInt ignore_index=-100) -> Tensor +inline at::Tensor nll_loss_nd_symint(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean, c10::SymInt ignore_index=-100) { + return at::_ops::nll_loss_nd::call(self, target, weight, reduction, ignore_index); +} +namespace symint { + template ::value>> + at::Tensor nll_loss_nd(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean, c10::SymInt ignore_index=-100) { + return at::_ops::nll_loss_nd::call(self, target, weight, reduction, ignore_index); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/polygamma.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/polygamma.h new file mode 100644 index 0000000000000000000000000000000000000000..beef10384552010c6ff00a083d6692e2c5dfb2bf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/polygamma.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::polygamma.out(int n, Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & polygamma_out(at::Tensor & out, int64_t n, const at::Tensor & self) { + return at::_ops::polygamma_out::call(n, self, out); +} +// aten::polygamma.out(int n, Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & polygamma_outf(int64_t n, const at::Tensor & self, at::Tensor & out) { + return at::_ops::polygamma_out::call(n, self, out); +} + +// aten::polygamma(int n, Tensor self) -> Tensor +inline at::Tensor polygamma(int64_t n, const at::Tensor & self) { + return at::_ops::polygamma::call(n, self); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad3d_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad3d_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..74c2e1e7889a44b33a28f8293b1f4a8593bc11f0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad3d_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_reflection_pad3d : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, at::ArrayRef padding); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad2d_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad2d_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..6bf18ba9091dc7876fb310ed7070548e52dedca5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad2d_backward.h @@ -0,0 +1,91 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::replication_pad2d_backward.grad_input(Tensor grad_output, Tensor self, SymInt[4] padding, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & replication_pad2d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding) { + return at::_ops::replication_pad2d_backward_grad_input::call(grad_output, self, c10::fromIntArrayRefSlow(padding), grad_input); +} +namespace symint { + template ::value>> + at::Tensor & replication_pad2d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding) { + return at::_ops::replication_pad2d_backward_grad_input::call(grad_output, self, c10::fromIntArrayRefSlow(padding), grad_input); + } +} + +// aten::replication_pad2d_backward.grad_input(Tensor grad_output, Tensor self, SymInt[4] padding, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & replication_pad2d_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding, at::Tensor & grad_input) { + return at::_ops::replication_pad2d_backward_grad_input::call(grad_output, self, c10::fromIntArrayRefSlow(padding), grad_input); +} +namespace symint { + template ::value>> + at::Tensor & replication_pad2d_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding, at::Tensor & grad_input) { + return at::_ops::replication_pad2d_backward_grad_input::call(grad_output, self, c10::fromIntArrayRefSlow(padding), grad_input); + } +} + +// aten::replication_pad2d_backward.grad_input(Tensor grad_output, Tensor self, SymInt[4] padding, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & replication_pad2d_backward_symint_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding) { + return at::_ops::replication_pad2d_backward_grad_input::call(grad_output, self, padding, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & replication_pad2d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding) { + return at::_ops::replication_pad2d_backward_grad_input::call(grad_output, self, padding, grad_input); + } +} + +// aten::replication_pad2d_backward.grad_input(Tensor grad_output, Tensor self, SymInt[4] padding, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & replication_pad2d_backward_symint_outf(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding, at::Tensor & grad_input) { + return at::_ops::replication_pad2d_backward_grad_input::call(grad_output, self, padding, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & replication_pad2d_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding, at::Tensor & grad_input) { + return at::_ops::replication_pad2d_backward_grad_input::call(grad_output, self, padding, grad_input); + } +} + +// aten::replication_pad2d_backward(Tensor grad_output, Tensor self, SymInt[4] padding) -> Tensor +inline at::Tensor replication_pad2d_backward(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding) { + return at::_ops::replication_pad2d_backward::call(grad_output, self, c10::fromIntArrayRefSlow(padding)); +} +namespace symint { + template ::value>> + at::Tensor replication_pad2d_backward(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding) { + return at::_ops::replication_pad2d_backward::call(grad_output, self, c10::fromIntArrayRefSlow(padding)); + } +} + +// aten::replication_pad2d_backward(Tensor grad_output, Tensor self, SymInt[4] padding) -> Tensor +inline at::Tensor replication_pad2d_backward_symint(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding) { + return at::_ops::replication_pad2d_backward::call(grad_output, self, padding); +} +namespace symint { + template ::value>> + at::Tensor replication_pad2d_backward(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding) { + return at::_ops::replication_pad2d_backward::call(grad_output, self, padding); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..60ffd02e47cfaeb22410ba399cabae8f46f6cb01 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_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_replication_pad3d : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, at::ArrayRef padding); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/requires_grad.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/requires_grad.h new file mode 100644 index 0000000000000000000000000000000000000000..b7ed7777aeddf556b373d49b5842f27a1ff3176e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/requires_grad.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/rnn_tanh_cell.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rnn_tanh_cell.h new file mode 100644 index 0000000000000000000000000000000000000000..9a23f91eb743d32501e133785fb18fadfccccaa8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rnn_tanh_cell.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::rnn_tanh_cell(Tensor input, Tensor hx, Tensor w_ih, Tensor w_hh, Tensor? b_ih=None, Tensor? b_hh=None) -> Tensor +inline 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={}) { + return at::_ops::rnn_tanh_cell::call(input, hx, w_ih, w_hh, b_ih, b_hh); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/searchsorted.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/searchsorted.h new file mode 100644 index 0000000000000000000000000000000000000000..e76c6a393968c2c194c1a7380b5050d2b500cac5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/searchsorted.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::searchsorted.Tensor(Tensor sorted_sequence, Tensor self, *, bool out_int32=False, bool right=False, str? side=None, Tensor? sorter=None) -> Tensor +inline at::Tensor searchsorted(const at::Tensor & sorted_sequence, const at::Tensor & self, bool out_int32=false, bool right=false, c10::optional side=c10::nullopt, const c10::optional & sorter={}) { + return at::_ops::searchsorted_Tensor::call(sorted_sequence, self, out_int32, right, side, sorter); +} + +// aten::searchsorted.Tensor_out(Tensor sorted_sequence, Tensor self, *, bool out_int32=False, bool right=False, str? side=None, Tensor? sorter=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & searchsorted_out(at::Tensor & out, const at::Tensor & sorted_sequence, const at::Tensor & self, bool out_int32=false, bool right=false, c10::optional side=c10::nullopt, const c10::optional & sorter={}) { + return at::_ops::searchsorted_Tensor_out::call(sorted_sequence, self, out_int32, right, side, sorter, out); +} +// aten::searchsorted.Tensor_out(Tensor sorted_sequence, Tensor self, *, bool out_int32=False, bool right=False, str? side=None, Tensor? sorter=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & searchsorted_outf(const at::Tensor & sorted_sequence, const at::Tensor & self, bool out_int32, bool right, c10::optional side, const c10::optional & sorter, at::Tensor & out) { + return at::_ops::searchsorted_Tensor_out::call(sorted_sequence, self, out_int32, right, side, sorter, out); +} + +// aten::searchsorted.Scalar(Tensor sorted_sequence, Scalar self, *, bool out_int32=False, bool right=False, str? side=None, Tensor? sorter=None) -> Tensor +inline at::Tensor searchsorted(const at::Tensor & sorted_sequence, const at::Scalar & self, bool out_int32=false, bool right=false, c10::optional side=c10::nullopt, const c10::optional & sorter={}) { + return at::_ops::searchsorted_Scalar::call(sorted_sequence, self, out_int32, right, side, sorter); +} + +// aten::searchsorted.Scalar_out(Tensor sorted_sequence, Scalar self, *, bool out_int32=False, bool right=False, str? side=None, Tensor? sorter=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & searchsorted_out(at::Tensor & out, const at::Tensor & sorted_sequence, const at::Scalar & self, bool out_int32=false, bool right=false, c10::optional side=c10::nullopt, const c10::optional & sorter={}) { + return at::_ops::searchsorted_Scalar_out::call(sorted_sequence, self, out_int32, right, side, sorter, out); +} +// aten::searchsorted.Scalar_out(Tensor sorted_sequence, Scalar self, *, bool out_int32=False, bool right=False, str? side=None, Tensor? sorter=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & searchsorted_outf(const at::Tensor & sorted_sequence, const at::Scalar & self, bool out_int32, bool right, c10::optional side, const c10::optional & sorter, at::Tensor & out) { + return at::_ops::searchsorted_Scalar_out::call(sorted_sequence, self, out_int32, right, side, sorter, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/select_copy_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/select_copy_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..12882704b1313bbac0b9f533ffe6dba754203905 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/select_copy_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 & select_copy_out(at::Tensor & out, const at::Tensor & self, int64_t dim, int64_t index); +TORCH_API at::Tensor & select_copy_outf(const at::Tensor & self, int64_t dim, int64_t index, at::Tensor & out); +TORCH_API at::Tensor & select_copy_symint_out(at::Tensor & out, const at::Tensor & self, int64_t dim, c10::SymInt index); +TORCH_API at::Tensor & select_copy_symint_outf(const at::Tensor & self, int64_t dim, c10::SymInt index, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sigmoid_backward_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sigmoid_backward_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..ff61eba0eb6bf21b6d4a7a5d3c12d4a01136b09d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sigmoid_backward_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_sigmoid_backward : public TensorIteratorBase { + + + void meta(const at::Tensor & grad_output, const at::Tensor & output); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..397cb0c9909cb71c96443c5a336cf93bba029142 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_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::softshrink_backward.grad_input(Tensor grad_output, Tensor self, Scalar lambd, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & softshrink_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd) { + return at::_ops::softshrink_backward_grad_input::call(grad_output, self, lambd, grad_input); +} +// aten::softshrink_backward.grad_input(Tensor grad_output, Tensor self, Scalar lambd, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & softshrink_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd, at::Tensor & grad_input) { + return at::_ops::softshrink_backward_grad_input::call(grad_output, self, lambd, grad_input); +} + +// aten::softshrink_backward(Tensor grad_output, Tensor self, Scalar lambd) -> Tensor +inline at::Tensor softshrink_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd) { + return at::_ops::softshrink_backward::call(grad_output, self, lambd); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_dim_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_dim_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cd9e2784c94a6ccfb097a3be2910a0a0f3bdbaae --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_dim_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 int64_t sparse_dim(const at::Tensor & self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_w_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_w_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..24920a15075e9c124c872fba20e37722c584519d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_w_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor special_chebyshev_polynomial_w(const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_w_out(at::Tensor & out, const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_w_outf(const at::Tensor & x, const at::Tensor & n, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_h_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_h_native.h new file mode 100644 index 0000000000000000000000000000000000000000..34e2cb69964de6643cf40dbf9cd6bd11326ee791 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_h_native.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_special_hermite_polynomial_h_out : public at::meta::structured_special_hermite_polynomial_h { +void impl(const at::Tensor & x, const at::Tensor & n, const at::Tensor & out); +}; +TORCH_API at::Tensor special_hermite_polynomial_h(const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_hermite_polynomial_h_out(const at::Scalar & x, const at::Tensor & n, at::Tensor & out); +TORCH_API at::Tensor special_hermite_polynomial_h(const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_hermite_polynomial_h_out(const at::Tensor & x, const at::Scalar & n, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_k0_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_k0_native.h new file mode 100644 index 0000000000000000000000000000000000000000..30dfd3449a4d3c040b6189001171a56939b20503 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_k0_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_special_modified_bessel_k0_out : public at::meta::structured_special_modified_bessel_k0 { +void impl(const at::Tensor & self, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k1_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k1_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..339220ef43f8ce2458dfd450628f57ae25c4e3f7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k1_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_k1 : 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/special_shifted_chebyshev_polynomial_u_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_u_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8ed8dc8aa2c587719e4579bf175c0c1367086137 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_u_compositeexplicitautograd_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor special_shifted_chebyshev_polynomial_u(const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_shifted_chebyshev_polynomial_u_out(at::Tensor & out, const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_shifted_chebyshev_polynomial_u_outf(const at::Scalar & x, const at::Tensor & n, at::Tensor & out); +TORCH_API at::Tensor special_shifted_chebyshev_polynomial_u(const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_shifted_chebyshev_polynomial_u_out(at::Tensor & out, const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_shifted_chebyshev_polynomial_u_outf(const at::Tensor & x, const at::Scalar & n, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_v.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_v.h new file mode 100644 index 0000000000000000000000000000000000000000..079cd6c4b33e785b85c60e5f4f77323642b85627 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_v.h @@ -0,0 +1,67 @@ +#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::special_shifted_chebyshev_polynomial_v(Tensor x, Tensor n) -> Tensor +inline at::Tensor special_shifted_chebyshev_polynomial_v(const at::Tensor & x, const at::Tensor & n) { + return at::_ops::special_shifted_chebyshev_polynomial_v::call(x, n); +} + +// aten::special_shifted_chebyshev_polynomial_v.x_scalar(Scalar x, Tensor n) -> Tensor +inline at::Tensor special_shifted_chebyshev_polynomial_v(const at::Scalar & x, const at::Tensor & n) { + return at::_ops::special_shifted_chebyshev_polynomial_v_x_scalar::call(x, n); +} + +// aten::special_shifted_chebyshev_polynomial_v.n_scalar(Tensor x, Scalar n) -> Tensor +inline at::Tensor special_shifted_chebyshev_polynomial_v(const at::Tensor & x, const at::Scalar & n) { + return at::_ops::special_shifted_chebyshev_polynomial_v_n_scalar::call(x, n); +} + +// aten::special_shifted_chebyshev_polynomial_v.out(Tensor x, Tensor n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_v_out(at::Tensor & out, const at::Tensor & x, const at::Tensor & n) { + return at::_ops::special_shifted_chebyshev_polynomial_v_out::call(x, n, out); +} +// aten::special_shifted_chebyshev_polynomial_v.out(Tensor x, Tensor n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_v_outf(const at::Tensor & x, const at::Tensor & n, at::Tensor & out) { + return at::_ops::special_shifted_chebyshev_polynomial_v_out::call(x, n, out); +} + +// aten::special_shifted_chebyshev_polynomial_v.x_scalar_out(Scalar x, Tensor n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_v_out(at::Tensor & out, const at::Scalar & x, const at::Tensor & n) { + return at::_ops::special_shifted_chebyshev_polynomial_v_x_scalar_out::call(x, n, out); +} +// aten::special_shifted_chebyshev_polynomial_v.x_scalar_out(Scalar x, Tensor n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_v_outf(const at::Scalar & x, const at::Tensor & n, at::Tensor & out) { + return at::_ops::special_shifted_chebyshev_polynomial_v_x_scalar_out::call(x, n, out); +} + +// aten::special_shifted_chebyshev_polynomial_v.n_scalar_out(Tensor x, Scalar n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_v_out(at::Tensor & out, const at::Tensor & x, const at::Scalar & n) { + return at::_ops::special_shifted_chebyshev_polynomial_v_n_scalar_out::call(x, n, out); +} +// aten::special_shifted_chebyshev_polynomial_v.n_scalar_out(Tensor x, Scalar n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_v_outf(const at::Tensor & x, const at::Scalar & n, at::Tensor & out) { + return at::_ops::special_shifted_chebyshev_polynomial_v_n_scalar_out::call(x, n, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_sinc_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_sinc_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..74445dc75e6b7d73b60b78926c9fd2551de451c2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_sinc_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_sinc(const at::Tensor & self); +TORCH_API at::Tensor & special_sinc_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & special_sinc_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_spherical_bessel_j0_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_spherical_bessel_j0_native.h new file mode 100644 index 0000000000000000000000000000000000000000..e110305b370bfd9566080c7d41bb26a2a30ae0bf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_spherical_bessel_j0_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_special_spherical_bessel_j0_out : public at::meta::structured_special_spherical_bessel_j0 { +void impl(const at::Tensor & x, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sub_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sub_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..db527c71af8f49fa8957519e238e7f1772964eaf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sub_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 sub(const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha=1); +TORCH_API at::Tensor & sub_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha=1); +TORCH_API at::Tensor & sub_outf(const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha, at::Tensor & out); +TORCH_API at::Tensor & sub_(at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha=1); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..980c00e7f4bf16c41d87992e2571790f0b35d47a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_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 take(const at::Tensor & self, const at::Tensor & index); +TORCH_API at::Tensor & take_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & index); +TORCH_API at::Tensor & take_outf(const at::Tensor & self, const at::Tensor & index, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/uniform_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/uniform_native.h new file mode 100644 index 0000000000000000000000000000000000000000..e7ef6fa9c860a8fc886482a56242d5e12d811a8a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/uniform_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 uniform(const at::Tensor & self, double from=0, double to=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & uniform_out(const at::Tensor & self, double from, double to, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor & uniform_(at::Tensor & self, double from=0, double to=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & uniform_meta_(at::Tensor & self, double from=0, double to=1, c10::optional generator=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_consecutive_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_consecutive_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..cb8b2291e20b8b75ff3dbf01e0cef04686ac413c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_consecutive_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 unique_consecutive { + using schema = ::std::tuple (const at::Tensor &, bool, 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::unique_consecutive") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "unique_consecutive(Tensor self, bool return_inverse=False, bool return_counts=False, int? dim=None) -> (Tensor, Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & self, bool return_inverse, bool return_counts, c10::optional dim); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool return_inverse, bool return_counts, c10::optional dim); +}; + +struct TORCH_API unique_consecutive_out { + using schema = ::std::tuple (const at::Tensor &, bool, bool, c10::optional, 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::unique_consecutive") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "unique_consecutive.out(Tensor self, bool return_inverse=False, bool return_counts=False, int? dim=None, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2) -> (Tensor(a!), Tensor(b!), Tensor(c!))") + static ::std::tuple call(const at::Tensor & self, bool return_inverse, bool return_counts, c10::optional dim, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool return_inverse, bool return_counts, c10::optional dim, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..ee6c0d108ea19bee8b688d0180d25f3f117e233e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_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_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") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "vec") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "upsample_bilinear2d.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_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") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "upsample_bilinear2d.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 { + 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") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "upsample_bilinear2d(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/upsample_nearest1d_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest1d_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1246c031759a8abcecc96ea1615461fcf6fc9cb7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest1d_cpu_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor 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 cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0b3f3cd53a586a6dbd1954b2b0a2aaed364277ab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_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 at::Tensor view(const at::Tensor & self, at::IntArrayRef size); +TORCH_API at::Tensor view_symint(const at::Tensor & self, c10::SymIntArrayRef size); + +} // namespace cuda +} // namespace at