diff --git a/.gitattributes b/.gitattributes index ff2c318650b390823be45406c68e34225f104c9e..a98dee2da2968b98cd6ff9570ba967f805956519 100644 --- a/.gitattributes +++ b/.gitattributes @@ -87,3 +87,4 @@ tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/ tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_refs/__pycache__/__init__.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/nn/modules/__pycache__/module.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/scheduler.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text +tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/codecache.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/codecache.cpython-311.pyc b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/codecache.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7117b7536f97d12df8421a9fe94bcf981f74cf95 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/__pycache__/codecache.cpython-311.pyc @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1a24c10bc84094a10d8939b8a88ad6adf045be858e0ba010cb9f309fc406a7 +size 136352 diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_indices_from_csr_to_coo_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_indices_from_csr_to_coo_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..628c62691e07802581d8dd42c59cc851810a94f7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_indices_from_csr_to_coo_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor _convert_indices_from_csr_to_coo(const at::Tensor & crow_indices, const at::Tensor & col_indices, bool out_int32=false, bool transpose=false); +TORCH_API at::Tensor & _convert_indices_from_csr_to_coo_out(at::Tensor & out, const at::Tensor & crow_indices, const at::Tensor & col_indices, bool out_int32=false, bool transpose=false); +TORCH_API at::Tensor & _convert_indices_from_csr_to_coo_outf(const at::Tensor & crow_indices, const at::Tensor & col_indices, bool out_int32, bool transpose, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cslt_compress_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cslt_compress_native.h new file mode 100644 index 0000000000000000000000000000000000000000..14fa409400727b4d4791addd68b391dadbac17bd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cslt_compress_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 _cslt_compress(const at::Tensor & input); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_flatten_weight.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_flatten_weight.h new file mode 100644 index 0000000000000000000000000000000000000000..5dc6e802701a5d9e4b5ab9cc315ede95805d3a80 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_flatten_weight.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::_cudnn_rnn_flatten_weight(Tensor[] weight_arr, int weight_stride0, SymInt input_size, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, bool bidirectional) -> Tensor +inline at::Tensor _cudnn_rnn_flatten_weight(at::TensorList weight_arr, int64_t weight_stride0, int64_t input_size, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, bool batch_first, bool bidirectional) { + return at::_ops::_cudnn_rnn_flatten_weight::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional); +} +namespace symint { + template ::value>> + at::Tensor _cudnn_rnn_flatten_weight(at::TensorList weight_arr, int64_t weight_stride0, int64_t input_size, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, bool batch_first, bool bidirectional) { + return at::_ops::_cudnn_rnn_flatten_weight::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional); + } +} + +// aten::_cudnn_rnn_flatten_weight(Tensor[] weight_arr, int weight_stride0, SymInt input_size, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, bool bidirectional) -> Tensor +inline at::Tensor _cudnn_rnn_flatten_weight_symint(at::TensorList weight_arr, int64_t weight_stride0, c10::SymInt input_size, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, bool bidirectional) { + return at::_ops::_cudnn_rnn_flatten_weight::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional); +} +namespace symint { + template ::value>> + at::Tensor _cudnn_rnn_flatten_weight(at::TensorList weight_arr, int64_t weight_stride0, c10::SymInt input_size, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, bool bidirectional) { + return at::_ops::_cudnn_rnn_flatten_weight::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional); + } +} + +// aten::_cudnn_rnn_flatten_weight.out(Tensor[] weight_arr, int weight_stride0, SymInt input_size, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, bool bidirectional, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _cudnn_rnn_flatten_weight_out(at::Tensor & out, at::TensorList weight_arr, int64_t weight_stride0, int64_t input_size, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, bool batch_first, bool bidirectional) { + return at::_ops::_cudnn_rnn_flatten_weight_out::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional, out); +} +namespace symint { + template ::value>> + at::Tensor & _cudnn_rnn_flatten_weight_out(at::Tensor & out, at::TensorList weight_arr, int64_t weight_stride0, int64_t input_size, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, bool batch_first, bool bidirectional) { + return at::_ops::_cudnn_rnn_flatten_weight_out::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional, out); + } +} + +// aten::_cudnn_rnn_flatten_weight.out(Tensor[] weight_arr, int weight_stride0, SymInt input_size, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, bool bidirectional, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _cudnn_rnn_flatten_weight_outf(at::TensorList weight_arr, int64_t weight_stride0, int64_t input_size, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, bool batch_first, bool bidirectional, at::Tensor & out) { + return at::_ops::_cudnn_rnn_flatten_weight_out::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional, out); +} +namespace symint { + template ::value>> + at::Tensor & _cudnn_rnn_flatten_weight_outf(at::TensorList weight_arr, int64_t weight_stride0, int64_t input_size, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, bool batch_first, bool bidirectional, at::Tensor & out) { + return at::_ops::_cudnn_rnn_flatten_weight_out::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional, out); + } +} + +// aten::_cudnn_rnn_flatten_weight.out(Tensor[] weight_arr, int weight_stride0, SymInt input_size, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, bool bidirectional, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _cudnn_rnn_flatten_weight_symint_out(at::Tensor & out, at::TensorList weight_arr, int64_t weight_stride0, c10::SymInt input_size, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, bool bidirectional) { + return at::_ops::_cudnn_rnn_flatten_weight_out::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional, out); +} +namespace symint { + template ::value>> + at::Tensor & _cudnn_rnn_flatten_weight_out(at::Tensor & out, at::TensorList weight_arr, int64_t weight_stride0, c10::SymInt input_size, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, bool bidirectional) { + return at::_ops::_cudnn_rnn_flatten_weight_out::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional, out); + } +} + +// aten::_cudnn_rnn_flatten_weight.out(Tensor[] weight_arr, int weight_stride0, SymInt input_size, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, bool bidirectional, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _cudnn_rnn_flatten_weight_symint_outf(at::TensorList weight_arr, int64_t weight_stride0, c10::SymInt input_size, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, bool bidirectional, at::Tensor & out) { + return at::_ops::_cudnn_rnn_flatten_weight_out::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional, out); +} +namespace symint { + template ::value>> + at::Tensor & _cudnn_rnn_flatten_weight_outf(at::TensorList weight_arr, int64_t weight_stride0, c10::SymInt input_size, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, bool bidirectional, at::Tensor & out) { + return at::_ops::_cudnn_rnn_flatten_weight_out::call(weight_arr, weight_stride0, input_size, mode, hidden_size, proj_size, num_layers, batch_first, bidirectional, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_flatten_weight_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_flatten_weight_native.h new file mode 100644 index 0000000000000000000000000000000000000000..10e5a1606fbdfa05181cf395000b421b065a85e3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_flatten_weight_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 & _cudnn_rnn_flatten_weight_out_symint(at::TensorList weight_arr, int64_t weight_stride0, c10::SymInt input_size, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, bool bidirectional, at::Tensor & out); +TORCH_API at::Tensor _cudnn_rnn_flatten_weight(at::TensorList weight_arr, int64_t weight_stride0, int64_t input_size, int64_t mode, int64_t hidden_size, int64_t proj_size, int64_t num_layers, bool batch_first, bool bidirectional); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_empty_per_channel_affine_quantized_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_empty_per_channel_affine_quantized_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c967991684c98f0956dffb1e08d204a4fa28a0fd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_empty_per_channel_affine_quantized_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 _empty_per_channel_affine_quantized(at::IntArrayRef size, const at::Tensor & scales, const at::Tensor & zero_points, int64_t axis, at::TensorOptions options={}, c10::optional memory_format=MemoryFormat::Contiguous); +TORCH_API at::Tensor _empty_per_channel_affine_quantized(at::IntArrayRef size, const at::Tensor & scales, const at::Tensor & zero_points, int64_t axis, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); +TORCH_API at::Tensor _empty_per_channel_affine_quantized_symint(c10::SymIntArrayRef size, const at::Tensor & scales, const at::Tensor & zero_points, int64_t axis, at::TensorOptions options={}, c10::optional memory_format=MemoryFormat::Contiguous); +TORCH_API at::Tensor _empty_per_channel_affine_quantized_symint(c10::SymIntArrayRef size, const at::Tensor & scales, const at::Tensor & zero_points, int64_t axis, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_cosh_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_cosh_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4ebd2c1bce1bcbe9b400f5a33f260ad4cee13abe --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_cosh_cuda_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::vector _foreach_cosh(at::TensorList self); +TORCH_API void _foreach_cosh_(at::TensorList self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..00fe4eaca57b954036ad132c1bbf076ce8724f5f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sqrt_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_sqrt(at::TensorList self); +TORCH_API void _foreach_sqrt_(at::TensorList self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_sdp_choice_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_sdp_choice_native.h new file mode 100644 index 0000000000000000000000000000000000000000..3b88038a894ffdd320f80a82157573ad7a4f8de4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_sdp_choice_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 int64_t _fused_sdp_choice_cpp(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const c10::optional & attn_mask={}, double dropout_p=0.0, bool is_causal=false, c10::optional scale=c10::nullopt); +TORCH_API int64_t _fused_sdp_choice_cuda(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const c10::optional & attn_mask={}, double dropout_p=0.0, bool is_causal=false, c10::optional scale=c10::nullopt); +TORCH_API int64_t _fused_sdp_choice_meta(const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const c10::optional & attn_mask={}, double dropout_p=0.0, bool is_causal=false, c10::optional scale=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_indices_copy_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_indices_copy_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ed385cdfbb788fa69ddbbb2388ff52a521470cfe --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_indices_copy_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 & _indices_copy_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor _indices_copy(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution_transpose.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution_transpose.h new file mode 100644 index 0000000000000000000000000000000000000000..ba819531604e2f2c81aedce6c94832dba6092ad2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution_transpose.h @@ -0,0 +1,91 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_mps_convolution_transpose(Tensor self, Tensor weight, SymInt[] padding, SymInt[] output_padding, SymInt[] stride, SymInt[] dilation, SymInt groups) -> Tensor +inline at::Tensor _mps_convolution_transpose(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef padding, at::IntArrayRef output_padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups) { + return at::_ops::_mps_convolution_transpose::call(self, weight, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(output_padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups); +} +namespace symint { + template ::value>> + at::Tensor _mps_convolution_transpose(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef padding, at::IntArrayRef output_padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups) { + return at::_ops::_mps_convolution_transpose::call(self, weight, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(output_padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups); + } +} + +// aten::_mps_convolution_transpose(Tensor self, Tensor weight, SymInt[] padding, SymInt[] output_padding, SymInt[] stride, SymInt[] dilation, SymInt groups) -> Tensor +inline at::Tensor _mps_convolution_transpose_symint(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups) { + return at::_ops::_mps_convolution_transpose::call(self, weight, padding, output_padding, stride, dilation, groups); +} +namespace symint { + template ::value>> + at::Tensor _mps_convolution_transpose(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups) { + return at::_ops::_mps_convolution_transpose::call(self, weight, padding, output_padding, stride, dilation, groups); + } +} + +// aten::_mps_convolution_transpose.out(Tensor self, Tensor weight, SymInt[] padding, SymInt[] output_padding, SymInt[] stride, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _mps_convolution_transpose_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef padding, at::IntArrayRef output_padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups) { + return at::_ops::_mps_convolution_transpose_out::call(self, weight, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(output_padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups, out); +} +namespace symint { + template ::value>> + at::Tensor & _mps_convolution_transpose_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef padding, at::IntArrayRef output_padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups) { + return at::_ops::_mps_convolution_transpose_out::call(self, weight, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(output_padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups, out); + } +} + +// aten::_mps_convolution_transpose.out(Tensor self, Tensor weight, SymInt[] padding, SymInt[] output_padding, SymInt[] stride, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _mps_convolution_transpose_outf(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef padding, at::IntArrayRef output_padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, at::Tensor & out) { + return at::_ops::_mps_convolution_transpose_out::call(self, weight, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(output_padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups, out); +} +namespace symint { + template ::value>> + at::Tensor & _mps_convolution_transpose_outf(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef padding, at::IntArrayRef output_padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, at::Tensor & out) { + return at::_ops::_mps_convolution_transpose_out::call(self, weight, c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(output_padding), c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(dilation), groups, out); + } +} + +// aten::_mps_convolution_transpose.out(Tensor self, Tensor weight, SymInt[] padding, SymInt[] output_padding, SymInt[] stride, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _mps_convolution_transpose_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups) { + return at::_ops::_mps_convolution_transpose_out::call(self, weight, padding, output_padding, stride, dilation, groups, out); +} +namespace symint { + template ::value>> + at::Tensor & _mps_convolution_transpose_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups) { + return at::_ops::_mps_convolution_transpose_out::call(self, weight, padding, output_padding, stride, dilation, groups, out); + } +} + +// aten::_mps_convolution_transpose.out(Tensor self, Tensor weight, SymInt[] padding, SymInt[] output_padding, SymInt[] stride, SymInt[] dilation, SymInt groups, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _mps_convolution_transpose_symint_outf(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out) { + return at::_ops::_mps_convolution_transpose_out::call(self, weight, padding, output_padding, stride, dilation, groups, out); +} +namespace symint { + template ::value>> + at::Tensor & _mps_convolution_transpose_outf(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out) { + return at::_ops::_mps_convolution_transpose_out::call(self, weight, padding, output_padding, stride, dilation, groups, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_softmax_with_shape.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_softmax_with_shape.h new file mode 100644 index 0000000000000000000000000000000000000000..4ab5a8a0041002fcf6adefadf0fd4a8dd3b881d6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_softmax_with_shape.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::_nested_tensor_softmax_with_shape(Tensor self, Tensor query) -> Tensor +inline at::Tensor _nested_tensor_softmax_with_shape(const at::Tensor & self, const at::Tensor & query) { + return at::_ops::_nested_tensor_softmax_with_shape::call(self, query); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_storage_offsets.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_storage_offsets.h new file mode 100644 index 0000000000000000000000000000000000000000..db673002a346572016f08a6fb29cc4b0073ca029 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_storage_offsets.h @@ -0,0 +1,34 @@ +#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::_nested_tensor_storage_offsets.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _nested_tensor_storage_offsets_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::_nested_tensor_storage_offsets_out::call(self, out); +} +// aten::_nested_tensor_storage_offsets.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _nested_tensor_storage_offsets_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::_nested_tensor_storage_offsets_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnz_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnz_native.h new file mode 100644 index 0000000000000000000000000000000000000000..6bb151e52ca9d3d64341664202c25a79dd22a67e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnz_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 int64_t _nnz_sparse(const at::Tensor & self); +TORCH_API int64_t _nnz_sparse_csr(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_softmax.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_softmax.h new file mode 100644 index 0000000000000000000000000000000000000000..a5882896b416d06569fd63724c5333536180344a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_softmax.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::_softmax(Tensor self, int dim, bool half_to_float) -> Tensor +inline at::Tensor _softmax(const at::Tensor & self, int64_t dim, bool half_to_float) { + return at::_ops::_softmax::call(self, dim, half_to_float); +} + +// aten::_softmax.out(Tensor self, int dim, bool half_to_float, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _softmax_out(at::Tensor & out, const at::Tensor & self, int64_t dim, bool half_to_float) { + return at::_ops::_softmax_out::call(self, dim, half_to_float, out); +} +// aten::_softmax.out(Tensor self, int dim, bool half_to_float, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _softmax_outf(const at::Tensor & self, int64_t dim, bool half_to_float, at::Tensor & out) { + return at::_ops::_softmax_out::call(self, dim, half_to_float, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_sum_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_sum_native.h new file mode 100644 index 0000000000000000000000000000000000000000..a76a2a4e0e5be7445ec2f8a1901c4461291c052b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_sum_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 at::Tensor _sparse_sum(const at::Tensor & self); +TORCH_API at::Tensor _sparse_sum(const at::Tensor & self, at::ScalarType dtype); +TORCH_API at::Tensor _sparse_sum(const at::Tensor & self, at::IntArrayRef dim); +TORCH_API at::Tensor & _sparse_sum_dim_out(const at::Tensor & self, at::IntArrayRef dim, at::Tensor & out); +TORCH_API at::Tensor _sparse_sum(const at::Tensor & self, at::IntArrayRef dim, at::ScalarType dtype); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_gru_cell_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_gru_cell_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ea78d987886d672740ce2d1c7e08ffc965acc5dd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_gru_cell_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 ::std::tuple _thnn_fused_gru_cell_backward_out(const at::Tensor & grad_hy, const at::Tensor & workspace, bool has_bias, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4); +TORCH_API ::std::tuple _thnn_fused_gru_cell_backward_cuda(const at::Tensor & grad_hy, const at::Tensor & workspace, bool has_bias); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unique2_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unique2_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7c21bad52550cc743ce8cdb0670b578e9206c445 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unique2_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 _unique2(const at::Tensor & self, bool sorted=true, bool return_inverse=false, bool return_counts=false); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..b585c8260b1e85dfdbae0035642af4a206893dec --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bilinear2d_aa_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured__upsample_bilinear2d_aa : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, at::ArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..8947b241d99a2b69e1e1a718417346903dd3e1fc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_native.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +TORCH_API at::Tensor _upsample_nearest_exact3d(const at::Tensor & input, at::OptionalIntArrayRef output_size, c10::optional> scale_factors); +struct TORCH_API structured__upsample_nearest_exact3d_out_cpu : public at::meta::structured__upsample_nearest_exact3d { +void impl(const at::Tensor & self, at::ArrayRef output_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & out); +}; +struct TORCH_API structured__upsample_nearest_exact3d_out_cuda : public at::meta::structured__upsample_nearest_exact3d { +void impl(const at::Tensor & self, at::ArrayRef output_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & out); +}; +TORCH_API at::Tensor _upsample_nearest_exact3d_quantized_cpu(const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcmul_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcmul_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ae5d8effd2d13f48d51ae05d886343dbd8c0be02 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcmul_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_addcmul_out : public at::meta::structured_addcmul { +void impl(const at::Tensor & self, const at::Tensor & tensor1, const at::Tensor & tensor2, const at::Scalar & value, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/alias_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/alias_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4ad23ce0577d552682209502825545fe9cfd7ee2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/alias_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 alias(const at::Tensor & self); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arctanh_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arctanh_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..cc74d29b879eb8376c06995774289e328f98f5f5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arctanh_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 arctanh { + 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::arctanh") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "arctanh(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 arctanh_ { + 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::arctanh_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "arctanh_(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 arctanh_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::arctanh") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "arctanh.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/atan2_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2_native.h new file mode 100644 index 0000000000000000000000000000000000000000..9d6ce68706eb2ba60a38e2d768609e93dfaedf30 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2_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_atan2_out : public at::meta::structured_atan2 { +void impl(const at::Tensor & self, const at::Tensor & other, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_update_stats_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_update_stats_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e5423a5c16e3363fbbac347f3d01f57f3a71e94c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_update_stats_cpu_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API ::std::tuple batch_norm_update_stats(const at::Tensor & input, const c10::optional & running_mean, const c10::optional & running_var, double momentum); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift.h new file mode 100644 index 0000000000000000000000000000000000000000..6aec113690257e42bfbd3c69f50a9dc7838396e8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_left_shift.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::bitwise_left_shift.Tensor(Tensor self, Tensor other) -> Tensor +inline at::Tensor bitwise_left_shift(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::bitwise_left_shift_Tensor::call(self, other); +} + +// aten::bitwise_left_shift.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_left_shift_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::bitwise_left_shift_Tensor_out::call(self, other, out); +} +// aten::bitwise_left_shift.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_left_shift_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::bitwise_left_shift_Tensor_out::call(self, other, out); +} + +// aten::bitwise_left_shift.Tensor_Scalar(Tensor self, Scalar other) -> Tensor +inline at::Tensor bitwise_left_shift(const at::Tensor & self, const at::Scalar & other) { + return at::_ops::bitwise_left_shift_Tensor_Scalar::call(self, other); +} + +// aten::bitwise_left_shift.Tensor_Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_left_shift_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other) { + return at::_ops::bitwise_left_shift_Tensor_Scalar_out::call(self, other, out); +} +// aten::bitwise_left_shift.Tensor_Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_left_shift_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out) { + return at::_ops::bitwise_left_shift_Tensor_Scalar_out::call(self, other, out); +} + +// aten::bitwise_left_shift.Scalar_Tensor(Scalar self, Tensor other) -> Tensor +inline at::Tensor bitwise_left_shift(const at::Scalar & self, const at::Tensor & other) { + return at::_ops::bitwise_left_shift_Scalar_Tensor::call(self, other); +} + +// aten::bitwise_left_shift.Scalar_Tensor_out(Scalar self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_left_shift_out(at::Tensor & out, const at::Scalar & self, const at::Tensor & other) { + return at::_ops::bitwise_left_shift_Scalar_Tensor_out::call(self, other, out); +} +// aten::bitwise_left_shift.Scalar_Tensor_out(Scalar self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_left_shift_outf(const at::Scalar & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::bitwise_left_shift_Scalar_Tensor_out::call(self, other, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clone_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clone_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..960b2e1d4625fe0375339deed4514f2de6a6ba7b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clone_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 clone { + using schema = at::Tensor (const at::Tensor &, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::clone") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "clone(Tensor self, *, MemoryFormat? memory_format=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::optional memory_format); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::optional memory_format); +}; + +struct TORCH_API clone_out { + using schema = at::Tensor & (const at::Tensor &, 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::clone") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "clone.out(Tensor self, *, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::optional memory_format, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::optional memory_format, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/complex_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/complex_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3dcf615a42e94eefcc2e849806fbaa9f6a092674 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/complex_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 & complex_out(at::Tensor & out, const at::Tensor & real, const at::Tensor & imag); +TORCH_API at::Tensor & complex_outf(const at::Tensor & real, const at::Tensor & imag, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8711d99791445f2daa6db706570daf4e6844b012 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_cuda_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor cosh(const at::Tensor & self); +TORCH_API at::Tensor & cosh_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & cosh_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & cosh_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_grid_sampler_backward_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_grid_sampler_backward_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d0efe22061dd82a6317beb9815b444fb161b0afc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_grid_sampler_backward_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API ::std::tuple cudnn_grid_sampler_backward_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & self, const at::Tensor & grid, const at::Tensor & grad_output); +TORCH_API ::std::tuple cudnn_grid_sampler_backward_outf(const at::Tensor & self, const at::Tensor & grid, const at::Tensor & grad_output, at::Tensor & out0, at::Tensor & out1); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dstack.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dstack.h new file mode 100644 index 0000000000000000000000000000000000000000..7d8763a9e099dd2be9ba2267348b81093d5d2eff --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/dstack.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::dstack(Tensor[] tensors) -> Tensor +inline at::Tensor dstack(at::TensorList tensors) { + return at::_ops::dstack::call(tensors); +} + +// aten::dstack.out(Tensor[] tensors, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & dstack_out(at::Tensor & out, at::TensorList tensors) { + return at::_ops::dstack_out::call(tensors, out); +} +// aten::dstack.out(Tensor[] tensors, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & dstack_outf(at::TensorList tensors, at::Tensor & out) { + return at::_ops::dstack_out::call(tensors, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..0e41ccb836b3f0075205e9a715e29d9a396d2e49 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_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_expm1 : public TensorIteratorBase { + + + void meta(const at::Tensor & self); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..547d98cee7414dc44598665c4fbe2aad37f2399e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_backward_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API fake_quantize_per_channel_affine_cachemask_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::fake_quantize_per_channel_affine_cachemask_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fake_quantize_per_channel_affine_cachemask_backward(Tensor grad, Tensor mask) -> Tensor") + static at::Tensor call(const at::Tensor & grad, const at::Tensor & mask); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad, const at::Tensor & mask); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3758201c755cdaf3e0d04e0eacb533969e1e4392 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_cachemask_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API ::std::tuple fake_quantize_per_channel_affine_cachemask_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis, int64_t quant_min, int64_t quant_max); +TORCH_API ::std::tuple fake_quantize_per_channel_affine_cachemask_outf(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 compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_irfft2.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_irfft2.h new file mode 100644 index 0000000000000000000000000000000000000000..713b32d5c919d4caec56c746bef4ac8e0fca5139 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_irfft2.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::fft_irfft2(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None) -> Tensor +inline at::Tensor fft_irfft2(const at::Tensor & self, at::OptionalIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt) { + return at::_ops::fft_irfft2::call(self, s.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*s)) : c10::nullopt, dim, norm); +} +namespace symint { + template ::value>> + at::Tensor fft_irfft2(const at::Tensor & self, at::OptionalIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt) { + return at::_ops::fft_irfft2::call(self, s.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*s)) : c10::nullopt, dim, norm); + } +} + +// aten::fft_irfft2(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None) -> Tensor +inline at::Tensor fft_irfft2_symint(const at::Tensor & self, at::OptionalSymIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt) { + return at::_ops::fft_irfft2::call(self, s, dim, norm); +} +namespace symint { + template ::value>> + at::Tensor fft_irfft2(const at::Tensor & self, at::OptionalSymIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt) { + return at::_ops::fft_irfft2::call(self, s, dim, norm); + } +} + +// aten::fft_irfft2.out(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & fft_irfft2_out(at::Tensor & out, const at::Tensor & self, at::OptionalIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt) { + return at::_ops::fft_irfft2_out::call(self, s.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*s)) : c10::nullopt, dim, norm, out); +} +namespace symint { + template ::value>> + at::Tensor & fft_irfft2_out(at::Tensor & out, const at::Tensor & self, at::OptionalIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt) { + return at::_ops::fft_irfft2_out::call(self, s.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*s)) : c10::nullopt, dim, norm, out); + } +} + +// aten::fft_irfft2.out(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & fft_irfft2_outf(const at::Tensor & self, at::OptionalIntArrayRef s, at::IntArrayRef dim, c10::optional norm, at::Tensor & out) { + return at::_ops::fft_irfft2_out::call(self, s.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*s)) : c10::nullopt, dim, norm, out); +} +namespace symint { + template ::value>> + at::Tensor & fft_irfft2_outf(const at::Tensor & self, at::OptionalIntArrayRef s, at::IntArrayRef dim, c10::optional norm, at::Tensor & out) { + return at::_ops::fft_irfft2_out::call(self, s.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*s)) : c10::nullopt, dim, norm, out); + } +} + +// aten::fft_irfft2.out(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & fft_irfft2_symint_out(at::Tensor & out, const at::Tensor & self, at::OptionalSymIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt) { + return at::_ops::fft_irfft2_out::call(self, s, dim, norm, out); +} +namespace symint { + template ::value>> + at::Tensor & fft_irfft2_out(at::Tensor & out, const at::Tensor & self, at::OptionalSymIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt) { + return at::_ops::fft_irfft2_out::call(self, s, dim, norm, out); + } +} + +// aten::fft_irfft2.out(Tensor self, SymInt[1]? s=None, int[1] dim=[-2,-1], str? norm=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & fft_irfft2_symint_outf(const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm, at::Tensor & out) { + return at::_ops::fft_irfft2_out::call(self, s, dim, norm, out); +} +namespace symint { + template ::value>> + at::Tensor & fft_irfft2_outf(const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm, at::Tensor & out) { + return at::_ops::fft_irfft2_out::call(self, s, dim, norm, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7ea591768bd37f66e5918f6dd021d352a5cd2941 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::tuple fractional_max_pool3d(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples); +TORCH_API ::std::tuple fractional_max_pool3d_out(at::Tensor & output, at::Tensor & indices, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples); +TORCH_API ::std::tuple fractional_max_pool3d_outf(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples, at::Tensor & output, at::Tensor & indices); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/from_file.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/from_file.h new file mode 100644 index 0000000000000000000000000000000000000000..6a55d501c1b32ac496b27383933e9d09152d0d60 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/from_file.h @@ -0,0 +1,43 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::from_file(str filename, bool? shared=None, int? size=0, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor from_file(c10::string_view filename, c10::optional shared=c10::nullopt, c10::optional size=0, at::TensorOptions options={}) { + return at::_ops::from_file::call(filename, shared, size, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +// aten::from_file(str filename, bool? shared=None, int? size=0, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor from_file(c10::string_view filename, c10::optional shared, c10::optional size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::from_file::call(filename, shared, size, dtype, layout, device, pin_memory); +} + +// aten::from_file.out(str filename, bool? shared=None, int? size=0, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & from_file_out(at::Tensor & out, c10::string_view filename, c10::optional shared=c10::nullopt, c10::optional size=0) { + return at::_ops::from_file_out::call(filename, shared, size, out); +} +// aten::from_file.out(str filename, bool? shared=None, int? size=0, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & from_file_outf(c10::string_view filename, c10::optional shared, c10::optional size, at::Tensor & out) { + return at::_ops::from_file_out::call(filename, shared, size, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_native.h new file mode 100644 index 0000000000000000000000000000000000000000..c7a8c38227e92fecf7e5334feb04228974bcfc8d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_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 instance_norm(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, const c10::optional & running_mean, const c10::optional & running_var, bool use_input_stats, double momentum, double eps, bool cudnn_enabled); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_leaf.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_leaf.h new file mode 100644 index 0000000000000000000000000000000000000000..7a2a0c37e8f4292e49eb43edcba268ac87c394e9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_leaf.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/isnan_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isnan_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d6f6d12ce72dc94ab37559c899704fe5cb68d44f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isnan_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 & isnan_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & isnan_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..63c26f63a95ca4075ea3f4fc4fe0645c930702b7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_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 leaky_relu_out { + using schema = at::Tensor & (const at::Tensor &, const at::Scalar &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::leaky_relu") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "leaky_relu.out(Tensor self, Scalar negative_slope=0.01, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Scalar & negative_slope, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & negative_slope, at::Tensor & out); +}; + +struct TORCH_API leaky_relu { + using schema = at::Tensor (const at::Tensor &, const at::Scalar &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::leaky_relu") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "leaky_relu(Tensor self, Scalar negative_slope=0.01) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Scalar & negative_slope); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & negative_slope); +}; + +struct TORCH_API leaky_relu_ { + using schema = at::Tensor & (at::Tensor &, const at::Scalar &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::leaky_relu_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "leaky_relu_(Tensor(a!) self, Scalar negative_slope=0.01) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Scalar & negative_slope); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Scalar & negative_slope); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_ex_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_ex_native.h new file mode 100644 index 0000000000000000000000000000000000000000..482c33f1339c147f8ba1b2c846003a3885fe2373 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_ex_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple linalg_solve_ex(const at::Tensor & A, const at::Tensor & B, bool left=true, bool check_errors=false); +TORCH_API ::std::tuple linalg_solve_ex_out(const at::Tensor & A, const at::Tensor & B, bool left, bool check_errors, at::Tensor & result, at::Tensor & info); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_triangular_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_triangular_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..a207b2ae4ce52ee1af745a9419debf6ac529df7e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_triangular_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API linalg_solve_triangular_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, 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::linalg_solve_triangular") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "linalg_solve_triangular.out(Tensor self, Tensor B, *, bool upper, bool left=True, bool unitriangular=False, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & B, bool upper, bool left, bool unitriangular, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & B, bool upper, bool left, bool unitriangular, at::Tensor & out); +}; + +struct TORCH_API linalg_solve_triangular { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, 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::linalg_solve_triangular") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "linalg_solve_triangular(Tensor self, Tensor B, *, bool upper, bool left=True, bool unitriangular=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & B, bool upper, bool left, bool unitriangular); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & B, bool upper, bool left, bool unitriangular); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log1p_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log1p_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..faa5515cd50444f2c47a711dfb55796886bc85ee --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log1p_compositeexplicitautogradnonfunctional_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor log1p(const at::Tensor & self); +TORCH_API at::Tensor & log1p_(at::Tensor & self); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_softmax_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_softmax_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7060dfe10932adac7251280360590b45d2a4fe7a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_softmax_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 & log_softmax_out(at::Tensor & out, const at::Tensor & self, int64_t dim, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & log_softmax_outf(const at::Tensor & self, int64_t dim, c10::optional dtype, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logdet_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logdet_native.h new file mode 100644 index 0000000000000000000000000000000000000000..8f3a25b4e6312d845972eddd2ec851cb0ffbf84f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logdet_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 logdet(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b8c5e70a7d5413e344355d2cf85f22335477d2e1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_backward_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor logit_backward(const at::Tensor & grad_output, const at::Tensor & self, c10::optional eps=c10::nullopt); +TORCH_API at::Tensor & logit_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, c10::optional eps=c10::nullopt); +TORCH_API at::Tensor & logit_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, c10::optional eps, at::Tensor & grad_input); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matrix_exp_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matrix_exp_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..768b3b802d3d29a4364f556c0fe349b5b99c9d44 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matrix_exp_backward_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API matrix_exp_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::matrix_exp_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "matrix_exp_backward(Tensor self, Tensor grad) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & grad); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & grad); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b6227e6152ef9b8743d08c60bb0492a07bf9cf80 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices_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 max_pool3d_with_indices_backward_grad_input { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, bool, const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::max_pool3d_with_indices_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "grad_input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "max_pool3d_with_indices_backward.grad_input(Tensor grad_output, Tensor self, int[3] kernel_size, int[3] stride, int[3] padding, int[3] dilation, bool ceil_mode, Tensor indices, *, Tensor(a!) grad_input) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices, at::Tensor & grad_input); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices, at::Tensor & grad_input); +}; + +struct TORCH_API max_pool3d_with_indices_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, bool, const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::max_pool3d_with_indices_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "max_pool3d_with_indices_backward(Tensor grad_output, Tensor self, int[3] kernel_size, int[3] stride, int[3] padding, int[3] dilation, bool ceil_mode, Tensor indices) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..cb61999b69974a3a0b4bde958da544af84d851a2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_max_pool2d_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_out(const at::Tensor & self, 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(const at::Tensor & self, 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/nanmean_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanmean_native.h new file mode 100644 index 0000000000000000000000000000000000000000..22d5ef1e9703e98b9b562e5d1cd80dcb4e5b27e0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanmean_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 nanmean(const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & nanmean_out(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad_native.h new file mode 100644 index 0000000000000000000000000000000000000000..1aeb86b0f356bf6cd6c3e6ad61d9e30d05846406 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad_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 pad_symint(const at::Tensor & self, c10::SymIntArrayRef pad, c10::string_view mode="constant", c10::optional value=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/positive_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/positive_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..232d47390e7f5ed442111d9b47707734b1700c47 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/positive_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 positive(const at::Tensor & self); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/randint_like_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/randint_like_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3df082405352489d96a7744348b466a84231a459 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/randint_like_ops.h @@ -0,0 +1,61 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API randint_like { + using schema = at::Tensor (const at::Tensor &, c10::SymInt, c10::optional, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::randint_like") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "randint_like(Tensor self, SymInt high, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, MemoryFormat? memory_format=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymInt high, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymInt high, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); +}; + +struct TORCH_API randint_like_low_dtype { + using schema = at::Tensor (const at::Tensor &, c10::SymInt, c10::SymInt, c10::optional, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::randint_like") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "low_dtype") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "randint_like.low_dtype(Tensor self, SymInt low, SymInt high, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, MemoryFormat? memory_format=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymInt low, c10::SymInt high, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymInt low, c10::SymInt high, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format); +}; + +struct TORCH_API randint_like_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymInt, 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::randint_like") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "randint_like.out(Tensor self, SymInt high, *, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::SymInt high, c10::optional memory_format, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymInt high, c10::optional memory_format, at::Tensor & out); +}; + +struct TORCH_API randint_like_low_dtype_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymInt, c10::SymInt, 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::randint_like") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "low_dtype_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "randint_like.low_dtype_out(Tensor self, SymInt low, SymInt high, *, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::SymInt low, c10::SymInt high, c10::optional memory_format, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymInt low, c10::SymInt high, c10::optional memory_format, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reciprocal_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reciprocal_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..35b127f2ec222def7a12a20b7beadd6f8316e96b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reciprocal_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 reciprocal(const at::Tensor & self); +TORCH_API at::Tensor & reciprocal_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & reciprocal_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & reciprocal_(at::Tensor & self); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/renorm_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/renorm_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c3d499b34ec0aa7c0b5a77cc7d4743a8b877b369 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/renorm_cuda_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor renorm(const at::Tensor & self, const at::Scalar & p, int64_t dim, const at::Scalar & maxnorm); +TORCH_API at::Tensor & renorm_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & p, int64_t dim, const at::Scalar & maxnorm); +TORCH_API at::Tensor & renorm_outf(const at::Tensor & self, const at::Scalar & p, int64_t dim, const at::Scalar & maxnorm, at::Tensor & out); +TORCH_API at::Tensor & renorm_(at::Tensor & self, const at::Scalar & p, int64_t dim, const at::Scalar & maxnorm); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/roll_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/roll_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..58644c7c76734c072edbea9732faa555bf4bc665 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/roll_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 roll { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef, at::IntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::roll") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "roll(Tensor self, SymInt[1] shifts, int[1] dims=[]) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef shifts, at::IntArrayRef dims); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef shifts, at::IntArrayRef dims); +}; + +struct TORCH_API roll_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymIntArrayRef, at::IntArrayRef, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::roll") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "roll.out(Tensor self, SymInt[1] shifts, int[1] dims=[], *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::SymIntArrayRef shifts, at::IntArrayRef dims, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef shifts, at::IntArrayRef dims, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rrelu_with_noise_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rrelu_with_noise_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..38f4925d4e1b591f7596a9eff97b97c3c2e4327c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rrelu_with_noise_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 rrelu_with_noise(const at::Tensor & self, const at::Tensor & noise, const at::Scalar & lower=0.125, const at::Scalar & upper=0.3333333333333333, bool training=false, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & rrelu_with_noise_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & noise, const at::Scalar & lower=0.125, const at::Scalar & upper=0.3333333333333333, bool training=false, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & rrelu_with_noise_outf(const at::Tensor & self, const at::Tensor & noise, const at::Scalar & lower, const at::Scalar & upper, bool training, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor & rrelu_with_noise_(at::Tensor & self, const at::Tensor & noise, const at::Scalar & lower=0.125, const at::Scalar & upper=0.3333333333333333, bool training=false, c10::optional generator=c10::nullopt); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..45a88633d4859db8af09942404e1cab13f163c5b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_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 silu(const at::Tensor & self); +TORCH_API at::Tensor & silu_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & silu_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & silu_(at::Tensor & self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_scatter.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_scatter.h new file mode 100644 index 0000000000000000000000000000000000000000..08e58a347e86f6a50c79b79b3322d29b082fa9c9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_scatter.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::slice_scatter(Tensor self, Tensor src, int dim=0, SymInt? start=None, SymInt? end=None, SymInt step=1) -> Tensor +inline at::Tensor slice_scatter(const at::Tensor & self, const at::Tensor & src, int64_t dim=0, c10::optional start=c10::nullopt, c10::optional end=c10::nullopt, int64_t step=1) { + return at::_ops::slice_scatter::call(self, src, dim, start.has_value() ? c10::make_optional(c10::SymInt(*start)) : c10::nullopt, end.has_value() ? c10::make_optional(c10::SymInt(*end)) : c10::nullopt, step); +} +namespace symint { + template ::value>> + at::Tensor slice_scatter(const at::Tensor & self, const at::Tensor & src, int64_t dim=0, c10::optional start=c10::nullopt, c10::optional end=c10::nullopt, int64_t step=1) { + return at::_ops::slice_scatter::call(self, src, dim, start.has_value() ? c10::make_optional(c10::SymInt(*start)) : c10::nullopt, end.has_value() ? c10::make_optional(c10::SymInt(*end)) : c10::nullopt, step); + } +} + +// aten::slice_scatter(Tensor self, Tensor src, int dim=0, SymInt? start=None, SymInt? end=None, SymInt step=1) -> Tensor +inline at::Tensor slice_scatter_symint(const at::Tensor & self, const at::Tensor & src, int64_t dim=0, c10::optional start=c10::nullopt, c10::optional end=c10::nullopt, c10::SymInt step=1) { + return at::_ops::slice_scatter::call(self, src, dim, start, end, step); +} +namespace symint { + template ::value>> + at::Tensor slice_scatter(const at::Tensor & self, const at::Tensor & src, int64_t dim=0, c10::optional start=c10::nullopt, c10::optional end=c10::nullopt, c10::SymInt step=1) { + return at::_ops::slice_scatter::call(self, src, dim, start, end, step); + } +} + +// aten::slice_scatter.out(Tensor self, Tensor src, int dim=0, SymInt? start=None, SymInt? end=None, SymInt step=1, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & slice_scatter_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & src, int64_t dim=0, c10::optional start=c10::nullopt, c10::optional end=c10::nullopt, int64_t step=1) { + return at::_ops::slice_scatter_out::call(self, src, dim, start.has_value() ? c10::make_optional(c10::SymInt(*start)) : c10::nullopt, end.has_value() ? c10::make_optional(c10::SymInt(*end)) : c10::nullopt, step, out); +} +namespace symint { + template ::value>> + at::Tensor & slice_scatter_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & src, int64_t dim=0, c10::optional start=c10::nullopt, c10::optional end=c10::nullopt, int64_t step=1) { + return at::_ops::slice_scatter_out::call(self, src, dim, start.has_value() ? c10::make_optional(c10::SymInt(*start)) : c10::nullopt, end.has_value() ? c10::make_optional(c10::SymInt(*end)) : c10::nullopt, step, out); + } +} + +// aten::slice_scatter.out(Tensor self, Tensor src, int dim=0, SymInt? start=None, SymInt? end=None, SymInt step=1, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & slice_scatter_outf(const at::Tensor & self, const at::Tensor & src, int64_t dim, c10::optional start, c10::optional end, int64_t step, at::Tensor & out) { + return at::_ops::slice_scatter_out::call(self, src, dim, start.has_value() ? c10::make_optional(c10::SymInt(*start)) : c10::nullopt, end.has_value() ? c10::make_optional(c10::SymInt(*end)) : c10::nullopt, step, out); +} +namespace symint { + template ::value>> + at::Tensor & slice_scatter_outf(const at::Tensor & self, const at::Tensor & src, int64_t dim, c10::optional start, c10::optional end, int64_t step, at::Tensor & out) { + return at::_ops::slice_scatter_out::call(self, src, dim, start.has_value() ? c10::make_optional(c10::SymInt(*start)) : c10::nullopt, end.has_value() ? c10::make_optional(c10::SymInt(*end)) : c10::nullopt, step, out); + } +} + +// aten::slice_scatter.out(Tensor self, Tensor src, int dim=0, SymInt? start=None, SymInt? end=None, SymInt step=1, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & slice_scatter_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & src, int64_t dim=0, c10::optional start=c10::nullopt, c10::optional end=c10::nullopt, c10::SymInt step=1) { + return at::_ops::slice_scatter_out::call(self, src, dim, start, end, step, out); +} +namespace symint { + template ::value>> + at::Tensor & slice_scatter_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & src, int64_t dim=0, c10::optional start=c10::nullopt, c10::optional end=c10::nullopt, c10::SymInt step=1) { + return at::_ops::slice_scatter_out::call(self, src, dim, start, end, step, out); + } +} + +// aten::slice_scatter.out(Tensor self, Tensor src, int dim=0, SymInt? start=None, SymInt? end=None, SymInt step=1, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & slice_scatter_symint_outf(const at::Tensor & self, const at::Tensor & src, int64_t dim, c10::optional start, c10::optional end, c10::SymInt step, at::Tensor & out) { + return at::_ops::slice_scatter_out::call(self, src, dim, start, end, step, out); +} +namespace symint { + template ::value>> + at::Tensor & slice_scatter_outf(const at::Tensor & self, const at::Tensor & src, int64_t dim, c10::optional start, c10::optional end, c10::SymInt step, at::Tensor & out) { + return at::_ops::slice_scatter_out::call(self, src, dim, start, end, step, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_bsr_tensor_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_bsr_tensor_native.h new file mode 100644 index 0000000000000000000000000000000000000000..970c4625ef121869233fe02a3e34b04cabb0fad1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_bsr_tensor_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 sparse_bsr_tensor(const at::Tensor & crow_indices, const at::Tensor & col_indices, const at::Tensor & values, at::IntArrayRef size, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +TORCH_API at::Tensor sparse_bsr_tensor(const at::Tensor & crow_indices, const at::Tensor & col_indices, const at::Tensor & values, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_i1_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_i1_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..669760680ecd229e35860a74c86cb8f5b992e0c0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_i1_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API special_i1 { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_i1") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_i1(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API special_i1_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_i1") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_i1.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k0_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k0_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..cbc198c7a3b6ddc4972871569fedc01eee9ae1be --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_scaled_modified_bessel_k0_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API special_scaled_modified_bessel_k0 { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_scaled_modified_bessel_k0") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_scaled_modified_bessel_k0(Tensor x) -> Tensor") + static at::Tensor call(const at::Tensor & x); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x); +}; + +struct TORCH_API special_scaled_modified_bessel_k0_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_scaled_modified_bessel_k0") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_scaled_modified_bessel_k0.out(Tensor x, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & x, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tan_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tan_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..0c56be6077a1ad4a15fff82b5404957c8ad515aa --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tan_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 tan { + 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::tan") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "tan(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 tan_ { + 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::tan_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "tan_(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 tan_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::tan") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "tan.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/trapezoid_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/trapezoid_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b564d37a59bf632f7afc1fc2decc666138e178d5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/trapezoid_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 trapezoid(const at::Tensor & y, const at::Tensor & x, int64_t dim=-1); +TORCH_API at::Tensor trapezoid(const at::Tensor & y, const at::Scalar & dx=1, int64_t dim=-1); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/triu_indices_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/triu_indices_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..6f9a263daa3363b6a100537d6c88ac6e5abf7c66 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/triu_indices_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 triu_indices { + using schema = at::Tensor (int64_t, int64_t, int64_t, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::triu_indices") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "triu_indices(int row, int col, int offset=0, *, ScalarType? dtype=long, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(int64_t row, int64_t col, int64_t offset, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, int64_t row, int64_t col, int64_t offset, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API triu_indices_out { + using schema = at::Tensor & (int64_t, int64_t, int64_t, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::triu_indices") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "triu_indices.out(int row, int col, int offset=0, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(int64_t row, int64_t col, int64_t offset, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, int64_t row, int64_t col, int64_t offset, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_dim_consecutive_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_dim_consecutive_native.h new file mode 100644 index 0000000000000000000000000000000000000000..146a0dfca1b3f6702b06f2b04856590cc9025c87 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_dim_consecutive_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 unique_dim_consecutive_out(const at::Tensor & self, int64_t dim, bool return_inverse, bool return_counts, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); +TORCH_API ::std::tuple unique_dim_consecutive_cpu(const at::Tensor & self, int64_t dim, bool return_inverse=false, bool return_counts=false); +TORCH_API ::std::tuple unique_dim_consecutive_cuda(const at::Tensor & self, int64_t dim, bool return_inverse=false, bool return_counts=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_dim_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_dim_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7b15fb6cf8e47283065235db5c564afaa8810043 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_dim_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 unique_dim(const at::Tensor & self, int64_t dim, bool sorted=true, bool return_inverse=false, bool return_counts=false); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c6bb219fa79714c4d70dfdadc90e1151c0ffe4a0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bilinear2d_compositeimplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor upsample_bilinear2d(const at::Tensor & input, at::OptionalIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); +TORCH_API at::Tensor upsample_bilinear2d_symint(const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_linear1d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_linear1d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..417afaa75d05afedd61cf46aa8b78beed7b6797b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_linear1d_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_linear1d_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_linear1d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "vec") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "upsample_linear1d.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_linear1d_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymIntArrayRef, bool, c10::optional, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::upsample_linear1d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "upsample_linear1d.out(Tensor self, SymInt[1] output_size, bool align_corners, float? scales=None, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales, at::Tensor & out); +}; + +struct TORCH_API upsample_linear1d { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef, 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_linear1d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "upsample_linear1d(Tensor self, SymInt[1] output_size, bool align_corners, float? scales=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest2d_backward_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest2d_backward_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d9e1053ef6df374d1d848bf25fb40c51cfa830ed --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest2d_backward_compositeexplicitautogradnonfunctional_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor upsample_nearest2d_backward(const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor upsample_nearest2d_backward_symint(const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..45d3cdaf5a6c51d494955fdc7ae0d66f089bb2f6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_native.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +TORCH_API at::Tensor upsample_trilinear3d(const at::Tensor & input, at::OptionalIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); +struct TORCH_API structured_upsample_trilinear3d_out_cpu : public at::meta::structured_upsample_trilinear3d { +void impl(const at::Tensor & self, at::ArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & out); +}; +struct TORCH_API structured_upsample_trilinear3d_out_cuda : public at::meta::structured_upsample_trilinear3d { +void impl(const at::Tensor & self, at::ArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f73e2a9b5f1aede026ad7cd32488f728cd2eb2d6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_cuda_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor view_as_real(const at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_native.h new file mode 100644 index 0000000000000000000000000000000000000000..75f7d135806b9499a176979889f64b4e66e6ce30 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor view_as_real(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..a13519b0c39bf434905b95994d56797103bdc45c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_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 view { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::view") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "view(Tensor(a) self, SymInt[] size) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef size); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef size); +}; + +struct TORCH_API view_dtype { + using schema = at::Tensor (const at::Tensor &, at::ScalarType); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::view") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dtype") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "view.dtype(Tensor(a) self, ScalarType dtype) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, at::ScalarType dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::ScalarType dtype); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/where_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/where_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..204567ea097a53a4dcdcecad030420508afb11b7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/where_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor where(const at::Tensor & condition, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & where_out(at::Tensor & out, const at::Tensor & condition, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & where_outf(const at::Tensor & condition, const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + +} // namespace cuda +} // namespace at