Remove unused header inclusion (#119667)

Fixes #ISSUE_NUMBER

Pull Request resolved: https://github.com/pytorch/pytorch/pull/119667
Approved by: https://github.com/Skylion007

c10/cuda/CUDADeviceAssertionHost.cpp

@@ -6,13 +6,12 @@
 #include <c10/util/irange.h>
 #include <cuda_runtime.h>
 
-#include <algorithm>
-#include <iostream>
 #include <memory>
-#include <sstream>
-#include <stdexcept>
 #include <string>
+#ifdef TORCH_USE_CUDA_DSA
+#include <chrono>
 #include <thread>
+#endif
 
 #define C10_CUDA_CHECK_WO_DSA(EXPR)                                 \
   do {                                                              \

c10/cuda/CUDAStream.cpp

@@ -8,8 +8,6 @@
 
 #include <atomic>
 #include <cstdint>
-#include <mutex>
-#include <vector>
 
 namespace c10::cuda {
 

c10/cuda/driver_api.cpp

@@ -3,7 +3,6 @@
 #include <c10/util/CallOnce.h>
 #include <c10/util/Exception.h>
 #include <dlfcn.h>
-#include <iostream>
 
 namespace c10::cuda {
 

torch/csrc/DataLoader.cpp

@@ -20,7 +20,6 @@
 #include <fmt/format.h>
 
 #include <sys/wait.h>
-#include <atomic>
 #include <csignal>
 #include <map>
 #include <set>

torch/csrc/Device.cpp

@@ -11,7 +11,6 @@
 #include <c10/util/Exception.h>
 
 #include <structmember.h>
-#include <cstring>
 #include <limits>
 #include <sstream>
 

torch/csrc/DynamicTypes.cpp

@@ -15,12 +15,7 @@
 #include <ATen/FunctionalStorageImpl.h>
 
 #include <array>
-#include <memory>
-#include <sstream>
 #include <stdexcept>
-#include <string>
-#include <unordered_map>
-#include <vector>
 
 namespace torch {
 namespace {

torch/csrc/autograd/function.cpp

@@ -6,10 +6,7 @@
 
 #include <ATen/ATen.h>
 
-#include <algorithm>
-#include <cstdint>
 #include <memory>
-#include <stdexcept>
 #include <string>
 #include <utility>
 #include <vector>

torch/csrc/autograd/profiler_kineto.cpp

@@ -22,9 +22,6 @@
 
 #include <ATen/Context.h>
 
-#include <deque>
-#include <limits>
-#include <sstream>
 #include <stdexcept>
 #include <utility>
 

torch/csrc/autograd/profiler_legacy.cpp

@@ -10,7 +10,6 @@
 #include <torch/library.h>
 
 #include <fstream>
-#include <list>
 #include <mutex>
 #include <sstream>
 #include <string>

torch/csrc/autograd/python_anomaly_mode.cpp

@@ -8,8 +8,6 @@
 #include <torch/csrc/utils/pybind.h>
 #include <torch/csrc/utils/python_strings.h>
 
-#include <iostream>
-
 namespace torch {
 namespace autograd {
 

torch/csrc/autograd/python_engine.cpp

@@ -22,7 +22,6 @@
 #endif
 
 #include <memory> // for unique_ptr
-#include <unordered_set>
 #include <utility>
 
 using namespace torch::autograd;

torch/csrc/autograd/python_function.cpp

@@ -32,12 +32,10 @@
 #include <torch/csrc/utils/python_strings.h>
 #include <torch/csrc/utils/tensor_dtypes.h>
 
-#include <exception>
 #include <functional>
 #include <memory>
 #include <stdexcept>
 #include <string>
-#include <tuple>
 #include <unordered_map>
 #include <unordered_set>
 #include <utility>

torch/csrc/autograd/python_variable.cpp

@@ -40,7 +40,6 @@
 #include <c10/core/SymIntArrayRef.h>
 #include <structmember.h>
 #include <cstdint>
-#include <iostream>
 #include <memory>
 #include <utility>
 #include <vector>

torch/csrc/autograd/python_variable_indexing.cpp

@@ -28,8 +28,6 @@
 #include <c10/util/irange.h>
 
 #include <c10/core/Layout.h>
-#include <tuple>
-#include <vector>
 
 using namespace at;
 using namespace torch::autograd::utils;

torch/csrc/autograd/saved_variable.cpp

@@ -9,8 +9,6 @@
 
 #include <ATen/Tensor.h>
 
-#include <cstdint>
-#include <list>
 #include <memory>
 #include <sstream>
 

torch/csrc/cuda/Tensor.cpp

@@ -7,9 +7,6 @@
 #include <torch/csrc/python_headers.h>
 #include <structmember.h>
 
-#include <stack>
-#include <tuple>
-#include <vector>
 #include <torch/csrc/cuda/THCP.h>
 
 #include <torch/csrc/utils/tensor_numpy.h>