From 0f0b4bf0295f988b62283efd72f08a5180d905c4 Mon Sep 17 00:00:00 2001
From: Yuanyuan Chen <cyyever@outlook.com>
Date: Sat, 18 Oct 2025 05:23:07 +0000
Subject: [PATCH] [1/N] Remove unused header inclusion (#165763)

This PR removes unused header inclusion in C++ files.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/165763
Approved by: https://github.com/Skylion007
---
 c10/core/AllocatorConfig.cpp                               | 1 -
 c10/core/SymInt.cpp                                        | 1 -
 c10/core/TensorImpl.cpp                                    | 1 -
 c10/core/TensorOptions.cpp                                 | 4 ----
 c10/core/impl/COW.cpp                                      | 1 -
 c10/core/impl/TorchDispatchModeTLS.cpp                     | 1 -
 c10/cuda/CUDADeviceAssertionHost.cpp                       | 2 --
 c10/cuda/CUDAMallocAsyncAllocator.cpp                      | 1 -
 c10/cuda/CUDAMiscFunctions.cpp                             | 1 -
 c10/cuda/driver_api.cpp                                    | 1 -
 c10/util/ApproximateClock.cpp                              | 3 +--
 c10/util/complex_math.cpp                                  | 2 --
 c10/util/signal_handler.cpp                                | 1 -
 torch/csrc/distributed/c10d/control_plane/WorkerServer.cpp | 1 -
 torch/csrc/profiler/util.cpp                               | 1 -
 15 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/c10/core/AllocatorConfig.cpp b/c10/core/AllocatorConfig.cpp
index 750336d143f..de09037113c 100644
--- a/c10/core/AllocatorConfig.cpp
+++ b/c10/core/AllocatorConfig.cpp
@@ -1,5 +1,4 @@
 #include <c10/core/AllocatorConfig.h>
-#include <c10/core/DeviceType.h>
 #include <c10/util/env.h>
 
 namespace c10::CachingAllocator {
diff --git a/c10/core/SymInt.cpp b/c10/core/SymInt.cpp
index 8b8ffedc23f..7ad5cdfb629 100644
--- a/c10/core/SymInt.cpp
+++ b/c10/core/SymInt.cpp
@@ -4,7 +4,6 @@
 #include <c10/core/SymNodeImpl.h>
 #include <c10/util/intrusive_ptr.h>
 #include <c10/util/safe_numerics.h>
-#include <functional>
 
 namespace c10 {
 
diff --git a/c10/core/TensorImpl.cpp b/c10/core/TensorImpl.cpp
index cd0321d3bb6..c59524a0932 100644
--- a/c10/core/TensorImpl.cpp
+++ b/c10/core/TensorImpl.cpp
@@ -9,7 +9,6 @@
 #include <c10/core/impl/TorchDispatchModeTLS.h>
 #include <c10/util/Logging.h>
 #include <c10/util/accumulate.h>
-#include <c10/util/irange.h>
 #include <optional>
 
 #include <utility>
diff --git a/c10/core/TensorOptions.cpp b/c10/core/TensorOptions.cpp
index 599868aea8f..d3282ae7114 100644
--- a/c10/core/TensorOptions.cpp
+++ b/c10/core/TensorOptions.cpp
@@ -1,9 +1,5 @@
 #include <c10/core/TensorOptions.h>
 
-#include <c10/core/Device.h>
-#include <c10/core/Layout.h>
-#include <c10/util/Optional.h>
-
 #include <iostream>
 
 namespace c10 {
diff --git a/c10/core/impl/COW.cpp b/c10/core/impl/COW.cpp
index 81bc86e64bd..78aa267d125 100644
--- a/c10/core/impl/COW.cpp
+++ b/c10/core/impl/COW.cpp
@@ -2,7 +2,6 @@
 
 #include <c10/core/Allocator.h>
 #include <c10/core/StorageImpl.h>
-#include <c10/core/alignment.h>
 #include <c10/core/impl/COWDeleter.h>
 #include <c10/util/Exception.h>
 #include <c10/util/ParallelGuard.h>
diff --git a/c10/core/impl/TorchDispatchModeTLS.cpp b/c10/core/impl/TorchDispatchModeTLS.cpp
index c8bdc1bb59b..55d9e24a572 100644
--- a/c10/core/impl/TorchDispatchModeTLS.cpp
+++ b/c10/core/impl/TorchDispatchModeTLS.cpp
@@ -1,5 +1,4 @@
 #include <c10/core/DispatchKey.h>
-#include <c10/core/SafePyObject.h>
 #include <c10/core/impl/LocalDispatchKeySet.h>
 #include <c10/core/impl/TorchDispatchModeTLS.h>
 #include <c10/util/irange.h>
diff --git a/c10/cuda/CUDADeviceAssertionHost.cpp b/c10/cuda/CUDADeviceAssertionHost.cpp
index a6d4c3fe907..d67ee4b23e6 100644
--- a/c10/cuda/CUDADeviceAssertionHost.cpp
+++ b/c10/cuda/CUDADeviceAssertionHost.cpp
@@ -1,8 +1,6 @@
 #include <c10/cuda/CUDADeviceAssertionHost.h>
 #include <c10/cuda/CUDAException.h>
 #include <c10/cuda/CUDAFunctions.h>
-#include <c10/util/Backtrace.h>
-#include <c10/util/Exception.h>
 #include <c10/util/env.h>
 #include <c10/util/irange.h>
 #include <cuda_runtime.h>
diff --git a/c10/cuda/CUDAMallocAsyncAllocator.cpp b/c10/cuda/CUDAMallocAsyncAllocator.cpp
index ce0f3d88554..2e9ad7d78d1 100644
--- a/c10/cuda/CUDAMallocAsyncAllocator.cpp
+++ b/c10/cuda/CUDAMallocAsyncAllocator.cpp
@@ -4,7 +4,6 @@
 #include <c10/cuda/CUDAGuard.h>
 #include <c10/util/UniqueVoidPtr.h>
 #include <c10/util/flat_hash_map.h>
-#include <c10/util/irange.h>
 
 #include <unordered_set>
 #include <vector>
diff --git a/c10/cuda/CUDAMiscFunctions.cpp b/c10/cuda/CUDAMiscFunctions.cpp
index b1b6170f891..b305008d44f 100644
--- a/c10/cuda/CUDAMiscFunctions.cpp
+++ b/c10/cuda/CUDAMiscFunctions.cpp
@@ -1,7 +1,6 @@
 #include <c10/cuda/CUDAMiscFunctions.h>
 #include <c10/util/env.h>
 #include <cuda_runtime.h>
-#include <cstring>
 #include <string>
 
 namespace c10::cuda {
diff --git a/c10/cuda/driver_api.cpp b/c10/cuda/driver_api.cpp
index d545bf5477b..887c2d06347 100644
--- a/c10/cuda/driver_api.cpp
+++ b/c10/cuda/driver_api.cpp
@@ -1,7 +1,6 @@
 #if !defined(USE_ROCM) && defined(PYTORCH_C10_DRIVER_API_SUPPORTED)
 #include <c10/cuda/CUDAException.h>
 #include <c10/cuda/driver_api.h>
-#include <c10/util/CallOnce.h>
 #include <c10/util/Exception.h>
 #include <c10/util/Logging.h>
 #include <cuda_runtime.h>
diff --git a/c10/util/ApproximateClock.cpp b/c10/util/ApproximateClock.cpp
index a69128a4483..53a7b7aa144 100644
--- a/c10/util/ApproximateClock.cpp
+++ b/c10/util/ApproximateClock.cpp
@@ -1,7 +1,6 @@
 #include <c10/util/ApproximateClock.h>
-#include <c10/util/ArrayRef.h>
+#include <c10/util/Exception.h>
 #include <c10/util/irange.h>
-#include <fmt/format.h>
 
 namespace c10 {
 
diff --git a/c10/util/complex_math.cpp b/c10/util/complex_math.cpp
index 886aadb1415..d1d690917a9 100644
--- a/c10/util/complex_math.cpp
+++ b/c10/util/complex_math.cpp
@@ -1,7 +1,5 @@
 #include <c10/util/complex.h>
 
-#include <cmath>
-
 // Note [ Complex Square root in libc++]
 // ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 // In libc++ complex square root is computed using polar form
diff --git a/c10/util/signal_handler.cpp b/c10/util/signal_handler.cpp
index 7c2bd055c58..831c0d02452 100644
--- a/c10/util/signal_handler.cpp
+++ b/c10/util/signal_handler.cpp
@@ -11,7 +11,6 @@
 #include <unistd.h>
 
 #include <atomic>
-#include <chrono>
 #include <condition_variable>
 #include <cstdint>
 #include <cstdio>
diff --git a/torch/csrc/distributed/c10d/control_plane/WorkerServer.cpp b/torch/csrc/distributed/c10d/control_plane/WorkerServer.cpp
index 02efb9ecbe0..908540e6852 100644
--- a/torch/csrc/distributed/c10d/control_plane/WorkerServer.cpp
+++ b/torch/csrc/distributed/c10d/control_plane/WorkerServer.cpp
@@ -5,7 +5,6 @@
 #include <c10/util/Exception.h>
 #include <c10/util/FileSystem.h>
 #include <c10/util/thread_name.h>
-#include <caffe2/utils/threadpool/WorkersPool.h>
 #include <torch/csrc/distributed/c10d/control_plane/WorkerServer.hpp>
 #include <torch/csrc/distributed/c10d/logging.h>
 
diff --git a/torch/csrc/profiler/util.cpp b/torch/csrc/profiler/util.cpp
index 0b2979e6fb7..d266958e2cb 100644
--- a/torch/csrc/profiler/util.cpp
+++ b/torch/csrc/profiler/util.cpp
@@ -1,6 +1,5 @@
 #include <torch/csrc/autograd/function.h>
 #include <torch/csrc/profiler/collection.h>
-#include <torch/csrc/profiler/kineto_shim.h>
 #include <torch/csrc/profiler/util.h>
 
 #include <c10/util/ArrayRef.h>