Fix the torch_cpu_library comments and make aten_bridge static

The same three-line comment sat at five link sites. It explained why the
line does not link torch, but not what torch_cpu_library does
differently, and "in a CUDA build" read as our own CUDA option rather
than how PyTorch was built.

Each site now says that torch records libtorch_cuda with a CUDA build of
PyTorch, so a CPU-only torch could not load the library, and that
torch_cpu_library does not.

At aten_bridge the old reason did not apply. aten_bridge is a static
library and is never loaded on its own. Its link matters because it is
passed on to _training_lib. But it was only static by default: with
BUILD_SHARED_LIBS=ON it became a shared library. Mark it STATIC so the
comment holds in every layout. Nothing installs it and only
_training_lib links it.

Author: shoumikhin

CMakeLists.txt

@@ -1439,7 +1439,7 @@ if(EXECUTORCH_BUILD_PYBIND)
       TORCH_PYTHON_LIBRARY torch_python PATHS "${TORCH_INSTALL_PREFIX}/lib"
     )
     add_library(
-      aten_bridge
+      aten_bridge STATIC
       ${CMAKE_CURRENT_SOURCE_DIR}/extension/aten_util/aten_bridge.cpp
     )
     set_target_properties(aten_bridge PROPERTIES CXX_STANDARD 20)
@@ -1450,9 +1450,8 @@ if(EXECUTORCH_BUILD_PYBIND)
       aten_bridge PUBLIC C10_USING_CUSTOM_GENERATED_MACROS
     )
     target_compile_options(aten_bridge PUBLIC ${_pybind_compile_options})
-    # torch_cpu_library is the CPU half of torch. Linking torch would also force
-    # libtorch_cuda into DT_NEEDED in a CUDA build, and a CPU-only torch could
-    # then not load this library.
+    # aten_bridge is static, so _training_lib gets this link. torch would record
+    # libtorch_cuda with a CUDA build of PyTorch; torch_cpu_library does not.
     if(EXECUTORCH_BUILD_SHARED)
       target_link_libraries(
         aten_bridge PRIVATE torch_cpu_library c10 executorch_shared

extension/llm/custom_ops/CMakeLists.txt

@@ -230,9 +230,8 @@ if(EXECUTORCH_BUILD_KERNELS_LLM_AOT)
   endif()
   executorch_target_link_shared_runtime(custom_ops_aot_lib)
 
-  # torch_cpu_library is the CPU half of torch. Linking torch would also force
-  # libtorch_cuda into DT_NEEDED in a CUDA build, and a CPU-only torch could
-  # then not load this library.
+  # torch would record libtorch_cuda with a CUDA build of PyTorch, so a CPU-only
+  # torch could not load this. torch_cpu_library does not.
   target_link_libraries(
     custom_ops_aot_lib PUBLIC cpublas torch_cpu_library extension_tensor
                               extension_threadpool

extension/llm/runner/CMakeLists.txt

@@ -122,9 +122,8 @@ if(EXECUTORCH_BUILD_PYBIND)
   )
   # Link with the extension_llm_runner library and its dependencies.
   #
-  # torch_cpu_library is the CPU half of torch. Linking torch would also force
-  # libtorch_cuda into DT_NEEDED in a CUDA build, and a CPU-only torch could
-  # then not load this library.
+  # torch would record libtorch_cuda with a CUDA build of PyTorch, so a CPU-only
+  # torch could not load this. torch_cpu_library does not.
   target_link_libraries(
     _llm_runner PRIVATE extension_llm_runner tokenizers::tokenizers
                         portable_lib ${TORCH_PYTHON_LIBRARY} torch_cpu_library

extension/training/CMakeLists.txt

@@ -53,9 +53,8 @@ if(EXECUTORCH_BUILD_PYBIND)
   # is resolved from it rather than from the whole-archive-forcing static
   # `executorch` target, so this module shares the one backend registry.
   #
-  # torch_cpu_library is the CPU half of torch. Linking torch would also force
-  # libtorch_cuda into DT_NEEDED in a CUDA build, and a CPU-only torch could
-  # then not load this library.
+  # torch would record libtorch_cuda with a CUDA build of PyTorch, so a CPU-only
+  # torch could not load this. torch_cpu_library does not.
   if(EXECUTORCH_BUILD_SHARED)
     set(_pybind_training_dep_libs ${TORCH_PYTHON_LIBRARY} etdump aten_bridge
                                   torch_cpu_library extension_training

tools/cmake/Codegen.cmake

@@ -334,9 +334,8 @@ function(gen_custom_ops_aot_lib)
   set_target_properties(${GEN_LIB_NAME} PROPERTIES CXX_STANDARD 20)
   target_compile_definitions(${GEN_LIB_NAME} PRIVATE USE_ATEN_LIB=1)
   include_directories(${TORCH_INCLUDE_DIRS})
-  # torch_cpu_library is the CPU half of torch. Linking torch would also force
-  # libtorch_cuda into DT_NEEDED in a CUDA build, and a CPU-only torch could
-  # then not load this library.
+  # torch would record libtorch_cuda with a CUDA build of PyTorch, so a CPU-only
+  # torch could not load this. torch_cpu_library does not.
   target_link_libraries(${GEN_LIB_NAME} PRIVATE torch_cpu_library)
 
   executorch_target_link_options_shared_lib(${GEN_LIB_NAME})