Update base for Update on "introduce cuda stream into runtime backend"

This diff introduces CUDA streams into the Executorch runtime backend. The changes include:

* Adding CUDA stream support to the `cuda_backend.cpp` file
* Including the `cuda_runtime.h` header file in `cuda_backend.cpp`
* Adding a `void* cuda_stream` field to the `AOTInductorModelContainer` struct in `aoti_model_container.h` to store the CUDA stream
* Defining a new macro `ET_CHECK_OR_LOG` in `log.h` to check a condition and log an error message if the condition is false.

Differential Revision: [D84128173](https://our.internmc.facebook.com/intern/diff/D84128173/)

[ghstack-poisoned]

Author: Gasoonjia

backends/aoti/CMakeLists.txt

@@ -44,8 +44,6 @@ target_link_options(aoti_common PUBLIC -Wl,--export-dynamic)
 target_link_libraries(
   aoti_common
   PUBLIC extension_tensor ${CMAKE_DL_LIBS}
-         # Link PyTorch libraries for AOTI functions
-         ${TORCH_LIBRARIES}
 )
 executorch_target_link_options_shared_lib(aoti_common)