#include "tensorflow/c/eager/tfe_context_internal.h"
#include "tensorflow/c/eager/tfe_op_internal.h"
#include "tensorflow/c/eager/tfe_tensorhandle_internal.h"
#include "tensorflow/c/tf_status.h"
#include "tensorflow/c/tf_status_helper.h"
#include "xla/tsl/c/tsl_status_internal.h"
#include "xla/tsl/distributed_runtime/coordination/coordination_service_agent.h"
#include "tensorflow/core/common_runtime/composite_device.h"

  // scheduled on that same threadpool, causing a deadlock in cases where the
  // caller of event_mgr->ThenExecute() blocks on the completion of the callback
  // (as in the case of ConstOp kernel creation on GPU, which involves copying a
  // CPU tensor to GPU).
  // Setting a larger thread pool does not help with the Swift caller, as we use
  // a different TFE context for each thread of execution (for running graph