// 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
  // functions, and their send/recvs corountines).

    job_def->mutable_tasks()->insert(
        {i, tensorflow::strings::StrCat("localhost:", port)});
  }
  auto* config = server_def.mutable_default_session_config();
  config->mutable_experimental()->set_collective_group_leader(
      tensorflow::strings::StrCat("/job:", job_name, "/replica:0/task:", 0));
  auto* rewrite_options =
      config->mutable_graph_options()->mutable_rewrite_options();
  rewrite_options->set_scoped_allocator_optimization(