diff --git a/controllers/llamaCPP.cc b/controllers/llamaCPP.cc
index 5756d0ccf..106e15956 100644
--- a/controllers/llamaCPP.cc
+++ b/controllers/llamaCPP.cc
@@ -714,7 +714,6 @@ bool llamaCPP::LoadModelImpl(std::shared_ptr<Json::Value> jsonBody) {
   }
   server_ctx_map[model_id].initialize();
 
-  //TODO(sang) make_unique only available on C++14
   if (inference_task_queue == nullptr ||
       task_queue_thread_num < params.n_parallel) {
     task_queue_thread_num = std::max(task_queue_thread_num, params.n_parallel);