diff --git a/controllers/llamaCPP.cc b/controllers/llamaCPP.cc
index 28c109d24..429bdab44 100644
--- a/controllers/llamaCPP.cc
+++ b/controllers/llamaCPP.cc
@@ -164,7 +164,7 @@ void llamaCPP::chatCompletion(
     data["frequency_penalty"] =
         (*jsonBody).get("frequency_penalty", 0).asFloat();
     data["presence_penalty"] = (*jsonBody).get("presence_penalty", 0).asFloat();
-
+    data["cache_prompt"] = true;
     const Json::Value &messages = (*jsonBody)["messages"];
     for (const auto &message : messages) {
       std::string input_role = message["role"].asString();