diff --git a/llama_cpp/server/app.py b/llama_cpp/server/app.py
index cd3255176..5611472af 100644
--- a/llama_cpp/server/app.py
+++ b/llama_cpp/server/app.py
@@ -344,6 +344,7 @@ def iterator() -> Iterator[llama_cpp.CreateCompletionStreamResponse]:
             ping_message_factory=_ping_message_factory,
         )
     else:
+        exit_stack.close()
         return iterator_or_completion