llm_server/routes/openai_request_handler.py

@@ -85,7 +85,6 @@ class OpenAIRequestHandler(RequestHandler):
             return backend_response, backend_response_status_code
 
     def handle_ratelimited(self, do_log: bool = True):
-        print('OAI ratelimited:', self.client_ip)
         model_choices, default_model = get_model_choices()
         default_model_info = model_choices[default_model]
         w = int(default_model_info['estimated_wait']) if default_model_info['estimated_wait'] > 0 else 2