llm_server/routes/openai/completions.py

@@ -84,9 +84,10 @@ def openai_completions(model_name=None):
                 }
             })
 
-            stats = redis.get('proxy_stats', dtype=dict)
-            if stats:
-                response.headers['x-ratelimit-reset-requests'] = stats['queue']['estimated_wait_sec']
+            # TODO:
+            # stats = redis.get('proxy_stats', dtype=dict)
+            # if stats:
+            #     response.headers['x-ratelimit-reset-requests'] = stats['queue']['estimated_wait_sec']
             return response, 200
         else:
             if not opts.enable_streaming: