Update app.py

app.py

@@ -154,8 +154,10 @@ class BasicAgent:
 def cleanup_memory():
     """Centralized memory cleanup function"""
     if torch.cuda.is_available():
-        torch.cuda.empty_cache()
         torch.cuda.synchronize()
+        torch.cuda.empty_cache()
+        import time
+        time.sleep(0.1)
     gc.collect()
 
 
@@ -214,7 +216,6 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
-        cleanup_memory()
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or question_text is None:
@@ -224,6 +225,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             submitted_answer = agent(question_text)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            cleanup_memory()
         except Exception as e:
              print(f"Error running agent on task {task_id}: {e}")
              results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})