update

app.py

@@ -42,8 +42,7 @@ def inference(question: str, doc_path: str, use_turbo=True) -> str:
     else:
         print("turbo-mode-off")
         kv_cache = get_model_kv_cache(context_ids)
-    
-    print("kv-length", kv_cache.get_seq_length())
+
 
     answer = generate_answer(MODEL, TOKENIZER, prompt_ids, kv_cache, context_length, 128)
     print(answer)