removes cache implementation static

app.py

@@ -218,7 +218,7 @@ def generate_response(message, history, system_message, max_tokens, temperature,
             attention_mask=inputs['attention_mask'],
             pad_token_id=tokenizer.eos_token_id,
             eos_token_id=tokenizer.eos_token_id,
-            cache_implementation="static"
+            # cache_implementation="static"
         )
         response = tokenizer.decode(output_ids[0], skip_special_tokens=True)        
         assistant_response = response[len(full_prompt):].strip()