Update app.py

app.py

@@ -27,7 +27,7 @@ print("Loading model into memory via llama-cpp-python...")
 llm = Llama(
     model_path=model_path,
     n_ctx=8192,       
-    n_threads=2,      
+    n_threads=8,      
     verbose=False     
 )
 print("Model loaded successfully!")