lru cache

app.py

@@ -3,6 +3,7 @@ import tempfile
 from pathlib import Path
 from typing import Tuple, Optional
 
+from functools import lru_cache
 import gradio as gr
 import numpy as np
 import torch
@@ -24,7 +25,7 @@ DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 # -----------------------------
 # Secure download + load
 # -----------------------------
-@gr.cache_resource
+@lru_cache
 def load_model():
     """
     Loads model weights from a PRIVATE HF repo using HF_TOKEN (Space Secret).