update colab notebook

colab_inference.ipynb

@@ -85,7 +85,7 @@
       "cell_type": "code",
       "source": [
         "torch_compile = True # @param {type: \"boolean\"}\n",
-        "cpu_offload = True # @param {type: \"boolean\"}\n",
+        "cpu_offload = False # @param {type: \"boolean\"}\n",
         "overlapped_decode = True # @param {type: \"boolean\"}\n",
         "#bf16 = True # @param {type: \"boolean\"}\n",
         "\n",