diff --git a/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb b/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb
index 1016aef1fe..fdf04cf03b 100644
--- a/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb
+++ b/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb
@@ -416,7 +416,6 @@
     "latency = []\n",
     "for i in range(total_samples):\n",
     "    data = dataset[i]\n",
-    "    # TODO: use IO Binding (see https://www.onnxruntime.ai/python/api_summary.html) to improve performance.\n",
     "    ort_inputs = {\n",
     "        'input_ids':  data[0].cpu().reshape(1, max_seq_length).numpy(),\n",
     "        'input_mask': data[1].cpu().reshape(1, max_seq_length).numpy(),\n",