Minor fixes

notebooks/onnx-graphsurgeon-inference-tensorrt.ipynb

@@ -21,6 +21,16 @@
     "python3 -m pip install onnx_graphsurgeon --index-url https://pypi.ngc.nvidia.com\n",
     "```\n",
     "\n",
+    "For us to begin with, TensorRT should be installed. You can check the install guide of TensorRT <https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html>. TensorRT provides Python wheels on Ubuntu 18.04+ or CentOS 7+ with Python versions 3.6 to 3.9 and CUDA 11.x:\n",
+    "\n",
+    "```\n",
+    "pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com\n",
+    "```\n",
+    "\n",
+    "Check out the details at <https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-pip>.\n",
+    "\n",
+    "And if you want to use the C++ interface of TensorRT, you can also use the docker published by Meta (Facebook) containing the TensorRT and PyTorch at Nvidia ngc: <https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch>.\n",
+    "\n",
     "The detailed results:\n",
     "\n",
     "```\n",
@@ -56,20 +66,6 @@
     "```"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "846df5a3",
-   "metadata": {},
-   "source": [
-    "For us to begin with, TensorRT should be installed. You can check the install guide of TensorRT <https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html>. TensorRT provides Python wheels on Ubuntu 18.04+ or CentOS 7+ with Python versions 3.6 to 3.9 and CUDA 11.x:\n",
-    "```\n",
-    "pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com\n",
-    "```\n",
-    "Check out the details at <https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-pip>.\n",
-    "\n",
-    "And if you want to use the C++ interface of TensorRT, you can also use the docker published by Meta (Facebook) containing the TensorRT and PyTorch at Nvidia ngc: <https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch>."
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 1,