Update run_inference_vllm.ipynb (#33032)

Enable verbose logging for Dataflow launch.

examples/notebooks/beam-ml/run_inference_vllm.ipynb

@@ -484,6 +484,7 @@
         "  def process(self, element, *args, **kwargs):\n",
         "    yield \"Input: {input}, Output: {output}\".format(input=element.example, output=element.inference)\n",
         "\n",
+        "logging.getLogger().setLevel(logging.INFO)  # Output additional Dataflow Job metadata and launch logs. \n",
         "prompts = [\n",
         "    \"Hello, my name is\",\n",
         "    \"The president of the United States is\",\n",