Enable dedicate endpoint for pytorch llama3 deployment

PiperOrigin-RevId: 699259509

notebooks/community/model_garden/model_garden_pytorch_llama3_deployment.ipynb

@@ -84,6 +84,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "language": "python",
       "metadata": {
         "cellView": "form",
         "id": "YXFGIp1l-qtT"
@@ -131,8 +132,6 @@
         ")\n",
         "\n",
         "models, endpoints = {}, {}\n",
-        "# Dedicated endpoint not supported yet\n",
-        "use_dedicated_endpoint = False\n",
         "\n",
         "# Get the default cloud project id.\n",
         "PROJECT_ID = os.environ[\"GOOGLE_CLOUD_PROJECT\"]\n",
@@ -220,6 +219,9 @@
         "# The pre-built serving docker images.\n",
         "VLLM_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20240721_0916_RC00\"\n",
         "\n",
+        "# @markdown Set use_dedicated_endpoint to False if you don't want to use [dedicated endpoint](https://cloud.google.com/vertex-ai/docs/general/deployment#create-dedicated-endpoint).\n",
+        "use_dedicated_endpoint = True  # @param {type:\"boolean\"}\n",
+        "\n",
         "\n",
         "def deploy_model_vllm(\n",
         "    model_name: str,\n",
@@ -516,6 +518,8 @@
       },
       "outputs": [],
       "source": [
+        "if use_dedicated_endpoint:\n",
+        "    DEDICATED_ENDPOINT_DNS = endpoints[\"vllm_gpu\"].gca_resource.dedicated_endpoint_dns\n",
         "ENDPOINT_RESOURCE_NAME = \"projects/{}/locations/{}/endpoints/{}\".format(\n",
         "    PROJECT_ID, REGION, endpoints[\"vllm_gpu\"].name\n",
         ")\n",