Enable dedicate endpoint for timesfm deployment

PiperOrigin-RevId: 700190957

Author: vertex-mg-bot

notebooks/community/model_garden/model_garden_timesfm_deployment_on_vertex.ipynb

@@ -306,6 +306,8 @@
         "print(\"Creating endpoint.\")\n",
         "\n",
         "SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/jax-timesfm-serve:20240828_1036_RC00\"\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(\n",
@@ -317,12 +319,14 @@
         "    accelerator_type: str = \"NVIDIA_L4\",\n",
         "    accelerator_count: int = 1,\n",
         "    deploy_source: str = \"notebook\",\n",
+        "    use_dedicated_endpoint: bool = False,\n",
         ") -> Tuple[aiplatform.Model, aiplatform.Endpoint]:\n",
         "    \"\"\"Creates a Vertex AI Endpoint and deploys TimesFM to the endpoint.\"\"\"\n",
         "    model_name_with_time = common_util.get_job_name_with_datetime(model_name)\n",
         "    endpoint = aiplatform.Endpoint.create(\n",
         "        display_name=f\"{model_name_with_time}-endpoint\",\n",
         "        credentials=aiplatform.initializer.global_config.credentials,\n",
+        "        dedicated_endpoint_enabled=use_dedicated_endpoint,\n",
         "    )\n",
         "\n",
         "    if accelerator_type == \"ACCELERATOR_TYPE_UNSPECIFIED\":\n",
@@ -374,6 +378,7 @@
         "    machine_type=machine_type,\n",
         "    accelerator_type=accelerator_type,\n",
         "    accelerator_count=accelerator_count,\n",
+        "    use_dedicated_endpoint=use_dedicated_endpoint,\n",
         ")"
       ]
     },
@@ -538,7 +543,10 @@
         "]\n",
         "\n",
         "# Query the endpoint.\n",
-        "results = endpoints[\"timesfm\"].predict(instances=instances)\n",
+        "results = endpoints[\"timesfm\"].predict(\n",
+        "    instances=instances,\n",
+        "    use_dedicated_endpoint=use_dedicated_endpoint,\n",
+        ")\n",
         "\n",
         "viz = Visualizer(nrows=1, ncols=3)\n",
         "viz.visualize_forecast(\n",
@@ -616,7 +624,8 @@
         "            \"timestamp_format\": \"%Y-%m-%d\",\n",
         "        }\n",
         "        for each_input, each_timestamp in zip(inputs, timestamps)\n",
-        "    ]\n",
+        "    ],\n",
+        "    use_dedicated_endpoint=use_dedicated_endpoint,\n",
         ")\n",
         "\n",
         "viz = Visualizer(nrows=1, ncols=3)\n",
@@ -788,10 +797,16 @@
         "    },\n",
         "]\n",
         "\n",
-        "response = endpoints[\"timesfm\"].predict(instances=cov_instances)\n",
+        "response = endpoints[\"timesfm\"].predict(\n",
+        "    instances=cov_instances,\n",
+        "    use_dedicated_endpoint=use_dedicated_endpoint,\n",
+        ")\n",
         "\n",
         "no_cov_instances = [{\"input\": task[\"input\"], \"horizon\": 40} for task in cov_instances]\n",
-        "no_cov_response = endpoints[\"timesfm\"].predict(instances=no_cov_instances)\n",
+        "no_cov_response = endpoints[\"timesfm\"].predict(\n",
+        "    instances=no_cov_instances,\n",
+        "    use_dedicated_endpoint=use_dedicated_endpoint,\n",
+        ")\n",
         "\n",
         "viz = Visualizer(nrows=3, ncols=2)\n",
         "for task_i, (per_input, per_gt) in enumerate(\n",