delete eval and train job if the job was triggered

PiperOrigin-RevId: 779098485

notebooks/community/model_garden/model_garden_axolotl_qwen3_finetuning.ipynb

@@ -1091,6 +1091,7 @@
         "    enable_jit_deepgemm: bool = False,\n",
         "    enable_dp_attention: bool = False,\n",
         "    dp_size: int = 1,\n",
+        "    enable_multimodal: bool = False,\n",
         "    use_dedicated_endpoint: bool = False,\n",
         "    max_num_seqs: int | None = None,\n",
         "    is_spot: bool = True,\n",
@@ -1154,6 +1155,9 @@
         "    if enable_dp_attention:\n",
         "        sglang_args.append(\"--enable-dp-attention\")\n",
         "\n",
+        "    if enable_multimodal:\n",
+        "        sglang_args.append(\"--enable-multimodal\")\n",
+        "\n",
         "    env_vars = {\n",
         "        \"MODEL_ID\": base_model_id,\n",
         "        \"DEPLOY_SOURCE\": \"notebook\",\n",

notebooks/community/model_garden/model_garden_gemma2_finetuning_on_vertex.ipynb

@@ -3,7 +3,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "language": "python",
       "metadata": {
         "cellView": "form",
         "id": "7d9bbf86da5e"
@@ -27,7 +26,6 @@
     },
     {
       "cell_type": "markdown",
-      "language": "markdown",
       "metadata": {
         "id": "99c1c3fc2ca5"
       },
@@ -117,7 +115,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "language": "python",
       "metadata": {
         "cellView": "form",
         "id": "855d6b96f291"
@@ -398,7 +395,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "language": "python",
       "metadata": {
         "cellView": "form",
         "id": "ivVGS9dHXPOz"
@@ -739,7 +735,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "language": "python",
       "metadata": {
         "cellView": "form",
         "id": "qmHW6m8xG_4U"
@@ -1047,7 +1042,12 @@
       "outputs": [],
       "source": [
         "# Delete the train job.\n",
-        "train_job.delete()\n",
+        "\n",
+        "if train_job:\n",
+        "    train_job.delete()\n",
+        "if RUN_EVALUATION and lm_eval_job:\n",
+        "    lm_eval_job.delete()\n",
+        "\n",
         "\n",
         "# @markdown  Delete the experiment models and endpoints to recycle the resources\n",
         "# @markdown  and avoid unnecessary continuous charges that may incur.\n",

notebooks/community/model_garden/model_garden_gemma3_deployment_on_vertex.ipynb

@@ -885,7 +885,7 @@
         "\n",
         "# @markdown Next fill out some request parameters:\n",
         "\n",
-        "user_image = \"https://upload.wikimedia.org/wikipedia/commons/thumb/c/cb/The_Blue_Marble_%28remastered%29.jpg/580px-The_Blue_Marble_%28remastered%29.jpg\"  # @param {type: \"string\"}\n",
+        "user_image = \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n",
         "user_message = \"What is in the image?\"  # @param {type: \"string\"}\n",
         "# @markdown If you encounter the issue like `ServiceUnavailable: 503 Took too long to respond when processing`, you can reduce the maximum number of output tokens, such as set `max_tokens` as 20.\n",
         "max_tokens = 50  # @param {type: \"integer\"}\n",

notebooks/community/model_garden/model_garden_gemma3_finetuning_on_vertex.ipynb

@@ -1002,7 +1002,12 @@
       "outputs": [],
       "source": [
         "# Delete the train job.\n",
-        "train_job.delete()\n",
+        "\n",
+        "if train_job:\n",
+        "    train_job.delete()\n",
+        "if RUN_EVALUATION and lm_eval_job:\n",
+        "    lm_eval_job.delete()\n",
+        "\n",
         "\n",
         "# @markdown  Delete the experiment models and endpoints to recycle the resources\n",
         "# @markdown  and avoid unnecessary continuous charges that may incur.\n",

notebooks/community/model_garden/model_garden_pytorch_deepseek_deployment.ipynb

@@ -897,6 +897,7 @@
         "    enable_jit_deepgemm: bool = False,\n",
         "    enable_dp_attention: bool = False,\n",
         "    dp_size: int = 1,\n",
+        "    enable_multimodal: bool = False,\n",
         "    use_dedicated_endpoint: bool = False,\n",
         "    max_num_seqs: int | None = None,\n",
         "    is_spot: bool = True,\n",
@@ -960,6 +961,9 @@
         "    if enable_dp_attention:\n",
         "        sglang_args.append(\"--enable-dp-attention\")\n",
         "\n",
+        "    if enable_multimodal:\n",
+        "        sglang_args.append(\"--enable-multimodal\")\n",
+        "\n",
         "    env_vars = {\n",
         "        \"MODEL_ID\": base_model_id,\n",
         "        \"DEPLOY_SOURCE\": \"notebook\",\n",

notebooks/community/model_garden/model_garden_pytorch_llama3_1_finetuning.ipynb

@@ -1091,7 +1091,11 @@
       "source": [
         "# @title Delete the model and endpoint\n",
         "\n",
-        "train_job.delete()\n",
+        "if train_job:\n",
+        "    train_job.delete()\n",
+        "if RUN_EVALUATION and lm_eval_job:\n",
+        "    lm_eval_job.delete()\n",
+        "\n",
         "\n",
         "# @markdown  Delete the experiment models and endpoints to recycle the resources\n",
         "# @markdown  and avoid unnecessary continuous charges that may incur.\n",

notebooks/community/model_garden/model_garden_pytorch_llama3_2_deployment.ipynb

@@ -1272,7 +1272,7 @@
         "\n",
         "# @markdown Next fill out some request parameters:\n",
         "\n",
-        "user_image = \"https://upload.wikimedia.org/wikipedia/commons/thumb/c/cb/The_Blue_Marble_%28remastered%29.jpg/580px-The_Blue_Marble_%28remastered%29.jpg\"  # @param {type: \"string\"}\n",
+        "user_image = \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n",
         "user_message = \"What is in the image?\"  # @param {type: \"string\"}\n",
         "# @markdown If you encounter the issue like `ServiceUnavailable: 503 Took too long to respond when processing`, you can reduce the maximum number of output tokens, such as set `max_tokens` as 20.\n",
         "max_tokens = 50  # @param {type: \"integer\"}\n",

notebooks/community/model_garden/model_garden_pytorch_llama3_3_finetuning.ipynb

@@ -1064,7 +1064,10 @@
       "source": [
         "# @title Delete the model and endpoint\n",
         "\n",
-        "train_job.delete()\n",
+        "if train_job:\n",
+        "    train_job.delete()\n",
+        "if RUN_EVALUATION and lm_eval_job:\n",
+        "    lm_eval_job.delete()\n",
         "\n",
         "# @markdown  Delete the experiment models and endpoints to recycle the resources\n",
         "# @markdown  and avoid unnecessary continuous charges that may incur.\n",

notebooks/community/model_garden/model_garden_pytorch_llama4_deployment.ipynb

@@ -656,7 +656,7 @@
         "\n",
         "# @markdown Next fill out some request parameters:\n",
         "\n",
-        "user_image = \"https://upload.wikimedia.org/wikipedia/commons/thumb/c/cb/The_Blue_Marble_%28remastered%29.jpg/580px-The_Blue_Marble_%28remastered%29.jpg\"  # @param {type: \"string\"}\n",
+        "user_image = \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n",
         "user_message = \"What is in the image?\"  # @param {type: \"string\"}\n",
         "# @markdown If you encounter the issue like `ServiceUnavailable: 503 Took too long to respond when processing`, you can reduce the maximum number of output tokens, such as set `max_tokens` as 20.\n",
         "max_tokens = 50  # @param {type: \"integer\"}\n",

notebooks/community/model_garden/model_garden_pytorch_qwen2_5_finetuning.ipynb

@@ -1010,7 +1010,11 @@
       "source": [
         "# @title Delete the model and endpoint\n",
         "\n",
-        "train_job.delete()\n",
+        "if train_job:\n",
+        "    train_job.delete()\n",
+        "if RUN_EVALUATION and lm_eval_job:\n",
+        "    lm_eval_job.delete()\n",
+        "\n",
         "\n",
         "# @markdown  Delete the experiment models and endpoints to recycle the resources\n",
         "# @markdown  and avoid unnecessary continuous charges that may incur.\n",

notebooks/community/model_garden/model_garden_pytorch_qwen3_deployment.ipynb

@@ -418,6 +418,7 @@
         "    enable_jit_deepgemm: bool = False,\n",
         "    enable_dp_attention: bool = False,\n",
         "    dp_size: int = 1,\n",
+        "    enable_multimodal: bool = False,\n",
         "    use_dedicated_endpoint: bool = False,\n",
         "    max_num_seqs: int | None = None,\n",
         "    is_spot: bool = True,\n",
@@ -481,6 +482,9 @@
         "    if enable_dp_attention:\n",
         "        sglang_args.append(\"--enable-dp-attention\")\n",
         "\n",
+        "    if enable_multimodal:\n",
+        "        sglang_args.append(\"--enable-multimodal\")\n",
+        "\n",
         "    env_vars = {\n",
         "        \"MODEL_ID\": base_model_id,\n",
         "        \"DEPLOY_SOURCE\": \"notebook\",\n",
@@ -557,6 +561,14 @@
         "    return model, endpoint\n",
         "\n",
         "\n",
+        "common_util.check_quota(\n",
+        "    project_id=PROJECT_ID,\n",
+        "    region=REGION,\n",
+        "    accelerator_type=accelerator_type,\n",
+        "    accelerator_count=accelerator_count,\n",
+        "    is_for_training=False,\n",
+        ")\n",
+        "\n",
         "models[LABEL], endpoints[LABEL] = deploy_model_sglang_multihost(\n",
         "    model_name=common_util.get_job_name_with_datetime(prefix=\"qwen3-serve\"),\n",
         "    model_id=model_id,\n",