No public description

MG_DOCKER_CODES_PIPER_ORIGIN_REV_ID: 875506020
bug: remove A100 as recommended specs (#4450 )
2026-09-26 14:42:04 +00:00 · 2026-02-25 21:44:41 -08:00 · 2026-02-25 14:05:36 +00:00 · 2026-02-25 13:46:19 +00:00 · 2026-02-23 20:57:43 -05:00 · 2026-02-23 19:45:59 +00:00
145 changed files with 4727 additions and 262 deletions
@@ -2,7 +2,7 @@ git+https://github.com/tensorflow/docs
 ipython
 jupyter
 nbconvert
-black==25.12.0
+black==26.1.0
 pyupgrade==3.21.2
 isort==7.0.0
 flake8==7.3.0
@@ -2,7 +2,7 @@ dllogger@git+https://github.com/NVIDIA/dllogger@v1.0.0

 # Fixing these libraries versions to avoid conflicting or broken packages.
 immutabledict==4.2.1
-protobuf==4.25.8
+protobuf==5.29.6
 opencv-python-headless==4.11.0.86
 docutils==0.16
 urllib3==2.6.3
@@ -31,8 +31,8 @@ packaging==25.0
 pathspec==0.12.1
 platformdirs==4.3.8
 proto-plus==1.26.1
-protobuf==5.29.4
-pyasn1==0.6.1
+protobuf==5.29.6
+pyasn1==0.6.2
 pyasn1_modules==0.4.2
 pydantic==2.11.4
 pydantic_core==2.33.2
@@ -27,6 +27,7 @@
 /vertex_endpoints/nvidia-triton/nvidia-triton-custom-container-prediction.ipynb @RajeshThallam
 /vertex_endpoints/optimized_tensorflow_runtime @vlasenkoalexey
 /notebooks/community/alphagenome/cloudai_alphagenome_vai_quickstart.ipynb @dpanigra
+/notebooks/community/alphagenome/cloudai_alphagenome_finetune.ipynb @dpanigra
 /notebooks/community/weathernext/weathernext_2_early_access_program.ipynb @dpanigra
 /notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb @mansari
 /notebooks/community/neo4j/graph_paysim.ipynb @benofben @laeg
@@ -1,7 +1,8 @@
 ![AlphaGenome header image](https://raw.githubusercontent.com/google-deepmind/alphagenome/refs/heads/main/docs/source/_static/header.png)

 # AlphaGenome
-[**Overview**](#overview) | [**Use Cases**](#use-cases) | [**Documentation**](#documentation) | [**Pricing**](#pricing) | [**Quick start**](#quick-start)
+[**Overview**](#overview) | [**Use Cases**](#use-cases) | [**Documentation**](#documentation) | [**Pricing**](#pricing) | [**Quick start inference**](#quick-start-inference) | 
+[**Quick start finetune**](#quick-start-finetune)

 ## Overview
 **Disclaimer:** *Experimental*.
@@ -89,5 +90,8 @@ To utilize these models via this service:
 *   **Pricing information** will be shared directly with users upon approval
    and placement on the allowlist.

-## Quick start
+## Quick start inference
 The quickest way to get started with the AlphaGenome in Google Cloud Platform is to run [our example notebook](cloudai_alphagenome_vai_quickstart.ipynb) in [Google Colab](https://colab.research.google.com/).
+
+## Quick start finetune
+The quickest way to get started with the AlphaGenome fineutning in Google Cloud Platform is to run [our finetuning notebook](cloudai_alphagenome_finetune.ipynb) in [Google Cloud Platform Enterprise Colab](https://docs.cloud.google.com/colab/docs/introduction).
@@ -37,7 +37,7 @@
        "    </a>\n",
        "  </td>\n",
        "  <td style=\"text-align: center\">\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/colab/import/https:%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fcommunity%2alphagenome%2Fcloudai_alphagenome_vai_quickstart.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/colab/import/https:%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fcommunity%2Falphagenome%2Fcloudai_alphagenome_vai_quickstart.ipynb\">\n",
        "      <img width=\"32px\" src=\"https://lh3.googleusercontent.com/JmcxdQi-qOpctIvWKgPtrzZdJJK-J3sWE1RsfjZNwshCFgE_9fULcNpuXYTilIR2hjwN\" alt=\"Google Cloud Colab Enterprise logo\"><br> Open in Colab Enterprise\n",
        "    </a>\n",
        "  </td>\n",
@@ -135,7 +135,7 @@
        "# Keep Service account and token empty when using the key\n",
        "service_account = \"\"  # @param {type:\"string\"}\n",
        "token = \"\"  # @param {type:\"string\"}\n",
-        "code_whl = \"alphagenome-0.4.2.3-py3-none-any.whl\"\n",
+        "code_whl = \"alphagenome-0.4.2.6-py3-none-any.whl\"\n",
        "file_path = f\"gs://alphagenome-whl/{code_whl}\"\n",
        "\n",
        "service_account = service_account or None\n",
@@ -214,7 +214,7 @@
        "from IPython.display import clear_output\n",
        "\n",
        "! pip install $code_whl\n",
-        "# clear_output()"
+        "clear_output()"
      ]
    },
    {
@@ -299,7 +299,6 @@
        "print(\"Creating HttpDnaClient...\")\n",
        "dna_model = dna_client_http.create_http_client(\n",
        "    vertex_ai_url=vertex_ai_url,\n",
-        "    model_version=\"FOLD_0\",\n",
        "    service_account=service_account,\n",
        "    token=token,\n",
        ")\n",
@@ -4459,17 +4458,7 @@
      "outputs": [],
      "source": [
        "def extract_k562(adata):\n",
-        "    if \"ontologyTerm\" in adata.var.columns and not adata.var[\"ontologyTerm\"].empty:\n",
-        "        mask = adata.var[\"ontologyTerm\"].apply(\n",
-        "            lambda x: isinstance(x, dict)\n",
-        "            and x.get(\"ontologyType\") == \"ONTOLOGY_TYPE_EFO\"\n",
-        "            and x.get(\"id\") == \"2067\"\n",
-        "        )\n",
-        "        values = adata.X[:, mask]\n",
-        "    else:\n",
-        "        raise ValueError(\n",
-        "            \"Expected 'ontologyTerm' column with dictionary values not found in adata.var\"\n",
-        "        )\n",
+        "    values = adata.X[:, adata.var[\"ontology_curie\"] == \"EFO:0002067\"]\n",
        "    assert values.size == 1\n",
        "    return values.flatten()[0]\n",
        "\n",
@@ -4648,9 +4637,7 @@
        }
      ],
      "source": [
-        "interval = Interval(\n",
-        "    chromosome=\"chr19\", start=2**20, end=2**20 + 2**20, strand=\".\"\n",
-        ")\n",
+        "interval = Interval(chromosome=\"chr19\", start=2**20, end=2**20 + 2**20, strand=\".\")\n",
        "\n",
        "scores = dna_model.score_interval(\n",
        "    interval,\n",
@@ -8,6 +8,7 @@ import json
 import multiprocessing
 import os
 import subprocess
+import sys
 from typing import Any, Union
 from absl import logging
 import accelerate
@@ -387,6 +388,57 @@ def load_tokenizer(
  return tokenizer


+def _get_indices_for_valid_length(
+    dataset: Any,
+    input_column: str,
+    max_sequence_length: int,
+    tokenizer: transformers.PreTrainedTokenizer,
+    context_name: str = "the dataset",
+) -> tuple[list[int], int, int]:
+  """Gets indices of examples shorter than or equal to max_seq_length.
+
+  Args:
+    dataset: The dataset to check.
+    input_column: The input column in the dataset.
+    max_sequence_length: The maximum sequence length.
+    tokenizer: The tokenizer.
+    context_name: A name for the dataset used in log messages.
+
+  Returns:
+    A tuple of (indices_to_keep, original_length, dropped_samples).
+  """
+  if not dataset:
+    return [], 0, 0
+
+  original_length = len(dataset)
+  indices_to_keep = [
+      i
+      for i, entry in enumerate(dataset)
+      if len(tokenizer(entry[input_column])["input_ids"]) <= max_sequence_length
+  ]
+  dropped_samples = original_length - len(indices_to_keep)
+
+  if dropped_samples > 0:
+    examples_removed_percent = (dropped_samples * 100) / original_length
+    logging.info(
+        "(%.2f%%) of examples token length is <= max-seq-length(%d); (%.2f%%) >"
+        " max-seq-length in %s. %d example(s) were longer than max-seq-length.",
+        100 - examples_removed_percent,
+        max_sequence_length,
+        examples_removed_percent,
+        context_name,
+        dropped_samples,
+    )
+  else:
+    logging.info(
+        "No samples were dropped from %s because all samples are"
+        " shorter than max_sequence_length=%d.",
+        context_name,
+        max_sequence_length,
+    )
+  return indices_to_keep, original_length, dropped_samples
+
+
 def get_filtered_dataset(
    dataset: Any,
    input_column: str,
@@ -411,33 +463,25 @@ def get_filtered_dataset(
    ValueError: If more than `example_removed_threshold` of the dataset is
      filtered out.
  """
-  actual_dataset_length = len(dataset)
-  filtered_dataset = dataset.filter(
-      lambda x: len(tokenizer(x[input_column])["input_ids"]) <= max_seq_length
-  )
-  filtered_dataset_length = len(filtered_dataset)
-  if actual_dataset_length != filtered_dataset_length:
-    examples_removed_percent = (
-        (actual_dataset_length - filtered_dataset_length)
-        * 100
-        / actual_dataset_length
-    )
-    logging.info(
-        "(%.2f%%) of examples token length is <= max-seq-length(%d); (%.2f%%) >"
-        " max-seq-length. Filtering out %d example(s) which are longer than"
-        " max-seq-length.",
-        100 - examples_removed_percent,
-        max_seq_length,
-        examples_removed_percent,
-        actual_dataset_length - filtered_dataset_length,
-    )
-    if examples_removed_percent > example_removed_threshold:
-      raise ValueError(
-          "More than %.2f%% of the dataset is filtered out. This may be due to"
-          " small value of max-seq-length(%d) or incorrect template. Please"
-          " increase the max-seq-length or check the template."
-          % (examples_removed_percent, max_seq_length)
+  indices_to_keep, original_length, dropped_samples = (
+      _get_indices_for_valid_length(
+          dataset, input_column, max_seq_length, tokenizer, "the dataset"
      )
+  )
+
+  if (
+      original_length > 0
+      and dropped_samples / original_length * 100 > example_removed_threshold
+  ):
+    examples_removed_percent = (dropped_samples * 100) / original_length
+    raise ValueError(
+        f"More than {examples_removed_percent:.2f}% of the dataset is filtered"
+        " out. This may be due to small value of"
+        f" max-seq-length({max_seq_length}) or incorrect template. Please"
+        " increase the max-seq-length or check the template."
+    )
+
+  filtered_dataset = dataset.select(indices_to_keep)
  print(f"Some formatted examples from the dataset are: {filtered_dataset[:5]}")
  return filtered_dataset

@@ -502,6 +546,62 @@ def load_dataset_with_template(
  return raw, templated


+def drop_long_sequences(
+    dataset: Any,
+    dataset_with_template: Any,
+    input_column: str,
+    max_sequence_length: int,
+    tokenizer: transformers.PreTrainedTokenizer,
+    dataset_dropped_threshold: float,
+    is_train: bool,
+) -> tuple[Any, Any, int]:
+  """Returns the dataset by removing examples that are longer than max_seq_length.
+
+  Args:
+    dataset: The dataset to filter.
+    dataset_with_template: The dataset with template to filter.
+    input_column: The input column in the dataset to be used.
+    max_sequence_length: The maximum sequence length.
+    tokenizer: The tokenizer.
+    dataset_dropped_threshold: The threshold for the number of samples dropped
+      from the dataset.
+    is_train: Whether the dataset is for training.
+
+  Returns:
+    A tuple of (filtered_dataset, filtered_dataset_with_template,
+    dropped_samples).
+  """
+  context_name = f"the {'train' if is_train else 'eval'} dataset"
+  indices_to_keep, original_length, dropped_samples = (
+      _get_indices_for_valid_length(
+          dataset_with_template,
+          input_column,
+          max_sequence_length,
+          tokenizer,
+          context_name,
+      )
+  )
+
+  if (
+      original_length > 0
+      and dropped_samples / original_length * 100 > dataset_dropped_threshold
+  ):
+    logging.error(
+        "More than %f%% of the samples were dropped from {%s} after"
+        " filtering for max_sequence_length=%d. Please check your dataset.",
+        dataset_dropped_threshold,
+        context_name,
+        max_sequence_length,
+    )
+    
+    # handling library when available.
+    sys.exit(1)
+
+  filtered_dataset = dataset.select(indices_to_keep)
+  filtered_dataset_with_template = dataset_with_template.select(indices_to_keep)
+  return filtered_dataset, filtered_dataset_with_template, dropped_samples
+
+
 def validate_dataset_with_template(
    dataset_name: str,
    split: str,
@@ -8,6 +8,7 @@ import json
 import multiprocessing
 import os
 import subprocess
+import sys
 from typing import Any, Union
 from absl import logging
 import accelerate
@@ -387,6 +388,57 @@ def load_tokenizer(
  return tokenizer


+def _get_indices_for_valid_length(
+    dataset: Any,
+    input_column: str,
+    max_sequence_length: int,
+    tokenizer: transformers.PreTrainedTokenizer,
+    context_name: str = "the dataset",
+) -> tuple[list[int], int, int]:
+  """Gets indices of examples shorter than or equal to max_seq_length.
+
+  Args:
+    dataset: The dataset to check.
+    input_column: The input column in the dataset.
+    max_sequence_length: The maximum sequence length.
+    tokenizer: The tokenizer.
+    context_name: A name for the dataset used in log messages.
+
+  Returns:
+    A tuple of (indices_to_keep, original_length, dropped_samples).
+  """
+  if not dataset:
+    return [], 0, 0
+
+  original_length = len(dataset)
+  indices_to_keep = [
+      i
+      for i, entry in enumerate(dataset)
+      if len(tokenizer(entry[input_column])["input_ids"]) <= max_sequence_length
+  ]
+  dropped_samples = original_length - len(indices_to_keep)
+
+  if dropped_samples > 0:
+    examples_removed_percent = (dropped_samples * 100) / original_length
+    logging.info(
+        "(%.2f%%) of examples token length is <= max-seq-length(%d); (%.2f%%) >"
+        " max-seq-length in %s. %d example(s) were longer than max-seq-length.",
+        100 - examples_removed_percent,
+        max_sequence_length,
+        examples_removed_percent,
+        context_name,
+        dropped_samples,
+    )
+  else:
+    logging.info(
+        "No samples were dropped from %s because all samples are"
+        " shorter than max_sequence_length=%d.",
+        context_name,
+        max_sequence_length,
+    )
+  return indices_to_keep, original_length, dropped_samples
+
+
 def get_filtered_dataset(
    dataset: Any,
    input_column: str,
@@ -411,33 +463,25 @@ def get_filtered_dataset(
    ValueError: If more than `example_removed_threshold` of the dataset is
      filtered out.
  """
-  actual_dataset_length = len(dataset)
-  filtered_dataset = dataset.filter(
-      lambda x: len(tokenizer(x[input_column])["input_ids"]) <= max_seq_length
-  )
-  filtered_dataset_length = len(filtered_dataset)
-  if actual_dataset_length != filtered_dataset_length:
-    examples_removed_percent = (
-        (actual_dataset_length - filtered_dataset_length)
-        * 100
-        / actual_dataset_length
-    )
-    logging.info(
-        "(%.2f%%) of examples token length is <= max-seq-length(%d); (%.2f%%) >"
-        " max-seq-length. Filtering out %d example(s) which are longer than"
-        " max-seq-length.",
-        100 - examples_removed_percent,
-        max_seq_length,
-        examples_removed_percent,
-        actual_dataset_length - filtered_dataset_length,
-    )
-    if examples_removed_percent > example_removed_threshold:
-      raise ValueError(
-          "More than %.2f%% of the dataset is filtered out. This may be due to"
-          " small value of max-seq-length(%d) or incorrect template. Please"
-          " increase the max-seq-length or check the template."
-          % (examples_removed_percent, max_seq_length)
+  indices_to_keep, original_length, dropped_samples = (
+      _get_indices_for_valid_length(
+          dataset, input_column, max_seq_length, tokenizer, "the dataset"
      )
+  )
+
+  if (
+      original_length > 0
+      and dropped_samples / original_length * 100 > example_removed_threshold
+  ):
+    examples_removed_percent = (dropped_samples * 100) / original_length
+    raise ValueError(
+        f"More than {examples_removed_percent:.2f}% of the dataset is filtered"
+        " out. This may be due to small value of"
+        f" max-seq-length({max_seq_length}) or incorrect template. Please"
+        " increase the max-seq-length or check the template."
+    )
+
+  filtered_dataset = dataset.select(indices_to_keep)
  print(f"Some formatted examples from the dataset are: {filtered_dataset[:5]}")
  return filtered_dataset

@@ -502,6 +546,62 @@ def load_dataset_with_template(
  return raw, templated


+def drop_long_sequences(
+    dataset: Any,
+    dataset_with_template: Any,
+    input_column: str,
+    max_sequence_length: int,
+    tokenizer: transformers.PreTrainedTokenizer,
+    dataset_dropped_threshold: float,
+    is_train: bool,
+) -> tuple[Any, Any, int]:
+  """Returns the dataset by removing examples that are longer than max_seq_length.
+
+  Args:
+    dataset: The dataset to filter.
+    dataset_with_template: The dataset with template to filter.
+    input_column: The input column in the dataset to be used.
+    max_sequence_length: The maximum sequence length.
+    tokenizer: The tokenizer.
+    dataset_dropped_threshold: The threshold for the number of samples dropped
+      from the dataset.
+    is_train: Whether the dataset is for training.
+
+  Returns:
+    A tuple of (filtered_dataset, filtered_dataset_with_template,
+    dropped_samples).
+  """
+  context_name = f"the {'train' if is_train else 'eval'} dataset"
+  indices_to_keep, original_length, dropped_samples = (
+      _get_indices_for_valid_length(
+          dataset_with_template,
+          input_column,
+          max_sequence_length,
+          tokenizer,
+          context_name,
+      )
+  )
+
+  if (
+      original_length > 0
+      and dropped_samples / original_length * 100 > dataset_dropped_threshold
+  ):
+    logging.error(
+        "More than %f%% of the samples were dropped from {%s} after"
+        " filtering for max_sequence_length=%d. Please check your dataset.",
+        dataset_dropped_threshold,
+        context_name,
+        max_sequence_length,
+    )
+    
+    # handling library when available.
+    sys.exit(1)
+
+  filtered_dataset = dataset.select(indices_to_keep)
+  filtered_dataset_with_template = dataset_with_template.select(indices_to_keep)
+  return filtered_dataset, filtered_dataset_with_template, dropped_samples
+
+
 def validate_dataset_with_template(
    dataset_name: str,
    split: str,
@@ -10,7 +10,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -10,7 +10,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -6,11 +6,11 @@
      "id": "DZ1j6RRg-Td6",
      "metadata": {
        "cellView": "form",
-        "id": "f705f4be70e9"
+        "id": "483138c1a042"
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -382,9 +382,9 @@
        "endpoints[\"sdk_custom\"] = model.deploy(\n",
        "    accept_eula=True,\n",
        "    use_dedicated_endpoint=use_dedicated_endpoint,\n",
-        "    serving_container_image_uri=\"us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20250430_0916_RC00_maas\",\n",
-        "    machine_type=\"a2-ultragpu-1g\",\n",
-        "    accelerator_type=\"NVIDIA_A100_80GB\",\n",
+        "    serving_container_image_uri=\"us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20251205_0916_RC01\",\n",
+        "    machine_type=\"g4-standard-48\",\n",
+        "    accelerator_type=\"NVIDIA_RTX_PRO_6000\",\n",
        "    accelerator_count=1,\n",
        ")"
      ]
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -10,7 +10,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -10,7 +10,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -6273,6 +6273,7 @@
        "        f\"--model-replicas={model_replicas}\",\n",
        "        \"--data-parallel-size=1\",\n",
        "        \"--swap-space=16\",\n",
+        "        f\"--total-gpus={accelerator_count}\",\n",
        "    ]\n",
        "\n",
        "    if multihost_gpu_node_count > 1:\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -450,8 +450,7 @@
  "metadata": {
    "colab": {
      "name": "model_garden_pytorch_flux_comfyui_workbench.ipynb",
-      "toc_visible": true,
-      "provenance": []
+      "toc_visible": true
    },
    "kernelspec": {
      "display_name": "Python 3",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -237,7 +237,7 @@
      },
      "outputs": [],
      "source": [
-        "model_version = \"minimax-m2\"  # @param [\"minimax-m2\"] {isTemplate:true}\n",
+        "model_version = \"minimax-m2\"  # @param [\"minimax-m2\", \"minimax-m2.1\"] {isTemplate:true}\n",
        "MODEL_NAME = f\"minimaxai/minimax-m2@{model_version}\""
      ]
    },
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
@@ -9,7 +9,7 @@
      },
      "outputs": [],
      "source": [
-        "# Copyright 2025 Google LLC\n",
+        "# Copyright 2026 Google LLC\n",
        "#\n",
        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
        "# you may not use this file except in compliance with the License.\n",
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Rayan DasoriyaandCopybara-Service	cb4916f590	No public description MG_DOCKER_CODES_PIPER_ORIGIN_REV_ID: 875506020	2026-02-25 21:44:41 -08:00
Damodar PanigrahiandGitHub	2933fe606b	bug: remove A100 as recommended specs (#4450 )	2026-02-25 14:05:36 +00:00
Damodar PanigrahiandGitHub	b468809df7	bug: ahref update (#4449 ) * bug: ahref update * fix: linter * fix: typo fix	2026-02-25 13:46:19 +00:00
Sam-DecigaandGitHub	0417d8b9c4	feat: Deprecate Claude 3 Haiku (#4448 ) Deprecation start date: Feb. 23, 2026 End of Support date: Aug. 23, 2026 b/485993204	2026-02-23 20:57:43 -05:00
Damodar PanigrahiandGitHub	7750e83fbb	fix: inference key change, finetuning jaxlib update (#4447 )	2026-02-23 19:45:59 +00:00
Damodar PanigrahiandGitHub	649800e646	feat: Alphagenome finetuning notebook (#4445 ) * feat: Alphagenome finetuning notebook * Update cloudai_alphagenome_finetune.ipynb Fixed the lint errors * Update cloudai_alphagenome_finetune.ipynb Fix lint errors * feat: Add Alphagenome finetune * feat: Include the Alphagenome finetuning notebook url in the readme. Update the codeowners * feat: Add alphagegenome finetune notebook to the readme, add user to codeowners * feat: fix spelling	2026-02-20 14:13:36 +00:00
Mend RenovateandGitHub	42b35056fa	chore(deps): update dependency black to v26 (#4422 )	2026-02-18 15:07:12 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	24974eda95	Bump protobuf (#4437 ) Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 4.25.8 to 5.29.6. - [Release notes](https://github.com/protocolbuffers/protobuf/releases) - [Commits](https://github.com/protocolbuffers/protobuf/commits) --- updated-dependencies: - dependency-name: protobuf dependency-version: 5.29.6 dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2026-02-18 15:06:37 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	ad41377783	Bump protobuf (#4438 ) Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 4.25.8 to 5.29.6. - [Release notes](https://github.com/protocolbuffers/protobuf/releases) - [Commits](https://github.com/protocolbuffers/protobuf/commits) --- updated-dependencies: - dependency-name: protobuf dependency-version: 5.29.6 dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2026-02-18 15:06:10 +00:00
Sam-DecigaandGitHub	36dea3ca01	feat: Anthropic Sonnet-4-6 launch (#4442 ) Signed-off-by: Sam-Deciga <decigagarcia@google.com>	2026-02-17 14:02:30 -05:00
hyper-param GitHub hyper-param	b75b2ea4d7	fix: updated with latest whl file version : alphagenome-0.4.2.6-py3-none-any.whl (#4439 ) Co-authored-by: hyper-param <peeyusht@google.com>	2026-02-10 18:27:03 +00:00
Vertex MG TeamandCopybara-Service	28f7fc4445	Add SAM 3 notebook to Vertex AI Model Garden. PiperOrigin-RevId: 866598579	2026-02-06 13:45:47 -08:00
Rayan DasoriyaandCopybara-Service	bf2c1226fd	Update the license year PiperOrigin-RevId: 866214899	2026-02-05 19:07:14 -08:00
Vertex MG TeamandCopybara-Service	2990c53292	Added notebook sample for batch inference using the remote sensing VMG models PiperOrigin-RevId: 866061602	2026-02-05 12:27:10 -08:00
Sam-DecigaandGitHub	531d9cfee0	feat: New Anthropic model (#4436 )	2026-02-05 14:07:05 -05:00
Vertex MG TeamandCopybara-Service	ff18ec7af5	Add --total-gpus to multi-model model-cohost deployment config. PiperOrigin-RevId: 863070590	2026-01-29 22:39:06 -08:00
Sam-DecigaandGitHub	008eb409ef	feat: NVIDIA-Llama-Nemotron-Super-49B (#4430 )	2026-01-29 08:51:52 -05:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	b2dba4b568	Bump pyasn1 (#4421 ) Bumps [pyasn1](https://github.com/pyasn1/pyasn1) from 0.6.1 to 0.6.2. - [Release notes](https://github.com/pyasn1/pyasn1/releases) - [Changelog](https://github.com/pyasn1/pyasn1/blob/main/CHANGES.rst) - [Commits](https://github.com/pyasn1/pyasn1/compare/v0.6.1...v0.6.2) --- updated-dependencies: - dependency-name: pyasn1 dependency-version: 0.6.2 dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2026-01-27 20:14:34 +00:00
Sam-DecigaandGitHub	665547f790	feat:New MARS8 model (#4429 ) * feat:New MARS8 model * feat:New MARS8 model	2026-01-27 10:43:43 -05:00
Vertex MG TeamandCopybara-Service	5078c44eb8	Updated the bucket path for the remote sensing models. PiperOrigin-RevId: 861234161	2026-01-26 09:47:01 -08:00
Bhaskar GoyalandGitHub	da6e46531e	feature: Retire Mistral 24.11 and Codestral 25.01 from Mistral Intro files. (#4427 )	2026-01-23 18:47:36 +00:00
hyper-param GitHub hyper-param	0a4091a3b1	fix: Fix json response parsing error (#4426 ) Co-authored-by: hyper-param <peeyusht@google.com>	2026-01-23 13:58:03 +00:00