Elenco dei framework supportati

Questa pagina elenca i framework supportati e i relativi pacchetti costituenti per i seguenti servizi:

Per una spiegazione approfondita delle norme di supporto dei framework, consulta Vertex AI delle norme di supporto del framework.

Framework supportati per l'addestramento personalizzato

Vertex AI utilizza le immagini container per configurare le risorse cloud che servono le tue richieste di addestramento. Le seguenti versioni sono supportate per per l'addestramento di container predefiniti:

TensorFlow

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
2.15 (Python 3.10) Solo TPU 23 ottobre 2024 23 ottobre 2025
  • us-docker.pkg.dev/vertex-ai/training/tf-tpu.2-15.cp310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-tpu.2-15.cp310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-tpu.2-15.cp310:latest
2.14 (Python 3.10) Solo CPU 26 set 2024 26 set 2025
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-14.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-14.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-14.py310:latest
2.14 (Python 3.10) GPU (CUDA 11.x) 26 set 2024 26 set 2025
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-14.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-14.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-14.py310:latest
2.13 (Python 3.10) Solo CPU 5 lug 2024 5 lug 2025
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-13.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-13.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-13.py310:latest
2.13 (Python 3.10) GPU (CUDA 11.x) 5 luglio 2024 5 lug 2025
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-13.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-13.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-13.py310:latest
2.12 (Python 3.10) Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-12.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-12.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-12.py310:latest
2.12 (Python 3.10) GPU (CUDA 11.x) 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-12.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-12.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-12.py310:latest
2.12 (Python 3.8) Solo TPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/training/tf-tpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-tpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-tpu.2-12:latest
2.11 (Python 3.10) Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-11.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-11.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-11.py310:latest
2.11 (Python 3.10) GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-11.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-11.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-11.py310:latest
2.11 (Python 3.7) Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-11:latest
2.11 (Python 3.7) GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-11:latest
2.9 (Python 3.10) Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-9.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-9.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-9.py310:latest
2.9 (Python 3.10) GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-9.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-9.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-9.py310:latest
2.9 (Python 3.7) Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-9:latest
2.9 (Python 3.7) GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-9:latest
2.8 (Python 3.10) Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-8.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-8.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-8.py310:latest
2.8 (Python 3.10) GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-8.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-8.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-8.py310:latest
2.8 (Python 3.7) Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-8:latest
2.8 (Python 3.7) GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-8:latest
2.7 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-7:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-7:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-7:latest
2.7 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-7:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-7:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-7:latest
2.6 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-6:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-6:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-6:latest
2.6 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-6:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-6:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-6:latest
2.5 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-5:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-5:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-5:latest
2.5 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-5:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-5:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-5:latest
2.4 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-4:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-4:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-4:latest
2.4 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-4:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-4:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-4:latest
2.3 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-3:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-3:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-3:latest
2.3 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-3:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-3:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-3:latest
2.2 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-2:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-2:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-2:latest
2.2 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-2:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-2:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-2:latest
2.1 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.2-1:latest
2.1 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.2-1:latest
1.15 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-cpu.1-15:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-cpu.1-15:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-cpu.1-15:latest
1.15 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/tf-gpu.1-15:latest
  • europe-docker.pkg.dev/vertex-ai/training/tf-gpu.1-15:latest
  • asia-docker.pkg.dev/vertex-ai/training/tf-gpu.1-15:latest

PyTorch

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
2.3 (Python 3.10) Solo CPU 24 aprile 2025 24 aprile 2026
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-3.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-3.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-3.py310:latest
2.3 (Python 3.10) Solo GPU (CUDA 12.x) 24 aprile 2025 24 aprile 2026
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-3.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-3.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-3.py310:latest
2.2 (Python 3.10) Solo CPU 30 gennaio 2025 23 ottobre 2026
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-2.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-2.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-2.py310:latest
2.2 (Python 3.10) Solo GPU (CUDA 12.x) 30 gennaio 2025 30 gennaio 2026
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-2.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-2.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-2.py310:latest
2.1 (Python 3.10) Solo CPU 4 ottobre 2024 4 ottobre 2025
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-1.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-1.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-1.py310:latest
2.1 (Python 3.10) Solo GPU (CUDA 12.x) 4 ottobre 2024 4 ottobre 2025
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-1.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-1.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-1.py310:latest
2.1 (Python 3.8) Solo TPU 23 ottobre 2024 23 ottobre 2025
  • us-docker.pkg.dev/vertex-ai/training/pytorch-tpu.2-1.cp310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-tpu.2-1.cp310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-tpu.2-1.cp310:latest
2.0 (Python 3.10) Solo CPU 15 mar 2024 15 marzo 2025
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-0.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-0.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.2-0.py310:latest
2.0 (Python 3.10) Solo GPU (CUDA 11.x) 15 marzo 2024 15 marzo 2025
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-0.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-0.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.2-0.py310:latest
2.0 (Python 3.8) Solo TPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/training/pytorch-tpu.2-0:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-tpu.2-0:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-tpu.2-0:latest
1.13 (Python 3.10) CPU o GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-13.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-13.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-13.py310:latest
1.13 (Python 3.7) CPU o GPU (CUDA 11.x) 8 dicembre 2023 8 dicembre 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-13:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-13:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-13:latest
1.12 (Python 3.10) CPU o GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-12.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-12.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-12.py310:latest
1.12 (Python 3.7) CPU o GPU (CUDA 11.x) 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-12:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-12:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-12:latest
1.11 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-11:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-11:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-11:latest
1.11 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-11:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-11:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-11:latest
1.10 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-10:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-10:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-10:latest
1.10 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-10:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-10:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-10:latest
1.9 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-9:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-9:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-9:latest
1.9 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-9:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-9:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-9:latest
1.7 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-7:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-7:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-7:latest
1.7 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-7:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-7:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-7:latest
1.6 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-6:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-6:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-xla.1-6:latest
1.6 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-6:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-6:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-6:latest
1.4 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-cpu.1-4:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-cpu.1-4:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-cpu.1-4:latest
1.4 (Python 3.7) GPU (CUDA 11.x) 1° settembre 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-4:latest
  • europe-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-4:latest
  • asia-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-4:latest

scikit-learn

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
1.0 (Python 3.10) Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/training/sklearn-cpu.1-0:latest
  • europe-docker.pkg.dev/vertex-ai/training/sklearn-cpu.1-0:latest
  • asia-docker.pkg.dev/vertex-ai/training/sklearn-cpu.1-0:latest
1.0 (Python 3.10) GPU (CUDA 11.x) 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/training/sklearn-gpu.1-0:latest
  • europe-docker.pkg.dev/vertex-ai/training/sklearn-gpu.1-0:latest
  • asia-docker.pkg.dev/vertex-ai/training/sklearn-gpu.1-0:latest
0.23 (Python 3.7) Solo CPU 1° set 2023 1° set 2024
  • us-docker.pkg.dev/vertex-ai/training/scikit-learn-cpu.0-23:latest
  • europe-docker.pkg.dev/vertex-ai/training/scikit-learn-cpu.0-23:latest
  • asia-docker.pkg.dev/vertex-ai/training/scikit-learn-cpu.0-23:latest

XGBoost

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
1.6 (Python 3.10) Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/training/xgboost-cpu.1-6:latest
  • europe-docker.pkg.dev/vertex-ai/training/xgboost-cpu.1-6:latest
  • asia-docker.pkg.dev/vertex-ai/training/xgboost-cpu.1-6:latest
1.6 (Python 3.10) GPU (CUDA 11.x) 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/training/xgboost-gpu.1-6:latest
  • europe-docker.pkg.dev/vertex-ai/training/xgboost-gpu.1-6:latest
  • asia-docker.pkg.dev/vertex-ai/training/xgboost-gpu.1-6:latest
1.1 (Python 3.7) Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/training/xgboost-cpu.1-1:latest
  • europe-docker.pkg.dev/vertex-ai/training/xgboost-cpu.1-1:latest
  • asia-docker.pkg.dev/vertex-ai/training/xgboost-cpu.1-1:latest

Framework supportati per previsioni e spiegazioni

Vertex AI utilizza le immagini container per configurare le risorse cloud per gestire le tue richieste di previsione. Le seguenti versioni sono supportate per container per previsioni e spiegazioni:

TensorFlow

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
2,13 Solo CPU 28 nov 2024 28 nov 2025
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-13:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-13:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-13:latest
2,13 GPU (CUDA 12.x) 28 novembre 2024 28 novembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-13:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-13:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-13:latest
2.12 Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-12:latest
2.12 GPU (CUDA 11.x) 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-12:latest
2,11 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-11:latest
2,11 GPU (CUDA 11.x) 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-11:latest
2.10 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-10:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-10:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-10:latest
2,10 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-10:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-10:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-10:latest
2,9 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-9:latest
2,9 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-9:latest
2,8 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest
2,8 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-8:latest
2.7 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-7:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-7:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-7:latest
2.7 GPU (CUDA 11.x) 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-7:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-7:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-7:latest
2,6 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-6:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-6:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-6:latest
2,6 GPU (CUDA 11.x) 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-6:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-6:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-6:latest
2,5 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-5:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-5:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-5:latest
2,5 GPU (CUDA 11.x) 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-5:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-5:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-5:latest
2,4 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-4:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-4:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-4:latest
2,4 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-4:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-4:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-4:latest
2.3 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-3:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-3:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-3:latest
2.3 GPU (CUDA 11.x) 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-3:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-3:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-3:latest
2.2 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-2:latest
2.2 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
2.1 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-1:latest
2.1 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
1,15 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf-cpu.1-15:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf-cpu.1-15:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf-cpu.1-15:latest
1,15 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf-gpu.1-15:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf-gpu.1-15:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf-gpu.1-15:latest

Runtime TensorFlow ottimizzato

Le seguenti immagini container utilizzano il runtime di TensorFlow ottimizzato. Per maggiori informazioni, consulta Utilizzare il runtime TensorFlow ottimizzato.

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
ogni notte Solo CPU Non applicabile Non applicabile
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.nightly:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.nightly:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.nightly:latest
ogni notte GPU (CUDA 12.x) Non applicabile Non applicabile
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.nightly:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.nightly:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.nightly:latest
ogni notte Cloud TPU Non applicabile Non applicabile
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.nightly:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.nightly:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.nightly:latest
2,16 Solo CPU 26 aprile 2024 26 aprile 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-16:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-16:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-16:latest
2,16 GPU (CUDA 12.x) 26 aprile 2024 26 aprile 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-16:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-16:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-16:latest
2,16 Cloud TPU 26 aprile 2024 26 aprile 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-16:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-16:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-16:latest
2,15 Solo CPU 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-15:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-15:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-15:latest
2,15 GPU (CUDA 12.x) 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-15:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-15:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-15:latest
2,15 Cloud TPU 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-15:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-15:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-15:latest
2,14 Solo CPU 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-14:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-14:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-14:latest
2,14 GPU (CUDA 12.x) 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-14:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-14:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-14:latest
2,13 Solo CPU 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-13:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-13:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-13:latest
2,13 GPU (CUDA 11.x) 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-13:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-13:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-13:latest
2.12 Solo CPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-12:latest
2.12 GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-12:latest
2,11 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-11:latest
2,11 GPU (CUDA 11.x) 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest
2.10 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-10:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-10:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-10:latest
2,10 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-10:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-10:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-10:latest
2,9 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-9:latest
2,9 GPU (CUDA 11.x) 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-9:latest
2,8 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-8:latest
2,8 GPU (CUDA 11.x) 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-8:latest

PyTorch

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
2.1 (Python 3.9) Solo CPU 1 dic 2024 1° dicembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-1:latest
2.1 (Python 3.9) GPU (CUDA 12.x) 1 dic 2024 1° dicembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-1:latest
2.1 (Python 3.9) Cloud TPU 1° dicembre 2024 1° dicembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-tpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-tpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-tpu.2-1:latest
2.0 (Python 3.9) Solo CPU 27 luglio 2024 27 luglio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-0:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-0:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-0:latest
2.0 (Python 3.9) GPU (CUDA 11.x) 27 luglio 2024 27 luglio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-0:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-0:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-0:latest
1.13 (Python 3.8) Solo CPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-13:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-13:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-13:latest
1.13 (Python 3.8) GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-13:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-13:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-13:latest
1,12 Solo CPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-12:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-12:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-12:latest
1,12 GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-12:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-12:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-12:latest
1,11 Solo CPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-11:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-11:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-11:latest
1,11 GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-11:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-11:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-11:latest

scikit-learn

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
1.3 (Python 3.10) Solo CPU 28 nov 2024 28 novembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-3:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-3:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-3:latest
1.2 (Python 3.10) Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-2:latest
1,0 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-0:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-0:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-0:latest
0,24 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-24:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-24:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-24:latest
0,23 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-23:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-23:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-23:latest
0,22 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-22:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-22:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-22:latest
0,20 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-20:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-20:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-20:latest

XGBoost

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
1.7 (Python 3.10) Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-7:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-7:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-7:latest
1.6 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-6:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-6:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-6:latest
1,5 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-5:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-5:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-5:latest
1.4 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-4:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-4:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-4:latest
1.3 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-3:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-3:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-3:latest
1.2 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-2:latest
1.1 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-1:latest
0,90 Solo CPU 15 nov 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-90:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-90:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-90:latest
0,82 Solo CPU 15 nov 2023 15 nov 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-82:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-82:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-82:latest

Versioni supportate di Ray su Vertex AI

Sono disponibili immagini container Ray on Vertex AI. Sono supportate le seguenti versioni dei container predefiniti:

Versione Ray Acceleratori supportati (e versione CUDA, se applicabile) Data di fine della patch e del supporto Fine della disponibilità Immagini supportate
2.33.0 (Python 3.10) Solo CPU 16 settembre 2025 16 settembre 2026
  • us-docker.pkg.dev/vertex-ai/training/ray-cpu.2-33.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/ray-cpu.2-33.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/ray-cpu.2-33.py310:latest
2.33.0 (Python 3.10) GPU (CUDA 11.x) 16 settembre 2025 16 settembre 2026
  • us-docker.pkg.dev/vertex-ai/training/ray-gpu.2-33.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/ray-gpu.2-33.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/ray-gpu.2-33.py310:latest
2.9.3 (Python 3.10) Solo CPU 7 maggio 2025 7 maggio 2026
  • us-docker.pkg.dev/vertex-ai/training/ray-cpu.2-9.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/ray-cpu.2-9.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/ray-cpu.2-9.py310:latest
2.9.3 (Python 3.10) GPU (CUDA 11.x) 7 maggio 2025 7 maggio 2026
  • us-docker.pkg.dev/vertex-ai/training/ray-gpu.2-9.py310:latest
  • europe-docker.pkg.dev/vertex-ai/training/ray-gpu.2-9.py310:latest
  • asia-docker.pkg.dev/vertex-ai/training/ray-gpu.2-9.py310:latest

Framework supportati per le pipeline

Vertex AI Pipelines supporta le seguenti versioni SDK del framework ML:

Poiché questi framework vengono aggiornati periodicamente per correggere bug e vulnerabilità, ti consigliamo di usa sempre la versione più recente della patch e rimani entro la fine della data del supporto. L'assistenza clienti non viene fornita se una versione è oltre la data di fine del supporto. Per ulteriori informazioni, consulta le norme di supporto del framework Vertex AI.

In generale, segui queste linee guida quando utilizzi i modelli di pipeline:

  • Rimani aggiornato con la versione patch più recente del framework ML.

  • Esegui l'upgrade dei modelli di pipeline nuovi ed esistenti all'ultima versione minore del framework ML almeno una volta ogni 12 mesi.

  • Quando viene resa disponibile una nuova versione principale di un framework ML, esegui la migrazione e modelli di pipeline esistenti alla nuova versione principale entro 24 mesi.

SDK Kubeflow Pipelines

KFP è il framework più comunemente usato per creare l'orchestrazione delle pipeline in Vertex AI Pipelines. Vertex AI Pipelines può eseguire le definizioni di pipeline compilate utilizzando KFP nella rappresentazione intermedia pipeline_spec (formato YAML IR) 2.0 o versioni successive.

Vertex AI Pipelines supporta le seguenti versioni dell'SDK KFP:

Framework Data di uscita Data di fine del supporto
SDK KFP 2 20 giugno 2023 Non applicabile
SDK KFP 1.8 3 set 2021 20 dicembre 2024

La versione più recente dell'SDK KFP interromperà il supporto delle versioni Python alla fine del ciclo di vita fine il giorno in cui vengono dichiarate. L'unica eccezione è Python 3.7, per il quale il supporto verrà interrotto il 23 aprile 2024.

SDK TensorFlow Extended (TFX)

TensorFlow rilascia una nuova versione secondaria di TensorFlow Extended (TFX) all'SDK circa ogni trimestre. Puoi comunque eseguire pipeline compilate precedenti dell'SDK, ma solo l'ultima versione secondaria riceve patch. Pertanto, ti consigliamo di mantenere aggiornata la versione minore più recente.

Framework Data di uscita Data di fine del supporto
SDK esteso TensorFlow 1.15 29 aprile 2024 29 aprile 2025
SDK TensorFlow Extended 1.14 6 settembre 2023 6 settembre 2024
SDK TensorFlow Extended 1.13 3 maggio 2023 3 maggio 2024
SDK TensorFlow Extended 1.12 19 dicembre 2022 19 dicembre 2023
SDK TensorFlow Extended 1.11 23 novembre 2022 23 novembre 2023
SDK TensorFlow Extended 1.10 4 ottobre 2022 4 ott 2023
SDK esteso 1.9 di TensorFlow 15 luglio 2022 15 luglio 2023
SDK TensorFlow Extended 1.8 25 maggio 2022 25 maggio 2023

Google Cloud Pipeline Components

Vertex AI Pipelines pubblica e applica regolarmente le patch ai seguenti pacchetti e immagini container per aiutarti nelle definizioni KFP:

Framework Data di uscita Data di fine del patch e del supporto Data di fine disponibilità Immagini supportate
Componenti della pipeline di Google Cloud 2 20 giugno 2023 Non applicabile Non applicabile gcr.io/ml-pipeline/google-cloud-pipeline-components:latest
Componenti della pipeline di Google Cloud 1 25 feb 2022 20 dicembre 2024 20 giugno 2025 gcr.io/ml-pipeline/google-cloud-pipeline-components:1.0.*

La versione più recente dell'SDK Google Cloud Pipeline Components non supporterà più le versioni di Python ritirate il giorno in cui vengono dichiarate ritirate. L'unica eccezione è Python 3.7, per il quale il supporto verrà interrotto il 23 aprile 2024.

Framework supportati per i notebook gestiti dall'utente di Vertex AI Workbench

Blocchi note gestiti dall'utente di Vertex AI Workbench supporta le versioni del framework ML riportate nelle tabelle seguenti. Per trovare un valore VERSION_DATE specifico per un'immagine, consulta Elenco delle versioni disponibili.

Versioni di base

Versione framework ML Versione patch attuale Acceleratori supportati Data di fine della patch e del supporto Data di fine della disponibilità Nome famiglia immagini
CPU di base (Python 3.10 / Debian 11) Non applicabile (N/A) Solo CPU 1 lug 2024 1 lug 2025 common-cpu-VERSION_DATE-debian-11
Base-cu122 (Python 3.10) CUDA 12.2 GPU (CUDA 12.2) 8 gennaio 2025 8 gennaio 2026 common-cu122-VERSION_DATE-debian-11-py310
Base-cu121 (Python 3.10) CUDA 12.1 GPU (CUDA 12.1) 28 febbraio 2024 28 febbraio 2025 common-cu121-VERSION_DATE-debian-11-py310
Base-cu118 (Python 3.10) CUDA 11.8 GPU (CUDA 11.8) 1° luglio 2024 1° luglio 2025 common-cu118-VERSION_DATE-debian-11-py310
Base-cu113 (Python 3.10) CUDA 11.3 GPU (CUDA 11.3) 1° gennaio 2024 1 gen 2025 common-cu113-VERSION_DATE-debian-11-py310
Base-cu113 (Python 3.7) CUDA 11.3 GPU (CUDA 11.3) 18 set 2023 18 settembre 2024 common-cu113-VERSION_DATE-py37
Base-cu110 (Python 3.7) CUDA 11.0 GPU (CUDA 11.0) 18 set 2023 18 settembre 2024 common-cu110-VERSION_DATE-py37
CPU di base (Python 3.7) Non applicabile (N/A) Solo CPU 18 settembre 2023 18 settembre 2024 common-cpu-VERSION_DATE-debian-10

Versioni TensorFlow

Versione framework ML Versione patch attuale Acceleratori supportati Data di fine della patch e del supporto Data di fine della disponibilità Nome famiglia immagini
2.17 (Python 3.10) 2.17.0 Solo CPU 11 luglio 2025 11 luglio 2026 tf-2-17-cpu-VERSION_DATE-py310
2.17 (Python 3.10) 2.17.0 GPU (CUDA 12.3) 11 lug 2025 11 luglio 2026 tf-2-17-cu123-VERSION_DATE-py310
2.16 (Python 3.10) 2.16.2 Solo CPU 28 giugno 2025 28 giugno 2026 tf-2-16-cpu-VERSION_DATE-py310
2.16 (Python 3.10) 2.16.2 GPU (CUDA 12.3) 28 giugno 2025 28 giugno 2026 tf-2-16-cu123-VERSION_DATE-py310
2.15 (Python 3.10) 2.15.0 Solo CPU 14 nov 2024 14 novembre 2025 tf-2-15-cpu-VERSION_DATE-py310
2.15 (Python 3.10) 2.15.0 GPU (CUDA 12.1) 14 nov 2024 14 novembre 2025 tf-2-15-cu121-VERSION_DATE-py310
2.14 (Python 3.10) 2.14.0 Solo CPU 26 set 2024 26 settembre 2025 tf-2-14-cpu-VERSION_DATE-py310
2.14 (Python 3.10) 2.14.0 GPU (CUDA 11.8) 26 set 2024 26 settembre 2025 tf-2-14-cu118-VERSION_DATE-py310
2.13 (Python 3.10) 2.13.0 Solo CPU 5 lug 2024 5 luglio 2025 tf-2-13-cpu-VERSION_DATE-py310
2.13 (Python 3.10) 2.13.0 GPU (CUDA 11.8) 5 luglio 2024 5 lug 2025 tf-2-13-cu118-VERSION_DATE-py310
2.12 (Python 3.10) 2.12.0 Solo CPU 30 giugno 2024 30 giugno 2025 tf-2-12-cpu-VERSION_DATE-py310
2.12 (Python 3.10) 2.12.0 GPU (CUDA 11.8) 18 gennaio 2024 18 gennaio 2025 tf-2-12-cu113-VERSION_DATE-py310
2.11 (Python 3.10) 2.11.0 Solo CPU 15 nov 2023 15 novembre 2024 tf-2-11-cpu-VERSION_DATE-py310
2.11 (Python 3.10) 2.11.0 GPU (CUDA 11.3) 15 nov 2023 15 novembre 2024 tf-2-11-cu113-VERSION_DATE-py310
2,11 2.11.0 Solo CPU 15 nov 2023 15 novembre 2024 tf-2-11-cpu-VERSION_DATE-py37
2,11 2.11.0 GPU (CUDA 11.3) 15 nov 2023 15 nov 2024 tf-2-11-cu113-VERSION_DATE-py37
2,10 2.10.1 Solo CPU 15 nov 2023 15 nov 2024 tf-2-10-cpu-VERSION_DATE-py37
2,10 2.10.1 GPU (CUDA 11.3) 15 nov 2023 15 novembre 2024 tf-2-10-cu113-VERSION_DATE-py37
2,9 2.9.3 Solo CPU 15 nov 2023 15 novembre 2024 tf-2-9-cpu-VERSION_DATE-py37
2,9 2.9.3 GPU (CUDA 11.3) 15 nov 2023 15 novembre 2024 tf-2-9-cu113-VERSION_DATE-py37
2,8 2.8.4 Solo CPU 15 nov 2023 15 novembre 2024 tf-2-8-cpu-VERSION_DATE-py37
2,8 2.8.4 GPU (CUDA 11.3) 15 nov 2023 15 novembre 2024 tf-2-8-cu113-VERSION_DATE-py37
2.6 (py39) 2.6.5 Solo CPU 1° set 2023 1° settembre 2024 tf-2-6-cpu-VERSION_DATE-py39
2.6 (py39) 2.6.5 GPU (CUDA 11.3) 1° set 2023 1° set 2024 tf-2-6-cu110-VERSION_DATE-py39
2.6 (py37) 2.6.5 Solo CPU 18 settembre 2023 18 set 2024 tf-2-6-cpu-VERSION_DATE-py37
2.6 (py37) 2.6.5 GPU (CUDA 11.3) 18 set 2023 18 set 2024 tf-2-6-cu110-VERSION_DATE-py37
2.3 2.3.4 Solo CPU 1° set 2023 1° set 2024 tf-2-3-cpu
2.3 2.3.4 GPU (CUDA 11.3) 1° set 2023 1° settembre 2024 tf-2-3-cu110-VERSION_DATE

Versioni PyTorch

Versione framework ML Versione patch attuale Acceleratori supportati Data di fine della patch e del supporto Data di fine della disponibilità Nome famiglia immagini
2.2 (Python 3.10) 2.2.0 CUDA 12.1 30 gennaio 2025 30 gennaio 2026 pytorch-2-2-VERSION_DATE-py310
2.1 (Python 3.10) 2.1.0 CUDA 12.1 4 ottobre 2024 4 ottobre 2025 pytorch-2-1-VERSION_DATE-py310
2.0 (Python 3.10) 2.0.0 CUDA 11.8 15 mar 2024 15 mar 2025 pytorch-2-0-VERSION_DATE-py310
1.13 (Python 3.10) 1.13.1 CUDA 11.3 8 dicembre 2023 8 dicembre 2024 pytorch-1-13-VERSION_DATE-py310
1,13 1.13.1 CUDA 11.3 8 dicembre 2023 8 dicembre 2024 pytorch-1-13-VERSION_DATE-py37
1,12 1.12.1 CUDA 11.3 1° set 2023 1° set 2024 pytorch-1-12-VERSION_DATE-py310

Passaggi successivi