Amazon SageMaker Adds Instance Preference Lists for Training and Processing Jobs
Amazon SageMaker now supports instance preference lists for AI training and processing jobs, allowing users to specify a prioritized list of acceptable instance types. This enhancement helps users find compute capacity more quickly, especially for high-demand GPUs during peak periods. The feature eliminates the need for complex retry logic or submitting multiple jobs concurrently to secure an available instance. It is generally available today across all AWS Regions where SageMaker operates.
Features (1) ›
- Specify Prioritized Instance Preferences for SageMaker Jobs
SageMaker users can now provide a prioritized list of desired instance types and counts when submitting training or processing jobs. This allows SageMaker to automatically launch the job on the first available configuration from the user's preferences, reducing wait times and the need for manual retries or custom logic.
https://aws.amazon.com/about-aws/whats-new/2026/09/amazon-sagemaker-training-processing-instance-pref-lists/
Related releases
- Amazon SageMaker Unified Studio Adds ODBC Support for Power BI and Analytics Tools AWS What's New ·
- AWS Glue zero-ETL Integrations Gain Table Property Ownership and Conflict Detection AWS What's New ·
- SageMaker JumpStart adds NVIDIA Qwen3.6-35B-A3B-NVFP4 and Alibaba Wan2.1-T2V-1.3B models AWS What's New ·
- Amazon SageMaker JumpStart Adds Granite-Speech, Kanana-2, and OpenFold3 Models AWS What's New ·
- Mistral AI's Ministral-3 Models Now on Amazon SageMaker JumpStart AWS What's New ·
- Gemma-4-31B LLMs from Google DeepMind and NVIDIA now on SageMaker JumpStart AWS What's New ·