Home icon

AWS Lambda adds support for GPU instances on Lambda Managed Instances

News



AWS Lambda now supports GPU-accelerated Event Functions on Lambda Managed Instances using EC2 G-series instances for AI inference, media processing, and scientific computing.

  • Run GPU workloads without managing drivers, frameworks, or scaling infrastructure
  • Lambda scales responsively based on GPU utilization, CPU utilization, and concurrency
  • Preconfigured GPU base images include vLLM, SGLang, and PyTorch frameworks
  • Support for container images with up to 32 GB NVMe ephemeral storage
  • Seekable OCI lazy loading and S3 artifact streaming reduce startup time
  • Multi-generation G-series instance fallback ensures resilience and availability
  • Available in all AWS Commercial Regions with Lambda Managed Instances support
  • Pricing: EC2 On-Demand rate plus 9.75% Lambda management fee and $0.20 per million requests

GPU-accelerated Lambda functions integrate with 200+ AWS event sources, enabling GPU compute as a serverless application step without infrastructure management.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Nov 18
2026
AWS Lambda now supports scale to and from zero for Lambda Managed Instances
Apr 30
2026
Amazon ECS Managed Instances now supports NVIDIA GPU metrics
Nov 12
2026
Automatically recover from GPU failures with Amazon ECS Managed Instances
Oct 1
2026
Amazon WorkSpaces Core Managed Instances adds support for NVIDIA Blackwell GPU

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.