Technology1 min read

AWS Lambda now supports GPU instances for Event Functions on Lambda Managed Instances

By · Published by Everything Blog

In short

Designed primarily for inference on small-to-mid-size models rather than foundation model training, the offering handles tasks ranging from agentic AI to 3D rendering. It works alongside the broader platform ecosystem, supporting workflow orchestration and isolated MicroVM sandboxes for untrusted code execution. Environments offer extended timeouts reaching 90 minutes for asynchronous calls while scaling up to 15,000 vCPUs per capacity provider.

Key points

  • Environments can process up to 48 concurrent requests while scaling to 15,000 vCPUs per c…: Environments can process up to 48 concurrent requests while scaling to 15,000 vCPUs per capacity provider.
  • The platform automatically handles provisioning, driver management, and event integration…: The platform automatically handles provisioning, driver management, and event integration without requiring manual cluster maintenance.
  • The infrastructure is explicitly optimized for inference workloads rather than the heavy…: The infrastructure is explicitly optimized for inference workloads rather than the heavy training of large foundation models.

Sources checked by our analysis pipeline: 1

AWS News Blog

AWS Lambda now supports GPU instances for Event Functions on Lambda Managed Instances

|

GPU support is now available for EC2 G-series GPU instances for Event Functions running on AWS Lambda Managed Instances (LMI). You can now run GPU-accelerated workloads, including machine learning inference, media processing, rendering, and scientific computing, on GPU instances with serverless simplicity. GPU-accelerated functions are deployed as container (Open Container Initiative, OCI) images. You build an OCI image, point the function at it, and let Lambda handle provisioning, scaling, and event integration. There are no GPU drivers, CUDA versions, or AMIs to reconcile, and no clusters or device plugins to operate. GPU-accelerated functions run on the same Lambda Managed Instances foundation that already gives you Amazon EC2 pricing and specialized compute without managing servers.

Why customers need this

Customers keep asking to run GPU workloads with the simplicity of serverless. Building on self-managed GPU infrastructure means selecting instances, installing and reconciling GPU drivers and CUDA libraries, planning capacity, writing scaling logic, and hand-building the event integrations that connect the GPU step to the…

Technology