← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

AWS Lambda Adds GPU Instance Support for Event Functions on Managed Instances

🔄 Updated 3d ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • AWS Lambda now supports GPU instances for Event Functions on LMI.
  • Users can run GPU-accelerated workloads like ML inference and media processing.
  • Deployment uses OCI images; Lambda manages provisioning, scaling, and event integration.
  • Feature optimizes GPU utilization and cost for event-driven tasks.

GPU Support for Serverless Functions

AWS Lambda has introduced support for GPU instances for Event Functions operating on Lambda Managed Instances (LMI). This enables the execution of GPU-accelerated workloads, including machine learning inference, media processing, rendering, and scientific computing, within a serverless environment.

Functions leveraging GPUs are deployed as Open Container Initiative (OCI) images. Users provide an OCI image, and Lambda manages the underlying infrastructure, including provisioning, scaling, and event integration, eliminating the need for manual management of GPU drivers, CUDA versions, or EC2 AMIs.

Addressing Customer Needs

This feature responds to customer demand for running GPU workloads with serverless simplicity. Previously, managing GPU infrastructure involved selecting instances, installing drivers, planning capacity, and developing custom scaling logic and event integrations. Existing serverless GPU services often lacked native AWS event sources, identity, or networking.

The update also addresses cost concerns associated with GPU utilization. GPUs are expensive, and traditional provisioning often leads to low utilization for smaller tasks. Lambda's new capability consolidates functions onto instances and keeps GPUs active across concurrent requests, maximizing utilization and reducing idle costs.

Workload Capabilities

The GPU-accelerated compute on Lambda Managed Instances supports both AI/ML inference and non-ML workloads. It is optimized for inference tasks rather than model training, and for custom models rather than large foundation models available through services like Amazon Bedrock.

Common applications include custom model inference for decision models, computer vision, speech-to-text, text-to-speech, recommendation systems, document analysis, and small-to-mid-size language models.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~4 min · 3 stories · Nov 21

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Reporting from

AWS Lambda now supports GPU instances for Event Functions running on Lambda Managed Instances (LMI), allowing users to execute GPU-accelerated workloads like machine learning inference and media processing with serverless management. This update simplifies deployment by handling GPU drivers, CUDA versions, and scaling, while also improving GPU utilization and cost efficiency for event-driven tasks.