AWS Lambda adds GPU support for Event Functions on Managed Instances
Tech

AWS Lambda adds GPU support for Event Functions on Managed Instances

TechNews Editorial
TechNews EditorialNov 19, 2026 · 1 min read
Share

Why it matters

AWS says developers can run event-triggered inference and media workloads on GPUs without managing GPU instances or drivers.

The facts

  • AWS Lambda Event Functions can now run on EC2 G-series GPUs through Lambda Managed Instances.
  • AWS says Lambda handles provisioning and scaling for GPU functions deployed as container images.
  • GPU functions support AWS event sources and up to 90-minute timeouts for certain invocations.

Advertisement

Amazon Web Services says Lambda Event Functions can now run on EC2 G-series GPU instances through Lambda Managed Instances. Developers can deploy a container image for work such as model inference, video processing or rendering. AWS says Lambda handles GPU provisioning and scaling.

The new support is aimed at inference rather than model training, according to AWS. It can run custom models, including smaller language models, as well as GPU tasks outside machine learning. Functions can be triggered by AWS event sources such as Amazon S3, Amazon SQS and Amazon EventBridge.

Developers choose GPU instance types and memory

Developers choose the GPU instance types a capacity provider can use and set the minimum accelerator memory a function needs. AWS says Lambda places the function on an available GPU that meets that requirement. Multiple requests can share an execution environment and one copy of a model in GPU memory.

AWS provides container base images with tools including CUDA, PyTorch and vLLM. Developers can also supply their own image. In an example using a small instruction-tuned model from Hugging Face, AWS says four concurrent requests completed in about the same time as one request in a single execution environment.

A developer brings two stopwatches together and points to their nearly matching elapsed-time readings.
Illustration: AI & Tech News

GPU functions support 90-minute timeouts

GPU functions support up to 90-minute timeouts for asynchronous and event source mapping invocations. AWS lists limits of 32 GB per container image, 32 GB of temporary storage and up to 48 concurrent requests per execution environment.

GPU support for Event Functions on Lambda Managed Instances is available now. AWS advises users to check their G-series instance quota before setting up a capacity provider, because new accounts may have a quota of zero.

What this means

Developers configuring GPU execution environments on new AWS accounts must inspect their G-series instance limits before building capacity providers, as initial account quotas can equal zero. For workloads focused on inference, developers can define minimum accelerator memory while allowing up to 48 concurrent requests to share a single model instance in GPU memory. AWS imposes constraints of 32 GB per container image and 32 GB of temporary storage, while providing base images pre-packaged with tools such as CUDA, PyTorch, and vLLM.

Source: Amazon Web Services

Newsletter

Get the best AI & tech news daily

A concise daily digest. Unsubscribe anytime.

We use your email only to send this newsletter.

Keep reading