<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/aws-lambda-adds-support-for-gpu-instances-on-lambda-managed-instances-8o7qdlzdh" -->

---
title: AWS Lambda adds support for GPU instances on Lambda...
description: AWS Lambda now supports GPU-accelerated Event Functions on Lambda Managed Instances using EC2 G-series instances. Workloads like AI inference, media...
canonical: https://daily.dev/posts/aws-lambda-adds-support-for-gpu-instances-on-lambda-managed-instances-8o7qdlzdh
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: AWS Lambda adds support for GPU instances on Lambda Managed Instances | daily.dev
og:description: AWS Lambda now supports GPU-accelerated Event Functions on Lambda Managed Instances using EC2 G-series instances. Workloads like AI inference, media...
og:url: https://daily.dev/posts/aws-lambda-adds-support-for-gpu-instances-on-lambda-managed-instances-8o7qdlzdh
og:image: https://api.daily.dev/og/posts/8O7qDlzDh.png
og:image:alt: AWS Lambda adds support for GPU instances on Lambda Managed Instances
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# AWS Lambda adds support for GPU instances on Lambda Managed Instances

**[AWS](https://daily.dev/sources/aws)** · 2 min read · 0 upvotes · 0 comments

## Summary

AWS Lambda now supports GPU-accelerated Event Functions on Lambda Managed Instances using EC2 G-series instances. Workloads like AI inference, media processing, 3D rendering, and scientific computing can run without managing GPU drivers or scaling. Lambda ships GPU base images preconfigured with vLLM, SGLang, and PyTorch, and offers up to 32 GB of NVMe ephemeral storage. Pricing is EC2 On-Demand rate plus a 9.75% Lambda management fee and $0.20 per million requests. The feature can also be configured through coding assistants like Kiro, Claude Code, or Codex via the Agent Toolkit for AWS.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://aws.amazon.com/about-aws/whats-new/2026/11/aws-lambda-gpu-managed-instances>

## Questions this post answers

### How much does AWS Lambda charge for GPU-accelerated functions on Managed Instances?

Pricing is the EC2 On-Demand price for the underlying G-series instance (Savings Plans and Reserved Instances apply), plus a 9.75% Lambda management fee and $0.20 per million requests. No separate GPU surcharge beyond the EC2 instance cost and this management fee is listed.

_Developers budgeting serverless GPU workloads can track AWS Lambda pricing changes like this on daily.dev._

### What GPU frameworks come preconfigured with AWS Lambda GPU support?

AWS Lambda provides GPU base images preconfigured with vLLM, SGLang, and PyTorch for GPU-accelerated Event Functions on Lambda Managed Instances, which use EC2 G-series instances. This removes the need to manually install GPU drivers or ML frameworks before deploying inference or compute workloads.

_Teams evaluating serverless options for AI inference can follow updates like this on daily.dev._

### How much ephemeral storage can an AWS Lambda GPU function use?

GPU-accelerated Lambda functions on Managed Instances support NVMe ephemeral storage of up to 32 GB per container image, intended for workloads with large artifacts such as model weights. Lambda also supports Seekable OCI (SOCI) lazy loading and streaming artifacts directly from Amazon S3 to reduce startup time.

_Engineers sizing storage for GPU workloads can keep up with serverless infrastructure limits like this on daily.dev._

## Similar posts on daily.dev

- [AWS Lambda supports up to 32 GB of memory and 16 vCPUs for Lambda Managed Instances](https://daily.dev/posts/aws-lambda-supports-up-to-32-gb-of-memory-and-16-vcpus-for-lambda-managed-instances-jp3xptauv) · AWS · 0 upvotes · 0 comments
- [Monitor AWS Lambda Managed Instances with Datadog](https://daily.dev/posts/monitor-aws-lambda-managed-instances-with-datadog-nhbvxfkll) · Datadog · 0 upvotes · 0 comments
- [AWS Lambda now supports Graviton5-powered EC2 instances on Lambda Managed Instances](https://daily.dev/posts/aws-lambda-now-supports-graviton5-powered-ec2-instances-on-lambda-managed-instances-y1s5k7m7y) · AWS · 1 upvotes · 1 comments
- [AWS Launches Lambda MicroVMs for Isolated Agent and User Code Execution](https://daily.dev/posts/aws-launches-lambda-microvms-for-isolated-agent-and-user-code-execution-gmabbyzxq) · InfoQ · 2 upvotes · 0 comments

---

Tags: [#gpu](https://daily.dev/tags/gpu), [#serverless](https://daily.dev/tags/serverless), [#aws-lambda](https://daily.dev/tags/aws-lambda), [#ai-inference](https://daily.dev/tags/ai-inference), [#aws-ec2](https://daily.dev/tags/aws-ec2)

[View this post on daily.dev](https://daily.dev/posts/aws-lambda-adds-support-for-gpu-instances-on-lambda-managed-instances-8o7qdlzdh)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"AWS Lambda adds support for GPU instances on Lambda Managed Instances","url":"https://daily.dev/posts/aws-lambda-adds-support-for-gpu-instances-on-lambda-managed-instances-8o7qdlzdh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/aws-lambda-adds-support-for-gpu-instances-on-lambda-managed-instances-8o7qdlzdh"},"datePublished":"2026-11-18T20:04:41.677Z","dateModified":"2026-11-18T20:14:08.026Z","description":"AWS Lambda now supports GPU-accelerated Event Functions on Lambda Managed Instances using EC2 G-series instances. Workloads like AI inference, media...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e82c8cceed8771f89f06dfc50fa9305d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e82c8cceed8771f89f06dfc50fa9305d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"AWS","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AWS","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/aws","url":"https://daily.dev/sources/aws"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/aws-lambda-adds-support-for-gpu-instances-on-lambda-managed-instances-8o7qdlzdh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"gpu,serverless,aws-lambda,ai-inference,aws-ec2","timeRequired":"PT2M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AWS","item":"https://daily.dev/sources/aws"},{"@type":"ListItem","position":3,"name":"AWS Lambda adds support for GPU instances on Lambda Managed Instances"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/aws-lambda-adds-support-for-gpu-instances-on-lambda-managed-instances-8o7qdlzdh#faq","mainEntity":[{"@type":"Question","name":"How much does AWS Lambda charge for GPU-accelerated functions on Managed Instances?","acceptedAnswer":{"@type":"Answer","text":"Pricing is the EC2 On-Demand price for the underlying G-series instance (Savings Plans and Reserved Instances apply), plus a 9.75% Lambda management fee and $0.20 per million requests. No separate GPU surcharge beyond the EC2 instance cost and this management fee is listed. Developers budgeting serverless GPU workloads can track AWS Lambda pricing changes like this on daily.dev."}},{"@type":"Question","name":"What GPU frameworks come preconfigured with AWS Lambda GPU support?","acceptedAnswer":{"@type":"Answer","text":"AWS Lambda provides GPU base images preconfigured with vLLM, SGLang, and PyTorch for GPU-accelerated Event Functions on Lambda Managed Instances, which use EC2 G-series instances. This removes the need to manually install GPU drivers or ML frameworks before deploying inference or compute workloads. Teams evaluating serverless options for AI inference can follow updates like this on daily.dev."}},{"@type":"Question","name":"How much ephemeral storage can an AWS Lambda GPU function use?","acceptedAnswer":{"@type":"Answer","text":"GPU-accelerated Lambda functions on Managed Instances support NVMe ephemeral storage of up to 32 GB per container image, intended for workloads with large artifacts such as model weights. Lambda also supports Seekable OCI (SOCI) lazy loading and streaming artifacts directly from Amazon S3 to reduce startup time. Engineers sizing storage for GPU workloads can keep up with serverless infrastructure limits like this on daily.dev."}}]}
```

