AWS Lambda adds GPU inference with up to 48 concurrent calls per GPU
11/22/2026 — 11/22, 15:17·1 sources (all)·1 reports (all)
Key takeaways
- AWS Lambda can now run event functions on EC2 G-series GPU instances through Lambda Managed Instances, with up to 48 concurrent invocations…
Background & analysis
On November 22, 2026, InfoQ's AI/ML channel reported that AWS Lambda has gained the ability to run inference workloads on GPUs. According to the report, AWS Lambda can execute Event Functions on EC2 G-series GPU instances through Lambda Managed Instances, with up to 48 concurrent invocations sharing a single model on each GPU.
In terms of how the service is set up, it offers prebuilt vLLM and SGLang base images that require no handler code, and it supports 90-minute asynchronous timeouts. Billing is structured as the underlying instance price plus an additional 9.75 percent fee. The first hands-on tests cited in the article recorded a publish time of roughly 8 minutes and noted that the service does not support response streaming.
At this point, the public record stops at those initial test findings, with no further updates or follow-up reports available. The article, attributed to Steef-Jan Wiggers, remains the sole coverage of the capability, so details beyond the launch configuration, pricing terms, and the published test observations have not yet been documented.
AI-generated from 1 reports · updated 1 hour ago
- Heat index
- 94
- All sources
- 1
- All reports
- 1
- First seen
- 2 hours ago
Reports on this story headlines open the original
AWS Lambda can now run Event Functions on EC2 G-series GPU instances via Lambda Managed Instances, letting up to 48 concurrent invocations share one model per GPU, InfoQ reports. It ships vLLM and SGLang base images that need no handler code, supports 90-minute asynchronous timeouts, and bills the instance price plus a 9.75% fee; early hands-on tests report an eight-minute publish and no response streaming.
InfoQ · AI/MLAI score 55
Other stories people are talking about
- Heat index 1177RisingLean Community verifies Anthropic and Claude Riemann hypothesis proof22 sources
- Heat index 1053RisingAnthropic falls 8.5% on day two, closing the first week at a $1.6 trillion valuation21 sources
- Heat index 501Thinking Machines Lab Open-Sources Inkling 2 Mini with 32GB Model Card Recommendation10 sources
- Heat index 412SEC probes Nvidia accounting practices as shares post seven-week slide9 sources
- Heat index 384Anthropic IPO total raise reaches $93.5 billion after greenshoe exercise14 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

