AWS Lambda Now Runs GPU Inference with 48 Concurrent Invocations Sharing One Model per GPU

Image: InfoQ
ad slot · in-content video 16:9
Coverage
More coverage
- AWS Lambda now runs Event Functions on EC2 G-series GPU instances through Lambda Managed Instances, with up to 48 concurrent invocations sharing one model per GPU, vLLM and SGLang base images that need no handler code, and 90-minute asynchronous timeouts. Billing is the instance price plus a 9.75…