AWS Deep Learning Containers for vLLM 0.13.0 on SageMaker¶
AWS Deep Learning Containers for SageMaker are now available with vLLM 0.13.0.
Announcements¶
-
Introduced vLLM 0.13.0 containers for SageMaker
-
Added Python 3.12 support
Core Packages¶
| Package | Version |
|---|---|
| vLLM | 0.13.0 |
| PyTorch | 2.9.0 |
| TorchVision | 0.24.0 |
| TorchAudio | 2.9.0 |
| FlashInfer | 0.5.3 |
| CUDA | 12.9.1 |
| cuDNN | 9.10.2.21 |
| NCCL | 2.28.3 |
| EFA | 1.45.1 |
| GDRCopy | 2.5.1 |
Security Advisory¶
AWS recommends that customers monitor critical security updates in the AWS Security Bulletin.
Reference¶
Docker Image URIs¶
763104351884.dkr.ecr.us-west-2.amazonaws.com/vllm:0.13.0-gpu-py312-cu129-ubuntu22.04-sagemaker
763104351884.dkr.ecr.us-west-2.amazonaws.com/vllm:0.13-gpu-py312-cu129-ubuntu22.04-sagemaker-v1
763104351884.dkr.ecr.us-west-2.amazonaws.com/vllm:0.13.0-gpu-py312
763104351884.dkr.ecr.us-west-2.amazonaws.com/vllm:0.13-gpu-py312
public.ecr.aws/deep-learning-containers/vllm:0.13.0-gpu-py312-cu129-ubuntu22.04-sagemaker
public.ecr.aws/deep-learning-containers/vllm:0.13-gpu-py312-cu129-ubuntu22.04-sagemaker-v1
public.ecr.aws/deep-learning-containers/vllm:0.13.0-gpu-py312
public.ecr.aws/deep-learning-containers/vllm:0.13-gpu-py312