One stop shop for running AI/ML on AWS
Docs · Available Images · Tutorials
AWS Deep Learning Containers (DLCs) are pre-built Docker images for running AI/ML workloads on AWS. Each image is tested and patched for security vulnerabilities. For more details, visit our documentation.
- [2026/06/14] vLLM v0.23.0 — EC2:
0.23.0-gpu-py312-ec2· SageMaker:0.23.0-gpu-py312· Step-3.7-Flash, Cosmos3 Reasoner, Gemma 4 Unified (encoder-free), Granite Speech Plus, Cohere Mini Code; Anthropic Messages API structured output. - [2026/06/13] SGLang v0.5.13 — EC2:
0.5.13-gpu-py312-ec2· SageMaker:0.5.13-gpu-py312· DeepSeek V4 (BCG, HiSparse PD, PP+PD), Kimi-K2.5, MiMo-V2, Ideogram 4 (FP8/NVFP4); SM120 + FP4 indexer support. - [2026/06/12] SGLang Server v1.0 (AL2023) — EC2:
server-cuda-v1.0· SageMaker:server-sagemaker-cuda-v1.0· First Amazon Linux 2023 SGLang Server images, built from upstream source; OpenAI-compatible API (port 30000 EC2/EKS, 8080 SageMaker); CUDA 13.0 for H100 + Blackwell; PyTorch 2.11.0; EFA, DeepEP, and Mooncake KV-cache bundled. - [2026/06/05] vLLM v0.22.1 — EC2:
0.22.1-gpu-py312-ec2· SageMaker:0.22.1-gpu-py312· JetBrains Mellum v2; DeepSeek-V4, OlmoHybrid, HyperCLOVAX fixes; AMD Zen CPU zentorch kernels. - [2026/05/30] vLLM v0.22.0 — EC2:
0.22.0-gpu-py312-ec2· SageMaker:0.22.0-gpu-py312· MiniCPM-V 4.6, InternS2 Preview, OpenVLA, EXAONE-4.5; DeepSeek V4 maturity (NVFP4 fused MoE, MTP speculative decoding); Blackwell SM12x support. - [2026/05/18] SGLang v0.5.12 — EC2:
0.5.12-gpu-py312-ec2· SageMaker:0.5.12-gpu-py312· DeepSeek V4, Intern-S2-Preview, MiniCPM-V 4.6, Laguna-XS.2, Ring-2.6-1T, Gemma 4 MTP. - [2026/05/16] vLLM v0.21.0 — EC2:
0.21.0-gpu-py312-ec2· SageMaker:0.21.0-gpu-py312· MiMo-V2.5, Laguna XS.2, Moondream3, Cohere MoE/Eagle; DeepSeek V4 on AMD + pipeline parallelism. - [2026/05/13] vLLM-Omni v0.20.0 — EC2:
omni-cuda-v1.1· SageMaker:omni-sagemaker-cuda-v1.1· Adds/v1/audio/generate(stable-audio-open) and/v1/videos/sync(unblocks video on SageMaker); supports CosyVoice3, ERNIE-Image-Turbo, Wan2.1-VACE-1.3B; CUDA 13.0 + PyTorch 2.11.0. - [2026/04/30] PyTorch v2.11.0 — EC2:
2.11.0-cu130-amzn2023· SageMaker:2.11.0-cu130-amzn2023-sagemaker· Amazon Linux 2023 with EFA, flash-attn, and transformer-engine.
- [2026/04/28] We cannot guarantee security patching on Ubuntu-based vLLM and SGLang images due to the lack of Ubuntu Pro licensing. Customers may continue using these images at their own discretion and risk. We recommend migrating to our Amazon Linux-based images.
- [2026/02/10] Extended support for PyTorch 2.6 Inference containers until June 30, 2026
- PyTorch 2.6 Inference images will continue to receive security patches and updates through end of June 2026
- For complete framework support timelines, see our Support Policy
- Distributed Training on Amazon EKS - Configure and validate a distributed training cluster with DLCs on Amazon EKS.
- DLCs with Amazon SageMaker AI & MLflow - Use DLCs with SageMaker AI managed MLflow for experiment tracking and model management.
- LLM Serving on Amazon EKS with vLLM - Deploy and serve LLMs on Amazon EKS using vLLM DLCs.
- Fine-tuning Meta Llama 3.2 Vision - Fine-tune and deploy Llama 3.2 Vision for web automation using DLCs, Amazon EKS, and Amazon Bedrock.
- DLCs with Amazon Q Developer and MCP - Streamline deep learning environments with Amazon Q Developer and Model Context Protocol.
- LLM Deployment on Amazon EKS - Deploy and optimize LLMs on Amazon EKS using vLLM DLCs. See also: Sample Code
This project is licensed under the Apache-2.0 License.