AWS deep-learning-containers documentation change
Summary
Updated documentation title to include EC2/ECS/EKS support; added Python 3.12 support section; specified x86_64 instance type support; included build/test details; added security scanning statement; restructured content and updated links.
Security assessment
Added explicit statement about security scanning ('All software components... scanned for security vulnerabilities') which documents existing security practices but doesn't address any specific vulnerability. No CVE or incident mentioned.
Diff
diff --git a/deep-learning-containers/latest/devguide/dlc-vllm-ec2.md b/deep-learning-containers/latest/devguide/dlc-vllm-ec2.md index 0e397ca0a..090d1eb40 100644 --- a//deep-learning-containers/latest/devguide/dlc-vllm-ec2.md +++ b//deep-learning-containers/latest/devguide/dlc-vllm-ec2.md @@ -5 +5 @@ -ChangelogSecurity AdvisoryAWS Regions support +ChangelogSecurity AdvisoryPython 3.12 SupportInstance Type SupportAWS Regions supportBuild and TestKnown Issues @@ -7 +7 @@ ChangelogSecurity AdvisoryAWS Regions support -# AWS Deep Learning Containers for vLLM with EFA Support +# AWS Deep Learning Containers for vLLM with EFA Support on EC2, ECS, and EKS @@ -9 +9 @@ ChangelogSecurity AdvisoryAWS Regions support -[AWS Deep Learning Containers (DLCs)](https://aws.amazon.com/machine-learning/containers/) now support vLLM images that are optimized for large language model serving. +[AWS Deep Learning Containers (DLCs)](https://aws.amazon.com/machine-learning/containers/) now support vLLM images that are optimized for large language model serving. The vLLM DLC provides a production-ready environment for deploying and serving LLMs with built-in support for EFA (Elastic Fabric Adapter). With vLLM's advanced features and optimizations pre-configured, this specialized container offer an ideal starting point for high-performance, scalable and efficient LLM serving for various use cases, from single-node to multi-node deployments. @@ -11,7 +11 @@ ChangelogSecurity AdvisoryAWS Regions support -The vLLM DLC provides a production-ready environment for deploying and serving LLMs with built-in support for EFA (Elastic Fabric Adapter). With vLLM's advanced features and optimizations pre-configured, this specialized container offer an ideal starting point for high-performance, scalable and efficient LLM serving for various use cases, from single-node to multi-node deployments. For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai). - -Get started quickly with the AWS Deep Learning Containers using the getting-started section in our [developer guide](https://docs.aws.amazon.com/dlami/latest/devguide/deep-learning-containers.html). - -If you are looking for a DLC to use with SageMaker, please refer to [this documentation](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#sagemaker-framework-containers-sm-support-only). - -To ensure you are using the latest DLC releases, we invite you to subscribe to our [DLC notification mechanism](https://docs.aws.amazon.com/deep-learning-containers/latest/devguide/dlc-release-notifications.html). +All software components in this container are scanned for security vulnerabilities and updated or patched in accordance with AWS Security best practices. A list of all available AWS DLCs can be found in our [github repo](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#dlc-available-image-user-guide). Get started quickly with AWS DLCs using the getting-started section in our [developer guide](https://docs.aws.amazon.com/dlami/latest/devguide/deep-learning-containers.html). To ensure you're using the latest DLC releases, we invite you to subscribe to our [DLC notification mechanism](https://docs.aws.amazon.com/deep-learning-containers/latest/devguide/dlc-release-notifications.html). If you are looking for a DLC to use with SageMaker, please refer to [this documentation](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#general-framework-containers-ec2-ecs-eks--sm-support). For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai/en/latest/). @@ -23 +17 @@ To learn about latest changes in vLLM DLC, checkout the [changelog](https://gith -A list of available containers can be found on [GitHub](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#ec2-vllm-containers-ec2-ecs-and-eks-support-only). +A list of available containers can be found on [GitHub](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#vllm-containers). @@ -27,2 +20,0 @@ A list of available containers can be found on [GitHub](https://github.com/aws/d -All software components in these images are scanned for security vulnerabilities and updated or patched in accordance with AWS Security best practices. - @@ -30,0 +23,8 @@ AWS recommends that customers monitor critical security updates in the [AWS Secu +## Python 3.12 Support + +Python 3.12 is supported. + +## Instance Type Support + +The containers support x86_64 instance types. + @@ -71,0 +72,15 @@ China (Ningxia) | cn-northwest-1 +## Build and Test + + * Built on: c5.18xlarge + + * Tested on: p4d.24xlarge, p5.48xlarge + + * Tested with deepseek-ai/DeepSeek-R1-Distill-Qwen-32B model, single-node and multi-node serving configurations + + + + +## Known Issues + +No known issues so far + @@ -78 +93 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -vLLM Deep Learning Containers +vLLM DLC on SageMaker @@ -80 +95 @@ vLLM Deep Learning Containers -PyTorch Deep Learning Containers +vLLM ARM64 DLC on EC2