AWS deep-learning-containers documentation change
Summary
Restructured documentation sections, updated security advisory placement, removed technical implementation details, and added changelog reference
Security assessment
The change moves security advisory content higher in the document and maintains statements about security scanning of components, but does not indicate any specific vulnerability being addressed. The addition of 'All software components...security best practices' reinforces existing security posture documentation rather than addressing new issues.
Diff
diff --git a/deep-learning-containers/latest/devguide/dlc-vllm-0-8-x86-ec2.md b/deep-learning-containers/latest/devguide/dlc-vllm-0-8-x86-ec2.md index 33eb86e07..59ee1d8a1 100644 --- a//deep-learning-containers/latest/devguide/dlc-vllm-0-8-x86-ec2.md +++ b//deep-learning-containers/latest/devguide/dlc-vllm-0-8-x86-ec2.md @@ -5 +5 @@ -Release NotesExample URLSecurity AdvisoryPython Support Instance Type Support AWS Regions support Build and Test Known Issues +ChangelogSecurity AdvisoryAWS Regions support @@ -11 +11 @@ Release NotesExample URLSecurity AdvisoryPython Support Instance Type Support AW -The vLLM DLC provides a production-ready environment for deploying and serving LLMs with built-in support for EFA (Elastic Fabric Adapter). +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). @@ -13,13 +13 @@ The vLLM DLC provides a production-ready environment for deploying and serving L -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. - -All software components in these images are scanned for security vulnerabilities and updated or patched in accordance with AWS Security best practices. - -A list of available containers can be found on [GitHub](https://github.com/aws/deep-learning-containers/blob/master/available_images.md#base-containers). 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). 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). 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). - -For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai/en/latest/). - -## Release Notes - - * LLM Serving: Pre-configured vLLM environment optimized for efficient large language model inference - - * EFA Integration: Built-in support for Elastic Fabric Adapter enabling high-performance multi-node serving +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). @@ -26,0 +15 @@ For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai +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). @@ -27,0 +17 @@ For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai +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). @@ -28,0 +19 @@ For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai +## Changelog @@ -30 +21 @@ For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai -## Example URL +To learn about latest changes in vLLM DLC, checkout the [changelog](https://github.com/aws/deep-learning-containers/blob/master/vllm/CHANGELOG.md). @@ -32,2 +23 @@ For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai - - 763104351884.dkr.ecr.us-west-2.amazonaws.com/vllm:0.8-gpu-py312-ec2 +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). @@ -37,7 +27 @@ For guide on how to use vLLM, checkout [vLLM documentation](https://docs.vllm.ai -AWS recommends that customers monitor critical security updates in the [AWS Security Bulletin](https://aws.amazon.com/security/security-bulletins/). - -## Python Support - -Python 3.12 is supported. - -## Instance Type Support +All software components in these images are scanned for security vulnerabilities and updated or patched in accordance with AWS Security best practices. @@ -45 +29 @@ Python 3.12 is supported. -The containers support x86_64 instance types. +AWS recommends that customers monitor critical security updates in the [AWS Security Bulletin](https://aws.amazon.com/security/security-bulletins/). @@ -88,18 +71,0 @@ China (Ningxia) | cn-northwest-1 -## Build and Test - - * Built on: c5.18xlarge - - * Tested on: p4d.24xlarge, p4de.24xlarge, p5.48xlarge - - * Tested with: [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) model, single-node and multi-node serving configurations. - - - - -## Known Issues - - * No known issues so far - - - -