用编码代理在 SageMaker AI 上部署 Hugging Face 模型
原标题：Deploy Hugging Face models on Amazon SageMaker AI with coding agents
AI 摘要
AWS Machine Learning Blog 介绍如何用编码代理（Kiro、Claude Code）在 Amazon SageMaker AI 上部署 Hugging Face 模型。文章指出无引导的代理会因部署知识过时而选错服务容器（如 TGI 无法加载 Qwen3），导致健康检查失败和 GPU 浪费；为此 Hugging Face Skills 提供六个开源技能，覆盖容器选择、镜像解析、自动扩缩容、CloudWatch 告警和资源清理等端到端流程。
正文节选
Deploy Hugging Face models on Amazon SageMaker AI with coding agents Deploying a Hugging Face model to production means making a dozen decisions: choosing the right serving container for the model’s architecture, confirming the current image tag for your AWS Region, and matching an instance type to the model’s memory footprint. Beyond infrastructure, you must wire autoscaling so you don’t burn GPU hours on an idle endpoint. You also set Amazon CloudWatch alarms that catch silent failures before