精选理由
AWS 把 SageMaker HyperPod 的推理能力补全了，能抓数据做审计、直接从 Hugging Face 拉模型、用 NVMe 加速启动，还有自定义域名和细粒度权限，搞企业部署可以看看。
亚马逊为 SageMaker HyperPod 推理新增五项企业级功能。多层级数据捕获支持审计和模型改进，可直接从 Hugging Face Hub 部署模型。本地 NVMe 模型加载减少冷启动时间，自动 Route 53 DNS 简化自定义域名配置。pod 级 IAM 通过自定义服务账户实现细粒度权限控制。
原文 · AWS Machine Learning Blog
Enhancing enterprise inference on Amazon SageMaker HyperPod with data capture, Hugging Face, NVMe, and Route 53 integration
In this post, we walk through five capabilities now available in SageMaker HyperPod inference: multi-tier data capture for auditing and model improvement, direct deployment from Hugging Face Hub, local NVMe model loading for faster cold starts, automated Route 53 DNS for custom domains, and pod-level IAM through custom service accounts.