产品
也叫：SageMaker AI
Amazon Web Services的服务，支持分布式多GPU和多节点配置，用于训练大型语言模型。
最近变化
2026-06-03 · 使用SFT和DPO技术可以提高AI代理执行复杂任务时选择正确工具的能力。
Amazon SageMaker AI 被反复提及时，通常意味着它正在影响产品路线、开发者工作流或 AI 产业判断。这个页面把分散材料合并成一个可持续更新的观察入口。
Build real-time voice applications with Amazon SageMaker AI and vLLM
AWS Machine Learning Blog · 8.7 分
Improve your agent’s tool-calling accuracy with SFT and DPO on Amazon SageMaker AI
AWS Machine Learning Blog · 8.5 分
Build a custom portal with embedded Amazon SageMaker AI MLflow Apps
AWS Machine Learning Blog · 8.5 分
已收录 4 篇与「Amazon SageMaker AI」相关的 AI 资讯和分析。
AWS combines SageMaker AI with vLLM to enable bidirectional streaming speech-to-text inference, supporting real-time voice assistants, live captions, and more with significantly reduced latency.
入选理由：SageMaker AI提供原生HTTP/2双向流式传输(端口8443)，自动处理HTTP/2事件流与WebSocket协议转换
By using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) techniques, you can significantly improve the tool-calling accuracy of a small language model on Amazon SageMaker AI. These methods combine high-quality datasets and human feedback to optimize the model’s interactions with digital tools.
入选理由：使用SFT和DPO技术可以提高AI代理执行复杂任务时选择正确工具的能力。
This solution provides a custom portal with embedded Amazon SageMaker AI MLflow Apps, giving teams a persistent, bookmarkable URL to the full MLflow web UI without presigned URLs or AWS Management Console access. It simplifies access management and integrates with existing SSO infrastructure.
入选理由：The solution uses a custom portal with embedded MLflow UI for easy access management.
AWS SageMaker AI now supports OpenAI-compatible API interfaces. Users can call models on SageMaker through OpenAI SDK, LangChain, or Strands Agents by only changing the endpoint URL, without needing custom clients or code rewrites.
入选理由：SageMaker AI 端点现在提供 /openai/v1 路径，支持 Chat Completions 请求和流式响应，Bearer Token 有效期最长12小时。
与「Amazon SageMaker AI」经常一起出现的 AI 术语。
💡 想追踪「Amazon SageMaker AI」的长期趋势？去 实体雷达 · Amazon SageMaker AI 查看详细分析和跨材料问答。
