---
格式版本: 2
标题: "Amazon SageMaker AI Batch Transform now supports G6e instances"
原文链接: "https://aws.amazon.com/cn/about-aws/whats-new/2026/09/sagemaker-batch-transform-g6e-instances/"
发布日期: "2026-09-04"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "llm:local:original_script_field"
发布时间证据: "postDateTime: 2026-09-04T08:00:00Z"
发布时间校准原因: "候选日期为正文元数据中的postDateTime字段，明确标识发布时间。"
发布时间校准置信度: "1"
发布时间候选数量: 1
发布时间严格候选数量: 0
发布时间原页读取状态: "source template page reused from URL open"
发布时间未找到原因: ""
发布时间校准时间: "2026-09-07T22:40:57+08:00"
发布时间仲裁状态: "confirmed"
发布时间仲裁尝试次数: 1
发布时间仲裁耗时毫秒: 2013
发现时间: "2026-09-07T22:07:26+08:00"
入库时间: "2026-09-07T14:41:14.733Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://aws.amazon.com/new"
匹配关键词:
  - "performance"
  - "GPU"
  - "AI"
相关厂家:
  - "AWS"
  - "NVIDIA"
  - "AMD"
相关专家:
  []
内容类型: "网页"
抓取工具: "Free Fetch + Defuddle"
清洗工具: "Defuddle Markdown + Defuddle/Readability 正文提取"
原始附件:
  []
AI优质: "否"
AI打分: 36
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "正文主线是AWS SageMaker AI Batch Transform新增支持EC2 G6e实例，属于云上批量推理/Serving服务扩展，并非超节点、AI Rack或机架级基础设施。来源为AWS官方公告，权威性高，但内容仅为服务可用性更新；G6e实例规格（8×L40S、48GB/GPU、AMD EPYC）是既有实例信息，相较知识库中P6-B200/P6-B300等平台无新增机架级架构、互连、供电、液冷或量产部署事实。可用区域和API入口属于区域扩展，不具备独立商业部署信号。未命中高价值准入通道，且属于批量推理服务/应用效率类型，按强否决项处理，总分不能进入55分区间。"
AI质检模型: "zj-deepseek-v4-flash"
AI质检时间: "2026-09-07T22:41:32+08:00"
AI主题相关性: 4
AI来源权威性: 13
AI新颖性: 4
AI技术细节: 7
AI商业部署信号: 2
AI完整性: 6
AI评分提示词版本: "v17-精简生产版"
AI评分提示词SHA256: "48fb9777f386026761b4873eaff30807694fb11e9b352d7c69bf2dfde750cc7d"
AI评分知识库版本: "knowledge_base_v1-20260819+runtime.99"
AI评分知识库SHA256: "0fbd91b8efdf08ea0580fc2df2684b6db7e286b65c7b6430d7666940f4e954c3"
AI评分知识库检索词: "[\"AWS\",\"NVIDIA\",\"AMD\",\"performance\",\"GPU\",\"https://aws.amazon.com/new\",\"G6e\",\"EC2\",\"aws.amazon.com/ec2/instance-types/g6e\",\"S3\",\"L40S\",\"GPUs\"]"
AI评分知识库命中: "[{\"id\":\"runtime-ba9a8fcaf332bae34960d0f8\",\"title\":\"Amazon EC2 P6-B200 instances are now available in the AWS Asia Pacific (Hyderabad) Region\",\"sourceType\":\"ai_excellent_article\",\"time\":\"2026-09-03\",\"matchedTerms\":[\"AWS\",\"NVIDIA\",\"performance\",\"GPU\",\"EC2\",\"GPUs\"],\"rank\":-17.558856416115457},{\"id\":\"runtime-ed0b613c85d0392cdd3f0821\",\"title\":\"Amazon EC2 P6-B200 instances are now available in the AWS Asia Pacific (Hyderabad) Region\",\"sourceType\":\"ai_excellent_article\",\"time\":\"2026-09-03\",\"matchedTerms\":[\"AWS\",\"NVIDIA\",\"performance\",\"GPU\",\"EC2\",\"GPUs\"],\"rank\":-17.558856416115457},{\"id\":\"runtime-b9ec799d769b0f4ba49df311\",\"title\":\"AWS and NVIDIA to Deliver 2 Million Additional GPUs and Next-Generation Infrastructure for Agentic and Physical AI\",\"sourceType\":\"ai_excellent_article\",\"time\":\"\",\"matchedTerms\":[\"AWS\",\"NVIDIA\",\"performance\",\"GPU\",\"EC2\",\"GPUs\"],\"rank\":-17.435487450890562},{\"id\":\"runtime-9f43a79e9c23b1f329d8a71a\",\"title\":\"AWS and NVIDIA to Deliver 2 Million Additional GPUs and Next-Generation Infrastructure for Agentic and Physical AI\",\"sourceType\":\"ai_excellent_article\",\"time\":\"\",\"matchedTerms\":[\"AWS\",\"NVIDIA\",\"performance\",\"GPU\",\"EC2\",\"GPUs\"],\"rank\":-16.21929147158481},{\"id\":\"runtime-83dfe7d4e2b1819cedc55a6a\",\"title\":\"Amazon EC2 P6-B300 instances are now available in the AWS Asia Pacific (Jakarta) Region\",\"sourceType\":\"ai_excellent_article\",\"time\":\"2026-09-03\",\"matchedTerms\":[\"AWS\",\"NVIDIA\",\"GPU\",\"EC2\",\"GPUs\"],\"rank\":-14.752755098553129}]"
采集批次: "2026年9月7日22点05分18秒"
采集批次ID: "20260907-220517-361"
去重键: "https://aws.amazon.com/cn/about-aws/whats-new/2026/09/sagemaker-batch-transform-g6e-instances"
---

Amazon SageMaker AI now supports [Amazon EC2 G6e instances](https://aws.amazon.com/ec2/instance-types/g6e/) for batch transform. Batch Transform enables you to run predictions on datasets stored in Amazon S3 and is suited for large datasets that do not require a persistent inference endpoint.

Amazon EC2 G6e instances are powered by up to eight NVIDIA L40S Tensor Core GPUs with 48 GB of memory per GPU and third-generation AMD EPYC processors. G6e instances deliver improved performance for GPU-intensive workloads. With this launch, you can use G6e instances for GPU-intensive offline inference workloads, including large language models and diffusion models that generate images, video, and audio. To get started, select a supported ml.g6e instance type when creating a Batch Transform job through AWS SDKs, AWS CLI, or the CreateTransformJob API.

G6e support for Batch Transform is available in US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), and Asia Pacific (Hyderabad). To learn more, visit the [Amazon SageMaker AI](https://aws.amazon.com/sagemaker/ai/deploy/) product page and see the [Batch Transform documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/batch-transform.html). For pricing information on these instances, please visit our [pricing page](https://aws.amazon.com/sagemaker/ai/pricing/?refid=ft_sagemaker).