跳到正文

AWS Announces Faster, Larger Amazon Bedrock AgentCore Runtime

AWS Machine Learning Blog当事人· Madhu Parthasarathy·· 8 小时前精选Run agents securely and efficiently with the next generation AgentCore runtime
打开原文
原文

中文版本尚未就绪 · 显示原文

图片来自 AWS Machine Learning Blog
谁
Amazon Web Services
引文
Today we’re announcing updates to AgentCore runtime that meet those demands.

发生了什么

AWS announced updates to the Amazon Bedrock AgentCore runtime, including sessions that start in under 2 seconds, scale up to 8 vCPUs and 32 GB, and support container images up to 10 GB. The runtime can reclaim unused memory and let idle agents scale to zero, while sessions retain hardware isolation. The updated runtime is available today in AWS Regions across North America, South America, Europe, and Asia Pacific.

推荐理由

The update combines faster startup, larger sessions, usage-based memory billing, and data storage within the isolation boundary, giving teams concrete infrastructure changes to weigh when moving agents into production.

接下来读什么

查看这件事的完整进展AWS expands Bedrock AgentCore Runtime capacity and speeds session starts

这件事到目前为止

AWS updated Amazon Bedrock AgentCore Runtime with session startup times under 2 seconds, capacity up to 8 vCPUs and 32 GB, and support for container images up to 10 GB. AWS says startup time is independent of image size and concurrency, and the new runtime is available in its North America, South America, Europe, and Asia Pacific Regions. The runtime can reclaim memory within minutes after an agent releases it and scale idle agents to zero. For always-on agents, AWS offers committed baseline pricing that sets a minimum memory charge per session while allowing on-demand bursts up to four times the baseline.

这条收录于 11月13日 AI 日报看这一期日报的全部内容