返回全部动态

Deepgram 增强 SageMaker AI 可观测性,推出计费与引擎级指标

原标题:Deepgram deepens Amazon SageMaker AI observability with Enhanced Metrics

AWS Machine Learning Blog一手来源产品发布质量 81

AI 摘要

Deepgram 宣布在 Amazon SageMaker AI 上推出两项新的可观测性功能:Deepgram Enhanced Metrics 和 Prometheus/OpenTelemetry 支持。前者通过 CloudWatch Embedded Metric Format 将计费和用量指标直接发布到用户的 CloudWatch 账户,无需额外代理或权限;后者提供引擎级和每 GPU 的指标。这些功能帮助用户在 AWS Marketplace 网络隔离环境下实现计费对账和容量规划,同时保持数据驻留和合规性。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

Deepgram deepens Amazon SageMaker AI observability with Enhanced Metrics Self-hosted speech AI has historically carried an observability trade-off. The service can tell you an endpoint is up and how many requests it served. The questions that actually drive capacity planning and cost management stay locked inside the vendor’s container: what you are billed for, which features your traffic uses, and what the inference engine is doing on each GPU. If you run Deepgram’s speech-to-text (STT) and tex


发布时间:2026-08-28 00:11
抓取时间:2026-08-28 18:12
来源机构:AWS
阅读原文aws.amazon.com