{"id":"7efaac74-2327-4cf6-8d8f-578c348f85fc","url":"https://api.tumn.com/news/7efaac74-2327-4cf6-8d8f-578c348f85fc","title":"Stop guessing auto scaling targets for TTS on Amazon SageMaker AI","summary":"Teams deploying custom text-to-speech models on Amazon SageMaker AI often guess at autoscaling thresholds, and a wrong guess either wastes GPU spend or breaches a latency SLO. This post deploys Kokoro-82M as a custom container and derives a measured autoscaling policy from two li","sections":[],"faq":[],"sources":[{"url":"https://aws.amazon.com/blogs/machine-learning/stop-guessing-auto-scaling-targets-for-tts-on-amazon-sagemaker-ai/","title":"AWS Machine Learning Blog","publishedAt":"2026-10-22T16:30:06.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-22T16:30:06.000Z","modifiedAt":"2026-10-22T22:25:55.000Z","checkedAt":"2026-10-22T22:25:55.212Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/7efaac74-2327-4cf6-8d8f-578c348f85fc.json","markdown":"https://api.tumn.com/news/7efaac74-2327-4cf6-8d8f-578c348f85fc.md"}}