
#600: Amazon SageMaker Multi Model Endpoints
AWS Podcast
The Complexity of Machine Learning
Inference is the process of using a trained ML model. In SageMaker we have four ML inference options, namely real-time endpoints, patch transform, async, and serverless inference. You've got a few different choices in terms of how you interact and the answers you get. And that's really driven by your use cases, isn't it? So there's some use cases where, yeah, if you're in a consumer flow, you need an answer immediately,. Whereas if you're trying to sort of understand data from a long time ago and seek connections, that may not be so time-bound.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.