Category: Amazon SageMaker AI

This post is co-written with Sunaina Kavi, AI/ML Product Manager at Omada Health. Omada Health, a longtime innovator in virtual healthcare delivery, launched a new nutrition experience in 2025, featuring OmadaSpark, an AI agent trained with robust clinical input that delivers real-time motivational interviewing and nutrition education. It was built on AWS. OmadaSpark was designed […]

Quantized models can be seamlessly deployed on Amazon SageMaker AI using a few lines of code. In this post, we explore why quantization matters—how it enables lower-cost inference, supports deployment on resource-constrained hardware, and reduces both the financial and environmental impact of modern LLMs, while preserving most of their original performance. We also take a deep dive into the principles behind PTQ and demonstrate how to quantize the model of your choice and deploy it on Amazon SageMaker.

This post, developed through a strategic scientific partnership between AWS and the Instituto de Ciência e Tecnologia Itaú (ICTi), P&D hub maintained by Itaú Unibanco, the largest private bank in Latin America, explores the technical aspects of sentiment analysis for both text and audio. We present experiments comparing multiple machine learning (ML) models and services, discuss the trade-offs and pitfalls of each approach, and highlight how AWS services can be orchestrated to build robust, end-to-end solutions. We also offer insights into potential future directions, including more advanced prompt engineering for large language models (LLMs) and expanding the scope of audio-based analysis to capture emotional cues that text data alone might miss.

This post provides a detailed architectural overview of how TrueLook built its AI-powered safety monitoring system using SageMaker AI, highlighting key technical decisions, pipeline design patterns, and MLOps best practices. You will gain valuable insights into designing scalable computer vision solutions on AWS, particularly around model training workflows, automated pipeline creation, and production deployment strategies for real-time inference.

Observe.ai developed the One Load Audit Framework (OLAF), which integrates with SageMaker to identify bottlenecks and performance issues in ML services, offering latency and throughput measurements under both static and dynamic data loads. In this blog post, you will learn how to use the OLAF utility to test and validate your SageMaker endpoint.

This post shows you how to migrate your self-managed MLflow tracking server to a MLflow App – a serverless tracking server on SageMaker AI that automatically scales resources based on demand while removing server patching and storage management tasks at no cost. Learn how to use the MLflow Export Import tool to transfer your experiments, runs, models, and other MLflow resources, including instructions to validate your migration’s success.

In this post, we demonstrate how to optimize large language model (LLM) inference on Amazon SageMaker AI using BentoML’s LLM-Optimizer to systematically identify the best serving configurations for your workload.

In this post, we explore how Qbtech streamlined their machine learning (ML) workflow using Amazon SageMaker AI, a fully managed service to build, train and deploy ML models, and AWS Glue, a serverless service that makes data integration simpler, faster, and more cost effective. This new solution reduced their feature engineering time from weeks to hours, while maintaining the high clinical standards required by healthcare providers.

In this post, we demonstrate hosting Voxtral models on Amazon SageMaker AI endpoints using vLLM and the Bring Your Own Container (BYOC) approach. vLLM is a high-performance library for serving large language models (LLMs) that features paged attention for improved memory management and tensor parallelism for distributing models across multiple GPUs.

Today, we are excited to introduce a new feature for SageMaker Studio: SOCI (Seekable Open Container Initiative) indexing. SOCI supports lazy loading of container images, where only the necessary parts of an image are downloaded initially rather than the entire container.