Announcing new ways to customize models with SageMaker AI, without managing GPUs

21d

Idade

Publicado: 22 de out. de 2026, 18:00 UTC
Coletado: 22 de out. de 2026, 18:00 UTC

Amazon SageMaker AI serverless model customization now includes training sessions, generally available today. You write and coordinate your own post-training loop (custom loss functions, reward signals, or multi-turn reinforcement learning) while SageMaker AI handles GPU allocation, distributed execution, fault recovery, and checkpoint storage.

Trecho da fonte

Companies getting real results from AI aren’t only using foundation models (FMs) off the shelf. They’re customizing open-weight models using post-training techniques such as reinforcement learning. A model trained on your business context, product catalog, or clinical vocabulary will be more accurate for your task and cost less to run. When you build agents, your data, workflows, evaluations, and success criteria also shape how the model behaves. However, model customization is difficult. You…

Leia o artigo completo em aws.amazon.com

O overfeed.news indexa e aponta. Publicamos um trecho curto — o artigo completo fica em AWS Machine Learning Blog.

Mais de AWS Machine Learning Blog

Entre para seguir esta fonte

AWS Machine Learning Bloghá 54 minutos

Four Amazon Bedrock inference choices that affect cost

Your Amazon Bedrock inference bill can keep climbing even after you tune prompts and application logic. Four request-level choices (cache duration, service tier, reasoning effort, and maxTokens) change how many tokens the service processes and the rate applied. We show how we tested each and how to verify the effect.

AWS Machine Learning Bloghá 2 horas

Tokenomics at scale: Track and cap Amazon Bedrock spend per IAM principal with CUR 2.0 and AWS Budgets

Get per-identity Amazon Bedrock cost visibility and enforceable spend limits using only AWS-native features, with no application code for the common case. Attribute spend with IAM principal tags, report with CUR 2.0 or Cost Explorer, and enforce with AWS Budgets actions that apply a Deny policy when a threshold is crossed.

AWS Machine Learning Bloghá 3 horas

Optimizing cost per task and proving agent ROI on Amazon Bedrock

Comparing per-token prices hides the real cost of running a model on Amazon Bedrock. This post shows how to calculate the true cost per task across four hidden cost drivers, reduce it with caching, routing, and output constraints, and prove agent ROI with human baselines, holdout experiments, and a five-dimension scorecard.

AWS Machine Learning Bloghá 3 horas

Building a self-service LLM gateway with Amazon Bedrock and LiteLLM

Build a self-service LLM gateway with LiteLLM on AWS Fargate that puts Amazon Bedrock foundation models behind an OpenAI-compatible API. Developers get instant access through a single API key, while platform teams gain per-user cost controls, quota isolation, and observability.

Mais de AWS Machine Learning Blog

Four Amazon Bedrock inference choices that affect cost↗

Tokenomics at scale: Track and cap Amazon Bedrock spend per IAM principal with CUR 2.0 and AWS Budgets↗

Optimizing cost per task and proving agent ROI on Amazon Bedrock↗

Building a self-service LLM gateway with Amazon Bedrock and LiteLLM↗

Four Amazon Bedrock inference choices that affect cost

Tokenomics at scale: Track and cap Amazon Bedrock spend per IAM principal with CUR 2.0 and AWS Budgets

Optimizing cost per task and proving agent ROI on Amazon Bedrock

Building a self-service LLM gateway with Amazon Bedrock and LiteLLM