cd/sources/aws-ml-blog· home› sources› AWS ML Blog
cat /sources/aws-ml-blog.feed | wc -l → 600

AWS ML Blog

articles 600 domain aws.amazon.com → page 2/30 feed RSS
15:42
2026-11-16
aws.amazon.com
ai-infrastructure

Use prompt caching with open-weight models on Amazon Bedrock

Amazon Bedrock now supports explicit prompt caching for open-weight models, letting applications mark reusable prompt prefixes with `prompt_cache_breakpoint` markers via the Chat Completions API and r…

22:03
2026-11-12
aws.amazon.com
ai-infrastructure

Deploy frontier AI models on AWS Trainium with SGLang-Neuron

Amazon announced that SGLang-Neuron, an out-of-tree plugin connecting the SGLang serving framework to AWS Trainium chips, is publicly available through an AWS Deep Learning Container released by Radix…

20:51
2026-11-12
aws.amazon.com
ai-infrastructure

Four Amazon Bedrock inference choices that affect cost

An AWS blog post details four request-level Amazon Bedrock settings — prompt cache duration, service tier, reasoning effort, and maxTokens — that change inference cost without altering the model or pr…

← prev page 2 / 30 next →