Timothy Shan·Oct 4Introduction to Amazon SageMakerThis article summarises what I learnt during a one-day Amazon SageMaker workshop in May 2022. We explored the machine learning lifecycle…
InTowards AWSbyxbill·Sep 30Gemma 4 on Amazon SageMaker: 4-Bit Embeddings Decode up to 1.39x Faster on One L4This article repacks Gemma 4’s quantization-aware trained (QAT) weights into several 4-bit and 8-bit formats and measures each one on the…
Harsh Prakash·Sep 24The Machine Learning Platform That’s Quietly Rewiring How Companies Build AIHello Again..
InLevel Up CodingbyGülden Bilgütay·Sep 11When Collaborative Filtering Has Nothing to Collaborate On: A SageMaker Fallback PatternCollaborative filtering has an attractive promise:
Miss Robot·Jul 19[AWS-AI] Amazon SageMaker Explained: From Data Preparation to Model DeploymentA beginner-friendly guide to building, training, tuning, and deploying Machine Learning models with AWS SageMaker.
InLoka EngineeringbyDidier·Jul 6Computer Vision at Scale on SageMaker Jobs: Four DecisionsTraining a vision model on millions of images is, more than anything, a data problem wearing an ML costume. The architecture can many times…A response icon1A response icon1
Hermes Herrera·Jun 13Shipping a Fine-Tuned 35B MoE Model to SageMaker Without Burning the Budget.Lessons from deploying a QLoRA-fine-tuned QWEN3.6–35B-A3B text-to-SQL model on a single-GPU endpoint.
![[AWS-AI] Amazon SageMaker Explained: From Data Preparation to Model Deployment](https://miro.medium.com/v2/resize:fill:160:106/1*uZD-xuHJFcsKKoaDlj4DDg.jpeg)
![[AWS-AI] Amazon SageMaker Explained: From Data Preparation to Model Deployment](https://miro.medium.com/v2/resize:fill:320:214/1*uZD-xuHJFcsKKoaDlj4DDg.jpeg)
