Blog
Technical deep dives into GPU systems, AI infrastructure, LLM optimization, and vision model engineering.
Personal Blogs
Coming Soon
Deep dives on GPU inference internals, LLM performance tradeoffs, and the systems design decisions that shape modern AI workloads.
AWS Published Blogs
Meta SAM 2.1 is now available in Amazon SageMaker JumpStart
Overview of SAM 2.1 and how to run segmentation workflows in JumpStart.
Llama 4 family of models now available in SageMaker JumpStart
A breakdown of the Llama 4 model suite and deployment patterns.
Build a RAG-based QnA application using Llama 3
End-to-end RAG pipeline using embedding, retrieval, and Llama 3 inference.
Simple guide to training Llama 2 with AWS Trainium
How to train Llama 2 using Trainium chips on SageMaker at scale.
Vision use cases with Llama 3 2–11B and 90B models
Applying Llama 3 multimodal models for OCR, VQA, image reasoning, and more.
Advanced RAG patterns on Amazon SageMaker
Architectures for scalable and production-grade RAG pipelines.
Get started quickly with Trainium & Inferentia using Neuron DLAMI + DLC
Launch optimized Neuron environments for training and inference workloads.