Kenhuangus SubstackChapter 5: Hardware-Aware Attention Kernels: FlashAttention-3, FlashDecoding & TPU Pallas6 minsTutorial
Towards AI (Medium)Fryday #8: 10 Agent Harnesses That Change What the Same Model Can Do10 minsResearch
Amazon EngineeringMonitoring production agent lifecycle with AWS DevOps Agent and AgentCore Evaluations5 minsAnalysis
Amazon EngineeringBeyond the price per token: Choosing the right OpenAI model on Amazon Bedrock for your workload5 minsAnalysis