AI
8.0
Exa boosts embedding throughput by 50% to index billions of documents on AWS AI chips
Exa optimized its embedding infrastructure on AWS Neuron hardware (Inferentia2 and Trainium2) to achieve 50% throughput gains for indexing billions of web documents. The company used agentic development workflows to drive cost-per-document improvements critical at web-scale, running inference on asynchronous pipelines to serve recent data quickly for semantic search and agent grounding.
Read article →