← Back

Wire · technology

Exa boosts embedding throughput by 50% to index billions of documents on AWS AI chips

Published

18 November 2026

Topic

technology

◆ Sectors

AI & ML

◆ Geography

United States

◆ Source

Read at aws.amazon.com →

◆ Verified

Fusion42 · 19 November 2026 · Fusion42 review

Exa has optimized its semantic embedding infrastructure on AWS AI chips, boosting throughput by 50% for indexing tens of billions of documents. This improvement was achieved by refining model execution with AWS Inferentia2 and Trainium2 hardware alongside an agentic development workflow.

This Wire brief sits within Fusion42's coverage of AI & ML.

◆ ◆ The Wire takeaway

You must optimise your ML model inference to match Exa's new throughput gains on AWS AI chips or risk being cost-inefficient at scale. Hardware choices like Inferentia2 now deliver a tangible performance advantage that can cut embedding costs significantly.

◆ Coverage

1 source · 18 Nov 2026

◆ Related on Wire

◆ Topics

AI & MLembeddingawsinferentiatrainiumsemantic-searchthroughput