cd /news/ai-infrastructure/exa-boosts-embedding-throughput-by-5… · home › topics › ai-infrastructure › article
[ARTICLE · art-172208] src=aws.amazon.com ↗ pub= topic=ai-infrastructure verified=true sentiment=↑ positive

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

Exa increased its embedding throughput by 50% to index billions of documents on AWS AI chips, according to AWS. The search company's indexing pipeline now runs on AWS's AI silicon, though the source provides no further technical detail on the chips or configuration used. The gain matters for Exa's ability to scale document indexing volume without a proportional increase in compute cost.

recommendation

Evaluate AWS AI chips for embedding workloads when indexing at scale; Exa reported 50% higher embedding throughput on them.

more in playbook: Inference and self-hosting
by read1 min views8 publishedNov 18, 2026
Exa boosts embedding throughput by 50% to index billions of documents on AWS AI chips
Image: AWS ML Blog

Search

AWS is the world's most comprehensive cloud, enabling organizations to accelerate innovation, reduce costs, and scale more efficiently

Migrate to modernize → Modernize to unlock data → unlock data to run AI

Get started with one of these featured services or browse all

From startups to enterprises, find AWS solutions scaled to your needs. Access tailored resources, pricing models, and support levels.

── more in #ai-infrastructure 4 stories · sorted by recency
── more on @exa 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/exa-boosts-embedding…] indexed:0 read:1min 2026-11-18 · —