Across WittyWires

Trending

Explore up to 50 current developments and conversations across WittyWires, ranked by momentum.

Exa Inferentia2 Optimization

Showing 1 relevant Discussions and stories, newest first

Forum story or discussion

Exa says AWS AI-chip tuning cut embedding costs by 47%

Exa says it improved the performance and cost of embedding one million documents by 47% on AWS Inferentia2, after tuning the model and writing custom kernels. The result offers a useful, concrete look at how AI infrastructure costs can be c

Open discussion →