We’re excited to implement @NVIDIA's Dynamo to enhance our inference capabilities.

Processing hundreds of millions of requests demands exceptional performance and reliability. Dynamo will help us scale efficiently as our models advance. pic.twitter.com/Kk1e9W4xiA

— Perplexity (@perplexity_ai) 18 mars 2025

We’re excited to implement @NVIDIA
's Dynamo to enhance our inference capabilities. Processing hundreds of millions of requests demands exceptional performance and reliability. Dynamo will help us scale efficiently as our models advance.

→ View original post on X — @perplexity_ai,