Back to AIBriefs
LaunchDevelopers

Perplexity AI unveils hybrid local-cloud inference system

The system, called the first hybrid local-server inference orchestrator, autonomously decides in real time which AI workloads run locally vs. in the cloud. Unveiled at Computex 2026, it aims to optimize performance and privacy.

·
8 days ago
Perplexity AI unveils hybrid local-cloud inference system — AIBriefs