Perplexity AI unveils hybrid local-cloud inference system at Computex 2026

Perplexity AI has introduced a hybrid inference system that routes AI queries between on-device models and server-based models. The system, described as an “air-traffic controller,” decides in real time whether a task runs locally on a PC or in the cloud. The feature is part of a broader move toward hybrid local-cloud AI processing.

本文综合以下全部报道写成，而非依据任何单一来源。