Tag

#Perplexity AI

4 articles

Perplexity AI Introduces Hybrid Local-Server Inference Orchestrator for Personal Computer: Automatic On-Device and Cloud Task Routing

Perplexity AI introduces a hybrid local-server inference orchestrator that automatically routes AI tasks between on-device and cloud models, enhancing both performance and privacy.

Jun 548

Perplexity built an “air-traffic controller” that decides in real time whether your AI query runs on your PC or in the cloud

Perplexity AI has introduced an intelligent system that dynamically splits AI workloads between local PCs and cloud servers, optimizing performance and cost.

Jun 259

tools

Perplexity AI Open-Sources Unigram Tokenizer That Achieves 5x Lower p50 Latency Than Hugging Face tokenizers Crate

Perplexity AI open-sources a new Unigram tokenizer that reduces p50 latency by 5x and cuts CPU utilization by 5-6x compared to Hugging Face tokenizers.

May 2853

Perplexity’s new Computer is another bet that users need many AI models

Perplexity AI introduces the Perplexity Computer, a unified system that combines multiple AI capabilities into one interface. The move reflects the industry's trend toward consolidating AI tools for enhanced user experience.

Feb 27136