Tag

Pair

All articles tagged with #pair

technology8 days ago•6 min saved

Nvidia PAIR Turns Your Idle Computers Into a Private Home AI Network

Nvidia unveiled PAIR (Personal AI Router), free/open-source software that turns idle home devices—PCs, laptops, Macs—into a coordinated, private AI cluster. It acts as an intelligent traffic controller, breaking tasks into sub-tasks and routing them to capable machines across the local network for parallel processing. It doesn’t pool VRAM or split a single model; instead, it assigns complete tasks to individual devices, supporting cross‑platform hardware (GeForce GPUs, Apple silicon, DGX Spark) and Windows/macOS/Linux, with no cloud subscription and even offline operation after models are downloaded. The setup requires about 8GB RAM and 20GB+ disk per machine and aims to let households run local AI securely and privately, at the edge.

via PCMag|

#ai #edge-computing #home-data-center

technology9 days ago•3 min saved

Nvidia PAIR Extends AI Tasks Across Home PCs

Nvidia's PAIR (Personal AI Router) is a beta, open-source system that lets AI agents split tasks into subagents and run them on other PCs in a home network, speeding workloads while keeping everything local; it requires RTX-class GPUs on the primary system and is currently compatible with Ollama and LM Studio engines, supports Windows/Mac/Linux, uses mDNS for discovery and MTLS for security, and the orchestrator assigns subagents to available machines without pooling GPU resources—so best performance comes from leaving those devices powered on.

via CNET|

#ai #local-network #nvidia

technology9 days ago•8 min saved

NVIDIA PAIR Turns Idle Home PCs Into a Private AI Cluster, Cutting Cloud Inference Bills

NVIDIA unveils PAIR, a software router that distributes AI inference across devices on a home network to create a private, cloud-free AI cluster. It auto-discovers machines, uses secure MTLS, and proxies via Ollama and LM Studio, with cross-platform support (Windows, Linux, macOS) and an open-source Apache 2.0 beta release. By routing idle GPU/CPU workloads to available nodes and avoiding apps like gaming on busy machines, PAIR aims to reduce cloud API usage—statements suggest substantial savings (e.g., around $1,200/month in cloud credits for certain workloads)—while keeping data and prompts local. It does not merge VRAM or tensor-split models; instead it uses a queue-based scheduler for multi-agent workflows, multi-tasking, and system offload, with planned future enhancements.

via Wccftech|

#ai-inference #edge-computing #home-cluster

ai9 days ago•24 min saved

Nvidia’s PAIR stitches idle home PCs into a private AI data center

Nvidia unveils Personal AI Router (PAIR), open-source software that discovers compatible PCs on your home network, links idle machines with Nvidia GPUs, and coordinates parallel AI inference without interrupting other tasks; secured with six-digit pairing and mutual TLS, PAIR supports Windows, Linux, and macOS, with beta available today and integration options for local agent apps like Perplexity Portable Computer, Hermes Agent, and OpenClaw.

via theverge.com|

#ai #in-home-computing #local-ai-inference