Local Ai
NVIDIA PAIR Virtual Inference Router Expands Available Compute on Your Local Network
NVIDIA’s PAIR Virtual Inference Router distributes AI inference requests across multiple local machines—supporting Ollama and LM Studio without any agent or harness changes—to mitigate multi‑agent bot
NVIDIA’s PAIR Virtual Inference Router distributes AI inference requests across multiple local machines—supporting Ollama and LM Studio without any agent or harness changes—to mitigate multi‑agent bottlenecks. It runs on NVIDIA GeForce RTX 20 Series, RTX PRO workstations, DGX Spark, and Apple M4+ silicon; a five‑subagent demo completed a workload in 8 min 48 s versus 18 min on a single laptop. The open‑source beta (available for Windows, macOS, Linux) uses mDNS discovery, MTLS encryption, and live GPU‑utilization scheduling to securely pair nodes and balance load across the cluster.
Related
- Use the Same Model Across Ollama, LM Studio, Jan, and your Favorite Local AI Apps
- Run @NousResearch's Hermes Agent fully locally on DGX Spark. 🚀 Our newest playbook shows you how to get set up via @Ollama step by step. 👇
Source: NVIDIA Developer | 2026-09-03