EV charging firm Xeal plans to deploy 100,000 Nvidia GPUs for edge inference network

EV charging firm Xeal plans to deploy over 100,000 NVIDIA GPUs across its existing U.S. network to create what it calls the “world’s first edge inference compute network using idle EV charging capacity.” The initiative leverages the company's current footprint of 1,600+ locations and 200MW of permitted, installed electrical infrastructure.

To facilitate this deployment, Xeal has developed Laitent Pods, specialized hardware units designed to house the compute resources. Each pod contains up to 48 Nvidia Hopper or Blackwell Ultra GPUs, allowing the company to repurpose idle electrical capacity at charging sites for AI inference workloads.