With Groq 3 LPX in Full Production, NVIDIA Extends Vera Rubin Inference for Agents

NVIDIA is expanding the capabilities of its Vera Rubin NVL72 system to support faster token generation for agentic AI applications. This update aims to improve how infrastructure components coordinate during complex, multi-step AI tasks. By focusing on inference speed within its broader factory architecture, the company seeks to enhance performance for autonomous agents that require low-latency processing.