NVIDIA Extends Vera Rubin Inference System with Groq 3 LPX

NVIDIA announced the full production of the Groq 3 LPX and its integration with the Vera Rubin rack-scale system, enhancing token generation for agentic systems.

The Vera Rubin NVL72 system is designed for fast token generation.

Groq 3 LPX is now in full production.

The system aims to improve the efficiency and performance of AI inference.

Source: https://blogs.nvidia.com/blog/vera-rubin-lpx-spectrum-x-nvlink-fusion/