On May 19, Jin10 reported that Nvidia CEO Jen-Hsun Huang announced the launch of NVLink Fusion, a groundbreaking innovation aimed at enhancing enterprise AI infrastructure. It supports the use of various hardware, including Nvidia's GB200 and GB300 systems. NVLink Fusion is designed to support semi-custom AI infrastructure tailored to the unique needs of enterprises, going beyond traditional custom chips to accommodate diverse configurations—whether that involves more CPUs, Nvidia GPUs, or semi-custom ASICs. The complexity of building these systems has always been a challenge, and NVLink Fusion addresses a critical element that enterprises have been missing when creating advanced and scalable AI environments.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Jen-Hsun Huang: Launching NVLink Fusion to Empower Enterprises in Custom AI Systems
On May 19, Jin10 reported that Nvidia CEO Jen-Hsun Huang announced the launch of NVLink Fusion, a groundbreaking innovation aimed at enhancing enterprise AI infrastructure. It supports the use of various hardware, including Nvidia's GB200 and GB300 systems. NVLink Fusion is designed to support semi-custom AI infrastructure tailored to the unique needs of enterprises, going beyond traditional custom chips to accommodate diverse configurations—whether that involves more CPUs, Nvidia GPUs, or semi-custom ASICs. The complexity of building these systems has always been a challenge, and NVLink Fusion addresses a critical element that enterprises have been missing when creating advanced and scalable AI environments.