NVIDIA NVLink Fusion Brings NVHBM to Next-Generation AI Infrastructure
NVIDIA NVLink Fusion enables NVHBM memory for custom XPU accelerators at hyperscale
NVIDIA is extending NVLink Fusion to bring its NVHBM memory technology to next-generation AI infrastructure, targeting hyperscalers and AI-native companies building custom accelerators. The move addresses the memory bandwidth bottleneck as AI models grow larger and reasoning workloads more complex. This positions NVIDIA as infrastructure for third-party XPUs, not just a chip vendor.