Reported by 2 outlets
The story so far
AI summary of the reporting below · Updated · How we work
Nvidia has quietly lowered published specifications for its next-generation Vera Rubin artificial intelligence computing architecture. Updated materials reveal reductions to listed HBM4 memory bandwidth by up to 26 percent alongside cutbacks to sixth-generation NVLink interconnect speeds across several configurations. [1][2]
The adjustments, noticed through comparisons of archived platform documents against current listings, were made without any public announcement. While Nvidia trimmed internal memory and NVLink interconnect throughput across setups such as the Vera Rubin NVL72, it simultaneously increased listed figures for scale-out networking bandwidth. [1][2]
A comparison of NVIDIA documents published in October with archived June material indicates that some listed Vera Rubin system bandwidth figures have changed. The reported revisions lower the listed HBM4 and NVLink bandwidth for several configurations, while increasing some networking figures.
via Guru3D
NVIDIA has quietly revised the specifications of its next-generation Vera Rubin AI computing platform, reducing HBM4 memory bandwidth and sixth-generation NVLink bandwidth across multiple configurations while increasing scale-out networking capabilities. Interestingly, the changes appear to have been made over a month ago, rather than being introduced recently.
via Wccftech