perspectiva aiqbenchCipuri & infrastructură
analiza aiqbench
This partnership leverages a disaggregated inference architecture where NVIDIA GPUs handle compute-bound prefill phases while SambaNova SN50 RDUs accelerate memory-bound decode phases, optimizing throughput for agentic AI workloads. By pairing these specialized accelerators, the solution improves efficiency and reduces latency without requiring high power-density racks, enabling scalable deployment in existing data centers.
1
Sursă care acoperăSambaNova
Supermicro Will Build and Sell SambaNova-Powered Inference Systems
SambaNova2 min de cititArticolul și perspectiva sunt în engleză.

De la SambaNova
FragmentSupermicro will integrate, validate, deliver, and support disaggregated inference systems that pair NVIDIA GPUs with SambaNova SN50 RDUs for agentic AI inference in data centers around the world. The systems will roll out in phases, beginning with an initial batch of 10,000 SN50 chips.
Extras afișat conform termenilor RSS ai publicației · 44 cuvinte · textul integral și figurile sunt pe site-ul publicației