NVDA · News · 20261105N

Datacenter Networking / Supercluster

NVIDIA CORP · 2026-11-05 · Importance 34 · Surprise 42

Supermicro, IBM and NVIDIA launched a KV-cache storage solution combining Supermicro Petascale storage servers, IBM Storage Scale, NVIDIA Dynamo inference software and NVIDIA Spectrum-X Ethernet switches. The system demonstrated up to 56 times faster time-to-first-token for long-context prompts. The partners positioned the solution to improve GPU utilization, throughput and infrastructure scalability for agentic AI and long-context generative AI workloads.