# Supermicro, IBM and NVIDIA put KV cache on shared storage and claim 56x faster first tokens > Source: > Published: 2026-11-05 14:44:52+00:00 # Supermicro, IBM and NVIDIA put KV cache on shared storage and claim 56x faster first tokens **Supermicro, IBM and NVIDIA say persistent KV cache on Petascale storage delivered up to 56x faster first tokens when long context was reused at 130,000-token prompts in joint testing.** By [RuntimeWire Staff](https://runtimewire.com/author/runtimewire-staff) · Published · Updated Primary source: [PR Newswire Business Technology](https://www.prnewswire.com/news-releases/supermicro-launches-kv-cache-solution-with-ibm-and-nvidia-demonstrating-significant-inference-performance-benefits-302928472.html) ## Why it matters Long-context and agentic workloads can require models to rebuild the same context again and again, using GPU cycles before the first token appears. A persistent, shared KV cache tier gives operators a way to reuse that work across requests and nodes, which can raise GPU utilization and concurrency without buying GPUs in proportion to context growth. Supermicro founder [Charles Liang (@charlesliang)](https://x.com/charlesliang?ref=runtimewire) is pushing his company deeper into the inference stack, this time with a storage system built to stop GPUs from redoing work they have already done. On November 5th, 2026, Supermicro announced a KV cache solution with IBM and NVIDIA that combines Supermicro Petascale all-flash storage servers, IBM Storage Scale software, NVIDIA Dynamo inference software and NVIDIA Spectrum-X Ethernet networking.… When you purchase through links in our articles, [we may earn a small commission](https://runtimewire.com/affiliate-monetization-standards). This doesn’t affect our editorial independence.