Nvidia’s new technique cuts LLM reasoning costs by 8x without losing accuracy

Nvidia researchers developed dynamic memory sparsification (DMS), a technique that compresses the KV cache in large language models by up to 8x while maintaining reasoning accuracy — and it can be ...

'Observational memory' cuts AI agent costs 10x and outscores RAG on long-context benchmarks

As AI agents move into production, teams are rethinking memory. Mastra’s open-source observational memory shows how stable ...
TechCrunch

ZeroPoint’s nanosecond-scale memory compression could tame power-hungry AI infrastructure

AI is only the latest and hungriest market for high-performance computing, and system architects are working around the clock to wring every drop of performance out of every watt. Swedish startup ...
Neowin

New compression tech vows "2-3x memory expansion" so you don't need to "Download More RAM"25 25

ZeroPoint Technology AB, a Swedish startup, has developed a new general-purpose memory compression technology called "Ziptilion" which the company claims can help system memory perform equivalent to ...