Tom Coughlin is quite the busy man. A well- respected, well-known figure in the storage industry, he runs his own analyst and consulting firm, served as IEEE President in 2024, chairs the Future of Memory and Storage (FMS) conference, and regularly writes for Forbes.
In a recent Forbes article, Tom examined an AI software layer known as All-in-Storage ANNS with Product Quantization (AiSAQ). Developed as an open-source technology, KIOXIA AiSAQ is designed to scale vector databases in the retrieval-augmented generation (RAG) phase of AI.
Tom spoke with KIOXIA’s Rory Bolt to gain deeper insight into how AiSAQ works - and how it can reduce reliance on costly DRAM while enhancing AI accuracy.
Check out Tom’s article on Forbes.com here.
Notes:
All other company names, product names and service names may be trademarks of their respective companies.
KIOXIA AiSAQ: All-in-Storage ANNS with Product Quantization, a novel method of index data placement, is a trademark of KIOXIA.
Disclaimer
The views and opinions expressed in this blog are those of the author(s) and do not necessarily reflect those of KIOXIA America, Inc.