KIOXIA AiSAQ Technology Designed to Reduce DRAM Requirements in Generative AI Systems Released as Open Source Software

 

SAN JOSE, Calif., January 28, 2025 –  KIOXIA today announced the open source release of its new All-in-Storage ANNS with Product Quantization (AiSAQ) technology. A novel "approximate nearest neighbor" search (ANNS) algorithm optimized for SSDs, KIOXIA AiSAQ™ software delivers scalable performance for retrieval-augmented generation (RAG) without placing index data in DRAM - and instead searching directly on SSDs.

Generative AI systems demand significant compute, memory, and storage resources. While they have the potential to drive transformative breakthroughs across various industries, their deployment often comes with high costs. RAG is a critical phase of AI that refines large language models (LLMs) with data specific to the company or application.

A central component of RAG is a vector database that accumulates and converts specific data into feature vectors in the database. RAG also utilizes an ANNS algorithm, which identifies vectors that improve the model based on similarity between the accumulated and target vectors. For RAG to be effective, it must rapidly retrieve the information most relevant to a query. Traditionally, ANNS algorithms are deployed in DRAM to achieve the high-speed performance required for these searches.

KIOXIA AiSAQ technology provides a scalable and efficient ANNS solution for billion-scale datasets with negligible memory usage and fast index switching capabilities.

Key Benefits of KIOXIA AiSAQ technology:

• Allows large-scale databases to operate without relying on limited DRAM resources, enhancing the performance of RAG systems.
• Eliminates the need to load index data into DRAM, enabling the vector database to launch instantly. This supports seamless switching between user-specific or application-specific databases on the same server for efficient RAG service delivery.
• Optimized for cloud systems by storing indexes in disaggregated storage for sharing across multiple servers. This approach dynamically adjusts vector database search performance for specific users or applications and facilitates the rapid migration of search instances between physical servers.

“Our AiSAQ solution unlocks the potential for RAG applications by enabling nearly limitless scalability with flash-based SSDs,” said Neville Ichhaporia, senior vice president and general manager of the SSD business unit at KIOXIA America, Inc. “KIOXIA has further optimized SSD-based ANNS to deliver performance comparable to leading in-memory solutions while using a fraction of expensive DRAM—making large-scale RAG applications more accessible than ever.”

KIOXIA is demonstrating its commitment to advancing AI by contributing its innovative KIOXIA AiSAQ technology to the community as open source software. For more information, please visit www.kioxia.com, and follow the company on X, formerly known as Twitter and LinkedIn^®.  

About KIOXIA America, Inc.

KIOXIA America, Inc. is the U.S.-based subsidiary of KIOXIA Corporation, a leading worldwide supplier of flash memory and solid-state drives (SSDs). From the invention of flash memory to today’s breakthrough BiCS FLASH™ 3D technology, KIOXIA continues to pioneer innovative memory, SSD and software solutions that enrich people's lives and expand society's horizons. The company's innovative 3D flash memory technology, BiCS FLASH, is shaping the future of storage in high-density applications, including advanced smartphones, PCs, automotive systems, data centers and generative AI systems. For more information, please visit KIOXIA.com.

Notes:

KIOXIA AiSAQ: All-in-Storage ANNS with Product Quantization, a novel method of index data placement, is a trademark of KIOXIA Corporation.

LinkedIn is a trademark of LinkedIn Corporation and its affiliates in the United States and/or other countries.

All other company names, product names and service names may be trademarks of third-party companies.

Information in this press release, including product pricing and specifications, content of services, and contact information is current and believed to be accurate on the date of the announcement, but is subject to change without prior notice. Technical and application information contained here is subject to the most recent applicable KIOXIA product specifications.