Integration Natively Extends Vector Index Scalability While Minimizing DRAM Footprint Within Industry Leading Open-Source Database

Kioxia America, Inc. today announced that its AiSAQ™ approximate nearest neighbor search (ANNS) software technology has been integrated into Milvus (starting with version 2.6.4), among the world’s most widely adopted open-source vector databases, created by Zilliz. This integration with Milvus gives developers and enterprises an easy, practical path to scaling AI applications without facing prohibitive memory costs.

As organizations adopt larger AI models and develop increasingly complex Retrieval Augmented Generation (RAG) pipelines, vector databases are challenged to keep pace with rapid growth in RAG and inference demands due to DRAM scalability constraints. By dramatically reducing DRAM requirements and enabling high-quality vector search, AiSAQ technology makes large-scale RAG deployments more accessible, more affordable, and easier to scale.

Milvus is the leading open-source vector database to power AI search, agentic systems, RAG, and multimodal workloads. As organizations increasingly rely on vector databases as core AI infrastructure - and scale to billions or even trillions of embeddings - DRAM cost has emerged as a major barrier to growth. With native KIOXIA AiSAQ technology integration, Milvus now supports SSD-optimized vector indexing, dramatically reducing memory usage while preserving high-quality search performance. This provides enterprises with a more cost-efficient path to scaling retrieval pipelines as embedding volumes grow.

“KIOXIA’s AiSAQ integration expands the range of indexing options available within Milvus and gives Milvus users another powerful way to scale AI retrieval cost-effectively,” said James Luan, VP of Engineering at Zilliz. “As AI workloads grow to an extremely large number of embeddings, optimizing memory cost becomes essential. AiSAQ further enhances the support of SSD-optimized vector search in the Milvus ecosystem, enabling developers to scale their AI applications and retrieval pipelines.”

First announced early this year, KIOXIA’s AiSAQ open-source software technology increases vector scalability by storing all RAG database elements on SSDs. It provides tuning options to prioritize either performance or high-volume vector scalability. Kioxia continues to advance AiSAQ to trillion-vector scale.

“AI is shifting from building massive foundation models to deploying scalable, cost-effective inference solutions that solve real-world problems,” said Rory Bolt, Sr. Fellow, Software, Kioxia America, Inc. “RAG is central to that shift, and AiSAQ was created to help the community take full advantage of SSD-based vector architectures. The integration with Milvus strengthens the open-source ecosystem and supports developers working to build faster, more efficient AI applications.”

Link to download KIOXIA AiSAQ open-source software: https://github.com/kioxia-jp/aisaq-diskann

Learn how Milvus integrates with AiSAQ: https://milvus.io/docs/aisaq.md

Learn more about and try Milvus: https://milvus.io/

For more information, please visit www.kioxia.com, and follow the company on X 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.

© 2025 KIOXIA America, Inc. All rights reserved. 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.

Notes:

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

https://www.kioxia.com/en-jp/business/news/2025/20250128-1.html

Development of Image Classification System Deploying Memory-Centric AI with High-capacity Storage https://www.kioxia.com/en-jp/rd/technology/topics/topics-39.html

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

View source version on businesswire.com: https://www.businesswire.com/news/home/20251216556818/en/

KIOXIA’s AiSAQ integration expands the range of indexing options available within Milvus and gives Milvus users another powerful way to scale AI retrieval cost-effectively.