KIOXIA's groundbreaking AiSAQ Technology now available in leading open-source vector database

KIOXIA's open-source AiSAQ (All-in-Storage ANNS with Product Quantization) has been a game-changer for running complex AI models by offloading vectorized data from expensive DRAM to SSD storage. With memory limitations and costs playing a significant role in which AI workloads can or cannot run, AiSAQ delivers a low-latency, scalable solution for Retrieval Augmented Generation (RAG) pipelines.

2

This week, KIOXIA announced that AiSAQ has been integrated into Milvus, one of the world's most widely adopted open-source vector databases. Starting with version 2.6.4, AI developers and enterprises can tap into the power of AiSAQ to scale AI applications with SSD storage. With the growth in RAG demands and the size of vector databases for inference, scaling DRAM is often not an option due to the exponential increase in cost.

KIOXIA's open-source AiSAQ is groundbreaking because it dramatically reduces DRAM requirements for running complex AI workloads, opening the door to large-scale system deployment that's more affordable and easier to scale, thanks to large capacity and fast SSD storage.

And with Milvus widely used in AI search, agentic systems, and multimodal workloads, KIOXIA AiSAQ technology integration brings SSD-optimized vector indexing to a broader audience.

"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."

"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."

KIOXIA AiSAQ open-source software is also available for download at GitHub.