Kioxia Integrates AiSAQ Into Milvus Vector Database
Kioxia Corporation announced that its AiSAQ approximate nearest neighbor search (ANNS) technology has been integrated into the open-source vector database Milvus, starting with version 2.6.4. The integration enables SSD-optimized vector search that sharply reduces DRAM requirements for Retrieval-Augmented Generation (RAG) and high-volume inference. Developers and enterprises can now scale vector search cost-effectively by storing RAG-related data on SSDs.
Key Points
- 1Integrates AiSAQ into Milvus 2.6.4, enabling SSD-optimized approximate nearest-neighbor search for vectors
- 2Reduces DRAM requirements for RAG and high-volume inference, addressing memory scalability bottlenecks
- 3Allows developers and enterprises to scale vector search cost-effectively using SSDs instead of large DRAM
Scoring Rationale
Official open-source Milvus integration enables practical SSD-based scaling for RAG, limited by incremental novelty over earlier AiSAQ announcement.
Sources
Public references used for this report.
Practice with real FinTech & Trading data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all FinTech & Trading problems
