KIOXIA AiSAQ Technology To Enhance AI Retrieval Performance Without DRAM Dependency
KUALA LUMPUR, Feb 3 (Bernama) -- Kioxia Corporation, a world leader in memory solutions, has announced the open-source release of its new All-in-Storage ANNS with Product Quantization (AiSAQ) technology.
A novel "approximate nearest neighbour" search (ANNS) algorithm optimised for solid-state drives (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 artificial intelligence (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.
Meanwhile, 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. It also utilises an ANNS algorithm, which identifies vectors that improve the model based on similarity between the accumulated and target vectors.
KIOXIA AiSAQ technology provides a scalable and efficient ANNS solution for billion-scale datasets with negligible memory usage and fast index switching capabilities with key benefits, including allowing large-scale databases to operate without relying on limited DRAM resources, enhancing the performance of RAG systems.
In addition, the technology eliminates the need to load index data into DRAM, enabling the vector database to launch instantly, while also optimising for cloud systems by storing indexes in disaggregated storage for sharing across multiple servers.
Kioxia is demonstrating its commitment to advancing AI by contributing its innovative KIOXIA AiSAQ technology to the community as open-source software.
-- BERNAMA