Artificial IntelligenceNewsProducts

KIOXIA AiSAQ Tech to Cut DRAM Needs in Gen AI Systems Goes Open Source

0

KIOXIA has announced the open-source release of its new All-in-Storage ANNS with Product Quantisation (AiSAQ) technology. A novel “approximate nearest neighbour” search (ANNS) algorithm optimised 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 computing, 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 utilises an ANNS algorithm, which identifies vectors that improve the model based on the 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:

  1. Allows large-scale databases to operate without relying on limited DRAM resources, enhancing the performance of RAG systems.
  2. 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.
  3. Optimised 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.

“The KIOXIA AiSAQ solution paves the way for almost infinite scaling of RAG applications in Generative AI Systems based on flash-based SSDs at the core,” said Axel Stoermann, Chief Technology Officer & VP at KIOXIA Europe GmbH. “Utilising SSD-based ANNS, we are reducing the reliance on costly DRAM while matching the performance needs of leading in-memory solutions – enhancing the performance range of large-scale RAG applications significantly.”

KIOXIA is demonstrating its commitment to advancing AI by contributing its innovative KIOXIA AiSAQ technology to the community as open-source software.

Prarthana Mary

Pure Storage and Micron Partner to Provide Scalable, Energy-Efficient Solutions for Hyperscale Data Centers

Previous article

Study: DeepSeek-R1 AI 11x Riskier for Harmful Content

Next article

You may also like

Comments

Comments are closed.