Saturday, 10 May 2025
English 日本語
  • My Feed
  • My Interests
  • My Saves
  • History
  • Blog
Subscribe
NA ITbusinesstoday Logo
  • Home
  • APAC
    • Japan
    • ANZ
    • Indonesia
    • Philippines
    • Singapore
    • Taiwan
    • Vietnam
  • Regional
  • International
  • Quick Reads
  • Knowledge Hub
    • Guest Articles
    • Staff Writers
  • News
  • Japan
  • APAC
  • Regional
  • Tech
  • International
  • Industrial Tech
  • Fintech
  • Martech
  • Health Tech
  • IOT
  • GovTech
  • Realty
  • HR Tech
English 日本語
NA ITbusinesstoday Logo
  • Home
  • APAC
    • Japan
    • ANZ
    • Indonesia
    • Philippines
    • Singapore
    • Taiwan
    • Vietnam
  • Regional
  • International
  • Quick Reads
  • Knowledge Hub
    • Guest Articles
    • Staff Writers
  • Industrial Tech
  • Martech
  • IOT
  • Tech
  • Health Tech
  • HR Tech
  • News
  • Knowledge Hub
  • FinTech
  • Home
  • Regional
  • International
  • APAC
    • ANZ
    • Indonesia
    • Japan
    • Philippines
    • Singapore
    • Taiwan
    • Vietnam
  • Knowledge Hub
    • Guest Articles
    • Staff Writers
  • English
    • English
    • Japanese
Follow US
ITBusinessToday © 2025 | All Rights Reserved
itbusinesstoday > Blog > Tech > Computing > KIOXIA AiSAQ™ Tech to Cut DRAM in AI Systems Released Open Source
APACComputingJapanNewsRegionalTech

KIOXIA AiSAQ™ Tech to Cut DRAM in AI Systems Released Open Source

NewsDesk
Last updated: April 16, 2025 4:04 pm
NewsDesk
Share
KIOXIA AiSAQ
SHARE

Kioxia Corporation, a world leader in memory solutions, announced the open-source release of its new All-in-Storage ANNS with Product Quantization (AiSAQ) technology. A novel “approximate nearest neighbor” search (ANNS) algorithm optimized 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 compute, 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 utilizes an ANNS algorithm, which identifies vectors that improve the model based on 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:

  • Allows large-scale databases to operate without relying on limited DRAM resources, enhancing the performance of RAG systems.
  • 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.
  • Optimized 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.

SOURCE: Businesswire

TAGGED:ComputingcybersecurityitbusinesstodayKIOXIA AiSAQKioxia CorporationNews
Share This Article
Email Copy Link Print
Previous Article BrainPad BrainPad Forms Subsidiary to Develop AI Agents and Consulting
Next Article USEN Group USEN Group Company Establishes “Cyber ​​Security Lab” for Small and Medium-Sized Enterprises

Latest News

ITBusinessToday Weekly News RoundUp Mitsubishi, Sony, KDDI, NEC & More
May 9, 2025
Japanese AI Is Revolutionizing Media Editing for All
May 9, 2025
Mark AI Launches to Simplify SEO Content for Businesses
May 9, 2025
IBM Unveils Microsoft Unit to Boost Business Change
May 9, 2025
KDDI, NEC Launch Japan Cybersecurity Venture Protect.jp
May 9, 2025
Ad imageAd image

You Might Also Like

Futureverse
APACBlockchainFinTechJapanNewsRegional
Futureverse, Rakuten Wallet Launch Web3 Pass Platform

Futureverse, a leader in AI and metaverse technology, has officially launched RakutenWallet.Pass in partnership with Rakuten Wallet. Starting…

By
NewsDesk
Miroku Information Services
APACFinTechJapanNewsRegional
Miroku Adds “AI Report” to its DX platform, Hirameki 7

Miroku Information Services Co., Ltd., which develops and sells financial and accounting systems and management…

By
NewsDesk
Medmain
APACFinTechHealth TechInvestmentsJapanNewsRegional
Medmain Raises $3.3M, Backed by One Capital and Others

Medmain Inc., a Japanese medtech startup that offers PidPort, an AI-powered cloud system to assist…

By
NewsDesk
Omakase
APACBlockchainFinTechJapanNewsRegional
Omakase and Remixpoint Team Up on Validator Business

Omakase Inc. is pleased to announce that it will partner with Remixpoint Inc. regarding the…

By
NewsDesk
NA ITbusinesstoday Logo
Facebook Linkedin X-twitter

Latest B2B Tech News, Innovations, Trends, and Startup Insights from Japan and the APAC Region

Connect PR

Top Categories

  • Industrial Tech
  • HR Tech
  • Health Tech
  • IOT
  • Tech
  • Martech

Useful Links

  • Contact Us
  • Guest Writer
  • Submit Press Release
  • GDPR
  • Terms & Conditions

Anteriad Corporate Privacy

  • Privacy Charter
  • Privacy Center
  • Privacy Policy
  • Privacy Policy Japan
  • Do Not Sell My Personal Information
  • Cookie Fraud Prevention Policy
  • Transparency of Data

ITBusinessToday © 2025 | All Rights Reserved

Anteriad Logo

ITBusinessToday © 2025 | All Rights Reserved

Welcome Back!

Sign in to your account

Username or Email Address
Password

Lost your password?