Kioxia reveals new undertaking known as AiSAQ which needs to substitute RAM with SSDs for AI knowledge processing
Greater (learn: 100TB+) SSDs might enhance RAG at a decrease value than utilizing reminiscence solely
No timeline has been given, however count on Kioxia’s rivals to supply related tech
Massive language fashions usually generate believable however factually incorrect outputs – in different phrases, they make stuff up. These “hallucination”s can harm reliability in information-critical duties comparable to medical analysis, authorized evaluation, monetary reporting, and scientific analysis.
Retrieval-Augmented Era (RAG) mitigates this problem by integrating exterior knowledge sources, permitting LLMs to entry real-time info throughout technology, lowering errors, and, by grounding outputs in present knowledge, bettering contextual accuracy. Implementing RAG successfully requires substantial reminiscence and storage sources, and that is significantly true for large-scale vector knowledge and indices. Historically, this knowledge has been saved in DRAM, which, whereas quick, is each costly and restricted in capability.
To handle these challenges, ServeTheHome reviews that at this 12 months’s CES, Japanese reminiscence large Kioxia launched AiSAQ – All-in-Storage Approximate Nearest Neighbor Search (ANNS) with Product Quantization – that makes use of high-capacity SSDs to retailer vector knowledge and indices. Kioxia claims AiSAQ considerably reduces DRAM utilization in comparison with DiskANN, providing a less expensive and scalable strategy for supporting massive AI fashions.
Extra accessible and cost-effective
(Picture credit score: Kioxia)
Shifting to SSD-based storage permits for the dealing with of bigger datasets with out the excessive prices related to in depth DRAM use.
Whereas accessing knowledge from SSDs could introduce slight latency in comparison with DRAM, the trade-off contains decrease system prices and improved scalability, which might assist higher mannequin efficiency and accuracy as bigger datasets present a richer basis for studying and inference.
Through the use of high-capacity SSDs, AiSAQ addresses the storage calls for of RAG whereas contributing to the broader purpose of creating superior AI applied sciences extra accessible and cost-effective. Kioxia hasn’t revealed when it plans to deliver AiSAQ to market, however its secure to guess rivals like Micron and SK Hynix may have one thing related within the works.
ServeTheHome concludes, “Everything is AI these days, and Kioxia is pushing this as well. Realistically, RAG is going to be an important part of many applications, and if there is an application that needs to access lots of data, but it is not used as frequently, this would be a great opportunity for something like Kioxia AiSAQ.”
Extra from TechRadar Professional
