- Kioxia reveals a new project called AiSAQ that wants to replace RAM with SSD for data processing with AI
- Larger SSDs (read: 100+ TB) could improve RAG at a lower cost than using memory alone
- No timeline has been given, but Kioxia’s rivals are expected to offer similar technology
Large language models often generate plausible but factually incorrect results; In other words, they invent things. These “hallucinations” can damage the reliability of critical reporting tasks such as medical diagnosis, legal analysis, financial reporting, and scientific research.
Recall Augmented Generation (RAG) mitigates this issue by integrating external data sources, allowing LLMs to access real-time information during generation, reduce errors, and, by basing results on current data, improve accuracy. contextual. Effective implementation of RAG requires significant memory and storage resources, and this is particularly true for large-scale vector data and indexes. Traditionally, this data has been stored in DRAM, which, while fast, is expensive and has limited capacity.
To address these challenges, serve the home reports that at this year’s CES, Japanese memory giant Kioxia introduced AiSAQ – Full Storage Approximate Nearest Neighbor Search (ANNS) with Product Quantization – which uses high-capacity SSDs to store indexes and vector data. Kioxia claims that AiSAQ significantly reduces DRAM usage compared to DiskANN, offering a more cost-effective and scalable approach to supporting large AI models.
More accessible and profitable
Switching to SSD-based storage makes it possible to handle larger data sets without the high costs associated with extensive use of DRAM.
While accessing data from SSD may introduce slight latency compared to DRAM, the trade-off includes lower system costs and better scalability, which can support better performance and model accuracy as larger data sets become available. Larger ones provide a richer basis for learning and inference.
By utilizing high-capacity SSDs, AiSAQ addresses RAG’s storage demands while contributing to the broader goal of making advanced AI technologies more accessible and cost-effective. Kioxia hasn’t revealed when it plans to bring AiSAQ to market, but it’s a safe bet that rivals like Micron and SK Hynix will have something similar in the works.
serve the home concludes: “Today everything is AI and Kioxia is also driving this. Realistically, RAG will be an important part of many applications, and if there is an application that needs to access a lot of data, but is not used as frequently, this would be a great opportunity for something like Kioxia AiSAQ.”
