Ars Technica

Google’s TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x

Even if you don’t know much about the inner workings of generative AI models, you probably know they need a lot of memory. Hence, it is currently almost impossible to buy a measly stick of RAM without ...

Microsoft PC Manager: Why high RAM usage isn't always a problem

Windows 11 loves using available RAM, but knowing when high memory usage is normal and when it's a warning sign makes all the ...

I found which apps were destroying my phone's memory; the culprits shocked me

I saved hundreds of megabytes of space ...
VentureBeat

Huawei's new open source technique shrinks LLMs to make them run on less powerful, less expensive hardware

Huawei’s Computing Systems Lab in Zurich has introduced a new open-source quantization method for large language models (LLMs) aimed at reducing memory demands without sacrificing output quality.
The Verge

Google’s TurboQuant algorithm aims to slash AI memory usage.

The compression algorithm works by shrinking the data stored by large language models, with Google’s research finding that it can reduce memory usage by at least six times “with zero accuracy loss.” ...
Semiconductor Engineering

Pooling CPU Memory for LLM Inference With Lower Latency and Higher Throughput (UC Berkeley)

“The rapid growth of LLMs has revolutionized natural language processing and AI analysis, but their increasing size and memory demands present significant challenges. A common solution is to spill ...
EurekAlert!

SeoulTech scientists develop ultra-lightweight memory manager that transforms embedded system performance

The lightweight allocator demonstrates 53% faster execution times and requires 23% lower memory usage, while needing only 530 lines of code. Embedded systems such as Internet of Things (IoT) devices ...