New KV cache compaction technique cuts LLM memory 50x without accuracy loss

MIT researchers developed Attention Matching, a KV cache compaction technique that compresses LLM memory by 50x in seconds — ...

Nvidia says it can shrink LLM memory 20x without changing model weights

Nvidia's KV Cache Transform Coding (KVTC) compresses LLM key-value cache by 20x without model changes, cutting GPU memory costs and time-to-first-token by up to 8x for multi-turn AI applications.
Hosted on MSN

Windows 11's memory compression is often overlooked, but you might want to enable it

Windows 11 has a habit of doing things quietly in the background and then getting blamed for them later. Memory compression is one of those features. It sounds like a gimmick and immediately gets ...
TechCrunch

ZeroPoint’s nanosecond-scale memory compression could tame power-hungry AI infrastructure

AI is only the latest and hungriest market for high-performance computing, and system architects are working around the clock to wring every drop of performance out of every watt. Swedish startup ...
Semiconductor Engineering

Freeing Up Near-Memory Capacity For Cache Using Compression Techniques In A Flat Hybrid-Memory Architecture

A technical paper titled “HMComp: Extending Near-Memory Capacity using Compression in Hybrid Memory” was published by researchers at Chalmers University of Technology and ZeroPoint Technologies.