TMCnet

Breaking the 100M Token Limit: EverMind's MSA Architecture Achieves Efficient End-to-End Long-Term Memory for LLMs

This approach can be viewed as a memory plug-in for large models, providing a fresh perspective and direction for solving the ...

Nvidia shrinks 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.

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 — ...
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.
Seeking Alpha

ZeroPoint Technologies Unveils Groundbreaking Compression Solution to Increase Foundational Model Addressable Memory by 50%

GOTHENBURG, Sweden, Feb. 20, 2025 /PRNewswire/ -- ZeroPoint Technologies AB today announced a breakthrough hardware-accelerated memory optimization product that enables the nearly instantaneous ...
TechSpot

Startup aims to tackle AI bottlenecks with novel memory compression techniques

Forward-looking: It's no secret that generative AI demands staggering computational power and memory bandwidth, making it a costly endeavor that only the wealthiest players can afford to compete in.
Nature

Video Compression Algorithms and Memory Efficiency

Video compression has become an essential technology to meet the burgeoning demand for high‐resolution content while maintaining manageable file sizes and transmission speeds. Recent advances in ...