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.
CRN

Violin Memory Unveils Cache Appliances For File-Based Data

Scalable memory array developer Violin Memory this week unveiled a new multiterabyte capacity solid-state cache memory system aimed at increasing the storage performance of enterprise applications.
Nature

Cache Performance and Memory Hierarchy Optimization

The dynamic interplay between processor speed and memory access times has rendered cache performance a critical determinant of computing efficiency. As modern systems increasingly rely on hierarchical ...
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.