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.

(CNW) MulticoreWare and Small Pixels Announce AI-Powered Integrated Video Optimization Solution to Dramatically Reduce Bandwidth and Infrastructure Costs

MulticoreWare, Inc., and Small Pixels today announced a strategic technology collaboration merging two powerful optimization solutions: MulticoreWare's Ultraziq and Small Pixels' SPAIQ Stream. The ...
IEEE

Hybrid-Smash: A Heterogeneous CPU-GPU Compression Library

Abstract: Compression algorithms are widely used to reduce data size and improve application performance. Nevertheless, data compression has a computational cost which can limit its use. GPUs could be ...
IEEE

Optimization and Performance Analysis of the SIREN Algorithm for Lossless Image Compression Across Various Medical Imaging Modalities

Abstract: Modern healthcare depends significantly on medical imaging technology which enables both patient diagnosis and medical treatment development and research activities. Efficient storage and ...
Tom's Hardware on MSN

Microsoft debuts DirectStorage 1.4 at GDC 2026, with Zstandard compression and GACL

DirectStorage 1.4 brings along key upgrades to the API, including support for Zstandard compression as well as CreatorID for ...