Tech Times on MSN

DeepSeek V4.1-Flash cuts agent memory costs fourfold with new architecture

DeepSeek V4.1-Flash, released September 10, cuts AI agent KV cache memory fourfold via four architectural techniques -- CED split, CSA2, FP4 quantization, and SWA elimination -- reducing per-token ...
Semiconductor Engineering

An Energy-Efficient DRAM Cache Architecture for Mobile Platforms With PCM-Based Main Memory

“A long battery life is a first-class design objective for mobile devices, and main memory accounts for a major portion of total energy consumption. Moreover, the energy consumption from memory is ...
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.
SiliconANGLE

New memory architecture targets AI inference bottlenecks

Lightbits Labs Ltd. today is introducing a new architecture aimed at addressing one of the most stubborn bottlenecks in large-scale artificial intelligence inference: the growing mismatch between the ...
HPCwire

Why Memory Pool Architectures Will Redefine KV Cache for AI Inference

The conversation surrounding AI infrastructure has correctly identified the key value (KV) cache as a critical bottleneck in scaling AI inference. As models push toward longer context windows and ...
techtarget

Cache vs. RAM: Differences between the two memory types

RAM and cache memory are both fast, volatile memory technologies that play a pivotal role in computing. So what's the key difference between the two? To borrow an adage from real estate: "Location, ...