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.
IEEE

Learning-Aided Evolutionary Algorithm for Solving Energy-Minimized Deadline-Constrained Task Scheduling Problem in Human-Cyber-Physical Systems

Abstract: This work addresses an energy-minimized deadline-constrained task scheduling problem in human-cyber-physical systems. It consists of three subproblems: processor allocation, task sequencing, ...
IEEE

A Neural Network Model Based on Differential Evolution Algorithm for Traveling Salesman Problem

Abstract: This paper presents a novel neural network-based optimization framework, NNDE, to solve the traveling salesman problem (TSP). The core idea is to use a radial basis function network (RBFN) ...
SDxCentral

Broadcom says the memory shortage is a software problem, and VCF is the fix

The unprecedented memory shortage has caught IT leaders off guard amid skyrocketing hardware price as supply stretching out to 2027 has all but been gobbled up. But of all the firms looking to ...
Barron's

Qualcomm and Arm Stocks Drop. The Memory Crunch Is the Problem.

Qualcomm and Arm Holdings were sinking early Thursday as the surging memory-chip prices that are hurting the smartphone market threaten their prospects.