DeepSeek’s conditional memory fixes silent LLM waste: GPU cycles lost to static lookups

Through systematic experiments DeepSeek found the optimal balance between computation and memory with 75% of sparse model ...
Business Wire

Enfabrica Unveils Industry’s First Ethernet-Based AI Memory Fabric System for Efficient Superscaling of LLM Inference

MOUNTAIN VIEW, Calif.--(BUSINESS WIRE)--Enfabrica Corporation, an industry leader in high-performance networking silicon for artificial intelligence (AI) and accelerated computing, today announced the ...
Semiconductor Engineering

HW-based Heterogeneous Memory Management for LLM Inferencing (KAIST, Stanford Unversity)

A new technical paper titled “Hardware-based Heterogeneous Memory Management for Large Language Model Inference” was published by researchers at KAIST and Stanford University. “A large language model ...
InfoWorld

Mem0: An open-source memory layer for LLM applications and AI agents

Combining an innovative hybrid data store and intelligent retrieval, Mem0 provides a robust foundation for building personalized AI experiences that improve over time. The stateless nature of large ...
Semiconductor Engineering

Pooling CPU Memory for LLM Inference With Lower Latency and Higher Throughput (UC Berkeley)

“The rapid growth of LLMs has revolutionized natural language processing and AI analysis, but their increasing size and memory demands present significant challenges. A common solution is to spill ...
manilatimes

EverMemOS Redefines Efficiency in AI Memory, Surpassing LLM Full-Context Perfomances with Far Fewer Tokens in Open Evaluation

The evaluation framework was developed to address a critical bottleneck in the AI industry: the absence of consistent, transparent methods to measure memory quality. Today's agents rely on a ...
InfoWorld

Unlocking LLM superpowers: How PagedAttention helps the memory maze

Large language models (LLMs) like GPT and PaLM are transforming how we work and interact, powering everything from programming assistants to universal chatbots. But here’s the catch: running these ...
EurekAlert!

SNU researchers develop AI technology that compresses LLM chatbot ‘conversation memory’ by 3–4 times

In long conversations, chatbots generate large “conversation memories” (KV). KVzip selectively retains only the information useful for any future question, autonomously verifying and compressing its ...
VentureBeat

This new framework lets LLM agents learn from experience, no fine-tuning required

A new learning paradigm developed by University College London (UCL) and Huawei Noah’s Ark Lab enables large language model (LLM) agents to dynamically adapt to their environment without fine-tuning ...