Google PM open-sources Always On Memory Agent, ditching vector databases for LLM-driven persistent memory

Enterprise AI teams are moving beyond single-turn assistants and into systems expected to remember preferences, preserve ...

New KV cache compaction technique cuts LLM memory 50x without accuracy loss

MIT researchers developed Attention Matching, a KV cache compaction technique that compresses LLM memory by 50x in seconds — ...
TMCnet

Nota AI Reduces Memory Usage of Upstage's Solar LLM by 72%, Demonstrating Proprietary Quantization Technology

Nota AI, an AI optimization technology company behind the Nota AI brand, announced that it has developed a next-generation quantization technology that significantly compresses the size of Solar, a ...

Memori Labs Launches Memori Cloud - The Fully Hosted SQL-Native Memory Layer for Production AI Agents

Memori Labs is the creator of the leading SQL-native memory layer for AI applications. Its open-source repository is one of the top-ranked memory systems on GitHub, with rapidly expanding developer ...
Morningstar

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 ...

SOCAMM2 Is The Memory Standard AI Is Looking For

AI infrastructure can't evolve as fast as model innovation. Memory architecture is one of the few levers capable of accelerating deployment cycles. Enter SOCAMM2 ...
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 ...
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 ...
Semiconductor Engineering

Dynamic KV Cache Scheduling in Heterogeneous Memory Systems for LLM Inference (Rensselaer Polytechnic Institute, IBM)

A new technical paper titled “Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System” was published by researchers at Rensselaer Polytechnic Institute and IBM. “Large ...
New Electronics

Rambus launches HBM4E controller IP for next‑generation AI memory performance

Rambus has introduced a new HBM4E Memory Controller IP, marking what the company describes as a major step forward in meeting ...
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 ...
XDA Developers on MSN

You're using your local LLM wrong if you're prompting it like a cloud LLM

Local models work best when you meet them halfway ...