Hosted on MSN

Google says TurboQuant cuts LLM KV-cache memory use 6x, boosts speed

Google researchers have published a new quantization technique called TurboQuant that compresses the key-value (KV) cache in large language models to 3.5 bits per channel, cutting memory consumption ...
Vietnam Investment Review on MSN

Dnotitia's STAR KV cuts KV cache by up to 20x earns ICML 2026 spotlight selection

SEOUL, South Korea, July 2, 2026 /PRNewswire/ -- Dnotitia Inc. (Dnotitia), a company specializing in long-term memory AI and semiconductor-based AI infrastructure technologies, has released the paper ...
Business Wire

Penguin Solutions Introduces Industry's First Production-Ready CXL-Based KV Cache Server

FREMONT, Calif.--(BUSINESS WIRE)--Penguin Solutions, Inc. (Nasdaq: PENG), the AI factory platform company, today announced the industry's first production-ready KV cache server that utilizes CXL ...
VentureBeat

Nvidia says it can shrink LLM memory 20x without changing model weights

Nvidia researchers have introduced a new technique that dramatically reduces how much memory large language models need to track conversation history — by as much as 20x — without modifying the 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 ...
SDxCentral

DDN, Google Cloud claim Lustre KV cache trick boosts AI inference throughput 75%

DDN added new capabilities to the Lustre platform it manages with Google Cloud, including means to share key-value (KV) cache to boost AI inference workloads. Unveiled at Google’s annual Next event, ...