DeepSeek's DSpark just made Nvidia's most important new bet harder to close

DeepSeek just released DSpark, an inference module that makes its AI models 60% to 85% faster without new hardware. Nvidia is ...
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 ...
InfoQ

Google’s TurboQuant Compression May Support Faster Inference, Same Accuracy on Less Capable Hardware

Google Research unveiled TurboQuant, a novel quantization algorithm that compresses large language models’ Key-Value caches by up to 6x. With 3.5-bit compression, near-zero accuracy loss, and no ...
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 ...
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, ...