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 ...
VentureBeat

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

Enterprise AI applications that handle large documents or long-horizon tasks face a severe memory bottleneck. As the context grows longer, so does the KV cache, the area where the model’s working ...
EDN

MRAM technologies: from space applications to unified cache memory?

Magneto-resistive random access memory (MRAM) is a non-volatile memory technology that relies on the (relative) magnetization state of two ferromagnetic layers to store binary information. Throughout ...
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

Adaptive RISC-V Cache Architecture for Near-Memory Extensions (Politecnico di Torino, EPFL)

A new technical paper titled “ARCANE: Adaptive RISC-V Cache Architecture for Near-memory Extensions” was published by researchers at Politecnico di Torino and EPFL. Abstract “Modern data-driven ...
TechSpot

AMD 3D V-Cache CPU memory used to create incredibly fast RAM disk

Why it matters: A RAM drive is traditionally conceived as a block of volatile memory "formatted" to be used as a secondary storage disk drive. RAM disks are extremely fast compared to HDDs or even ...
EDN

SoC design: When a network-on-chip meets cache coherency

Many people have heard the term cache coherency without fully understanding the considerations in the context of system-on-chip (SoC) devices, especially those using a network-on-chip (NoC). To ...