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 — without the hours of GPU training that prior methods required.

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

Nvidia's KV Cache Transform Coding (KVTC) compresses LLM key-value cache by 20x without model changes, cutting GPU memory ...
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 ...
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 ...