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

The research introduces a novel memory architecture called MSA (Memory Sparse Attention). Through a combination of the Memory ...

The dynamic interplay between processor speed and memory access times has rendered cache performance a critical determinant of computing efficiency. As modern systems increasingly rely on hierarchical ...

For the past few years, AI infrastructure has focused on compute above all other metrics. More accelerators, larger clusters and higher FLOPS drove the conversation to make the most of GPUs. This ...

A technical paper titled “HMComp: Extending Near-Memory Capacity using Compression in Hybrid Memory” was published by researchers at Chalmers University of Technology and ZeroPoint Technologies.

How lossless data compression can reduce memory and power requirements. How ZeroPoint’s compression technology differs from the competition. One can never have enough memory, and one way to get more ...

Accelerating memory-dependent AI processes, Penguin's MemoryAI KV cache server increases memory capacity by integrating 3 TB ...

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 ...

The latest Area-51 desktop from Alienware centers around AMD’s Ryzen 7 9800X3D, an 8-core processor with 104MB of total cache ...