Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models

N Leroux, PP Manea, C Sudarshan… - arxiv preprint arxiv …, 2024 - arxiv.org
Transformer neural networks, driven by self-attention mechanisms, are core components of
foundational and Large Language Models. In generative transformers, self-attention uses …

Differential Phase Change Memory (PCM) Cell for Drift-Compensated In-Memory Computing

L Pistolesi, L Ravelli, A Glukhov… - … on Electron Devices, 2024 - ieeexplore.ieee.org
Phase change memory (PCM) is a scalable, reliable, and robust technology for embedded
and stand-alone memory device. PCM has also been extensively demonstrated for analog …