2 papers
cs.AR2026
FlashAccel: Leveraging High-Bandwidth Flash (HBF) for High-Throughput LLM Inference
Xinyu Wang, Yalong Xue, Xiaotian Sun +5
Large language model (LLM) inference is increasingly limited by the capacity of High-Bandwidth Memory (HBM) in GPUs, as model weights and KV cache grow rapidly. High-Bandwidth Flas…
physics.app-ph2018
Tetrahedral amorphous carbon resistive memories with graphene-based electrodes
A. K. Ott, C. Dou, U. Sassi +5
Resistive-switching memories are alternative to Si-based ones, which face scaling and high power consumption issues. Tetrahedral amorphous carbon (ta-C) shows reversible, non-volat…