4 papers
Parameter Efficient Machine Unlearning on Hybrid Resistive Memory based Compute-in-Memory Accelerators
Ning Lin, Jichang Yang, Yangu He +17
Resistive memory compute-in-memory accelerators provide energy efficient analogue matrix vector multiplication for neural network inference, but frequent reprogramming of analogue…
Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks
Tian Zhang, Yujia Tong, Junhao Dong +3
The deployment of quantized neural networks on edge devices, combined with privacy regulations like GDPR, creates an urgent need for machine unlearning in quantized models. However…
QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching
Ke Xu, Yixin Wang, Zhongcheng Li +3
Elastic precision quantization enables multi-bit deployment via a single optimization pass, fitting diverse quantization scenarios.Yet, the high storage and optimization costs asso…
Serving Large Language Models on Huawei CloudMatrix384
Pengfei Zuo, Huimin Lin, Junbo Deng +43
The rapid evolution of large language models (LLMs), driven by growing parameter scales, adoption of mixture-of-experts (MoE) architectures, and expanding context lengths, imposes…