2 papers
cs.LG2025
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models
Yuhan Kang, Yang Shi, Mei We +5
Post-training pruning, as one of the key techniques for compressing large language models, plays a vital role in lightweight model deployment and model sparsity. However, current m…
cs.AR2022
BP-Im2col: Implicit Im2col Supporting AI Backpropagation on Systolic Arrays
Jianchao Yang, Mei Wen, Junzhong Shen +5
State-of-the-art systolic array-based accelerators adopt the traditional im2col algorithm to accelerate the inference of convolutional layers. However, traditional im2col cannot ef…