1
PALS: Percentile-Aware Layerwise Sparsity for LLM Pruning
突破传统一刀切剪枝，PALS按每层百分位自适应稀疏度，精准提升大模型压缩效率。
arXiv:2607.07557v1 Announce Type: cross Abstract: One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a …