From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction
"LLM压缩" 相关文章
70% 大小，100% 准确！完美压缩 LLM 性能 0 损失，推理速度最高飙升 39 倍
SeedLM: A Post-Training Compression Method that Uses Pseudo-Random Generators to Efficiently Encode and Compress LLM Weights
