COSPADI: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
"LLM压缩" 相关文章
COSPADI: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
Optimize open LLMs using GPTQ and Hugging Face Optimum
Less is More: Selective Reflection for Compatible and Efficient Knowledge Distillation in Large Language Models
From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction
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
