1
UniRank: Unified Rank Allocation for Low-Rank LLM Compression
提出统一秩分配方法,突破低秩分解压缩LLM的瓶颈,兼顾效率与性能。
arXiv:2606.21847v1 Announce Type: cross Abstract: Low-rank decomposition serves as a promising compression paradigm for large language models, however…