1
Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs
新型SVD压缩框架,利用反向信号影响度量引导低秩近似,在保持大模型功能的同时实现高效压缩。
arXiv:2606.19993v1 Announce Type: new Abstract: We present Activation- and Influence-Aware Ranks (AIR), an SVD-based LLM compression framework that gu…