1
Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression
重新审视张量分解在LLM压缩中的核心作用，为后训练压缩提供新思路。
arXiv:2606.03465v1 Announce Type: cross Abstract: Post-training compression is essential for deploying large language models (LLMs) under tight resour…