TensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models
arXiv:2604.17104v3 Announce Type: replace-cross Abstract: Modern model hubs store hundreds of petabytes of large language models (LLMs), with fine-tuned variants dominating the storage footprint. These variants contain substantial cross-model redundancy that delta compression can exploit by storing only the difference between a target and a reference model. However, compression effectiveness depends critically on choosing a similar reference. At model-hub scale, this is challenging because mode…