CopyLoop: Fast Looped Transformer Decoding via Context Copying and Shallow Screening
arXiv:2610.38822v1 Announce Type: cross Abstract: Looped Transformers increase computational capacity through the repeated application of shared blocks, but their recurrent depth makes conventional full-depth decoding expensive. While existing speculative pipelines accelerate generation by processing consecutive token positions at varying depths, they are typically limited by sequential decoding overheads. We introduce CopyLoop, a training-free decoding algorithm that combines low-cost context-…