arXiv NLP
techCenter
Affix Cache for Diffusion Large Language Modelstranslating…
1 min readUnknownarXiv Press Group
arXiv:2608.26140v1 Announce Type: new
Abstract: Diffusion Large Language Models (DLLMs) enable non-autoregressive decoding and bidirectional context modeling, but efficient inference remains challenging. Unlike autoregressive systems, whose key-value (KV) cache can be reused…