Paper notes · NeurIPS 2025
dKV-Cache: The Cache for Diffusion Language Models
A KV cache for masked diffusion that does not need semi-autoregressive blocks. The observation: a token’s keys and values jump when it goes from [MASK] to decoded, then barely move. So cache decoded tokens only, one step after they are decoded, keep recomputing the masked ones, and refresh everything every few steps.
§3.3 step by step: one answer token is decoded per step, in a non-sequential order. Switch the options to compare caching at once against one step late, and Decode against PD.
cache a decoded token
refresh
prompt at refresh
Loading PDF… open it directly
PDF reproduced unmodified under CC BY 4.0. Highlights and notes are mine.