activation-reuse

Tag

Cards List
#activation-reuse

DARE: Diffusion Language Model Activation Reuse for Efficient Inference

arXiv cs.LG · 2026-05-12 Cached

This paper introduces DARE, a method for improving the inference efficiency of Diffusion Large Language Models by reusing cached key-value and output activations to reduce computational redundancy with negligible quality loss.

0 favorites 0 likes
← Back to home

Submit Feedback