KV-cache compression

dLLM-Cache

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

Superseded baseline#104 of 234 most-superseded · first seen May 17, 2025

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 1 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.