Method Drift›KV-cache compression
Superseded baseline#137 of 234 most-superseded
Elastic-Cache
Attention Is All You Need for KV Cache in Diffusion LLMsKV-cache compression · first seen Oct 16, 2025
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites Elastic-Cache as a baseline.
“although Fast-dLLM wu2025 and Elastic-Cache Tri2025 can provide certain acceleration benefits for short-text tasks, their throughput rapidly deteriorates as context length grows, often accompanied by further reductions in accuracy.”
— WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.