KV-cache compression
dKV-Cache
dKV-Cache: The Cache for Diffusion Language Models
Superseded baseline#64 of 234 most-superseded · first seen May 21, 2025
Superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 2 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating dKV-Cache. Values are copied from the source paper's tables — verify against the cited paper.
Elastic-Cache beats dKV-Cache
53.6 vs 5.7
speedup vs baseline · [GSM8K 5-shot, 512 tokens]
Attention Is All You Need for KV Cache in Diffusion LLMs
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.