Method Drift›KV-cache compression
Superseded baseline#64 of 234 most-superseded
dKV-Cache
dKV-Cache: The Cache for Diffusion Language ModelsKV-cache compression · 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superseded — cited as a baseline and beaten by newer methods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.
- Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
Sparse-dLLM (ours) beats dKV-Cache · Throughput (TPS) [LLaDA-8B-Instruct]
3.4 vs 1.4
- Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
Sparse-dLLM (ours) beats dKV-Cache · Throughput (TPS) [Dream-v0-7B-Instruct]
3.6 vs 1.4
- Attention Is All You Need for KV Cache in Diffusion LLMs
Elastic-Cache beats dKV-Cache · speedup vs baseline [GSM8K 5-shot, 512 tokens]
53.6 vs 5.7
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.