Method Drift›KV-cache compression
Superseded baseline#104 of 234 most-superseded
dLLM-Cache
dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive CachingKV-cache compression · first seen May 17, 2025
superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating dLLM-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 dLLM-Cache · Throughput (TPS) [LLaDA-8B-Instruct]
3.4 vs 2.3
- Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
Sparse-dLLM (ours) beats dLLM-Cache · Throughput (TPS) [Dream-v0-7B-Instruct]
3.6 vs 1.2
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.