KV-cache compression
Fast-dLLM
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Superseded baseline#49 of 234 most-superseded · first seen May 28, 2025
Superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 2 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites Fast-dLLM 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.
Beaten on benchmarks
Head-to-head results where a newer method reports beating Fast-dLLM. Values are copied from the source paper's tables — verify against the cited paper.
Elastic-Cache beats Fast-dLLM
45.1 vs 14.1
speedup vs baseline · [GSM8K 5-shot, 512 Gen Length, Confident-Aware Decoding]
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.