The 172× Speedup Has an Evidence Budget
TL;DR for operators Prefilling-dLLM v21 demonstrates that a diffusion language model can learn to select distant context efficiently rather than repeatedly attending to every token. At 128K context, its per-generated-token decoding latency is approximately 172× lower than full dense attention, and it leads the tested sparse methods on three selected retrieval tasks. Yet its LongBench average is 25.4, below sliding-window attention at 30.9 and full dense attention at 44.3. ...