arXiv AI By Siva Rajesh Kasa, Yasong Dai, Sumit Negi, Hongdong Li

Fast-dLLM++: Fr\'echet Profile Decoding for Faster Diffusion LLM Inference

Read the original on arXiv AI →

arXiv:2606. 02955v3 Announce Type: replace-cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language
Sep 21

Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models

Ripple-Pivot Search (RPS) is a training‑free decoding method for Diffusion Large Language Models that identifies mid‑entropy pivot positions to reduce uncertainty across remaining masked tokens. By proactively committing these pivots and evaluating token assignments via lookahead, RPS enables more tokens to be unmasked in parallel, speeding up decoding. Experiments on three dLLMs and four reasoning/code‑generation benchmarks show 4–10× wall‑clock speedup over standard decoding, up to 18× with KV caching, while maintaining or improving generation quality.

By Yushi Ye, Xu Chen, Haoyun Jiang, Jinsong Lan, Haihong Tang, Xiangtao Li, Mingming Gong, Ivor Tsang, Yanfeng Wang, Jiangchao Yao