The paper introduces self‑orchestrating language models that annotate semantic dependence—identifying which tokens rely on others—to guide efficient inference. By leveraging these annotations, the authors design runtimes that parallelize autoregressive decoding, evict intermediate context, or determine denoising orders, achieving Pareto‑optimal quality‑efficiency trade‑offs. Three systems—PASTA, TIP, and Planned Diffusion—demonstrate these techniques for parallel decoding, memory‑efficient reasoning, and efficient discrete diffusion, respectively.
By Tian Jin
arXiv:2509.11252v3 Announce Type: replace-cross
Abstract: LLMs have become the mainstream approaches to code generation. Existing LLMs mainly employ autoregressive generation, i.e. generating code to...
By Chengze Li, Yitong Zhang, Jia Li, Liyi Cai, Ge Li
arXiv:2607. 12829v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models.
By Daehoon Gwak, Minhyung Lee, Junwoo Park, Jaegul Choo
Flash-dLLM is a training‑free inference acceleration framework that improves the speed and memory efficiency of Diffusion Large Language Models (dLLMs). It tackles GPU memory I/O bottlenecks by introducing an I/O‑aware fused KV‑cache kernel and then employs a draft‑and‑verify decoding strategy that uses the dLLM itself as both drafter and verifier. Experiments on mathematical reasoning and code‑generation tasks show Flash‑dLLM outperforms existing acceleration methods, achieving up to 11.0× speedups over the Elastic‑Cache baseline.
By Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen
arXiv:2606. 29215v1 Announce Type: new Abstract: Block Diffusion Language Models (BD-LMs) improve diffusion-based text generation with KV caching and flexible-length generation.
By Yijie Jin, Jiajun Xu, Yuxuan Liu, Chenkai Xu, Yi Tu, Jiajun Li, Dandan Tu, Xiaohui Yan, Kai Yu, Pengfei Liu, Zhijie Deng
Diff Diffusion is a diffusion-inspired large language model framework designed for efficient code editing. It predicts edit paths from an original snippet to its revised form by representing denoising as structured edit operations, and uses multi-stage training and efficient parallel decoding to focus computation on changed regions. The approach matches or outperforms autoregressive baselines while achieving up to 2.78× faster inference and a 39.0% reduction in median model latency in production.
By Xiaolong Xu, Hao Jiang, Bo Jiang, Zhiwen Deng, Ningyuan Sun, Bingzhou Chen, Jin Chen, Chenxing Wei