d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation

• URL: http://arxiv.org/abs/2601.07568v1
• Date: Mon, 12 Jan 2026 14:25:36 GMT
• Title: d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
• Authors: Yu-Yang Qian, Junda Su, Lanxiang Hu, Peiyuan Zhang, Zhijie Deng, Peng Zhao, Hao Zhang,
• Abstract summary: Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs.<n>Current methods typically focus on only one-side of the coin, targeting either efficiency or performance.<n>We propose d3LLM (Pseudo-Distilled Diffusion Large Language Model), striking a balance between accuracy and parallelism.
• Score: 31.922313594074925
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently face an accuracy-parallelism trade-off. Despite increasing interest, existing methods typically focus on only one-side of the coin, targeting either efficiency or performance. To address this limitation, we propose d3LLM (Pseudo-Distilled Diffusion Large Language Model), striking a balance between accuracy and parallelism: (i) during training, we introduce pseudo-trajectory distillation to teach the model which tokens can be decoded confidently at early steps, thereby improving parallelism; (ii) during inference, we employ entropy-based multi-block decoding with a KV-cache refresh mechanism to achieve high parallelism while maintaining accuracy. To better evaluate dLLMs, we also introduce AUP (Accuracy Under Parallelism), a new metric that jointly measures accuracy and parallelism. Experiments demonstrate that our d3LLM achieves up to 10$\times$ speedup over vanilla LLaDA/Dream and 5$\times$ speedup over AR models without much accuracy drop. Our code is available at https://github.com/hao-ai-lab/d3LLM.

Related papers

• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• Fast and Accurate Causal Parallel Decoding using Jacobi Forcing [41.89066334075016]
  Jacobi Forcing is a progressive distillation paradigm where models are trained on their own generated parallel decoding trajectories.<n>We introduce multi-block decoding with rejection recycling, which enables up to 4.5x higher token acceptance count per iteration and nearly 4.0x wall-clock speedup.
  arXiv  Detail & Related papers  (2025-12-16T18:45:18Z)
• Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Way [23.877854550033224]
  Diffusion-based large language models (dLLMs) have exhibited substantial potential for parallel text generation.<n>Current dLLMs suffer from fixed generation lengths, which indicates the generation lengths of dLLMs have to be determined before decoding.<n>We propose to train a diffusion LLM with native variable generation lengths, abbreviated as dLLM-Var.
  arXiv  Detail & Related papers  (2025-10-28T16:32:43Z)
• dParallel: Learnable Parallel Decoding for dLLMs [77.24184219948337]
  Diffusion large language models (dLLMs) offer parallel token prediction and lower inference latency.<n>Existing open-source models still require nearly token-length decoding steps to ensure performance.<n>We introduce dParallel, a simple and effective method that unlocks the inherent parallelism of dLLMs for fast sampling.
  arXiv  Detail & Related papers  (2025-09-30T16:32:52Z)
• Fast-dLLM v2: Efficient Block-Diffusion LLM [64.38006546510337]
  Fast-dLLM v2 is a block diffusion language model that adapts pretrained AR models into dLLMs for parallel text generation.<n>This represents a 500x reduction in training data compared to full-attention diffusion LLMs such as Dream (580B tokens)
  arXiv  Detail & Related papers  (2025-09-30T14:40:18Z)
• Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing [14.22753953706955]
  Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs for text generation.<n>This paper breaks this barrier based on a simple and effective strategy named discrete diffusion forcing (D2F)<n>In this way, vanilla dLLMs are refurbished into an AR-diffusion hybrid paradigm for efficient inference.
  arXiv  Detail & Related papers  (2025-08-08T04:51:37Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [60.407727995313074]
  We introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel.<n>APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.
  arXiv  Detail & Related papers  (2025-05-31T06:10:10Z)
• Large Language Diffusion Models [93.26422905620008]
  Large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs)<n>We introduce LLaDA, a diffusion model trained from scratch under the pre-training and supervised fine-tuning paradigm.<n>Across extensive benchmarks on general tasks, math, code, and so on, LLaDA demonstrates strong scalability and performs comparably to our self-constructed ARM baselines.
  arXiv  Detail & Related papers  (2025-02-14T08:23:51Z)
• Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment [56.44025052765861]
  Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs. We show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x.
  arXiv  Detail & Related papers  (2024-05-06T16:03:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.