Accelerating Diffusion Large Language Models with SlowFast: The Three Golden Principles

• URL: http://arxiv.org/abs/2506.10848v1
• Date: Thu, 12 Jun 2025 16:08:28 GMT
• Title: Accelerating Diffusion Large Language Models with SlowFast: The Three Golden Principles
• Authors: Qingyan Wei, Yaojie Zhang, Zhiyuan Liu, Dongrui Liu, Linfeng Zhang,
• Abstract summary: Diffusion-based language models (dLLMs) have emerged as a promising alternative to traditional autoregressive LLMs.<n>Existing sampling strategies for dLLMs, such as confidence-based or semi-autoregressive decoding, often suffer from static behavior.<n>We propose SlowFast Sampling, a novel dynamic sampling strategy that alternates between exploratory and accelerated decoding stages.
• Score: 25.10417042130122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based language models (dLLMs) have emerged as a promising alternative to traditional autoregressive LLMs by enabling parallel token generation and significantly reducing inference latency. However, existing sampling strategies for dLLMs, such as confidence-based or semi-autoregressive decoding, often suffer from static behavior, leading to suboptimal efficiency and limited flexibility. In this paper, we propose SlowFast Sampling, a novel dynamic sampling strategy that adaptively alternates between exploratory and accelerated decoding stages. Our method is guided by three golden principles: certainty principle, convergence principle, and positional principle, which govern when and where tokens can be confidently and efficiently decoded. We further integrate our strategy with dLLM-Cache to reduce redundant computation. Extensive experiments across benchmarks and models show that SlowFast Sampling achieves up to 15.63$\times$ speedup on LLaDA with minimal accuracy drop, and up to 34.22$\times$ when combined with caching. Notably, our approach outperforms strong autoregressive baselines like LLaMA3 8B in throughput, demonstrating that well-designed sampling can unlock the full potential of dLLMs for fast and high-quality generation.

Related papers

• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction [58.044803442346115]
  Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive computational complexity and memory overhead during inference.<n>We propose Sparse-dLLM, the first training-free framework integrating dynamic cache eviction with sparse attention via delayed bidirectional sparse caching.
  arXiv  Detail & Related papers  (2025-08-04T16:14:03Z)
• R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning [60.37610817226533]
  Chain-of-thought (CoT) reasoning encourages step-by-step intermediate reasoning during inference.<n>CoT introduces substantial computational overhead due to its reliance on autoregressive decoding over long token sequences.<n>We present R-Stitch, a token-level, confidence-based hybrid decoding framework that accelerates CoT inference.
  arXiv  Detail & Related papers  (2025-07-23T08:14:36Z)
• ODE$_t$(ODE$_l$): Shortcutting the Time and Length in Diffusion and Flow Models for Faster Sampling [33.87434194582367]
  In this work, we explore a complementary direction in which the quality-complexity tradeoff can be dynamically controlled.<n>We employ time- and length-wise consistency terms during flow matching training, and as a result, the sampling can be performed with an arbitrary number of time steps.<n>Compared to the previous state of the art, image generation experiments on CelebA-HQ and ImageNet show a latency reduction of up to 3$times$ in the most efficient sampling mode.
  arXiv  Detail & Related papers  (2025-06-26T18:59:59Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [50.9948753314669]
  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)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute [54.22256089592864]
  This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute.<n>Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple models, even weaker ones, to leverage their complementary strengths.
  arXiv  Detail & Related papers  (2025-04-01T13:13:43Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• Beyond Autoregression: Fast LLMs via Self-Distillation Through Time [1.5858234832499587]
  We show that diffusion language models are capable of generating at least 32 tokens simultaneously, while exceeding the performance of AR models in text quality and on the LAMBADA natural language understanding benchmark.<n> Practically, at the 1.3B parameters scale, diffusion models, even without caching, can generate tokens at a rate that is up to 8 times faster than AR models employing KV-caching.
  arXiv  Detail & Related papers  (2024-10-28T13:56:30Z)
• SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration [10.970637831760136]
  Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality.<n>We introduce SWIFT, an on-the-fly self-speculative decoding algorithm that adaptively selects intermediate layers of LLMs to skip during inference.<n>Our experiments demonstrate that SWIFT can achieve over a 1.3x-1.6x speedup while preserving the original distribution of the generated text.
  arXiv  Detail & Related papers  (2024-10-09T14:15:30Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)

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.