DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse

• URL: http://arxiv.org/abs/2607.15650v1
• Date: Fri, 17 Jul 2026 05:56:42 GMT
• Title: DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse
• Abstract summary: Recent advances in AI-generated content have driven widespread adoption of Diffusion Transformers (DiTs) for high-resolution, long-duration content generation.<n>We present DiTango, an efficient parallel framework for DiT generation.<n>We show that DiTango achieves up to 1.9x end-to-end and 3.2x attention speedup with near-linear scaling in multi-node settings.
• Score: 9.472841051080133
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in AI-generated content have driven widespread adoption of Diffusion Transformers (DiTs) for high-resolution, long-duration content generation. While parallelization techniques accelerate diffusion inference, they face significant scalability challenges due to excessive communication overhead in multi-node environments. We observe that sequence partitions in Context Parallelism (CP) exhibit distinct heterogeneity: spatially proximate partitions contribute more significantly to attention computation results. By mapping this heterogeneous pattern to hierarchical communication topology, we can access high-contribution partitions with reduced communication cost. This insight motivates our novel selective attention state mechanism that strategically balances partial attention computation and historical result reuse across denoising steps. We present DiTango, an efficient parallel framework for DiT generation. DiTango features an anchor-guided state selection planner that optimizes computation-reuse decisions for each partition, complemented by a runtime that orchestrates efficient state-centric operations. This design achieves superior system efficiency while preserving generation quality. Experimental evaluation on popular diffusion models demonstrates that DiTango achieves up to 1.9x end-to-end and 3.2x attention speedup with near-linear scaling in multi-node settings, while maintaining generation quality comparable to state-of-the-art approaches.

Related papers

• Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation [53.60856261088647]
  This paper proposes to shift the condensation paradigm from optimization-based inversion to deterministic latent mapping.<n>We represent action segments as continuous trajectories anchored by sparse latent points in the noise manifold.<n>Our framework significantly outperforms state-of-the-art methods in segmentation performance across common datasets.
  arXiv  Detail & Related papers  (2026-07-10T04:00:26Z)
• Complexity-Balanced Diffusion Splitting [20.558008394592097]
  Complexity-Balanced Splitting (CBS) is a principled framework for temporal capacity allocation.<n>CBS partitions the diffusion timeline into segments of equal approximation burden.<n>CBS consistently improves quality without increasing per-step inference cost.
  arXiv  Detail & Related papers  (2026-06-04T17:57:15Z)
• Rethinking Vector Field Learning for Generative Segmentation [50.08025820235397]
  Taming diffusion models for generative segmentation has attracted increasing attention.<n>We revisit diffusion segmentation from the perspective of vector field learning.<n>We propose a principled vector field reshaping strategy that augments the learned vanishing velocity field with a detached distance-aware correction term.<n>This correction introduces both attractive and repulsive interactions, enhancing gradient magnitudes near centroids while preserving the original diffusion training framework.
  arXiv  Detail & Related papers  (2026-03-19T17:58:19Z)
• LADR: Locality-Aware Dynamic Rescue for Efficient Text-to-Image Generation with Diffusion Large Language Models [10.535207607235046]
  Locality-Aware Dynamic Rescue (LADR) is a training-free method that expedites inference by exploiting the spatial Markov property of images.<n>LADR prioritizes the recovery of tokens at the ''generation frontier'', regions spatially adjacent to observed pixels.<n>Experiments on four text-to-image generation benchmarks demonstrate that our LADR achieves an approximate 4 x speedup over standard baselines.
  arXiv  Detail & Related papers  (2026-03-13T15:12:41Z)
• Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems [52.842088497389746]
  This letter focuses on an anti-jamming collaborative inference system in the presence of a malicious jammer.<n>We first analyze the effects of jamming and DNN partitioning on inference accuracy via data regression.<n>We propose an efficient alternating optimization-based algorithm, which decomposes the problem into three subproblems.
  arXiv  Detail & Related papers  (2026-03-03T03:52:52Z)
• Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness [7.596181361033662]
  Diffusion Transformers (DiTs) require intensive full-attention computation.<n>We present Jano, a training-free framework that leverages this insight for efficient region-aware generation.<n>Jano achieves substantial acceleration (average 2.0 times speedup, up to 2.4 times) while preserving generation quality.
  arXiv  Detail & Related papers  (2026-02-28T07:35:01Z)
• Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models [64.92045568376705]
  Coherent Contextual Decoding (CCD) is a novel inference framework built upon two core innovations.<n>CCD employs a trajectory rectification mechanism that leverages historical context to enhance sequence coherence.<n>Instead of rigid allocations based on diffusion steps, we introduce an adaptive sampling strategy that dynamically adjusts the unmasking budget for each step.
  arXiv  Detail & Related papers  (2025-11-26T09:49:48Z)
• Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism [26.365397387678396]
  Diffusion models have emerged as a powerful class of generative models across various modalities, including image, video, and audio synthesis.<n>We propose textbfParaStep, a novel parallelization method based on a reuse-then-predict mechanism that parallelizes diffusion inference by exploiting similarity between adjacent denoising steps.<n>ParaStep achieves end-to-end speedups of up to textbf3.88$times$ on SVD, textbf2.43$times$ on CogVideoX-2b, and textbf6.56$times
  arXiv  Detail & Related papers  (2025-05-20T06:58:40Z)
• TS-HTFA: Advancing Time Series Forecasting via Hierarchical Text-Free Alignment with Large Language Models [14.411646409316624]
  We introduce textbfHierarchical textbfText-textbfFree textbfAlignment (textbfTS-HTFA), a novel method for time-series forecasting.<n>We replace paired text data with adaptive virtual text based on QR decomposition word embeddings and learnable prompt.<n>Experiments on multiple time-series benchmarks demonstrate that HTFA achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-23T12:57:24Z)
• State-Free Inference of State-Space Models: The Transfer Function Approach [132.83348321603205]
  State-free inference does not incur any significant memory or computational cost with an increase in state size. We achieve this using properties of the proposed frequency domain transfer function parametrization. We report improved perplexity in language modeling over a long convolutional Hyena baseline.
  arXiv  Detail & Related papers  (2024-05-10T00:06:02Z)
• Bidirectional Long-Range Parser for Sequential Data Understanding [3.76054468268713]
  We introduce BLRP (Bidirectional Long-Range), a novel and versatile attention mechanism designed to increase performance and efficiency on long-sequence tasks. We show the benefits and versatility of our approach on vision and language domains by demonstrating competitive results against state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-04-08T05:45:03Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)

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.