Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers

• URL: http://arxiv.org/abs/2506.05096v3
• Date: Mon, 09 Jun 2025 03:34:47 GMT
• Title: Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers
• Authors: Haosong Liu, Yuge Cheng, Zihan Liu, Aiyue Chen, Jing Lin, Yiwu Yao, Chen Chen, Jingwen Leng, Yu Feng, Minyi Guo,
• Abstract summary: Video diffusion transformers (vDiTs) have made impressive progress in text-to-video generation, but their high computational demands present major challenges for practical deployment.<n>We introduce ASTRAEA, an automatic framework that searches for near-optimal configurations for vDiT-based video generation.
• Score: 22.349130691342687
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video diffusion transformers (vDiTs) have made impressive progress in text-to-video generation, but their high computational demands present major challenges for practical deployment. While existing acceleration methods reduce workload at various granularities, they often rely on heuristics, limiting their applicability. We introduce ASTRAEA, an automatic framework that searches for near-optimal configurations for vDiT-based video generation. At its core, ASTRAEA proposes a lightweight token selection mechanism and a memory-efficient, GPU-parallel sparse attention strategy, enabling linear reductions in execution time with minimal impact on generation quality. To determine optimal token reduction for different timesteps, we further design a search framework that leverages a classic evolutionary algorithm to automatically determine the distribution of the token budget effectively. Together, ASTRAEA achieves up to 2.4x inference speedup on a single GPU with great scalability (up to 13.2x speedup on 8 GPUs) while retaining better video quality compared to the state-of-the-art methods (<0.5% loss on the VBench score compared to the baseline vDiT models).

Related papers

• Taming Diffusion Transformer for Real-Time Mobile Video Generation [72.20660234882594]
  Diffusion Transformers (DiT) have shown strong performance in video generation tasks, but their high computational cost makes them impractical for resource-constrained devices like smartphones.<n>We propose a series of novel optimizations to significantly accelerate video generation and enable real-time performance on mobile platforms.
  arXiv  Detail & Related papers  (2025-07-17T17:59:10Z)
• Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching [57.7533917467934]
  EasyCache is a training-free acceleration framework for video diffusion models.<n>We conduct comprehensive studies on various large-scale video generation models, including OpenSora, Wan2.1, and HunyuanVideo.<n>Our method achieves leading acceleration performance, reducing inference time by up to 2.1-3.3$times$ compared to the original baselines.
  arXiv  Detail & Related papers  (2025-07-03T17:59:54Z)
• Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models [34.131515004434846]
  We introduce Temporal In-Context Fine-Tuning (TIC-FT), an efficient approach for adapting pretrained video diffusion models to conditional generation tasks.<n>TIC-FT requires no architectural changes and achieves strong performance with as few as 10-30 training samples.<n>We validate our method across a range of tasks, including image-to-video and video-to-video generation, using large-scale base models such as CogVideoX-5B and Wan-14B.
  arXiv  Detail & Related papers  (2025-06-01T12:57:43Z)
• Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation [1.3207844222875191]
  Diffusion Transformers (DiTs) achieve state-of-the-art results in text-to-image, text-to-video generation, and editing.<n> Static caching mitigates this by reusing features across fixed steps but fails to adapt to generation dynamics.<n>We propose Foresight, an adaptive layer-reuse technique that reduces computational redundancy across denoising steps while preserving baseline performance.
  arXiv  Detail & Related papers  (2025-05-31T00:52:17Z)
• FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge [60.000984252907195]
  Auto-regressive (AR) models have recently shown promise in visual generation tasks due to their superior sampling efficiency.<n>Video generation requires a substantially larger number of tokens to produce coherent temporal frames, resulting in significant overhead during the decoding phase.<n>We propose the textbfFastCar framework to accelerate the decode phase for the AR video generation by exploring the temporal redundancy.
  arXiv  Detail & Related papers  (2025-05-17T05:00:39Z)
• DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance [43.423240627266644]
  Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality.<n>However, their computational cost remains a major bottleneck-attention alone accounts for over 80% of total latency.<n>We propose the DraftAttention, a training-free framework for the acceleration of video diffusion transformers with dynamic sparse attention on GPUs.
  arXiv  Detail & Related papers  (2025-05-17T04:34:34Z)
• QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation [84.91431271257437]
  Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation.<n>DiTs come with significant drawbacks, including increased computational and memory costs.<n>We propose QuantCache, a novel training-free inference acceleration framework.
  arXiv  Detail & Related papers  (2025-03-09T10:31:51Z)
• Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints [51.83081671798784]
  Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability.<n>DiT's practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference.<n>We propose Skip-DiT, a novel DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets.
  arXiv  Detail & Related papers  (2024-11-26T17:28:10Z)
• Adaptive Caching for Faster Video Generation with Diffusion Transformers [52.73348147077075]
  Diffusion Transformers (DiTs) rely on larger models and heavier attention mechanisms, resulting in slower inference speeds. We introduce a training-free method to accelerate video DiTs, termed Adaptive Caching (AdaCache) We also introduce a Motion Regularization (MoReg) scheme to utilize video information within AdaCache, controlling the compute allocation based on motion content.
  arXiv  Detail & Related papers  (2024-11-04T18:59:44Z)
• SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity [15.872209884833977]
  We propose a memory-efficient scheduling method to eliminate memory overhead and an online adjustment mechanism to minimize accuracy degradation. SparseTem achieves speedup of 1.79x for EfficientDet and 4.72x for CRNN, with minimal accuracy drop and no additional memory overhead.
  arXiv  Detail & Related papers  (2024-10-28T07:13:25Z)
• ReBotNet: Fast Real-time Video Enhancement [59.08038313427057]
  Most restoration networks are slow, have high computational bottleneck, and can't be used for real-time video enhancement. In this work, we design an efficient and fast framework to perform real-time enhancement for practical use-cases like live video calls and video streams. To evaluate our method, we emulate two new datasets that real-world video call and streaming scenarios, and show extensive results on multiple datasets where ReBotNet outperforms existing approaches with lower computations, reduced memory requirements, and faster inference time.
  arXiv  Detail & Related papers  (2023-03-23T17:58:05Z)
• Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design [66.39546326221176]
  Attention-based neural networks have become pervasive in many AI tasks. The use of the attention mechanism and feed-forward network (FFN) demands excessive computational and memory resources. This paper proposes a hardware-friendly variant that adopts a unified butterfly sparsity pattern to approximate both the attention mechanism and the FFNs.
  arXiv  Detail & Related papers  (2022-09-20T09:28:26Z)

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.