Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers
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).
Code (0)
등록된 구현이 없습니다.
Tasks
GPUText-to-Video GenerationToken ReductionVideo GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Astraea: Grammar-based Fairness Testing
Software often produces biased outputs. In particular, machine learning (ML) based software are known to produce erroneous predictions when processing discriminatory inputs. Such unfair program behavior can be caused by …
FairnessFault DiagnosisAstraea: A State-Aware Scheduling Engine for LLM-Powered Agents
Large Language Models (LLMs) are increasingly being deployed as intelligent agents. Their multi-stage workflows, which alternate between local computation and calls to external network services like Web APIs, introduce a…
Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications
Federated learning (FL) is a distributed deep learning method which enables multiple participants, such as mobile phones and IoT devices, to contribute a neural network model while their private training data remains in …
Data AugmentationEdge-computingFederated LearningGeneral ClassificationTowards Fair and Efficient Learning-based Congestion Control
Recent years have witnessed a plethora of learning-based solutions for congestion control (CC) that demonstrate better performance over traditional TCP schemes. However, they fail to provide consistently good convergence…
Deep Reinforcement LearningFairnessSODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer
Diffusion Transformers have become a dominant paradigm in visual generation, yet their low inference efficiency remains a key bottleneck hindering further advancement. Among common training-free techniques, caching offer…