paper-with-me

홈 › Papers

EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation

2026-03-30 · Sravanth Kodavanti, Manjunath Arveti, Sowmya Vajrala, Srinivas Miriyala, Vikram N R arxiv

Diffusion Transformers (DiT) have established a new state-of-the-art in high-fidelity image synthesis; however, their massive computational complexity and memory requirements hinder local deployment on resource-constrained edge devices. In this paper, we introduce EdgeDiT, a family of hardware-efficient generative transformers specifically engineered for mobile Neural Processing Units (NPUs), such as the Qualcomm Hexagon and Apple Neural Engine (ANE). By leveraging a hardware-aware optimization framework, we systematically identify and prune structural redundancies within the DiT backbone that are particularly taxing for mobile data-flows. Our approach yields a series of lightweight models that achieve a 20-30% reduction in parameters, a 36-46% decrease in FLOPs, and a 1.65-fold reduction in on-device latency without sacrificing the scaling advantages or the expressive capacity of the original transformer architecture. Extensive benchmarking demonstrates that EdgeDiT offers a superior Pareto-optimal trade-off between Frechet Inception Distance (FID) and inference latency compared to both optimized mobile U-Nets and vanilla DiT variants. By enabling responsive, private, and offline generative AI directly on-device, EdgeDiT provides a scalable blueprint for transitioning large-scale foundation models from high-end GPUs to the palm of the user.

📄 PDF Abstract BibTeX arXiv:2603.28405

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Frame-based Equivariant Diffusion Models for 3D Molecular Generation

2025-09-23 · Mohan Guo, Cong Liu, Patrick Forré arxiv

Recent methods for molecular generation face a trade-off: they either enforce strict equivariance with costly architectures or relax it to gain scalability and flexibility. We propose a frame-based diffusion paradigm tha…

HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

2020-05-28 · ACL 2020 6 · Hanrui Wang, Zhanghao Wu, Zhijian Liu, Han Cai 외

Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are difficult to be deployed on hardware due to the intensive computation. To enable low-latency inference on resource-constrained hardware…

CPUDecoderGPUMachine Translation+3

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

2026-01-13 · Dongting Hu, Aarush Gupta, Magzhan Gabidolla, Arpit Sahni 외 arxiv

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an e…

Image Generation

S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation

2026-01-19 · Lin Zhao, Yushu Wu, Aleksei Lebedev, Dishani Lahiri 외 arxiv

Diffusion Transformers (DiTs) have recently improved video generation quality. However, their heavy computational cost makes real-time or on-device generation infeasible. In this work, we introduce S2DiT, a Streaming San…

Video Generation

Scalable, Tokenization-Free Diffusion Model Architectures with Efficient Initial Convolution and Fixed-Size Reusable Structures for On-Device Image Generation

2024-11-09 · Sanchar Palit, Sathya Veera Reddy Dendi, Mallikarjuna Talluri, Raj Narayana Gadde

Vision Transformers and U-Net architectures have been widely adopted in the implementation of Diffusion Models. However, each architecture presents specific challenges while realizing them on-device. Vision Transformers …

Conditional Image GenerationImage GenerationNoise EstimationUnconditional Image Generation