# DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction

arXiv: https://arxiv.org/abs/2607.15846 · HTML: https://mlsanity.com/paper/2607.15846/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 62 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets](https://mlsanity.com/paper/1906.05474/) (2019)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks](https://mlsanity.com/paper/1909.13144/) (2019)
- [SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference](https://mlsanity.com/paper/2502.18137/) (2025)
- [DiTFastAttn: Attention Compression for Diffusion Transformer Models](https://mlsanity.com/paper/2406.08552/) (2024)
- [Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers](https://mlsanity.com/paper/2406.17343/) (2024)
- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [Benchmarking TPU, GPU, and CPU Platforms for Deep Learning](https://mlsanity.com/paper/1907.10701/) (2019)
- [DeepScaleTool : A Tool for the Accurate Estimation of Technology Scaling in the Deep-Submicron Era](https://mlsanity.com/paper/2102.10195/) (2021)
- [Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator](https://mlsanity.com/paper/2308.11030/) (2023)
- [Token Caching for Diffusion Transformer Acceleration](https://mlsanity.com/paper/2409.18523/) (2024)
- [Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization](https://mlsanity.com/paper/2406.12930/) (2024)
- [MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization](https://mlsanity.com/paper/2411.05282/) (2024)
- [MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models](https://mlsanity.com/paper/2503.11972/) (2025)
- [SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs](https://mlsanity.com/paper/2405.17025/) (2024)
- [EXION: Exploiting Inter- and Intra-Iteration Output Sparsity for Diffusion Models](https://mlsanity.com/paper/2501.05680/) (2025)
- [FlexCache: Flexible Approximate Cache System for Video Diffusion](https://mlsanity.com/paper/2501.04012/) (2024)
- [PATCHEDSERVE: A Patch Management Framework for SLO-Optimized Hybrid Resolution Diffusion Serving](https://mlsanity.com/paper/2501.09253/) (2025)

## Built on by (most cited first, 1 of 1)

- [Hardware Acceleration of Block-Diffusion LLM for Edge Devices](https://mlsanity.com/paper/2609.01084/) (2026)

## Abstract (arXiv)

Diffusion Transformers (DiTs) have been widely used in many tasks, including image synthesis, video generation, and content editing. However, their multi-iteration inference process leads to performance inefficiency and high energy consumption. Existing acceleration methods primarily focus on reducing temporal redundancy between adjacent timesteps, but often overlook the specific features of DiTs. As a result, these approaches either suffer from great accuracy degradation or fail to achieve high efficiency. We present DSTAR, a software-hardware co-design framework that accelerates DiT inference by reducing spatial and temporal redundancy. At the algorithmic level, DSTAR introduces a fine-grained mixed-precision quantization method for differential activations in linear operations, significantly increasing the proportion of low-bit computations. Additionally, DSTAR incorporates a sparse attention reuse mechanism to minimize redundant computation in attention layers. For architectural support, we design a specialized hardware accelerator which achieves high efficiency in both latency and energy consumption. Evaluation on seven typical DiTs demonstrates that DSTAR achieves up to 7.33x latency speedup and 41.89x energy savings compared to an NVIDIA A100 GPU, and achieves up to 2.54x latency speedup and 3.68x energy savings compared to SOTA accelerators, without accuracy degradation.