# Accelerating Parallel Diffusion Model Serving with Residual Compression

arXiv: https://arxiv.org/abs/2507.17511 · HTML: https://mlsanity.com/paper/2507.17511/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 23 Jul 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 24 of 24)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM](https://mlsanity.com/paper/2104.04473/) (2021)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [Error Feedback Fixes SignSGD and other Gradient Compression Schemes](https://mlsanity.com/paper/1901.09847/) (2019)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization](https://mlsanity.com/paper/1905.13727/) (2019)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch](https://mlsanity.com/paper/2102.04010/) (2021)
- [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](https://mlsanity.com/paper/2411.05007/) (2024)
- [Sequence Parallelism: Long Sequence Training from System Perspective](https://mlsanity.com/paper/2105.13120/) (2021)
- [DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models](https://mlsanity.com/paper/2402.19481/) (2024)
- [TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models](https://mlsanity.com/paper/2102.07988/) (2021)
- [USP: A Unified Sequence Parallelism Approach for Long Context Generative AI](https://mlsanity.com/paper/2405.07719/) (2024)
- [xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism](https://mlsanity.com/paper/2411.01738/) (2024)
- [On Communication Compression for Distributed Optimization on Heterogeneous Data](https://mlsanity.com/paper/2009.02388/) (2020)
- [Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study](https://mlsanity.com/paper/2411.13588/) (2024)
- [Partially Conditioned Patch Parallelism for Accelerated Diffusion Model Inference](https://mlsanity.com/paper/2412.02962/) (2024)

## Built on by (most cited first, 2 of 2)

- [Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling](https://mlsanity.com/paper/2602.21760/) (2026)
- [SparSP: Exploiting Communication Sparsity for Sequence-Parallel Video DiTs](https://mlsanity.com/paper/2609.32197/) (2026)

## Abstract (arXiv)

Diffusion models produce realistic images and videos but require substantial computational resources, necessitating multi-accelerator parallelism for real-time deployment. However, parallel inference introduces significant communication overhead from exchanging large activations between devices, limiting efficiency and scalability. We present CompactFusion, a compression framework that significantly reduces communication while preserving generation quality. Our key observation is that diffusion activations exhibit strong temporal redundancy-adjacent steps produce highly similar activations, saturating bandwidth with near-duplicate data carrying little new information. To address this inefficiency, we seek a more compact representation that encodes only the essential information. CompactFusion achieves this via Residual Compression that transmits only compressed residuals (step-wise activation differences). Based on empirical analysis and theoretical justification, we show that it effectively removes redundant data, enabling substantial data reduction while maintaining high fidelity. We also integrate lightweight error feedback to prevent error accumulation. CompactFusion establishes a new paradigm for parallel diffusion inference, delivering lower latency and significantly higher generation quality than prior methods. On 4xL20, it achieves 3.0x speedup while greatly improving fidelity. It also uniquely supports communication-heavy strategies like sequence parallelism on slow networks, achieving 6.7x speedup over prior overlap-based method. CompactFusion applies broadly across diffusion models and parallel settings, and integrates easily without requiring pipeline rework. Portable implementation demonstrated on xDiT is publicly available at https://github.com/Cobalt-27/CompactFusion