# QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation

arXiv: https://arxiv.org/abs/2503.06545 · HTML: https://mlsanity.com/paper/2503.06545/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://mlsanity.com/paper/2208.04202/) (2022)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation](https://mlsanity.com/paper/2406.02540/) (2024)
- [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2411.02397/) (2024)
- [DiffiT: Diffusion Vision Transformers for Image Generation](https://mlsanity.com/paper/2312.02139/) (2023)
- [Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers](https://mlsanity.com/paper/2406.17343/) (2024)
- [Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation](https://mlsanity.com/paper/2303.10326/) (2023)
- [A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation](https://mlsanity.com/paper/2405.13762/) (2024)
- [Unraveling the Temporal Dynamics of the Unet in Diffusion Models](https://mlsanity.com/paper/2312.14965/) (2023)

## Built on by (most cited first, 21 of 21)

- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [DVD-Quant: Data-free Video Diffusion Transformers Quantization](https://mlsanity.com/paper/2505.18663/) (2025)
- [HERO: Hierarchical Extrapolation and Refresh for Efficient World Models](https://mlsanity.com/paper/2508.17588/) (2025)
- [DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space](https://mlsanity.com/paper/2509.25180/) (2025)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization](https://mlsanity.com/paper/2602.09883/) (2026)
- [ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization](https://mlsanity.com/paper/2602.22948/) (2026)
- [Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms](https://mlsanity.com/paper/2603.28489/) (2026)
- [FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing](https://mlsanity.com/paper/2509.22244/) (2025)
- [CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers](https://mlsanity.com/paper/2509.24416/) (2025)
- [CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion](https://mlsanity.com/paper/2607.23159/) (2026)
- [SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation](https://mlsanity.com/paper/2509.13848/) (2025)
- [D2Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs](https://mlsanity.com/paper/2602.02546/) (2026)
- [GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction](https://mlsanity.com/paper/2605.15852/) (2026)
- [FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching](https://mlsanity.com/paper/2605.09003/) (2026)
- [Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs](https://mlsanity.com/paper/2605.18165/) (2026)
- [A Lightweight Dual-Mode Optimization for Generative Face Video Coding](https://mlsanity.com/paper/2508.13547/) (2025)
- [6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models](https://mlsanity.com/paper/2603.18742/) (2026)
- [CAST: Reconstruction-Coupled Acceleration of Interactive World Models](https://mlsanity.com/paper/2609.34144/) (2026)
- [VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction](https://mlsanity.com/paper/2610.01013/) (2026)
- [SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching](https://mlsanity.com/paper/2610.02660/) (2026)

## Abstract (arXiv)

Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks, including increased computational and memory costs, which hinder their deployment on resource-constrained devices. Current acceleration techniques, such as quantization and cache mechanism, offer limited speedup and are often applied in isolation, failing to fully address the complexities of DiT architectures. In this paper, we propose QuantCache, a novel training-free inference acceleration framework that jointly optimizes hierarchical latent caching, adaptive importance-guided quantization, and structural redundancy-aware pruning. QuantCache achieves an end-to-end latency speedup of 6.72× on Open-Sora with minimal loss in generation quality. Extensive experiments across multiple video generation benchmarks demonstrate the effectiveness of our method, setting a new standard for efficient DiT inference. The code and models will be available at https://github.com/JunyiWuCode/QuantCache.