6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models

• URL: http://arxiv.org/abs/2603.18742v1
• Date: Thu, 19 Mar 2026 10:45:11 GMT
• Title: 6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models
• Abstract summary: Diffusion transformers have demonstrated remarkable capabilities in generating videos.<n>However, their practical deployment is constrained by high memory usage and computational cost.<n>Post-Training Quantization provides a practical way to reduce memory usage and boost speed.
• Score: 32.45415555978057
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical way to reduce memory usage and boost computation speed. Existing quantization methods typically apply a static bit-width allocation, overlooking the quantization difficulty of activations across diffusion timesteps, leading to a suboptimal trade-off between efficiency and quality. In this paper, we propose a inference time NVFP4/INT8 Mixed-Precision Quantization framework. We find a strong linear correlation between a block's input-output difference and the quantization sensitivity of its internal linear layers. Based on this insight, we design a lightweight predictor that dynamically allocates NVFP4 to temporally stable layers to maximize memory compression, while selectively preserving INT8 for volatile layers to ensure robustness. This adaptive precision strategy enables aggressive quantization without compromising generation quality. Beside this, we observe that the residual between the input and output of a Transformer block exhibits high temporal consistency across timesteps. Leveraging this temporal redundancy, we introduce Temporal Delta Cache (TDC) to skip computations for these invariant blocks, further reducing the computational cost. Extensive experiments demonstrate that our method achieves 1.92$\times$ end-to-end acceleration and 3.32$\times$ memory reduction, setting a new baseline for efficient inference in Video DiTs.

Related papers

• Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping [95.91466630940084]
  Diffusion Transformers (DiTs) have significantly enhanced text-to-image (T2I) generation quality, enabling high-quality personalized content creation.<n>We propose a memory-efficient fine-tuning framework called DiT-BlockSkip, integrating timestep-aware dynamic patch sampling and block skipping.<n>Our approach achieves competitive personalization performance qualitatively and quantitatively, while reducing memory usage substantially.
  arXiv  Detail & Related papers  (2026-03-21T11:02:18Z)
• ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer Acceleration [14.306565517230775]
  Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment.<n>Existing methods suffer from two key limitations: (1) uniform caching intervals fail to align with the non-uniform temporal dynamics of DiT, and (2) naive feature reuse with excessively large caching intervals can lead to severe error accumulation.<n>We propose ProCache, a training-free dynamic feature caching framework that addresses these issues via two core components.
  arXiv  Detail & Related papers  (2025-12-19T07:27:19Z)
• QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification [67.15451442018258]
  Diffusion transformers exhibit remarkable video generation capability, yet their prohibitive computational and memory costs hinder practical deployment.<n>Model quantization and attention sparsification are two promising directions for compression, but each alone suffers severe performance degradation under aggressive compression.<n>We propose textbfQuantSparse, a unified framework that integrates model quantization with attention sparsification.
  arXiv  Detail & Related papers  (2025-09-28T06:49:44Z)
• SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching [17.724549528455317]
  Diffusion models have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications.<n>We present SpeCa, a novel 'Forecast-then-verify' acceleration framework that effectively addresses both limitations.<n>Our approach implements a parameter-free verification mechanism that efficiently evaluates prediction reliability, enabling real-time decisions to accept or reject each prediction.
  arXiv  Detail & Related papers  (2025-09-15T06:46:22Z)
• S$^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation [55.35880044416441]
  We propose S$2$Q-VDiT, a post-training quantization framework for video diffusion models (V-DMs)<n>Under W4A6 quantization, S$2$Q-VDiT achieves lossless performance while delivering $3.9times$ model compression and $1.3times$ inference acceleration.
  arXiv  Detail & Related papers  (2025-08-06T02:12:29Z)
• MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation [74.34220141721231]
  We present MPQ-DMv2, an improved textbfMixed textbfPrecision textbfQuantization framework for extremely low-bit textbfDiffusion textbfModels.
  arXiv  Detail & Related papers  (2025-07-06T08:16:50Z)
• CacheQuant: Comprehensively Accelerated Diffusion Models [3.78219736760145]
  CacheQuant is a novel training-free paradigm that comprehensively accelerates diffusion models by jointly optimizing model caching and quantization techniques.<n> Experimental results show that CacheQuant achieves a 5.18 speedup and 4 compression for Stable Diffusion on MS-COCO, with only a 0.02 loss in CLIP score.
  arXiv  Detail & Related papers  (2025-03-03T09:04:51Z)
• TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models [49.65286242048452]
  We propose a novel method dubbed Timestep-Channel Adaptive Quantization for Diffusion Models (TCAQ-DM)<n>The proposed method substantially outperforms the state-of-the-art approaches in most cases.
  arXiv  Detail & Related papers  (2024-12-21T16:57:54Z)
• Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints [51.83081671798784]
  Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability.<n>DiT's practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference.<n>We propose Skip-DiT, an image and video generative DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets.
  arXiv  Detail & Related papers  (2024-11-26T17:28:10Z)
• SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity [19.900719882624028]
  We propose a memory-efficient scheduling method to eliminate memory overhead and an online adjustment mechanism to minimize accuracy degradation.<n>SparseTem achieves speedup of 1.79x for EfficientDet and 4.72x for CRNN, with minimal accuracy drop and no additional memory overhead.
  arXiv  Detail & Related papers  (2024-10-28T07:13:25Z)
• Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching [56.286064975443026]
  We make an interesting and somehow surprising observation: the computation of a large proportion of layers in the diffusion transformer, through a caching mechanism, can be readily removed even without updating the model parameters. We introduce a novel scheme, named Learningto-Cache (L2C), that learns to conduct caching in a dynamic manner for diffusion transformers. Experimental results show that L2C largely outperforms samplers such as DDIM and DPM-r, alongside prior cache-based methods at the same inference speed.
  arXiv  Detail & Related papers  (2024-06-03T18:49:57Z)
• Accurate Block Quantization in LLMs with Outliers [0.6138671548064355]
  The demand for inference on extremely large scale LLMs has seen enormous growth in recent months. The problem is aggravated by the exploding raise in the lengths of the sequences being processed. Various quantization techniques have been proposed that allow accurate quantization for both weights and activations.
  arXiv  Detail & Related papers  (2024-03-29T12:15:06Z)
• QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning [52.157939524815866]
  In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty.<n>We propose to adjust these distributions through weight finetuning to be more quantization-friendly.<n>Our method demonstrates its efficacy across three high-resolution image generation tasks.
  arXiv  Detail & Related papers  (2024-02-06T03:39:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.