DVD-Quant: Data-free Video Diffusion Transformers Quantization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhiteng, Li, Hanxuan, Wu, Junyi, Liu, Kai, Qin, Haotong, Kong, Linghe, Chen, Guihai, Zhang, Yulun, Yang, Xiaokang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915838766874624
author Li, Zhiteng
Li, Hanxuan
Wu, Junyi
Liu, Kai
Qin, Haotong
Kong, Linghe
Chen, Guihai
Zhang, Yulun
Yang, Xiaokang
author_facet Li, Zhiteng
Li, Hanxuan
Wu, Junyi
Liu, Kai
Qin, Haotong
Kong, Linghe
Chen, Guihai
Zhang, Yulun
Yang, Xiaokang
contents Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While post-training quantization (PTQ) presents a promising approach to accelerate Video DiT models, existing methods suffer from two critical limitations: (1) dependence on computation-heavy and inflexible calibration procedures, and (2) considerable performance deterioration after quantization. To address these challenges, we propose DVD-Quant, a novel Data-free quantization framework for Video DiTs. Our approach integrates three key innovations: (1) Bounded-init Grid Refinement (BGR) and (2) Auto-scaling Rotated Quantization (ARQ) for calibration data-free quantization error reduction, as well as (3) $δ$-Guided Bit Switching ($δ$-GBS) for adaptive bit-width allocation. Extensive experiments across multiple video generation benchmarks demonstrate that DVD-Quant achieves an approximately 2$\times$ speedup over full-precision baselines on advanced DiT models while maintaining visual fidelity. Notably, DVD-Quant is the first to enable W4A4 PTQ for Video DiTs without compromising video quality. Code and models will be available at https://github.com/lhxcs/DVD-Quant.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18663
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DVD-Quant: Data-free Video Diffusion Transformers Quantization
Li, Zhiteng
Li, Hanxuan
Wu, Junyi
Liu, Kai
Qin, Haotong
Kong, Linghe
Chen, Guihai
Zhang, Yulun
Yang, Xiaokang
Computer Vision and Pattern Recognition
Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While post-training quantization (PTQ) presents a promising approach to accelerate Video DiT models, existing methods suffer from two critical limitations: (1) dependence on computation-heavy and inflexible calibration procedures, and (2) considerable performance deterioration after quantization. To address these challenges, we propose DVD-Quant, a novel Data-free quantization framework for Video DiTs. Our approach integrates three key innovations: (1) Bounded-init Grid Refinement (BGR) and (2) Auto-scaling Rotated Quantization (ARQ) for calibration data-free quantization error reduction, as well as (3) $δ$-Guided Bit Switching ($δ$-GBS) for adaptive bit-width allocation. Extensive experiments across multiple video generation benchmarks demonstrate that DVD-Quant achieves an approximately 2$\times$ speedup over full-precision baselines on advanced DiT models while maintaining visual fidelity. Notably, DVD-Quant is the first to enable W4A4 PTQ for Video DiTs without compromising video quality. Code and models will be available at https://github.com/lhxcs/DVD-Quant.
title DVD-Quant: Data-free Video Diffusion Transformers Quantization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.18663