paper-with-me

홈 › Papers

FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers

2025-03-19 · Ruichen Chen, Keith G. Mills, Di Niu

Diffusion Models (DM) have revolutionized the text-to-image visual generation process. However, the large computational cost and model footprint of DMs hinders practical deployment, especially on edge devices. Post-training quantization (PTQ) is a lightweight method to alleviate these burdens without the need for training or fine-tuning. While recent DM PTQ methods achieve W4A8 on integer-based PTQ, two key limitations remain: First, while most existing DM PTQ methods evaluate on classical DMs like Stable Diffusion XL, 1.5 or earlier, which use convolutional U-Nets, newer Diffusion Transformer (DiT) models like the PixArt series, Hunyuan and others adopt fundamentally different transformer backbones to achieve superior image synthesis. Second, integer (INT) quantization is prevailing in DM PTQ but doesn't align well with the network weight and activation distribution, while Floating-Point Quantization (FPQ) is still under-investigated, yet it holds the potential to better align the weight and activation distributions in low-bit settings for DiT. In response, we introduce FP4DiT, a PTQ method that leverages FPQ to achieve W4A6 quantization. Specifically, we extend and generalize the Adaptive Rounding PTQ technique to adequately calibrate weight quantization for FPQ and demonstrate that DiT activations depend on input patch data, necessitating robust online activation quantization techniques. Experimental results demonstrate that FP4DiT outperforms integer-based PTQ at W4A6 and W4A8 precision and generates convincing visual content on PixArt-$\alpha$, PixArt-$\Sigma$ and Hunyuan in terms of several T2I metrics such as HPSv2 and CLIP.

📄 PDF Abstract BibTeX arXiv:2503.15465

Code (1)

cccrrrccc/fp4dit 공식 구현 pytorch

Tasks

Image GenerationQuantization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Models

2024-08-13 · Cheng Chen, Christina Giannoula, Andreas Moshovos

Diffusion models are emerging models that generate images by iteratively denoising random Gaussian noise using deep neural networks. These models typically exhibit high computational and memory demands, necessitating eff…

DenoisingQuantization

HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization

2024-05-30 · Wenxuan Liu, Sai Qian Zhang

Diffusion Transformers (DiTs) have recently gained substantial attention in both industrial and academic fields for their superior visual generation capabilities, outperforming traditional diffusion models that use U-Net…

Quantization

Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning

2025-01-01 · CVPR 2025 1 · Maosen Zhao, Pengtao Chen, Chong Yu, Yan Wen 외

Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, p…

DenoisingQuantization

BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers

2026-03-10 · Chaodong Xiao, Zhengqiang Zhang, Lei Zhang arxiv

Transformers have achieved widespread and remarkable success, while the computational complexity of their attention modules remains a major bottleneck for vision tasks. Existing methods mainly employ 8-bit or 4-bit quant…

Phoenix: A Low-Precision Floating-Point Quantization Oriented Architecture for Convolutional Neural Networks

2020-02-29

Convolutional neural networks (CNNs) achieve state-of-the-art performance at the cost of becoming deeper and larger. Although quantization (both fixed-point and floating-point) has proven effective for reducing storage a…

Quantization