Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2406.11100 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914836575682560 |
|---|---|
| author | Yang, Yuewei Wang, Jialiang Dai, Xiaoliang Zhang, Peizhao Zhang, Hongbo |
| author_facet | Yang, Yuewei Wang, Jialiang Dai, Xiaoliang Zhang, Peizhao Zhang, Hongbo |
| contents | Diffusion Models (DMs) utilize an iterative denoising process to transform random noise into synthetic data. Initally proposed with a UNet structure, DMs excel at producing images that are virtually indistinguishable with or without conditioned text prompts. Later transformer-only structure is composed with DMs to achieve better performance. Though Latent Diffusion Models (LDMs) reduce the computational requirement by denoising in a latent space, it is extremely expensive to inference images for any operating devices due to the shear volume of parameters and feature sizes. Post Training Quantization (PTQ) offers an immediate remedy for a smaller storage size and more memory-efficient computation during inferencing. Prior works address PTQ of DMs on UNet structures have addressed the challenges in calibrating parameters for both activations and weights via moderate optimization. In this work, we pioneer an efficient PTQ on transformer-only structure without any optimization. By analysing challenges in quantizing activations and weights for diffusion transformers, we propose a single-step sampling calibration on activations and adapt group-wise quantization on weights for low-bit quantization. We demonstrate the efficiency and effectiveness of proposed methods with preliminary experiments on conditional image generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11100 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Analysis on Quantizing Diffusion Transformers Yang, Yuewei Wang, Jialiang Dai, Xiaoliang Zhang, Peizhao Zhang, Hongbo Computer Vision and Pattern Recognition Diffusion Models (DMs) utilize an iterative denoising process to transform random noise into synthetic data. Initally proposed with a UNet structure, DMs excel at producing images that are virtually indistinguishable with or without conditioned text prompts. Later transformer-only structure is composed with DMs to achieve better performance. Though Latent Diffusion Models (LDMs) reduce the computational requirement by denoising in a latent space, it is extremely expensive to inference images for any operating devices due to the shear volume of parameters and feature sizes. Post Training Quantization (PTQ) offers an immediate remedy for a smaller storage size and more memory-efficient computation during inferencing. Prior works address PTQ of DMs on UNet structures have addressed the challenges in calibrating parameters for both activations and weights via moderate optimization. In this work, we pioneer an efficient PTQ on transformer-only structure without any optimization. By analysing challenges in quantizing activations and weights for diffusion transformers, we propose a single-step sampling calibration on activations and adapt group-wise quantization on weights for low-bit quantization. We demonstrate the efficiency and effectiveness of proposed methods with preliminary experiments on conditional image generation. |
| title | An Analysis on Quantizing Diffusion Transformers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.11100 |