Accelerating Diffusion Transformer via Error-Optimized Cache

• URL: http://arxiv.org/abs/2501.19243v1
• Date: Fri, 31 Jan 2025 15:58:15 GMT
• Title: Accelerating Diffusion Transformer via Error-Optimized Cache
• Authors: Junxiang Qiu, Shuo Wang, Jinda Lu, Lin Liu, Houcheng Jiang, Yanbin Hao,
• Abstract summary: Diffusion Transformer (DiT) is a crucial method for content generation. Existing caching methods accelerate generation by reusing DiT features from the previous time step and skipping calculations in the next. They tend to locate and cache low-error modules without focusing on reducing caching-induced errors. We propose the Error-d Cache (EOC) to solve this problem.
• Score: 17.991719406545876
• License:
• Abstract: Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time consumption of sampling. Existing caching methods accelerate generation by reusing DiT features from the previous time step and skipping calculations in the next, but they tend to locate and cache low-error modules without focusing on reducing caching-induced errors, resulting in a sharp decline in generated content quality when increasing caching intensity. To solve this problem, we propose the Error-Optimized Cache (EOC). This method introduces three key improvements: (1) Prior knowledge extraction: Extract and process the caching differences; (2) A judgment method for cache optimization: Determine whether certain caching steps need to be optimized; (3) Cache optimization: reduce caching errors. Experiments show that this algorithm significantly reduces the error accumulation caused by caching (especially over-caching). On the ImageNet dataset, without significantly increasing the computational burden, this method improves the quality of the generated images under the over-caching, rule-based, and training-based methods. Specifically, the Fr\'echet Inception Distance (FID) values are improved as follows: from 6.857 to 5.821, from 3.870 to 3.692 and form 3.539 to 3.451 respectively.

Related papers

• Accelerating Diffusion Transformers with Dual Feature Caching [25.36988865752475]
  Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs. As an effective approach for DiT acceleration, feature caching methods are designed to cache the features of DiT in previous timesteps. aggressively reusing all the features cached in previous timesteps leads to a severe drop in generation quality.
  arXiv  Detail & Related papers  (2024-12-25T14:00:14Z)
• Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model [55.64316746098431]
  Timestep Embedding Aware Cache (TeaCache) is a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps. TeaCache achieves up to 4.41x acceleration over Open-Sora-Plan with negligible degradation of visual quality.
  arXiv  Detail & Related papers  (2024-11-28T12:50:05Z)
• InstCache: A Predictive Cache for LLM Serving [9.878166964839512]
  We propose to predict user-instructions by an instruction-aligned LLM and store them in a predictive cache, so-called InstCache. Experimental results show that InstCache can achieve up to 51.34% hit rate on LMSys dataset, which corresponds to a 2x speedup, at a memory cost of only 4.5GB.
  arXiv  Detail & Related papers  (2024-11-21T03:52:41Z)
• Efficient Inference of Vision Instruction-Following Models with Elastic Cache [76.44955111634545]
  We introduce Elastic Cache, a novel strategy for efficient deployment of instruction-following large vision-language models. We propose an importance-driven cache merging strategy to prune redundancy caches. For instruction encoding, we utilize the frequency to evaluate the importance of caches. Results on a range of LVLMs demonstrate that Elastic Cache not only boosts efficiency but also notably outperforms existing pruning methods in language generation.
  arXiv  Detail & Related papers  (2024-07-25T15:29:05Z)
• 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)
• Cache Me if You Can: Accelerating Diffusion Models through Block Caching [67.54820800003375]
  A large image-to-image network has to be applied many times to iteratively refine an image from random noise. We investigate the behavior of the layers within the network and find that 1) the layers' output changes smoothly over time, 2) the layers show distinct patterns of change, and 3) the change from step to step is often very small. We propose a technique to automatically determine caching schedules based on each block's changes over timesteps.
  arXiv  Detail & Related papers  (2023-12-06T00:51:38Z)
• DeepCache: Accelerating Diffusion Models for Free [65.02607075556742]
  DeepCache is a training-free paradigm that accelerates diffusion models from the perspective of model architecture. DeepCache capitalizes on the inherent temporal redundancy observed in the sequential denoising steps of diffusion models. Under the same throughput, DeepCache effectively achieves comparable or even marginally improved results with DDIM or PLMS.
  arXiv  Detail & Related papers  (2023-12-01T17:01:06Z)
• Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching [72.50506500576746]
  We propose a novel caching paradigm, that we named approximate-key caching. While approximate cache hits alleviate DL inference workload and increase the system throughput, they however introduce an approximation error. We analytically model our caching system performance for classic LRU and ideal caches, we perform a trace-driven evaluation of the expected performance, and we compare the benefits of our proposed approach with the state-of-the-art similarity caching.
  arXiv  Detail & Related papers  (2021-12-13T13:49:11Z)

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.