Token Caching for Diffusion Transformer Acceleration
- URL: http://arxiv.org/abs/2409.18523v1
- Date: Fri, 27 Sep 2024 08:05:34 GMT
- Title: Token Caching for Diffusion Transformer Acceleration
- Authors: Jinming Lou, Wenyang Luo, Yufan Liu, Bing Li, Xinmiao Ding, Weiming Hu, Jiajiong Cao, Yuming Li, Chenguang Ma,
- Abstract summary: TokenCache is a novel post-training acceleration method for diffusion transformers.
It reduces redundant computations among tokens across inference steps.
We show that TokenCache achieves an effective trade-off between generation quality and inference speed for diffusion transformers.
- Score: 30.437462937127773
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their high computational cost, arising from the quadratic computational complexity of attention mechanisms and multi-step inference, presents a significant bottleneck. To address this challenge, we propose TokenCache, a novel post-training acceleration method that leverages the token-based multi-block architecture of transformers to reduce redundant computations among tokens across inference steps. TokenCache specifically addresses three critical questions in the context of diffusion transformers: (1) which tokens should be pruned to eliminate redundancy, (2) which blocks should be targeted for efficient pruning, and (3) at which time steps caching should be applied to balance speed and quality. In response to these challenges, TokenCache introduces a Cache Predictor that assigns importance scores to tokens, enabling selective pruning without compromising model performance. Furthermore, we propose an adaptive block selection strategy to focus on blocks with minimal impact on the network's output, along with a Two-Phase Round-Robin (TPRR) scheduling policy to optimize caching intervals throughout the denoising process. Experimental results across various models demonstrate that TokenCache achieves an effective trade-off between generation quality and inference speed for diffusion transformers. Our code will be publicly available.
Related papers
- Efficient Token Compression for Vision Transformer with Spatial Information Preserved [59.79302182800274]
Token compression is essential for reducing the computational and memory requirements of transformer models.
We propose an efficient and hardware-compatible token compression method called Prune and Merge.
arXiv Detail & Related papers (2025-03-30T14:23:18Z) - Exposure Bias Reduction for Enhancing Diffusion Transformer Feature Caching [7.393824353099595]
Diffusion Transformer (DiT) has exhibited impressive generation capabilities but faces great challenges due to its high computational complexity.
We analyze the impact of caching on the SNR of the diffusion process.
We introduce EB-Cache, a joint cache strategy that aligns the Non-exposure bias.
arXiv Detail & Related papers (2025-03-10T09:49:18Z) - QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation [84.91431271257437]
Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation.
DiTs come with significant drawbacks, including increased computational and memory costs.
We propose QuantCache, a novel training-free inference acceleration framework.
arXiv Detail & Related papers (2025-03-09T10:31:51Z) - Adaptive Caching for Faster Video Generation with Diffusion Transformers [52.73348147077075]
Diffusion Transformers (DiTs) rely on larger models and heavier attention mechanisms, resulting in slower inference speeds.
We introduce a training-free method to accelerate video DiTs, termed Adaptive Caching (AdaCache)
We also introduce a Motion Regularization (MoReg) scheme to utilize video information within AdaCache, controlling the compute allocation based on motion content.
arXiv Detail & Related papers (2024-11-04T18:59:44Z) - SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity [15.872209884833977]
We propose a memory-efficient scheduling method to eliminate memory overhead and an online adjustment mechanism to minimize accuracy degradation.
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) - ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference [41.41316718220569]
ExpertFlow is designed to enhance inference efficiency by accommodating flexible routing and enabling efficient expert scheduling between CPU and GPU.
Our experiments demonstrate that ExpertFlow achieves up to 93.72% GPU memory savings and enhances inference speed by 2 to 10 times compared to baseline methods.
arXiv Detail & Related papers (2024-10-23T15:24:54Z) - Accelerating Diffusion Transformers with Token-wise Feature Caching [19.140800616594294]
Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs.
We introduce token-wise feature caching, allowing us to adaptively select the most suitable tokens for caching.
Experiments on PixArt-$alpha$, OpenSora, and DiT demonstrate our effectiveness in both image and video generation with no requirements for training.
arXiv Detail & Related papers (2024-10-05T03:47:06Z) - 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) - Efficient Transformer Encoders for Mask2Former-style models [57.54752243522298]
ECO-M2F is a strategy to self-select the number of hidden layers in the encoder conditioned on the input image.
The proposed approach reduces expected encoder computational cost while maintaining performance.
It is flexible in architecture configurations, and can be extended beyond the segmentation task to object detection.
arXiv Detail & Related papers (2024-04-23T17:26:34Z) - Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference [2.8241099113277666]
"Keyformer" is an innovative inference-time approach to mitigate the challenges associated with KV cache size and memory bandwidth utilization.
We evaluate Keyformer's performance across three foundational models: GPT-J, Cerebras-GPT, and MPT.
arXiv Detail & Related papers (2024-03-14T02:42:42Z) - 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) - Adaptive Fourier Neural Operators: Efficient Token Mixers for
Transformers [55.90468016961356]
We propose an efficient token mixer that learns to mix in the Fourier domain.
AFNO is based on a principled foundation of operator learning.
It can handle a sequence size of 65k and outperforms other efficient self-attention mechanisms.
arXiv Detail & Related papers (2021-11-24T05:44:31Z)
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.