As a result, our method significantly accelerates ViTs for dense prediction tasks.

Diffusion models have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. These models face two fundamental challenges: strict temporal dependencies preventing parallelization, and computationally intensive forward passes required at each denoising step. Drawing inspiration from speculative decoding in large language models, we present SpeCa, a novel 'Forecast-then-verify' acceleration framework that effectively addresses both limitations. SpeCa's core innovation lies in introducing Speculative Sampling to diffusion models, predicting intermediate features for subsequent timesteps based on fully computed reference timesteps. Our approach implements a parameter-free verification mechanism that efficiently evaluates prediction reliability, enabling real-time decisions to accept or reject each prediction while incurring negligible computational overhead. Furthermore, SpeCa introduces sample-adaptive computation allocation that dynamically modulates resources based on generation complexity, allocating reduced computation for simpler samples while preserving intensive processing for complex instances. Experiments demonstrate 6.34x acceleration on FLUX with minimal quality degradation (5.5% drop), 7.3x speedup on DiT while preserving generation fidelity, and 79.84% VBench score at 6.1x acceleration for HunyuanVideo. The verification mechanism incurs minimal overhead (1.67%-3.5% of full inference costs), establishing a new paradigm for efficient diffusion model inference while maintaining generation quality even at aggressive acceleration ratios. Our codes have been released in Github: \textbf{https://github.com/Shenyi-Z/Cache4Diffusion}

Large language models (LLMs) exhibit remarkable reasoning capabilities across diverse downstream tasks. However, their autoregressive nature leads to substantial inference latency, posing challenges for real-time applications. Speculative sampling mitigates this issue by introducing a drafting phase followed by a parallel validation phase, enabling faster token generation and verification. Existing approaches, however, overlook the inherent coherence in text generation, limiting their efficiency. To address this gap, we propose a Speculative Sampling with Syntactic and Semantic Coherence (S$^4$C) framework, which extends speculative sampling by leveraging multi-head drafting for rapid token generation and a continuous verification tree for efficient candidate validation and feature reuse. Experimental results demonstrate that S$^4$C surpasses baseline methods across mainstream tasks, offering enhanced efficiency, parallelism, and the ability to generate more valid tokens with fewer computational resources. On Spec-bench benchmarks, S$^4$C achieves an acceleration ratio of 2.26x-2.60x, outperforming state-of-the-art methods.

Large language models (LLMs) have achieved remarkable performance across a wide range of NLP tasks. However, their substantial inference cost poses a major barrier to real-world deployment, especially in latency-sensitive scenarios. To address this challenge, we propose \textbf{DASH}, an adaptive layer-skipping framework that dynamically selects computation paths conditioned on input characteristics. We model the skipping process as a Markov Decision Process (MDP), enabling fine-grained token-level decisions based on intermediate representations. To mitigate potential performance degradation caused by skipping, we introduce a lightweight compensation mechanism that injects differential rewards into the decision process. Furthermore, we design an asynchronous execution strategy that overlaps layer computation with policy evaluation to minimize runtime overhead. Experiments on multiple LLM architectures and NLP benchmarks show that our method achieves significant inference acceleration while maintaining competitive task performance, outperforming existing methods.

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 and reuse them in the next timesteps, allowing us to skip the computation in the next timesteps. However, on the one hand, aggressively reusing all the features cached in previous timesteps leads to a severe drop in generation quality. On the other hand, conservatively caching only the features in the redundant layers or tokens but still computing the important ones successfully preserves the generation quality but results in reductions in acceleration ratios. Observing such a tradeoff between generation quality and acceleration performance, this paper begins by quantitatively studying the accumulated error from cached features. Surprisingly, we find that aggressive caching does not introduce significantly more caching errors in the caching step, and the conservative feature caching can fix the error introduced by aggressive caching. Thereby, we propose a dual caching strategy that adopts aggressive and conservative caching iteratively, leading to significant acceleration and high generation quality at the same time. Besides, we further introduce a V-caching strategy for token-wise conservative caching, which is compatible with flash attention and requires no training and calibration data. Our codes have been released in Github: \textbf{Code: \href{https://github.com/Shenyi-Z/DuCa}{\texttt{\textcolor{cyan}{https://github.com/Shenyi-Z/DuCa}}}}

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion transformers by caching the features in previous timesteps and reusing them in the following timesteps. However, previous caching methods ignore that different tokens exhibit different sensitivities to feature caching, and feature caching on some tokens may lead to 10$\times$ more destruction to the overall generation quality compared with other tokens. In this paper, we introduce token-wise feature caching, allowing us to adaptively select the most suitable tokens for caching, and further enable us to apply different caching ratios to neural layers in different types and depths. Extensive experiments on PixArt-$\alpha$, OpenSora, and DiT demonstrate our effectiveness in both image and video generation with no requirements for training. For instance, 2.36$\times$ and 1.93$\times$ acceleration are achieved on OpenSora and PixArt-$\alpha$ with almost no drop in generation quality.

Recent advancements in Large Language Models (LLMs) have shown remarkable performance across a wide range of tasks. Despite this, the auto-regressive nature of LLM decoding, which generates only a single token per forward propagation, fails to fully exploit the parallel computational power of GPUs, leading to considerable latency. To address this, we introduce a novel speculative decoding method named FIRP which generates multiple tokens instead of one at each decoding step. We achieve this by predicting the intermediate hidden states of future tokens (tokens have not been decoded yet) and then using these pseudo hidden states to decode future tokens, specifically, these pseudo hidden states are predicted with simple linear transformation in intermediate layers of LLMs. Once predicted, they participate in the computation of all the following layers, thereby assimilating richer semantic information. As the layers go deeper, the semantic gap between pseudo and real hidden states is narrowed and it becomes feasible to decode future tokens with high accuracy. To validate the effectiveness of FIRP, we conduct extensive experiments, showing a speedup ratio of 1.9x-3x in several models and datasets, analytical experiments also prove our motivations.

Existing speculative decoding methods typically require additional model structure and training processes to assist the model for draft token generation. This makes the migration of acceleration methods to the new model more costly and more demanding on device memory. To address this problem, we propose the Make Some Noise (MSN) training framework as a replacement for the supervised fine-tuning stage of the large language model. The training method simply introduces some noise at the input for the model to learn the denoising task. It significantly enhances the parallel decoding capability of the model without affecting the original task capability. In addition, we propose a tree-based retrieval-augmented Jacobi (TR-Jacobi) decoding strategy to further improve the inference speed of MSN models. Experiments in both the general and code domains have shown that MSN can improve inference speed by 2.3-2.7x times without compromising model performance. The MSN model also achieves comparable acceleration ratios to the SOTA model with additional model structure on Spec-Bench.

Diffusion Transformers have recently demonstrated unprecedented generative capabilities for various tasks. The encouraging results, however, come with the cost of slow inference, since each denoising step requires inference on a transformer model with a large scale of parameters. In this study, we make an interesting and somehow surprising observation: the computation of a large proportion of layers in the diffusion transformer, through introducing a caching mechanism, can be readily removed even without updating the model parameters. In the case of U-ViT-H/2, for example, we may remove up to 93.68% of the computation in the cache steps (46.84% for all steps), with less than 0.01 drop in FID. To achieve this, we introduce a novel scheme, named Learning-to-Cache (L2C), that learns to conduct caching in a dynamic manner for diffusion transformers. Specifically, by leveraging the identical structure of layers in transformers and the sequential nature of diffusion, we explore redundant computations between timesteps by treating each layer as the fundamental unit for caching. To address the challenge of the exponential search space in deep models for identifying layers to cache and remove, we propose a novel differentiable optimization objective. An input-invariant yet timestep-variant router is then optimized, which can finally produce a static computation graph. Experimental results show that L2C largely outperforms samplers such as DDIM and DPM-Solver, alongside prior cache-based methods at the same inference speed.