Zhihang Yuan

Yuzhang Shang, Zhihang Yuan, Qiang Wu et al. · berkeley

This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. Due to previous binarization methods collapsing LLMs, we propose a novel approach, Partially-Binarized LLM (PB-LLM), which can achieve extreme low-bit quantization while maintaining the linguistic reasoning capacity of quantized LLMs. Specifically, our exploration first uncovers the ineffectiveness of naive applications of existing binarization algorithms and highlights the imperative role of salient weights in achieving low-bit quantization. Thus, PB-LLM filters a small ratio of salient weights during binarization, allocating them to higher-bit storage, i.e., partially-binarization. PB-LLM is extended to recover the capacities of quantized LMMs, by analyzing from the perspective of post-training quantization (PTQ) and quantization-aware training (QAT). Under PTQ, combining the concepts from GPTQ, we reconstruct the binarized weight matrix guided by the Hessian matrix and successfully recover the reasoning capacity of PB-LLM in low-bit. Under QAT, we freeze the salient weights during training, explore the derivation of optimal scaling factors crucial for minimizing the quantization error, and propose a scaling mechanism based on this derived scaling strategy for residual binarized weights. Those explorations and the developed methodologies significantly contribute to rejuvenating the performance of low-bit quantized LLMs and present substantial advancements in the field of network binarization for LLMs.The code is available at https://github.com/hahnyuan/BinaryLLM.

Yizeng Han, Zhihang Yuan, Yifan Pu et al.

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial redundancy in image features and saves a considerable amount of unnecessary computation. However, the theoretical efficiency achieved by previous methods can hardly translate into a realistic speedup, especially on the multi-core processors (e.g. GPUs). The key challenge is that the existing literature has only focused on designing algorithms with minimal computation, ignoring the fact that the practical latency can also be influenced by scheduling strategies and hardware properties. To bridge the gap between theoretical computation and practical efficiency, we propose a latency-aware spatial-wise dynamic network (LASNet), which performs coarse-grained spatially adaptive inference under the guidance of a novel latency prediction model. The latency prediction model can efficiently estimate the inference latency of dynamic networks by simultaneously considering algorithms, scheduling strategies, and hardware properties. We use the latency predictor to guide both the algorithm design and the scheduling optimization on various hardware platforms. Experiments on image classification, object detection and instance segmentation demonstrate that the proposed framework significantly improves the practical inference efficiency of deep networks. For example, the average latency of a ResNet-101 on the ImageNet validation set could be reduced by 36% and 46% on a server GPU (Nvidia Tesla-V100) and an edge device (Nvidia Jetson TX2 GPU) respectively without sacrificing the accuracy. Code is available at https://github.com/LeapLabTHU/LASNet.

Yizeng Han, Zeyu Liu, Zhihang Yuan et al.

Dynamic computation has emerged as a promising avenue to enhance the inference efficiency of deep networks. It allows selective activation of computational units, leading to a reduction in unnecessary computations for each input sample. However, the actual efficiency of these dynamic models can deviate from theoretical predictions. This mismatch arises from: 1) the lack of a unified approach due to fragmented research; 2) the focus on algorithm design over critical scheduling strategies, especially in CUDA-enabled GPU contexts; and 3) challenges in measuring practical latency, given that most libraries cater to static operations. Addressing these issues, we unveil the Latency-Aware Unified Dynamic Networks (LAUDNet), a framework that integrates three primary dynamic paradigms-spatially adaptive computation, dynamic layer skipping, and dynamic channel skipping. To bridge the theoretical and practical efficiency gap, LAUDNet merges algorithmic design with scheduling optimization, guided by a latency predictor that accurately gauges dynamic operator latency. We've tested LAUDNet across multiple vision tasks, demonstrating its capacity to notably reduce the latency of models like ResNet-101 by over 50% on platforms such as V100, RTX3090, and TX2 GPUs. Notably, LAUDNet stands out in balancing accuracy and efficiency. Code is available at: https://www.github.com/LeapLabTHU/LAUDNet.

Zhihang Yuan, Lin Niu, Jiawei Liu et al.

Large-scale language models (LLMs) have demonstrated impressive performance, but their deployment presents challenges due to their significant memory usage. This issue can be alleviated through quantization. In this paper, we identify that the challenge in quantizing activations in LLMs arises from varying ranges across channels, rather than solely the presence of outliers. To address this challenge, we introduce a quantization method called RPTQ, which utilizes a reorder-based approach. By rearranging the channels and quantizing them in clusters, RPTQ effectively mitigates the impact of range differences between channels. To minimize the overhead of the reorder operation, we fuse it into the layer norm operation and weights in linear layers. In our experiments, RPTQ achieved a significant breakthrough by utilizing 3-bit activation in LLMs for the first time, resulting in a substantial reduction in memory usage. For instance, quantizing OPT-175b can lead to a memory consumption reduction of up to 80%.

Zhihang Yuan, Jiawei Liu, Jiaxiang Wu et al.

Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures. Despite its effectiveness and convenience, the reliability of PTQ methods in the presence of some extrem cases such as distribution shift and data noise remains largely unexplored. This paper first investigates this problem on various commonly-used PTQ methods. We aim to answer several research questions related to the influence of calibration set distribution variations, calibration paradigm selection, and data augmentation or sampling strategies on PTQ reliability. A systematic evaluation process is conducted across a wide range of tasks and commonly-used PTQ paradigms. The results show that most existing PTQ methods are not reliable enough in term of the worst-case group performance, highlighting the need for more robust methods. Our findings provide insights for developing PTQ methods that can effectively handle distribution shift scenarios and enable the deployment of quantized DNNs in real-world applications.

Luning Wang, Shiyao Li, Xuefei Ning et al.

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache compression methods typically focus on quantization and token pruning, which have compression limits, and excessive sparsity can lead to severe performance degradation. Other methods design new architectures with less KV overhead but require significant training overhead. To address the above two drawbacks, we further explore the redundancy in the channel dimension and apply an architecture-level design with minor training costs. Therefore, we introduce CSKV, a training-efficient Channel Shrinking technique for KV cache compression: (1) We first analyze the singular value distribution of the KV cache, revealing significant redundancy and compression potential along the channel dimension. Based on this observation, we propose using low-rank decomposition for key and value layers and storing the low-dimension features. (2) To preserve model performance, we introduce a bi-branch KV cache, including a window-based full-precision KV cache and a low-precision compressed KV cache. (3) To reduce the training costs, we minimize the layer-wise reconstruction loss for the compressed KV cache instead of retraining the entire LLMs. Extensive experiments show that CSKV can reduce the memory overhead of the KV cache by 80% while maintaining the model's long-context capability. Moreover, we show that our method can be seamlessly combined with quantization to further reduce the memory overhead, achieving a compression ratio of up to 95%. Code is available at https://github.com/wln20/CSKV.

Lin Niu, Jiawei Liu, Zhihang Yuan et al.

Efficient inference for object detection networks is a major challenge on edge devices. Post-Training Quantization (PTQ), which transforms a full-precision model into low bit-width directly, is an effective and convenient approach to reduce model inference complexity. But it suffers severe accuracy drop when applied to complex tasks such as object detection. PTQ optimizes the quantization parameters by different metrics to minimize the perturbation of quantization. The p-norm distance of feature maps before and after quantization, Lp, is widely used as the metric to evaluate perturbation. For the specialty of object detection network, we observe that the parameter p in Lp metric will significantly influence its quantization performance. We indicate that using a fixed hyper-parameter p does not achieve optimal quantization performance. To mitigate this problem, we propose a framework, DetPTQ, to assign different p values for quantizing different layers using an Object Detection Output Loss (ODOL), which represents the task loss of object detection. DetPTQ employs the ODOL-based adaptive Lp metric to select the optimal quantization parameters. Experiments show that our DetPTQ outperforms the state-of-the-art PTQ methods by a significant margin on both 2D and 3D object detectors. For example, we achieve 31.1/31.7(quantization/full-precision) mAP on RetinaNet-ResNet18 with 4-bit weight and 4-bit activation.

Tianyu Fu, Yi Ge, Yichen You et al. · tsinghua

Large Language Models (LLMs) achieve impressive reasoning capabilities at the cost of substantial inference overhead, posing substantial deployment challenges. Although distilled Small Language Models (SLMs) significantly enhance efficiency, their performance suffers as they fail to follow LLMs' reasoning paths. Luckily, we reveal that only a small fraction of tokens genuinely diverge reasoning paths between LLMs and SLMs. Most generated tokens are either identical or exhibit neutral differences, such as minor variations in abbreviations or expressions. Leveraging this insight, we introduce **Roads to Rome (R2R)**, a neural token routing method that selectively utilizes LLMs only for these critical, path-divergent tokens, while leaving the majority of token generation to the SLM. We also develop an automatic data generation pipeline that identifies divergent tokens and generates token-level routing labels to train the lightweight router. We apply R2R to combine R1-1.5B and R1-32B models from the DeepSeek family, and evaluate on challenging math, coding, and QA benchmarks. With an average activated parameter size of 5.6B, R2R surpasses the average accuracy of R1-7B by 1.6x, outperforming even the R1-14B model. Compared to R1-32B, it delivers a 2.8x wall-clock speedup with comparable performance, advancing the Pareto frontier of test-time scaling efficiency. Our code is available at https://github.com/thu-nics/R2R.

JiangYong Yu, Sifan Zhou, Dawei Yang et al.

Multimodal large language models (MLLMs) have garnered widespread attention due to their ability to understand multimodal input. However, their large parameter sizes and substantial computational demands severely hinder their practical deployment and application.While quantization is an effective way to reduce model size and inference latency, its application to MLLMs remains underexplored. In this paper, we propose MQuant, a post-training quantization (PTQ) framework designed to tackle the unique challenges of multimodal large language models (MLLMs). Conventional quantization often struggles with MLLMs because of (a) high inference latency from large visual token counts, (b) distributional disparities between visual and textual tokens, and (c) extreme outliers introduced by Hadamard-based transformations. To address these issues, MQuant introduces: Modality-Specific Static Quantization (MSQ), assigning distinct static scales for visual vs. textual tokens; Attention-Invariant Flexible Switching (AIFS), reordering tokens to preserve casual attention while eliminating expensive token-wise scale computations; Rotation Magnitude Suppression (RMS), mitigating weight outliers arising from online Hadamard rotations. On five mainstream MLLMs (including Qwen-VL, MiniCPM-V, CogVLM2), MQuant under W4A8 achieves near-floating-point accuracy (<1% degradation) while reducing inference latency by up to 30%, significantly outperforming existing PTQ baselines. Our MQuant effectively bridges the gap for efficient and accurate MLLMs inference in resource-constrained devices. Code has been released in https://github.com/StiphyJay/MQuant.

Zixuan Zhou, Xuefei Ning, Ke Hong et al. · tsinghua

Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirements of LLM inference pose challenges for deployment in resource-constrained scenarios. Efforts within the field have been directed towards developing techniques aimed at enhancing the efficiency of LLM inference. This paper presents a comprehensive survey of the existing literature on efficient LLM inference. We start by analyzing the primary causes of the inefficient LLM inference, i.e., the large model size, the quadratic-complexity attention operation, and the auto-regressive decoding approach. Then, we introduce a comprehensive taxonomy that organizes the current literature into data-level, model-level, and system-level optimization. Moreover, the paper includes comparative experiments on representative methods within critical sub-fields to provide quantitative insights. Last but not least, we provide some knowledge summary and discuss future research directions.

Haoxuan Wang, Yuzhang Shang, Zhihang Yuan et al.

The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit quantization efficiently. In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty, and propose to adjust these distributions through weight finetuning to be more quantization-friendly. We provide both theoretical and empirical evidence supporting finetuning as a practical and reliable solution. Building on this approach, we further distinguish two critical types of quantized layers: those responsible for retaining essential temporal information and those particularly sensitive to bit-width reduction. By selectively finetuning these layers under both local and global supervision, we mitigate performance degradation while enhancing quantization efficiency. Our method demonstrates its efficacy across three high-resolution image generation tasks, obtaining state-of-the-art performance across multiple bit-width settings.

Xing Hu, Zhixuan Chen, Dawei Yang et al.

Mixture-of-Experts (MoE) large language models (LLMs), which leverage dynamic routing and sparse activation to enhance efficiency and scalability, have achieved higher performance while reducing computational costs. However, these models face significant memory overheads, limiting their practical deployment and broader adoption. Post-training quantization (PTQ), a widely used method for compressing LLMs, encounters severe accuracy degradation and diminished generalization performance when applied to MoE models. This paper investigates the impact of MoE's sparse and dynamic characteristics on quantization and identifies two primary challenges: (1) Inter-expert imbalance, referring to the uneven distribution of samples across experts, which leads to insufficient and biased calibration for less frequently utilized experts; (2) Intra-expert imbalance, arising from MoE's unique aggregation mechanism, which leads to varying degrees of correlation between different samples and their assigned experts. To address these challenges, we propose MoEQuant, a novel quantization framework tailored for MoE LLMs. MoE-Quant includes two novel techniques: 1) Expert-Balanced Self-Sampling (EBSS) is an efficient sampling method that efficiently constructs a calibration set with balanced expert distributions by leveraging the cumulative probabilities of tokens and expert balance metrics as guiding factors. 2) Affinity-Guided Quantization (AGQ), which incorporates affinities between experts and samples into the quantization process, thereby accurately assessing the impact of individual samples on different experts within the MoE layer. Experiments demonstrate that MoEQuant achieves substantial performance gains (more than 10 points accuracy gain in the HumanEval for DeepSeekMoE-16B under 4-bit quantization) and boosts efficiency.

Zhaofeng Hu, Sifan Zhou, Zhihang Yuan et al.

3D single object tracking is essential in autonomous driving and robotics. Existing methods often struggle with sparse and incomplete point cloud scenarios. To address these limitations, we propose a Multimodal-guided Virtual Cues Projection (MVCP) scheme that generates virtual cues to enrich sparse point clouds. Additionally, we introduce an enhanced tracker MVCTrack based on the generated virtual cues. Specifically, the MVCP scheme seamlessly integrates RGB sensors into LiDAR-based systems, leveraging a set of 2D detections to create dense 3D virtual cues that significantly improve the sparsity of point clouds. These virtual cues can naturally integrate with existing LiDAR-based 3D trackers, yielding substantial performance gains. Extensive experiments demonstrate that our method achieves competitive performance on the NuScenes dataset.

Rui Xie, Tianchen Zhao, Zhihang Yuan et al. · tsinghua

Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial computational resources, limiting their applicability on resource-constrained devices. To address this issue, we conducted analysis and identified significant redundancy in three dimensions of the VAR model: (1) the attention map, (2) the attention outputs when using classifier free guidance, and (3) the data precision. Correspondingly, we proposed efficient attention mechanism and low-bit quantization method to enhance the efficiency of VAR models while maintaining performance. With negligible performance lost (less than 0.056 FID increase), we could achieve 85.2% reduction in attention computation, 50% reduction in overall memory and 1.5x latency reduction. To ensure deployment feasibility, we developed efficient training-free compression techniques and analyze the deployment feasibility and efficiency gain of each technique.

Songsheng Wang, Rucheng Yu, Zhihang Yuan et al.

Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models. While Speculative Decoding (SD) has shown efficacy in accelerating Large Language Models (LLMs) by incorporating efficient drafting and parallel verification, allowing multiple tokens to be generated in one forward pass, its application to VLA models remains unexplored. This work introduces Spec-VLA, an SD framework designed to accelerate VLA models. Due to the difficulty of the action prediction task and the greedy decoding mechanism of the VLA models, the direct application of the advanced SD framework to the VLA prediction task yields a minor speed improvement. To boost the generation speed, we propose an effective mechanism to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model. Empirical results across diverse test scenarios affirm the effectiveness of the Spec-VLA framework, and further analysis substantiates the impact of our proposed strategies, which enhance the acceptance length by 44%, achieving 1.42 times speedup compared with the OpenVLA baseline, without compromising the success rate. The success of the Spec-VLA framework highlights the potential for broader application of speculative execution in VLA prediction scenarios.

Zhihang Yuan, Yuzhang Shang, Hanling Zhang et al.

Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these models face efficiency challenges due to their sequential token generation nature and reliance on computationally intensive diffusion-based sampling. We present ECAR (Efficient Continuous Auto-Regressive Image Generation via Multistage Modeling), an approach that addresses these limitations through two intertwined innovations: (1) a stage-wise continuous token generation strategy that reduces computational complexity and provides progressively refined token maps as hierarchical conditions, and (2) a multistage flow-based distribution modeling method that transforms only partial-denoised distributions at each stage comparing to complete denoising in normal diffusion models. Holistically, ECAR operates by generating tokens at increasing resolutions while simultaneously denoising the image at each stage. This design not only reduces token-to-image transformation cost by a factor of the stage number but also enables parallel processing at the token level. Our approach not only enhances computational efficiency but also aligns naturally with image generation principles by operating in continuous token space and following a hierarchical generation process from coarse to fine details. Experimental results demonstrate that ECAR achieves comparable image quality to DiT Peebles & Xie [2023] while requiring 10$\times$ FLOPs reduction and 5$\times$ speedup to generate a 256$\times$256 image.

Yi Guo, Wei Wang, Zhihang Yuan et al.

Generative models like Flow Matching have achieved state-of-the-art performance but are often hindered by a computationally expensive iterative sampling process. To address this, recent work has focused on few-step or one-step generation by learning the average velocity field, which directly maps noise to data. MeanFlow, a leading method in this area, learns this field by enforcing a differential identity that connects the average and instantaneous velocities. In this work, we argue that this differential formulation is a limiting special case of a more fundamental principle. We return to the first principles of average velocity and leverage the additivity property of definite integrals. This leads us to derive a novel, purely algebraic identity we term Interval Splitting Consistency. This identity establishes a self-referential relationship for the average velocity field across different time intervals without resorting to any differential operators. Based on this principle, we introduce SplitMeanFlow, a new training framework that enforces this algebraic consistency directly as a learning objective. We formally prove that the differential identity at the core of MeanFlow is recovered by taking the limit of our algebraic consistency as the interval split becomes infinitesimal. This establishes SplitMeanFlow as a direct and more general foundation for learning average velocity fields. From a practical standpoint, our algebraic approach is significantly more efficient, as it eliminates the need for JVP computations, resulting in simpler implementation, more stable training, and broader hardware compatibility. One-step and two-step SplitMeanFlow models have been successfully deployed in large-scale speech synthesis products (such as Doubao), achieving speedups of 20x.

Yuxuan Yue, Zukang Xu, Zhihang Yuan et al.

Large Language Models (LLMs) face significant challenges in edge deployment due to their massive parameter scale. Vector Quantization (VQ), a clustering-based quantization method, serves as a prevalent solution to this issue for its extremely low-bit (even at 2-bit) and considerable accuracy. Since a vector is a quantity in mathematics and physics that has both direction and magnitude, existing VQ works typically quantize them in a coupled manner. However, we find that direction exhibits significantly greater sensitivity to quantization compared to the magnitude. For instance, when separately clustering the directions and magnitudes of weight vectors in LLaMA-2-7B, the accuracy drop of zero-shot tasks are 46.5\% and 2.3\%, respectively. This gap even increases with the reduction of clustering centers. Further, Euclidean distance, a common metric to access vector similarities in current VQ works, places greater emphasis on reducing the magnitude error. This property is contrary to the above finding, unavoidably leading to larger quantization errors. To these ends, this paper proposes Polar Coordinate Decoupled Vector Quantization (PCDVQ), an effective and efficient VQ framework consisting of two key modules: 1) Polar Coordinate Decoupling (PCD), which transforms vectors into their polar coordinate representations and perform independent quantization of the direction and magnitude parameters.2) Distribution Aligned Codebook Construction (DACC), which optimizes the direction and magnitude codebooks in accordance with the source distribution. Experimental results show that PCDVQ outperforms baseline methods at 2-bit level by at least 1.5\% zero-shot accuracy, establishing a novel paradigm for accurate and highly compressed LLMs.

Zhihang Yuan, Siyuan Wang, Rui Xie et al.

In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free paradigm that can make use of adaptive temporal compression in latent space. While existing video generative models apply fixed compression rates via pretrained VAE, we observe that real-world video content exhibits substantial temporal non-uniformity, with high-motion segments containing more information than static scenes. Based on this insight, DLFR-VAE dynamically adjusts the latent frame rate according to the content complexity. Specifically, DLFR-VAE comprises two core innovations: (1) A Dynamic Latent Frame Rate Scheduler that partitions videos into temporal chunks and adaptively determines optimal frame rates based on information-theoretic content complexity, and (2) A training-free adaptation mechanism that transforms pretrained VAE architectures into a dynamic VAE that can process features with variable frame rates. Our simple but effective DLFR-VAE can function as a plug-and-play module, seamlessly integrating with existing video generation models and accelerating the video generation process.

Zhihang Yuan, Rui Xie, Yuzhang Shang et al.

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal non-uniformity of real-world videos and observe that videos exhibit dynamic information density, with high-motion segments demanding greater detail preservation than static scenes. Inspired by this temporal non-uniformity, we propose VGDFR, a training-free approach for Diffusion-based Video Generation with Dynamic Latent Frame Rate. VGDFR adaptively adjusts the number of elements in latent space based on the motion frequency of the latent space content, using fewer tokens for low-frequency segments while preserving detail in high-frequency segments. Specifically, our key contributions are: (1) A dynamic frame rate scheduler for DiT video generation that adaptively assigns frame rates for video segments. (2) A novel latent-space frame merging method to align latent representations with their denoised counterparts before merging those redundant in low-resolution space. (3) A preference analysis of Rotary Positional Embeddings (RoPE) across DiT layers, informing a tailored RoPE strategy optimized for semantic and local information capture. Experiments show that VGDFR can achieve a speedup up to 3x for video generation with minimal quality degradation.

Zhihang Yuan, Hanling Zhang, Pu Lu et al.

Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators. We propose DiTFastAttn, a post-training compression method to alleviate the computational bottleneck of DiT. We identify three key redundancies in the attention computation during DiT inference: (1) spatial redundancy, where many attention heads focus on local information; (2) temporal redundancy, with high similarity between the attention outputs of neighboring steps; (3) conditional redundancy, where conditional and unconditional inferences exhibit significant similarity. We propose three techniques to reduce these redundancies: (1) Window Attention with Residual Sharing to reduce spatial redundancy; (2) Attention Sharing across Timesteps to exploit the similarity between steps; (3) Attention Sharing across CFG to skip redundant computations during conditional generation. We apply DiTFastAttn to DiT, PixArt-Sigma for image generation tasks, and OpenSora for video generation tasks. Our results show that for image generation, our method reduces up to 76% of the attention FLOPs and achieves up to 1.8x end-to-end speedup at high-resolution (2k x 2k) generation.

Zhihang Yuan, Yuzhang Shang, Yue Song et al.

In this paper, we introduce a new post-training compression paradigm for Large Language Models (LLMs) to facilitate their wider adoption. We delve into LLM weight low-rank decomposition, and find that the challenges of this task stem from (1) the distribution variance in the LLM activations and (2) the sensitivity difference among various kinds of layers. To address these issues, we propose a training-free approach called Activation-aware Singular Value Decomposition (ASVD). Specifically, ASVD manages activation outliers by transforming the weight matrix based on the activation distribution. This transformation allows the outliers in the activation matrix to be absorbed into the transformed weight matrix, thereby enhancing decomposition accuracy. Additionally, we propose an efficient iterative calibration process to optimize layer-specific decomposition by addressing the varying sensitivity of different LLM layers. In this way, ASVD can compress a network by 10%-30%. Based on the success of the low-rank decomposition of projection matrices in the self-attention module, we further introduce ASVD to compress the KV cache. By reducing the channel dimension of KV activations, memory requirements for KV cache can be largely reduced. ASVD can further achieve 50% KV cache reductions without performance drop in a training-free manner.

Zhihang Yuan, Yiqi Chen, Chenhao Xue et al.

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quantization. Most existing approaches share the scaling factors layerwisely or channelwisely for quantization of convolutional layers. Channelwise quantization and layerwise quantization have been widely used in various applications. However, other quantization granularities are rarely explored. In this paper, we will explore the sub-layerwise granularity that shares the scaling factor across multiple input and output channels. We propose an efficient post-training quantization method in sub-layerwise granularity (PTQ-SL). Then we systematically experiment on various granularities and observe that the prediction accuracy of the quantized neural network has a strong correlation with the granularity. Moreover, we find that adjusting the position of the channels can improve the performance of sub-layerwise quantization. Therefore, we propose a method to reorder the channels for sub-layerwise quantization. The experiments demonstrate that the sub-layerwise quantization with appropriate channel reordering can outperform the channelwise quantization.

Zhihang Yuan, Xin Liu, Bingzhe Wu et al.

Dynamic inference is a feasible way to reduce the computational cost of convolutional neural network(CNN), which can dynamically adjust the computation for each input sample. One of the ways to achieve dynamic inference is to use multi-stage neural network, which contains a sub-network with prediction layer at each stage. The inference of a input sample can exit from early stage if the prediction of the stage is confident enough. However, design a multi-stage CNN architecture is a non-trivial task. In this paper, we introduce a general framework, ENAS4D, which can efficiently search for optimal multi-stage CNN architecture for dynamic inference in a well-designed search space. Firstly, we propose a method to construct the search space with multi-stage convolution. The search space include different numbers of layers, different kernel sizes and different numbers of channels for each stage and the resolution of input samples. Then, we train a once-for-all network that supports to sample diverse multi-stage CNN architecture. A specialized multi-stage network can be obtained from the once-for-all network without additional training. Finally, we devise a method to efficiently search for the optimal multi-stage network that trades the accuracy off the computational cost taking the advantage of once-for-all network. The experiments on the ImageNet classification task demonstrate that the multi-stage CNNs searched by ENAS4D consistently outperform the state-of-the-art method for dyanmic inference. In particular, the network achieves 74.4% ImageNet top-1 accuracy under 185M average MACs.

Zhihang Yuan, Bingzhe Wu, Zheng Liang et al.

Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference process according to each input sample, which can considerably reduce the computational cost on "easy" samples while maintaining the overall model performance. In this paper, we introduce a general framework, S2DNAS, which can transform various static CNN models to support dynamic inference via neural architecture search. To this end, based on a given CNN model, we first generate a CNN architecture space in which each architecture is a multi-stage CNN generated from the given model using some predefined transformations. Then, we propose a reinforcement learning based approach to automatically search for the optimal CNN architecture in the generated space. At last, with the searched multi-stage network, we can perform dynamic inference by adaptively choosing a stage to evaluate for each sample. Unlike previous works that introduce irregular computations or complex controllers in the inference or re-design a CNN model from scratch, our method can generalize to most of the popular CNN architectures and the searched dynamic network can be directly deployed using existing deep learning frameworks in various hardware devices.