arXiv subjects

Zhengang Li

Publications and source records attributed to Zhengang Li.

At least 19 recordsLinked to original sources

arXiv2025

FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge

Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially larger number of tokens to produce coherent temporal frames, resulting in significant overhead during the decoding phase. Our key observations are: (i) MLP modules in the decode phase dominate the inference latency, and (ii) there exists high temporal redundancy in MLP outputs of adjacent frames. In this paper, we propose the \textbf{FastCar} framework to accelerate the decode phase for the AR video generation by exploring the temporal redundancy. The Temporal Attention Score (TAS) is proposed to determine whether to apply the replay strategy (\textit{i.e.}, reusing cached MLP outputs from the previous frame to reduce redundant computations) with detailed theoretical analysis and justification. Also, we develop a hardware accelerator on FPGA with Dynamic Resource Scheduling (DRS) based on TAS to enable better resource utilization and faster inference. Experimental results demonstrate the effectiveness of our method, which outperforms traditional sparse attention approaches with more than 2.1x decoding speedup and higher energy efficiency on the edge. Furthermore, by combining FastCar and sparse attention, FastCar can boost the performance of sparse attention with alleviated drifting, demonstrating our unique advantages for high-resolution and long-duration video generation. Code: https://github.com/shawnricecake/fast-car

cs.CV↗

arXiv2025

Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge

Large Language Models (LLMs) stand out for their impressive performance in intricate language modeling tasks. However, their demanding computational and memory needs pose obstacles for broad use on edge devices. Quantization is then introduced to boost LLMs' on-device efficiency. Recent works show that 8-bit or lower weight quantization is feasible with minimal impact on end-to-end task performance, while the activation is still not quantized. On the other hand, mainstream commodity edge devices still struggle to execute these sub-8-bit quantized networks effectively. In this paper, we propose Agile-Quant, an activation-guided quantization framework for popular Large Language Models (LLMs), and implement an end-to-end accelerator on multiple edge devices for faster inference. Considering the hardware profiling and activation analysis, we first introduce a basic activation quantization strategy to balance the trade-off of task performance and real inference speed. Then we leverage the activation-aware token pruning technique to reduce the outliers and the adverse impact on attentivity. Ultimately, we utilize the SIMD-based 4-bit multiplier and our efficient TRIP matrix multiplication to implement the accelerator for LLMs on the edge. We apply our framework on different scales of LLMs including LLaMA, OPT, and BLOOM with 4-bit or 8-bit for the activation and 4-bit for the weight quantization. Experiments show that Agile-Quant achieves simultaneous quantization of model weights and activations while maintaining task performance comparable to existing weight-only quantization methods. Moreover, in the 8- and 4-bit scenario, Agile-Quant achieves an on-device speedup of up to 2.55x compared to its FP16 counterparts across multiple edge devices, marking a pioneering advancement in this domain. Code: https://github.com/shawnricecake/agile-quant

cs.LG↗

arXiv2024

LUTMUL: Exceed Conventional FPGA Roofline Limit by LUT-based Efficient Multiplication for Neural Network Inference

For FPGA-based neural network accelerators, digital signal processing (DSP) blocks have traditionally been the cornerstone for handling multiplications. This paper introduces LUTMUL, which harnesses the potential of look-up tables (LUTs) for performing multiplications. The availability of LUTs typically outnumbers that of DSPs by a factor of 100, offering a significant computational advantage. By exploiting this advantage of LUTs, our method demonstrates a potential boost in the performance of FPGA-based neural network accelerators with a reconfigurable dataflow architecture. Our approach challenges the conventional peak performance on DSP-based accelerators and sets a new benchmark for efficient neural network inference on FPGAs. Experimental results demonstrate that our design achieves the best inference speed among all FPGA-based accelerators, achieving a throughput of 1627 images per second and maintaining a top-1 accuracy of 70.95% on the ImageNet dataset.

cs.AR↗

arXiv2024

Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers

Vision transformers (ViTs) have demonstrated their superior accuracy for computer vision tasks compared to convolutional neural networks (CNNs). However, ViT models are often computation-intensive for efficient deployment on resource-limited edge devices. This work proposes Quasar-ViT, a hardware-oriented quantization-aware architecture search framework for ViTs, to design efficient ViT models for hardware implementation while preserving the accuracy. First, Quasar-ViT trains a supernet using our row-wise flexible mixed-precision quantization scheme, mixed-precision weight entanglement, and supernet layer scaling techniques. Then, it applies an efficient hardware-oriented search algorithm, integrated with hardware latency and resource modeling, to determine a series of optimal subnets from supernet under different inference latency targets. Finally, we propose a series of model-adaptive designs on the FPGA platform to support the architecture search and mitigate the gap between the theoretical computation reduction and the practical inference speedup. Our searched models achieve 101.5, 159.6, and 251.6 frames-per-second (FPS) inference speed on the AMD/Xilinx ZCU102 FPGA with 80.4%, 78.6%, and 74.9% top-1 accuracy, respectively, for the ImageNet dataset, consistently outperforming prior works.

cs.LG↗

arXiv2024

SuperFlow: A Fully-Customized RTL-to-GDS Design Automation Flow for Adiabatic Quantum-Flux-Parametron Superconducting Circuits

Superconducting circuits, like Adiabatic Quantum-Flux-Parametron (AQFP), offer exceptional energy efficiency but face challenges in physical design due to sophisticated spacing and timing constraints. Current design tools often neglect the importance of constraint adherence throughout the entire design flow. In this paper, we propose SuperFlow, a fully-customized RTL-to-GDS design flow tailored for AQFP devices. SuperFlow leverages a synthesis tool based on CMOS technology to transform any input RTL netlist to an AQFP-based netlist. Subsequently, we devise a novel place-and-route procedure that simultaneously considers wirelength, timing, and routability for AQFP circuits. The process culminates in the generation of the AQFP circuit layout, followed by a Design Rule Check (DRC) to identify and rectify any layout violations. Our experimental results demonstrate that SuperFlow achieves 12.8% wirelength improvement on average and 12.1% better timing quality compared with previous state-of-the-art placers for AQFP circuits.

cs.ET↗

arXiv2024

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model

While AI-generated content has garnered significant attention, achieving photo-realistic video synthesis remains a formidable challenge. Despite the promising advances in diffusion models for video generation quality, the complex model architecture and substantial computational demands for both training and inference create a significant gap between these models and real-world applications. This paper presents SNED, a superposition network architecture search method for efficient video diffusion model. Our method employs a supernet training paradigm that targets various model cost and resolution options using a weight-sharing method. Moreover, we propose the supernet training sampling warm-up for fast training optimization. To showcase the flexibility of our method, we conduct experiments involving both pixel-space and latent-space video diffusion models. The results demonstrate that our framework consistently produces comparable results across different model options with high efficiency. According to the experiment for the pixel-space video diffusion model, we can achieve consistent video generation results simultaneously across 64 x 64 to 256 x 256 resolutions with a large range of model sizes from 640M to 1.6B number of parameters for pixel-space video diffusion models.

cs.CV↗

arXiv2024

A Video Coding Method Based on Neural Network for CLIC2024

This paper presents a video coding scheme that combines traditional optimization methods with deep learning methods based on the Enhanced Compression Model (ECM). In this paper, the traditional optimization methods adaptively adjust the quantization parameter (QP). The key frame QP offset is set according to the video content characteristics, and the coding tree unit (CTU) level QP of all frames is also adjusted according to the spatial-temporal perception information. Block importance mapping technology (BIM) is also introduced, which adjusts the QP according to the block importance. Meanwhile, the deep learning methods propose a convolutional neural network-based loop filter (CNNLF), which is turned on/off based on the rate-distortion optimization at the CTU and frame level. Besides, intra-prediction using neural networks (NN-intra) is proposed to further improve compression quality, where 8 neural networks are used for predicting blocks of different sizes. The experimental results show that compared with ECM-3.0, the proposed traditional methods and adding deep learning methods improve the PSNR by 0.54 dB and 1 dB at 0.05Mbps, respectively; 0.38 dB and 0.71dB at 0.5 Mbps, respectively, which proves the superiority of our method.

eess.IV↗

arXiv2023

SupeRBNN: Randomized Binary Neural Network Using Adiabatic Superconductor Josephson Devices

Adiabatic Quantum-Flux-Parametron (AQFP) is a superconducting logic with extremely high energy efficiency. By employing the distinct polarity of current to denote logic `0' and `1', AQFP devices serve as excellent carriers for binary neural network (BNN) computations. Although recent research has made initial strides toward developing an AQFP-based BNN accelerator, several critical challenges remain, preventing the design from being a comprehensive solution. In this paper, we propose SupeRBNN, an AQFP-based randomized BNN acceleration framework that leverages software-hardware co-optimization to eventually make the AQFP devices a feasible solution for BNN acceleration. Specifically, we investigate the randomized behavior of the AQFP devices and analyze the impact of crossbar size on current attenuation, subsequently formulating the current amplitude into the values suitable for use in BNN computation. To tackle the accumulation problem and improve overall hardware performance, we propose a stochastic computing-based accumulation module and a clocking scheme adjustment-based circuit optimization method. We validate our SupeRBNN framework across various datasets and network architectures, comparing it with implementations based on different technologies, including CMOS, ReRAM, and superconducting RSFQ/ERSFQ. Experimental results demonstrate that our design achieves an energy efficiency of approximately 7.8x10^4 times higher than that of the ReRAM-based BNN framework while maintaining a similar level of model accuracy. Furthermore, when compared with superconductor-based counterparts, our framework demonstrates at least two orders of magnitude higher energy efficiency.

cs.ET↗

arXiv2023

A Life-Cycle Energy and Inventory Analysis of Adiabatic Quantum-Flux-Parametron Circuits

The production process of superconductive integrated circuits is complex and consumes significant amounts of resources and energy. Therefore, it is crucial to evaluate the environmental impact of this emerging technology. An attractive option for the next generation of superconductive technology is Adiabatic Quantum-Flux-Parametron (AQFP) devices. This study is the first to present a comprehensive process-based life-cycle assessment (LCA) and inventory analysis of AQFP integrated circuits. To generate relevant outcomes, we conduct a comparative LCA that included the bulk CMOS technology. The inventory analysis considered the manufacturing, assembly, and use phases of the circuits. To ensure a fair assessment, we choose the 32-bit AQFP RISC-V single-core processor as the reference functional unit and compare its performance with that of a CMOS counterpart. Our findings reveal that the AQFP processor consumes several orders of magnitude less energy during the use phase than its CMOS counterpart. Consequently, the total life cycle energy (which encompasses manufacturing and assembly energies) of AQFP integrated circuits improves at least by two orders of magnitude.

cs.ET↗

arXiv2023

StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks

Obstacle detection is a safety-critical problem in robot navigation, where stereo matching is a popular vision-based approach. While deep neural networks have shown impressive results in computer vision, most of the previous obstacle detection works only leverage traditional stereo matching techniques to meet the computational constraints for real-time feedback. This paper proposes a computationally efficient method that employs a deep neural network to detect occupancy from stereo images directly. Instead of learning the point cloud correspondence from the stereo data, our approach extracts the compact obstacle distribution based on volumetric representations. In addition, we prune the computation of safety irrelevant spaces in a coarse-to-fine manner based on octrees generated by the decoder. As a result, we achieve real-time performance on the onboard computer (NVIDIA Jetson TX2). Our approach detects obstacles accurately in the range of 32 meters and achieves better IoU (Intersection over Union) and CD (Chamfer Distance) scores with only 2% of the computation cost of the state-of-the-art stereo model. Furthermore, we validate our method's robustness and real-world feasibility through autonomous navigation experiments with a real robot. Hence, our work contributes toward closing the gap between the stereo-based system in robot perception and state-of-the-art stereo models in computer vision. To counter the scarcity of high-quality real-world indoor stereo datasets, we collect a 1.36 hours stereo dataset with a mobile robot which is used to fine-tune our model. The dataset, the code, and further details including additional visualizations are available at https://lhy.xyz/stereovoxelnet

cs.RO↗

arXiv2023

HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers

While vision transformers (ViTs) have continuously achieved new milestones in the field of computer vision, their sophisticated network architectures with high computation and memory costs have impeded their deployment on resource-limited edge devices. In this paper, we propose a hardware-efficient image-adaptive token pruning framework called HeatViT for efficient yet accurate ViT acceleration on embedded FPGAs. By analyzing the inherent computational patterns in ViTs, we first design an effective attention-based multi-head token selector, which can be progressively inserted before transformer blocks to dynamically identify and consolidate the non-informative tokens from input images. Moreover, we implement the token selector on hardware by adding miniature control logic to heavily reuse existing hardware components built for the backbone ViT. To improve the hardware efficiency, we further employ 8-bit fixed-point quantization, and propose polynomial approximations with regularization effect on quantization error for the frequently used nonlinear functions in ViTs. Finally, we propose a latency-aware multi-stage training strategy to determine the transformer blocks for inserting token selectors and optimize the desired (average) pruning rates for inserted token selectors, in order to improve both the model accuracy and inference latency on hardware. Compared to existing ViT pruning studies, under the similar computation cost, HeatViT can achieve 0.7%$\sim$8.9% higher accuracy; while under the similar model accuracy, HeatViT can achieve more than 28.4%$\sim$65.3% computation reduction, for various widely used ViTs, including DeiT-T, DeiT-S, DeiT-B, LV-ViT-S, and LV-ViT-M, on the ImageNet dataset. Compared to the baseline hardware accelerator, our implementations of HeatViT on the Xilinx ZCU102 FPGA achieve 3.46$\times$$\sim$4.89$\times$ speedup.

cs.AR↗

arXiv2022

Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization

Vision transformers (ViTs) are emerging with significantly improved accuracy in computer vision tasks. However, their complex architecture and enormous computation/storage demand impose urgent needs for new hardware accelerator design methodology. This work proposes an FPGA-aware automatic ViT acceleration framework based on the proposed mixed-scheme quantization. To the best of our knowledge, this is the first FPGA-based ViT acceleration framework exploring model quantization. Compared with state-of-the-art ViT quantization work (algorithmic approach only without hardware acceleration), our quantization achieves 0.47% to 1.36% higher Top-1 accuracy under the same bit-width. Compared with the 32-bit floating-point baseline FPGA accelerator, our accelerator achieves around 5.6x improvement on the frame rate (i.e., 56.8 FPS vs. 10.0 FPS) with 0.71% accuracy drop on ImageNet dataset for DeiT-base.

cs.CV↗

arXiv2022

FAIVConf: Face enhancement for AI-based Video Conference with Low Bit-rate

Recently, high-quality video conferencing with fewer transmission bits has become a very hot and challenging problem. We propose FAIVConf, a specially designed video compression framework for video conferencing, based on the effective neural human face generation techniques. FAIVConf brings together several designs to improve the system robustness in real video conference scenarios: face-swapping to avoid artifacts in background animation; facial blurring to decrease transmission bit-rate and maintain the quality of extracted facial landmarks; and dynamic source update for face view interpolation to accommodate a large range of head poses. Our method achieves a significant bit-rate reduction in the video conference and gives much better visual quality under the same bit-rate compared with H.264 and H.265 coding schemes.

eess.IV↗

arXiv2022

F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization

Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision models. To reduce it, existing quantization approaches require high-precision INT32 or full-precision multiplication during inference for scaling or dequantization. This introduces a noticeable cost in terms of memory, speed, and required energy. To tackle these issues, we present F8Net, a novel quantization framework consisting of only fixed-point 8-bit multiplication. To derive our method, we first discuss the advantages of fixed-point multiplication with different formats of fixed-point numbers and study the statistical behavior of the associated fixed-point numbers. Second, based on the statistical and algorithmic analysis, we apply different fixed-point formats for weights and activations of different layers. We introduce a novel algorithm to automatically determine the right format for each layer during training. Third, we analyze a previous quantization algorithm -- parameterized clipping activation (PACT) -- and reformulate it using fixed-point arithmetic. Finally, we unify the recently proposed method for quantization fine-tuning and our fixed-point approach to show the potential of our method. We verify F8Net on ImageNet for MobileNet V1/V2 and ResNet18/50. Our approach achieves comparable and better performance, when compared not only to existing quantization techniques with INT32 multiplication or floating-point arithmetic, but also to the full-precision counterparts, achieving state-of-the-art performance.

cs.CV↗

arXiv2021

Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration

Weight pruning is an effective model compression technique to tackle the challenges of achieving real-time deep neural network (DNN) inference on mobile devices. However, prior pruning schemes have limited application scenarios due to accuracy degradation, difficulty in leveraging hardware acceleration, and/or restriction on certain types of DNN layers. In this paper, we propose a general, fine-grained structured pruning scheme and corresponding compiler optimizations that are applicable to any type of DNN layer while achieving high accuracy and hardware inference performance. With the flexibility of applying different pruning schemes to different layers enabled by our compiler optimizations, we further probe into the new problem of determining the best-suited pruning scheme considering the different acceleration and accuracy performance of various pruning schemes. Two pruning scheme mapping methods, one is search-based and the other is rule-based, are proposed to automatically derive the best-suited pruning regularity and block size for each layer of any given DNN. Experimental results demonstrate that our pruning scheme mapping methods, together with the general fine-grained structured pruning scheme, outperform the state-of-the-art DNN optimization framework with up to 2.48$\times$ and 1.73$\times$ DNN inference acceleration on CIFAR-10 and ImageNet dataset without accuracy loss.

cs.LG↗

arXiv2021

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge

Recently, a new trend of exploring sparsity for accelerating neural network training has emerged, embracing the paradigm of training on the edge. This paper proposes a novel Memory-Economic Sparse Training (MEST) framework targeting for accurate and fast execution on edge devices. The proposed MEST framework consists of enhancements by Elastic Mutation (EM) and Soft Memory Bound (&S) that ensure superior accuracy at high sparsity ratios. Different from the existing works for sparse training, this current work reveals the importance of sparsity schemes on the performance of sparse training in terms of accuracy as well as training speed on real edge devices. On top of that, the paper proposes to employ data efficiency for further acceleration of sparse training. Our results suggest that unforgettable examples can be identified in-situ even during the dynamic exploration of sparsity masks in the sparse training process, and therefore can be removed for further training speedup on edge devices. Comparing with state-of-the-art (SOTA) works on accuracy, our MEST increases Top-1 accuracy significantly on ImageNet when using the same unstructured sparsity scheme. Systematical evaluation on accuracy, training speed, and memory footprint are conducted, where the proposed MEST framework consistently outperforms representative SOTA works. A reviewer strongly against our work based on his false assumptions and misunderstandings. On top of the previous submission, we employ data efficiency for further acceleration of sparse training. And we explore the impact of model sparsity, sparsity schemes, and sparse training algorithms on the number of removable training examples. Our codes are publicly available at: https://github.com/boone891214/MEST.

cs.LG↗

arXiv2021

GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity

It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices because even the powerful modern mobile devices are considered as ``resource-constrained'' when executing large-scale DNNs. It necessitates the sparse model inference via weight pruning, i.e., DNN weight sparsity, and it is desirable to design a new DNN weight sparsity scheme that can facilitate real-time inference on mobile devices while preserving a high sparse model accuracy. This paper designs a novel mobile inference acceleration framework GRIM that is General to both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) and that achieves Real-time execution and high accuracy, leveraging fine-grained structured sparse model Inference and compiler optimizations for Mobiles. We start by proposing a new fine-grained structured sparsity scheme through the Block-based Column-Row (BCR) pruning. Based on this new fine-grained structured sparsity, our GRIM framework consists of two parts: (a) the compiler optimization and code generation for real-time mobile inference; and (b) the BCR pruning optimizations for determining pruning hyperparameters and performing weight pruning. We compare GRIM with Alibaba MNN, TVM, TensorFlow-Lite, a sparse implementation based on CSR, PatDNN, and ESE (a representative FPGA inference acceleration framework for RNNs), and achieve up to 14.08x speedup.

cs.LG↗

arXiv2021

Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI

Recent research demonstrated the promise of using resistive random access memory (ReRAM) as an emerging technology to perform inherently parallel analog domain in-situ matrix-vector multiplication -- the intensive and key computation in deep neural networks (DNNs). However, hardware failure, such as stuck-at-fault defects, is one of the main concerns that impedes the ReRAM devices to be a feasible solution for real implementations. The existing solutions to address this issue usually require an optimization to be conducted for each individual device, which is impractical for mass-produced products (e.g., IoT devices). In this paper, we rethink the value of weight pruning in ReRAM-based DNN design from the perspective of model fault tolerance. And a differential mapping scheme is proposed to improve the fault tolerance under a high stuck-on fault rate. Our method can tolerate almost an order of magnitude higher failure rate than the traditional two-column method in representative DNN tasks. More importantly, our method does not require extra hardware cost compared to the traditional two-column mapping scheme. The improvement is universal and does not require the optimization process for each individual device.

cs.LG↗