PyTorchKR Papers

최신 논문

총 2,230편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2408.04093공식 코드 · Papers with Code

Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters

Self-attention is the core mathematical operation of modern transformer architectures and is also a significant computational bottleneck due to its quadratic complexity in the sequence length. In this work, we derive the scalar energy function whose gradient computes the self-attention block, thus elucidating the theoretical underpinnings of self-attention, providing a Bayesian interpretation of the operation and linking it closely with energy-based models such as Hopfield Networks. Our formulation reveals that the reduction across the sequence axis can be efficiently computed in parallel through a tree reduction. Our algorithm, for parallelizing attention computation across multiple GPUs enables cross-device decoding to be performed asymptotically faster (up to 8x faster in our experiments) than alternative approaches such as Ring Attention, while also requiring significantly less communication volume and incurring 2x less peak memory. Our code is publicly available here: \url{https://github.com/Zyphra/tree_attention}.

arXiv:2408.04015공식 코드 · Papers with Code

Image-to-LaTeX Converter for Mathematical Formulas and Text

In this project, we train a vision encoder-decoder model to generate LaTeX code from images of mathematical formulas and text. Utilizing a diverse collection of image-to-LaTeX data, we build two models: a base model with a Swin Transformer encoder and a GPT-2 decoder, trained on machine-generated images, and a fine-tuned version enhanced with Low-Rank Adaptation (LoRA) trained on handwritten formulas. We then compare the BLEU performance of our specialized model on a handwritten test set with other similar models, such as Pix2Text, TexTeller, and Sumen. Through this project, we contribute open-source models for converting images to LaTeX and provide from-scratch code for building these models with distributed training and GPU optimizations.

arXiv:2408.03647공식 코드 · Papers with Code

Real-time Event Recognition of Long-distance Distributed Vibration Sensing with Knowledge Distillation and Hardware Acceleration

Fiber-optic sensing, especially distributed optical fiber vibration (DVS) sensing, is gaining importance in internet of things (IoT) applications, such as industrial safety monitoring and intrusion detection. Despite their wide application, existing post-processing methods that rely on deep learning models for event recognition in DVS systems face challenges with real-time processing of large sample data volumes, particularly in long-distance applications. To address this issue, we propose to use a four-layer convolutional neural network (CNN) with ResNet as the teacher model for knowledge distillation. This results in a significant improvement in accuracy, from 83.41% to 95.39%, on data from previously untrained environments. Additionally, we propose a novel hardware design based on field-programmable gate arrays (FPGA) to further accelerate model inference. This design replaces multiplication with binary shift operations and quantizes model weights, enabling high parallelism and low latency. Our implementation achieves an inference time of 0.083 ms for a spatial-temporal sample covering a 12.5 m fiber length and 0.256 s time frame. This performance enables real-time signal processing over approximately 38.55 km of fiber, about $2.14\times$ the capability of an Nvidia GTX 4090 GPU. The proposed method greatly enhances the efficiency of vibration pattern recognition, promoting the use of DVS as a smart IoT system. The data and code are available at https://github.com/HUST-IOF/Efficient-DVS.

arXiv:2408.03735공식 코드 · Papers with Code

Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation

This paper presents the first study to explore the potential of parameter quantization for multimodal large language models to alleviate the significant resource constraint encountered during vision-language instruction tuning. We introduce a Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW. This method is grounded in two key innovations: (1) The learning of group-wise scale factors for quantized LLM weights to mitigate the quantization error arising from activation outliers and achieve more effective vision-language instruction tuning; (2) The implementation of a multimodal warmup that progressively integrates linguistic and multimodal training samples, thereby preventing overfitting of the quantized model to multimodal data while ensuring stable adaptation of multimodal large language models to downstream vision-language tasks. Extensive experiments demonstrate that models quantized by QSLAW perform on par with, or even surpass, their full-precision counterparts, while facilitating up to 1.4 times reduction in VL tuning time and GPU consumption. Our code is released at https://github.com/xjjxmu/QSLAW.

arXiv:2408.01654공식 코드 · Papers with Code

Deep Patch Visual SLAM

Recent work in visual SLAM has shown the effectiveness of using deep network backbones. Despite excellent accuracy, however, such approaches are often expensive to run or do not generalize well zero-shot. Their runtime can also fluctuate wildly while their frontend and backend fight for access to GPU resources. To address these problems, we introduce Deep Patch Visual (DPV) SLAM, a method for monocular visual SLAM on a single GPU. DPV-SLAM maintains a high minimum framerate and small memory overhead (5-7G) compared to existing deep SLAM systems. On real-world datasets, DPV-SLAM runs at 1x-4x real-time framerates. We achieve comparable accuracy to DROID-SLAM on EuRoC and TartanAir while running 2.5x faster using a fraction of the memory. DPV-SLAM is an extension to the DPVO visual odometry system; its code can be found in the same repository: https://github.com/princeton-vl/DPVO

arXiv:2408.02354공식 코드 · Papers with Code

RECE: Reduced Cross-Entropy Loss for Large-Catalogue Sequential Recommenders

Scalability is a major challenge in modern recommender systems. In sequential recommendations, full Cross-Entropy (CE) loss achieves state-of-the-art recommendation quality but consumes excessive GPU memory with large item catalogs, limiting its practicality. Using a GPU-efficient locality-sensitive hashing-like algorithm for approximating large tensor of logits, this paper introduces a novel RECE (REduced Cross-Entropy) loss. RECE significantly reduces memory consumption while allowing one to enjoy the state-of-the-art performance of full CE loss. Experimental results on various datasets show that RECE cuts training peak memory usage by up to 12 times compared to existing methods while retaining or exceeding performance metrics of CE loss. The approach also opens up new possibilities for large-scale applications in other domains.

arXiv:2408.01584공식 코드 · Papers with Code

GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS

Multi-agent learning algorithms have been successful at generating superhuman planning in various games but have had limited impact on the design of deployed multi-agent planners. A key bottleneck in applying these techniques to multi-agent planning is that they require billions of steps of experience. To enable the study of multi-agent planning at scale, we present GPUDrive. GPUDrive is a GPU-accelerated, multi-agent simulator built on top of the Madrona Game Engine capable of generating over a million simulation steps per second. Observation, reward, and dynamics functions are written directly in C++, allowing users to define complex, heterogeneous agent behaviors that are lowered to high-performance CUDA. Despite these low-level optimizations, GPUDrive is fully accessible through Python, offering a seamless and efficient workflow for multi-agent, closed-loop simulation. Using GPUDrive, we train reinforcement learning agents on the Waymo Open Motion Dataset, achieving efficient goal-reaching in minutes and scaling to thousands of scenarios in hours. We open-source the code and pre-trained agents at https://github.com/Emerge-Lab/gpudrive.

arXiv:2408.01391공식 코드 · Papers with Code

FT K-means: A High-Performance K-means on GPU with Fault Tolerance

K-means is a widely used algorithm in clustering, however, its efficiency is primarily constrained by the computational cost of distance computing. Existing implementations suffer from suboptimal utilization of computational units and lack resilience against soft errors. To address these challenges, we introduce FT K-means, a high-performance GPU-accelerated implementation of K-means with online fault tolerance. We first present a stepwise optimization strategy that achieves competitive performance compared to NVIDIA's cuML library. We further improve FT K-means with a template-based code generation framework that supports different data types and adapts to different input shapes. A novel warp-level tensor-core error correction scheme is proposed to address the failure of existing fault tolerance methods due to memory asynchronization during copy operations. Our experimental evaluations on NVIDIA T4 GPU and A100 GPU demonstrate that FT K-means without fault tolerance outperforms cuML's K-means implementation, showing a performance increase of 10\%-300\% in scenarios involving irregular data shapes. Moreover, the fault tolerance feature of FT K-means introduces only an overhead of 11\%, maintaining robust performance even with tens of errors injected per second.

arXiv:2408.01000공식 코드 · Papers with Code

Adaptive Two-Stage Cloud Resource Scaling via Hierarchical Multi-Indicator Forecasting and Bayesian Decision-Making

The surging demand for cloud computing resources, driven by the rapid growth of sophisticated large-scale models and data centers, underscores the critical importance of efficient and adaptive resource allocation. As major tech enterprises deploy massive infrastructures with thousands of GPUs, existing cloud platforms still struggle with low resource utilization due to key challenges: capturing hierarchical indicator structures, modeling non-Gaussian distributions, and decision-making under uncertainty. To address these challenges, we propose HRAMONY, an adaptive Hierarchical Attention-based Resource Modeling and Decision-Making System. HARMONY combines hierarchical multi-indicator distribution forecasting and uncertainty-aware Bayesian decision-making. It introduces a novel hierarchical attention mechanism that comprehensively models complex inter-indicator dependencies, enabling accurate predictions that can adapt to evolving environment states. By transforming Gaussian projections into adaptive non-Gaussian distributions via Normalizing Flows. Crucially, HARMONY leverages the full predictive distributions in an adaptive Bayesian process, proactively incorporating uncertainties to optimize resource allocation while robustly meeting SLA constraints under varying conditions. Extensive evaluations across four large-scale cloud datasets demonstrate HARMONY's state-of-the-art performance, significantly outperforming nine established methods. A month-long real-world deployment validated HARMONY's substantial practical impact, realizing over 35,000 GPU hours in savings and translating to $100K+ in cost reduction, showcasing its remarkable economic value through adaptive, uncertainty-aware scaling. Our code is available at https://github.com/Floating-LY/HARMONY1.

arXiv:2408.00374공식 코드 · Papers with Code

Conformal Trajectory Prediction with Multi-View Data Integration in Cooperative Driving

Current research on trajectory prediction primarily relies on data collected by onboard sensors of an ego vehicle. With the rapid advancement in connected technologies, such as vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, valuable information from alternate views becomes accessible via wireless networks. The integration of information from alternative views has the potential to overcome the inherent limitations associated with a single viewpoint, such as occlusions and limited field of view. In this work, we introduce V2INet, a novel trajectory prediction framework designed to model multi-view data by extending existing single-view models. Unlike previous approaches where the multi-view data is manually fused or formulated as a separate training stage, our model supports end-to-end training, enhancing both flexibility and performance. Moreover, the predicted multimodal trajectories are calibrated by a post-hoc conformal prediction module to get valid and efficient confidence regions. We evaluated the entire framework using the real-world V2I dataset V2X-Seq. Our results demonstrate superior performance in terms of Final Displacement Error (FDE) and Miss Rate (MR) using a single GPU. The code is publicly available at: \url{https://github.com/xichennn/V2I_trajectory_prediction}.

arXiv:2407.21217공식 코드 · Papers with Code

NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elements

Multiphysics problems that are characterized by complex interactions among fluid dynamics, heat transfer, structural mechanics, and electromagnetics, are inherently challenging due to their coupled nature. While experimental data on certain state variables may be available, integrating these data with numerical solvers remains a significant challenge. Physics-informed neural networks (PINNs) have shown promising results in various engineering disciplines, particularly in handling noisy data and solving inverse problems in partial differential equations (PDEs). However, their effectiveness in forecasting nonlinear phenomena in multiphysics regimes, particularly involving turbulence, is yet to be fully established. This study introduces NeuroSEM, a hybrid framework integrating PINNs with the high-fidelity Spectral Element Method (SEM) solver, Nektar++. NeuroSEM leverages the strengths of both PINNs and SEM, providing robust solutions for multiphysics problems. PINNs are trained to assimilate data and model physical phenomena in specific subdomains, which are then integrated into the Nektar++ solver. We demonstrate the efficiency and accuracy of NeuroSEM for thermal convection in cavity flow and flow past a cylinder. We applied NeuroSEM to the Rayleigh-B\'enard convection system, including cases with missing thermal boundary conditions and noisy datasets, and to real particle image velocimetry (PIV) data to capture flow patterns characterized by horseshoe vortical structures. The framework's plug-and-play nature facilitates its extension to other multiphysics or multiscale problems. Furthermore, NeuroSEM is optimized for efficient execution on emerging integrated GPU-CPU architectures. This hybrid approach enhances the accuracy and efficiency of simulations, making it a powerful tool for tackling complex engineering challenges in various scientific domains.

arXiv:2407.21118공식 코드 · Papers with Code

Palu: Compressing KV-Cache with Low-Rank Projection

Post-training KV-Cache compression methods typically either sample a subset of effectual tokens or quantize the data into lower numerical bit width. However, these methods cannot exploit redundancy in the hidden dimension of the KV tensors. This paper presents a hidden dimension compression approach called Palu, a KV-Cache compression framework that utilizes low-rank projection to reduce inference-time LLM memory usage. Palu decomposes the linear layers into low-rank matrices, caches compressed intermediate states, and reconstructs the full keys and values on the fly. To improve accuracy, compression rate, and efficiency, Palu further encompasses (1) a medium-grained low-rank decomposition scheme, (2) an efficient rank search algorithm, (3) low-rank-aware quantization compatibility enhancements, and (4) optimized GPU kernels with operators fusion. Extensive experiments with popular LLMs show that Palu compresses KV-Cache by 50% while maintaining strong accuracy and delivering up to 1.89x on the RoPE-based attention module. When combined with quantization, Palu's inherent quantization-friendly design yields small to negligible extra accuracy degradation while saving additional memory than quantization-only methods and achieving up to 2.91x speedup for the RoPE-based attention. Moreover, it maintains comparable or even better accuracy (up to 1.19 lower perplexity) compared to quantization-only methods. These results demonstrate Palu's superior capability to effectively address the efficiency and memory challenges of LLM inference posed by KV-Cache. Our code is publicly available at: https://github.com/shadowpa0327/Palu

arXiv:2407.21011공식 코드 · Papers with Code

CLEFT: Language-Image Contrastive Learning with Efficient Large Language Model and Prompt Fine-Tuning

Recent advancements in Contrastive Language-Image Pre-training (CLIP) have demonstrated notable success in self-supervised representation learning across various tasks. However, the existing CLIP-like approaches often demand extensive GPU resources and prolonged training times due to the considerable size of the model and dataset, making them poor for medical applications, in which large datasets are not always common. Meanwhile, the language model prompts are mainly manually derived from labels tied to images, potentially overlooking the richness of information within training samples. We introduce a novel language-image Contrastive Learning method with an Efficient large language model and prompt Fine-Tuning (CLEFT) that harnesses the strengths of the extensive pre-trained language and visual models. Furthermore, we present an efficient strategy for learning context-based prompts that mitigates the gap between informative clinical diagnostic data and simple class labels. Our method demonstrates state-of-the-art performance on multiple chest X-ray and mammography datasets compared with various baselines. The proposed parameter efficient framework can reduce the total trainable model size by 39% and reduce the trainable language model to only 4% compared with the current BERT encoder.

arXiv:2407.20761공식 코드 · Papers with Code

OmniBal: Towards Fast Instruct-tuning for Vision-Language Models via Omniverse Computation Balance

Recently, vision-language instruct-tuning models have made significant progress due to their more comprehensive understanding of the world. In this work, we discovered that large-scale 3D parallel training on those models leads to an imbalanced computation load across different devices. The vision and language parts are inherently heterogeneous: their data distribution and model architecture differ significantly, which affects distributed training efficiency. We rebalanced the computational loads from data, model, and memory perspectives to address this issue, achieving more balanced computation across devices. These three components are not independent but are closely connected, forming an omniverse balanced training framework. Specifically, for the data, we grouped instances into new balanced mini-batches within and across devices. For the model, we employed a search-based method to achieve a more balanced partitioning. For memory optimization, we adaptively adjusted the re-computation strategy for each partition to utilize the available memory fully. We conducted extensive experiments to validate the effectiveness of our method. Compared with the open-source training code of InternVL-Chat, we significantly reduced GPU days, achieving about 1.8x speed-up. Our method's efficacy and generalizability were further demonstrated across various models and datasets. Codes will be released at https://github.com/ModelTC/OmniBal.

arXiv:2407.20584공식 코드 · Papers with Code

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have attempted to compress LLMs using one-shot pruning methods. However, these methods often suffer from considerable performance degradation on complex language understanding tasks, raising concerns about the feasibility of pruning in LLMs. To address this issue, we propose Adaptive Sparse Trainer (AST), a novel and efficient retraining framework tailored for semi-structured sparse models. AST enables models to learn optimal masks during the weight update process without incurring additional computational overhead. Furthermore, we demonstrate that incorporating knowledge distillation significantly improves retraining efficiency and enhances model performance under fixed computational constraints. Additionally, a supplementary set of well-initialized parameters is integrated to further augment the model's efficacy. AST achieves state-of-the-art performance with minimal training cost. When applied to the LLaMA2-7B model, AST reduces the perplexity and zero-shot accuracy gap between dense and 2:4 semi-structured sparse models to 0.6 and 1.16%, respectively, utilizing less than 0.4% of the pretraining tokens and GPU hours. Our work demonstrates the feasibility of deploying semi-structured sparse LLMs and offers a promising alternative for achieving highly compressed models when combined with existing quantization techniques.

arXiv:2407.19650공식 코드 · Papers with Code

Practical Video Object Detection via Feature Selection and Aggregation

Compared with still image object detection, video object detection (VOD) needs to particularly concern the high across-frame variation in object appearance, and the diverse deterioration in some frames. In principle, the detection in a certain frame of a video can benefit from information in other frames. Thus, how to effectively aggregate features across different frames is key to the target problem. Most of contemporary aggregation methods are tailored for two-stage detectors, suffering from high computational costs due to the dual-stage nature. On the other hand, although one-stage detectors have made continuous progress in handling static images, their applicability to VOD lacks sufficient exploration. To tackle the above issues, this study invents a very simple yet potent strategy of feature selection and aggregation, gaining significant accuracy at marginal computational expense. Concretely, for cutting the massive computation and memory consumption from the dense prediction characteristic of one-stage object detectors, we first condense candidate features from dense prediction maps. Then, the relationship between a target frame and its reference frames is evaluated to guide the aggregation. Comprehensive experiments and ablation studies are conducted to validate the efficacy of our design, and showcase its advantage over other cutting-edge VOD methods in both effectiveness and efficiency. Notably, our model reaches \emph{a new record performance, i.e., 92.9\% AP50 at over 30 FPS on the ImageNet VID dataset on a single 3090 GPU}, making it a compelling option for large-scale or real-time applications. The implementation is simple, and accessible at \url{https://github.com/YuHengsss/YOLOV}.

arXiv:2407.18443공식 코드 · Papers with Code

HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors

We propose HYBRIDDEPTH, a robust depth estimation pipeline that addresses key challenges in depth estimation,including scale ambiguity, hardware heterogeneity, and generalizability. HYBRIDDEPTH leverages focal stack, data conveniently accessible in common mobile devices, to produce accurate metric depth maps. By incorporating depth priors afforded by recent advances in singleimage depth estimation, our model achieves a higher level of structural detail compared to existing methods. We test our pipeline as an end-to-end system, with a newly developed mobile client to capture focal stacks, which are then sent to a GPU-powered server for depth estimation. Comprehensive quantitative and qualitative analyses demonstrate that HYBRIDDEPTH outperforms state-of-the-art(SOTA) models on common datasets such as DDFF12 and NYU Depth V2. HYBRIDDEPTH also shows strong zero-shot generalization. When trained on NYU Depth V2, HYBRIDDEPTH surpasses SOTA models in zero-shot performance on ARKitScenes and delivers more structurally accurate depth maps on Mobile Depth. The code is available at https://github.com/cake-lab/HybridDepth/.

arXiv:2407.16424공식 코드 · Papers with Code

ESOD: Efficient Small Object Detection on High-Resolution Images

Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually sparsely distributed and locally clustered. Therefore, massive feature extraction computations are wasted on the non-target background area of images. Recent works have tried to pick out target-containing regions using an extra network and perform conventional object detection, but the newly introduced computation limits their final performance. In this paper, we propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing, which can avoid redundant feature extraction and reduce the computation cost. Incorporating a sparse detection head, we are able to detect small objects on high-resolution inputs (e.g., 1080P or larger) for superior performance. The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs. Extensive experiments demonstrate the efficacy and efficiency of our method. In particular, our method consistently surpasses the SOTA detectors by a large margin (e.g., 8% gains on AP) on the representative VisDrone, UAVDT, and TinyPerson datasets. Code is available at https://github.com/alibaba/esod.

arXiv:2407.11062공식 코드 · Papers with Code

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Large language models (LLMs) are crucial in modern natural language processing and artificial intelligence. However, they face challenges in managing their significant memory requirements. Although quantization-aware training (QAT) offers a solution by reducing memory consumption through low-bit representations with minimal accuracy loss, it is impractical due to substantial training resources. To address this, we propose Efficient Quantization-Aware Training (EfficientQAT), a more feasible QAT algorithm. EfficientQAT involves two consecutive phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP). To the best of our knowledge, Block-AP is the first method to enable direct training of all parameters in a block-wise manner, reducing accuracy loss in low-bit scenarios by enhancing the solution space during optimization. E2E-QP then trains only the quantization parameters (step sizes) end-to-end, further improving the performance of quantized models by considering interactions among all sub-modules. Extensive experiments demonstrate that EfficientQAT outperforms previous quantization methods across a range of models, including base LLMs, instruction-tuned LLMs, and multimodal LLMs, with scales from 7B to 70B parameters at various quantization bits. For instance, EfficientQAT obtains a 2-bit Llama-2-70B model on a single A100-80GB GPU in 41 hours, with less than 3 points accuracy degradation compared to the full precision (69.48 vs. 72.41). Code is available at https://github.com/OpenGVLab/EfficientQAT.

arXiv:2407.14982공식 코드 · Papers with Code

GreenStableYolo: Optimizing Inference Time and Image Quality of Text-to-Image Generation

Tuning the parameters and prompts for improving AI-based text-to-image generation has remained a substantial yet unaddressed challenge. Hence we introduce GreenStableYolo, which improves the parameters and prompts for Stable Diffusion to both reduce GPU inference time and increase image generation quality using NSGA-II and Yolo. Our experiments show that despite a relatively slight trade-off (18%) in image quality compared to StableYolo (which only considers image quality), GreenStableYolo achieves a substantial reduction in inference time (266% less) and a 526% higher hypervolume, thereby advancing the state-of-the-art for text-to-image generation.