PyTorchKR Papers

최신 논문

총 2,229편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2501.17792공식 코드 · Papers with Code

CrowdSplat: Exploring Gaussian Splatting For Crowd Rendering

We present CrowdSplat, a novel approach that leverages 3D Gaussian Splatting for real-time, high-quality crowd rendering. Our method utilizes 3D Gaussian functions to represent animated human characters in diverse poses and outfits, which are extracted from monocular videos. We integrate Level of Detail (LoD) rendering to optimize computational efficiency and quality. The CrowdSplat framework consists of two stages: (1) avatar reconstruction and (2) crowd synthesis. The framework is also optimized for GPU memory usage to enhance scalability. Quantitative and qualitative evaluations show that CrowdSplat achieves good levels of rendering quality, memory efficiency, and computational performance. Through these experiments, we demonstrate that CrowdSplat is a viable solution for dynamic, realistic crowd simulation in real-time applications.

arXiv:2501.15129공식 코드 · Papers with Code

EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning

Evolutionary Reinforcement Learning (EvoRL) has emerged as a promising approach to overcoming the limitations of traditional reinforcement learning (RL) by integrating the Evolutionary Computation (EC) paradigm with RL. However, the population-based nature of EC significantly increases computational costs, thereby restricting the exploration of algorithmic design choices and scalability in large-scale settings. To address this challenge, we introduce $\texttt{$\textbf{EvoRL}$}$, the first end-to-end EvoRL framework optimized for GPU acceleration. The framework executes the entire training pipeline on accelerators, including environment simulations and EC processes, leveraging hierarchical parallelism through vectorization and compilation techniques to achieve superior speed and scalability. This design enables the efficient training of large populations on a single machine. In addition to its performance-oriented design, $\texttt{$\textbf{EvoRL}$}$ offers a comprehensive platform for EvoRL research, encompassing implementations of traditional RL algorithms (e.g., A2C, PPO, DDPG, TD3, SAC), Evolutionary Algorithms (e.g., CMA-ES, OpenES, ARS), and hybrid EvoRL paradigms such as Evolutionary-guided RL (e.g., ERL, CEM-RL) and Population-Based AutoRL (e.g., PBT). The framework's modular architecture and user-friendly interface allow researchers to seamlessly integrate new components, customize algorithms, and conduct fair benchmarking and ablation studies. The project is open-source and available at: https://github.com/EMI-Group/evorl.

arXiv:2501.10375공식 코드 · Papers with Code

DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference

Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory-constrained devices. While GPUs offer fast inference, their limited memory compared to CPUs means not all experts can be stored on the GPU simultaneously, necessitating frequent, costly data transfers from CPU memory, often negating GPU speed advantages. To address this, we present DAOP, an on-device MoE inference engine to optimize parallel GPU-CPU execution. DAOP dynamically allocates experts between CPU and GPU based on per-sequence activation patterns, and selectively pre-calculates predicted experts on CPUs to minimize transfer latency. This approach enables efficient resource utilization across various expert cache ratios while maintaining model accuracy through a novel graceful degradation mechanism. Comprehensive evaluations across various datasets show that DAOP outperforms traditional expert caching and prefetching methods by up to 8.20x and offloading techniques by 1.35x while maintaining accuracy.

arXiv:2501.16273공식 코드 · Papers with Code

Return of the Encoder: Maximizing Parameter Efficiency for SLMs

The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters or fewer - our systematic analysis across GPU, CPU, and NPU platforms reveals that encoder-decoder architectures achieve 47% lower first-token latency and 4.7x higher throughput compared to decoder-only models on edge devices. These gains may be attributed to encoder-decoder's one-time input processing and efficient separation of understanding and generation phases. We introduce a novel knowledge distillation framework that enables encoder-decoder models to leverage capabilities from large scalable decoder-only teachers while preserving their architectural advantages, achieving up to 6 average performance points improvement across diverse tasks, with significant gains in asymmetric sequence tasks where input and output distributions can benefit from different processing approaches. When combined with modern advances like Rotary Positional Embeddings (RoPE) and Vision encoders, our systematic investigation demonstrates that encoder-decoder architectures provide a more practical path toward deploying capable language models in resource-constrained environments. Our findings challenge the prevailing trend toward decoder-only scaling, showing that architectural choices become increasingly crucial as parameter budgets decrease, particularly for on-device and edge deployments where computational efficiency is paramount.

arXiv:2501.13986공식 코드 · Papers with Code

An Efficient Sparse Kernel Generator for O(3)-Equivariant Deep Networks

Rotation equivariant graph neural networks, i.e. networks designed to guarantee certain geometric relations between their inputs and outputs, yield state of the art performance on spatial deep learning tasks. They exhibit high data efficiency during training and significantly reduced inference time for interatomic potential calculations compared to classical approaches. Key to these models is the Clebsch-Gordon (CG) tensor product, a kernel that contracts two dense feature vectors with a highly-structured sparse tensor to produce a dense output vector. The operation, which may be repeated millions of times for typical equivariant models, is a costly and inefficient bottleneck. We introduce a GPU sparse kernel generator for the CG tensor product that provides significant speedups over the best existing open and closed-source implementations. Our implementation achieves high performance by carefully managing the limited GPU shared memory through static analysis at model compile-time, minimizing reads and writes to global memory. We break the tensor product into a series of smaller kernels with operands that fit entirely into registers, enabling us to emit long arithmetic instruction streams that maximize instruction-level parallelism. By fusing the CG tensor product with a subsequent graph convolution, we reduce both intermediate storage and global memory traffic over naive approaches that duplicate input data. We also provide optimized kernels for the gradient of the CG tensor product and a novel identity for the higher partial derivatives required to predict interatomic forces. Our kernels offer up to 1.3x speedup over NVIDIA's closed-source cuEquivariance package, as well as 10x speedup over the widely-used e3nn package. In FP64 precision, we offer up to 6.2x inference-time speedup for the MACE chemistry foundation model over the original unoptimized version.

arXiv:2501.12670공식 코드 · Papers with Code

Learning Versatile Optimizers on a Compute Diet

Learned optimization has emerged as a promising alternative to hand-crafted optimizers, with the potential to discover stronger learned update rules that enable faster, hyperparameter-free training of neural networks. A critical element for practically useful learned optimizers, that can be used off-the-shelf after meta-training, is strong meta-generalization: the ability to apply the optimizers to new tasks. Recent state-of-the-art work in learned optimizers, VeLO (Metz et al., 2022), requires a large number of highly diverse meta-training tasks along with massive computational resources, 4000 TPU months, to achieve meta-generalization. This makes further improvements to such learned optimizers impractical. In this work, we identify several key elements in learned optimizer architectures and meta-training procedures that can lead to strong meta-generalization. We also propose evaluation metrics to reliably assess quantitative performance of an optimizer at scale on a set of evaluation tasks. Our proposed approach, Celo, makes a significant leap in improving the meta-generalization performance of learned optimizers and also outperforms tuned state-of-the-art optimizers on a diverse set of out-of-distribution tasks, despite being meta-trained for just 24 GPU hours.

arXiv:2501.11253공식 코드 · Papers with Code

How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?

The pre-training and fine-tuning paradigm has become prominent in transfer learning. For example, if the model is pre-trained on ImageNet and then fine-tuned to PASCAL, it can significantly outperform that trained on PASCAL from scratch. While ImageNet pre-training has shown enormous success, it is formed in 2D, and the learned features are for classification tasks; when transferring to more diverse tasks, like 3D image segmentation, its performance is inevitably compromised due to the deviation from the original ImageNet context. A significant challenge lies in the lack of large, annotated 3D datasets rivaling the scale of ImageNet for model pre-training. To overcome this challenge, we make two contributions. Firstly, we construct AbdomenAtlas 1.1 that comprises 9,262 three-dimensional computed tomography (CT) volumes with high-quality, per-voxel annotations of 25 anatomical structures and pseudo annotations of seven tumor types. Secondly, we develop a suite of models that are pre-trained on our AbdomenAtlas 1.1 for transfer learning. Our preliminary analyses indicate that the model trained only with 21 CT volumes, 672 masks, and 40 GPU hours has a transfer learning ability similar to the model trained with 5,050 (unlabeled) CT volumes and 1,152 GPU hours. More importantly, the transfer learning ability of supervised models can further scale up with larger annotated datasets, achieving significantly better performance than preexisting pre-trained models, irrespective of their pre-training methodologies or data sources. We hope this study can facilitate collective efforts in constructing larger 3D medical datasets and more releases of supervised pre-trained models.

arXiv:2501.11587공식 코드 · Papers with Code

Recurrent Diffusion for Large-Scale Parameter Generation

Parameter generation has struggled to scale up for a long time, significantly limiting its range of applications. In this study, we introduce \textbf{R}ecurrent diffusion for large-scale \textbf{P}arameter \textbf{G}eneration, called \textbf{RPG}. We first divide the trained parameters into non-overlapping parts, after which a recurrent model is proposed to learn their relationships. The recurrent model's outputs, as conditions, are then fed into a diffusion model to generate the neural network parameters. Using only a single GPU, recurrent diffusion enables us to generate popular vision and language models such as ConvNeXt-L and LoRA parameters of LLaMA-7B. Meanwhile, across various architectures and tasks, the generated parameters consistently perform comparable results over trained networks. Notably, our approach also shows the potential to generate models for handling unseen tasks, which largely increases the practicality of parameter generation. Our code is available \href{https://github.com/NUS-HPC-AI-Lab/Recurrent-Parameter-Generation}{here}.

arXiv:2501.08071공식 코드 · Papers with Code

CuAsmRL: Optimizing GPU SASS Schedules via Deep Reinforcement Learning

Large language models (LLMs) are remarked by their substantial computational requirements. To mitigate the cost, researchers develop specialized CUDA kernels, which often fuse several tensor operations to maximize the utilization of GPUs as much as possible. However, those specialized kernels may still leave performance on the table as CUDA assembly experts show that manual optimization of GPU SASS schedules can lead to better performance, and trial-and-error is largely employed to manually find the best GPU SASS schedules. In this work, we employ an automatic approach to optimize GPU SASS schedules, which thus can be integrated into existing compiler frameworks. The key to automatic optimization is training an RL agent to mimic how human experts perform manual scheduling. To this end, we formulate an assembly game, where RL agents can play to find the best GPU SASS schedules. The assembly game starts from a \textit{-O3} optimized SASS schedule, and the RL agents can iteratively apply actions to mutate the current schedules. Positive rewards are generated if the mutated schedules get higher throughput by executing on GPUs. Experiments show that CuAsmRL can further improve the performance of existing specialized CUDA kernels transparently by up to $26\%$, and on average $9\%$. Moreover, it is used as a tool to reveal potential optimization moves learned automatically.

arXiv:2501.07145공식 코드 · Papers with Code

A User's Guide to $\texttt{KSig}$: GPU-Accelerated Computation of the Signature Kernel

The signature kernel is a positive definite kernel for sequential and temporal data that has become increasingly popular in machine learning applications due to powerful theoretical guarantees, strong empirical performance, and recently introduced various scalable variations. In this chapter, we give a short introduction to $\texttt{KSig}$, a $\texttt{Scikit-Learn}$ compatible Python package that implements various GPU-accelerated algorithms for computing signature kernels, and performing downstream learning tasks. We also introduce a new algorithm based on tensor sketches which gives strong performance compared to existing algorithms. The package is available at https://github.com/tgcsaba/ksig.

arXiv:2412.00088공식 코드 · Papers with Code

Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators

Optimizing neural networks with loss that contain high-dimensional and high-order differential operators is expensive to evaluate with back-propagation due to $\mathcal{O}(d^{k})$ scaling of the derivative tensor size and the $\mathcal{O}(2^{k-1}L)$ scaling in the computation graph, where $d$ is the dimension of the domain, $L$ is the number of ops in the forward computation graph, and $k$ is the derivative order. In previous works, the polynomial scaling in $d$ was addressed by amortizing the computation over the optimization process via randomization. Separately, the exponential scaling in $k$ for univariate functions ($d=1$) was addressed with high-order auto-differentiation (AD). In this work, we show how to efficiently perform arbitrary contraction of the derivative tensor of arbitrary order for multivariate functions, by properly constructing the input tangents to univariate high-order AD, which can be used to efficiently randomize any differential operator. When applied to Physics-Informed Neural Networks (PINNs), our method provides >1000$\times$ speed-up and >30$\times$ memory reduction over randomization with first-order AD, and we can now solve \emph{1-million-dimensional PDEs in 8 minutes on a single NVIDIA A100 GPU}. This work opens the possibility of using high-order differential operators in large-scale problems.

arXiv:2501.06589공식 코드 · Papers with Code

Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping

Large language model inference is both memory-intensive and time-consuming, often requiring distributed algorithms to efficiently scale. Various model parallelism strategies are used in multi-gpu training and inference to partition computation across multiple devices, reducing memory load and computation time. However, using model parallelism necessitates communication of information between GPUs, which has been a major bottleneck and limits the gains obtained by scaling up the number of devices. We introduce Ladder Residual, a simple architectural modification applicable to all residual-based models that enables straightforward overlapping that effectively hides the latency of communication. Our insight is that in addition to systems optimization, one can also redesign the model architecture to decouple communication from computation. While Ladder Residual can allow communication-computation decoupling in conventional parallelism patterns, we focus on Tensor Parallelism in this paper, which is particularly bottlenecked by its heavy communication. For a Transformer model with 70B parameters, applying Ladder Residual to all its layers can achieve 29% end-to-end wall clock speed up at inference time with TP sharding over 8 devices. We refer the resulting Transformer model as the Ladder Transformer. We train a 1B and 3B Ladder Transformer from scratch and observe comparable performance to a standard dense transformer baseline. We also show that it is possible to convert parts of the Llama-3.1 8B model to our Ladder Residual architecture with minimal accuracy degradation by only retraining for 3B tokens. We release our code for training and inference for easier replication of experiments.

arXiv:2501.06838공식 코드 · Papers with Code

Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution

Implicit Neural Representation (INR) has been successfully employed for Arbitrary-scale Super-Resolution (ASR). However, INR-based models need to query the multi-layer perceptron module numerous times and render a pixel in each query, resulting in insufficient representation capability and computational efficiency. Recently, Gaussian Splatting (GS) has shown its advantages over INR in both visual quality and rendering speed in 3D tasks, which motivates us to explore whether GS can be employed for the ASR task. However, directly applying GS to ASR is exceptionally challenging because the original GS is an optimization-based method through overfitting each single scene, while in ASR we aim to learn a single model that can generalize to different images and scaling factors. We overcome these challenges by developing two novel techniques. Firstly, to generalize GS for ASR, we elaborately design an architecture to predict the corresponding image-conditioned Gaussians of the input low-resolution image in a feed-forward manner. Each Gaussian can fit the shape and direction of an area of complex textures, showing powerful representation capability. Secondly, we implement an efficient differentiable 2D GPU/CUDA-based scale-aware rasterization to render super-resolved images by sampling discrete RGB values from the predicted continuous Gaussians. Via end-to-end training, our optimized network, namely GSASR, can perform ASR for any image and unseen scaling factors. Extensive experiments validate the effectiveness of our proposed method.

arXiv:2501.05880공식 코드 · Papers with Code

TakuNet: an Energy-Efficient CNN for Real-Time Inference on Embedded UAV systems in Emergency Response Scenarios

Designing efficient neural networks for embedded devices is a critical challenge, particularly in applications requiring real-time performance, such as aerial imaging with drones and UAVs for emergency responses. In this work, we introduce TakuNet, a novel light-weight architecture which employs techniques such as depth-wise convolutions and an early downsampling stem to reduce computational complexity while maintaining high accuracy. It leverages dense connections for fast convergence during training and uses 16-bit floating-point precision for optimization on embedded hardware accelerators. Experimental evaluation on two public datasets shows that TakuNet achieves near-state-of-the-art accuracy in classifying aerial images of emergency situations, despite its minimal parameter count. Real-world tests on embedded devices, namely Jetson Orin Nano and Raspberry Pi, confirm TakuNet's efficiency, achieving more than 650 fps on the 15W Jetson board, making it suitable for real-time AI processing on resource-constrained platforms and advancing the applicability of drones in emergency scenarios. The code and implementation details are publicly released.

arXiv:2501.06138공식 코드 · Papers with Code

MS-Temba : Multi-Scale Temporal Mamba for Efficient Temporal Action Detection

Action detection in real-world scenarios is particularly challenging due to densely distributed actions in hour-long untrimmed videos. It requires modeling both short- and long-term temporal relationships while handling significant intra-class temporal variations. Previous state-of-the-art (SOTA) Transformer-based architectures, though effective, are impractical for real-world deployment due to their high parameter count, GPU memory usage, and limited throughput, making them unsuitable for very long videos. In this work, we innovatively adapt the Mamba architecture for action detection and propose Multi-scale Temporal Mamba (MS-Temba), comprising two key components: Temporal Mamba (Temba) Blocks and the Temporal Mamba Fuser. Temba Blocks include the Temporal Local Module (TLM) for short-range temporal modeling and the Dilated Temporal SSM (DTS) for long-range dependencies. By introducing dilations, a novel concept for Mamba, TLM and DTS capture local and global features at multiple scales. The Temba Fuser aggregates these scale-specific features using Mamba to learn comprehensive multi-scale representations of untrimmed videos. MS-Temba is validated on three public datasets, outperforming SOTA methods on long videos and matching prior methods on short videos while using only one-eighth of the parameters.

arXiv:2501.03944공식 코드 · Papers with Code

A GPU Implementation of Multi-Guiding Spark Fireworks Algorithm for Efficient Black-Box Neural Network Optimization

Swarm intelligence optimization algorithms have gained significant attention due to their ability to solve complex optimization problems. However, the efficiency of optimization in large-scale problems limits the use of related methods. This paper presents a GPU-accelerated version of the Multi-Guiding Spark Fireworks Algorithm (MGFWA), which significantly improves the computational efficiency compared to its traditional CPU-based counterpart. We benchmark the GPU-MGFWA on several neural network black-box optimization problems and demonstrate its superior performance in terms of both speed and solution quality. By leveraging the parallel processing power of modern GPUs, the proposed GPU-MGFWA results in faster convergence and reduced computation time for large-scale optimization tasks. The proposed implementation offers a promising approach to accelerate swarm intelligence algorithms, making them more suitable for real-time applications and large-scale industrial problems. Source code is released at https://github.com/mxxxr/MGFWA.

arXiv:2501.03895공식 코드 · Papers with Code

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and textual instructions into the context of large language models (LLMs), where large-scale parameters and numerous context tokens (predominantly vision tokens) result in substantial computational overhead. Previous efforts towards efficient LMMs always focus on replacing the LLM backbone with smaller models, while neglecting the crucial issue of token quantity. In this paper, we introduce LLaVA-Mini, an efficient LMM with minimal vision tokens. To achieve a high compression ratio of vision tokens while preserving visual information, we first analyze how LMMs understand vision tokens and find that most vision tokens only play a crucial role in the early layers of LLM backbone, where they mainly fuse visual information into text tokens. Building on this finding, LLaVA-Mini introduces modality pre-fusion to fuse visual information into text tokens in advance, thereby facilitating the extreme compression of vision tokens fed to LLM backbone into one token. LLaVA-Mini is a unified large multimodal model that can support the understanding of images, high-resolution images, and videos in an efficient manner. Experiments across 11 image-based and 7 video-based benchmarks demonstrate that LLaVA-Mini outperforms LLaVA-v1.5 with just 1 vision token instead of 576. Efficiency analyses reveal that LLaVA-Mini can reduce FLOPs by 77%, deliver low-latency responses within 40 milliseconds, and process over 10,000 frames of video on the GPU hardware with 24GB of memory.

arXiv:2501.02573공식 코드 · Papers with Code

LeetDecoding: A PyTorch Library for Exponentially Decaying Causal Linear Attention with CUDA Implementations

The machine learning and data science community has made significant while dispersive progress in accelerating transformer-based large language models (LLMs), and one promising approach is to replace the original causal attention in a generative pre-trained transformer (GPT) with \emph{exponentially decaying causal linear attention}. In this paper, we present LeetDecoding, which is the first Python package that provides a large set of computation routines for this fundamental operator. The launch of LeetDecoding was motivated by the current lack of (1) clear understanding of the complexity regarding this operator, (2) a comprehensive collection of existing computation methods (usually spread in seemingly unrelated fields), and (3) CUDA implementations for fast inference on GPU. LeetDecoding's design is easy to integrate with existing linear-attention LLMs, and allows for researchers to benchmark and evaluate new computation methods for exponentially decaying causal linear attention. The usage of LeetDecoding does not require any knowledge of GPU programming and the underlying complexity analysis, intentionally making LeetDecoding accessible to LLM practitioners. The source code of LeetDecoding is provided at \href{https://github.com/Computational-Machine-Intelligence/LeetDecoding}{this GitHub repository}, and users can simply install LeetDecoding by the command \texttt{pip install leet-decoding}.

arXiv:2501.02314공식 코드 · Papers with Code

RadarNeXt: Real-Time and Reliable 3D Object Detector Based On 4D mmWave Imaging Radar

3D object detection is crucial for Autonomous Driving (AD) and Advanced Driver Assistance Systems (ADAS). However, most 3D detectors prioritize detection accuracy, often overlooking network inference speed in practical applications. In this paper, we propose RadarNeXt, a real-time and reliable 3D object detector based on the 4D mmWave radar point clouds. It leverages the re-parameterizable neural networks to catch multi-scale features, reduce memory cost and accelerate the inference. Moreover, to highlight the irregular foreground features of radar point clouds and suppress background clutter, we propose a Multi-path Deformable Foreground Enhancement Network (MDFEN), ensuring detection accuracy while minimizing the sacrifice of speed and excessive number of parameters. Experimental results on View-of-Delft and TJ4DRadSet datasets validate the exceptional performance and efficiency of RadarNeXt, achieving 50.48 and 32.30 mAPs with the variant using our proposed MDFEN. Notably, our RadarNeXt variants achieve inference speeds of over 67.10 FPS on the RTX A4000 GPU and 28.40 FPS on the Jetson AGX Orin. This research demonstrates that RadarNeXt brings a novel and effective paradigm for 3D perception based on 4D mmWave radar.

arXiv:2501.01046공식 코드 · Papers with Code

FED: Fast and Efficient Dataset Deduplication Framework with GPU Acceleration

Dataset deduplication plays a crucial role in enhancing data quality, ultimately improving training performance and efficiency of LLMs. A commonly used method for data deduplication is the MinHash LSH algorithm. Recently, NVIDIA introduced a GPU-based MinHash LSH deduplication method, but it remains suboptimal, leaving room for further improvement in processing efficiency. This paper proposes a GPU-accelerated deduplication framework \sys that optimizes MinHash LSH for GPU clusters and leverages computationally efficient and partially reusable non-cryptographic hash functions. \sys significantly outperforms the CPU-based deduplication tool included in SlimPajama by up to 58.3 times and the GPU-based deduplication tool included in NVIDIA NeMo Curator by up to 8.6 times when processing 1 million documents with a node of four GPUs. Deduplication of 1.2 trillion tokens is completed in just 5.1 hours in a four-node, 16-GPU environment. The related code is publicly available on GitHub (https://github.com/mcrl/FED).