PyTorchKR Papers

최신 논문

총 5,357편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2409.18102공식 코드 · Papers with Code

MALPOLON: A Framework for Deep Species Distribution Modeling

This paper describes a deep-SDM framework, MALPOLON. Written in Python and built upon the PyTorch library, this framework aims to facilitate training and inferences of deep species distribution models (deep-SDM) and sharing for users with only general Python language skills (e.g., modeling ecologists) who are interested in testing deep learning approaches to build new SDMs. More advanced users can also benefit from the framework's modularity to run more specific experiments by overriding existing classes while taking advantage of press-button examples to train neural networks on multiple classification tasks using custom or provided raw and pre-processed datasets. The framework is open-sourced on GitHub and PyPi along with extensive documentation and examples of use in various scenarios. MALPOLON offers straightforward installation, YAML-based configuration, parallel computing, multi-GPU utilization, baseline and foundational models for benchmarking, and extensive tutorials/documentation, aiming to enhance accessibility and performance scalability for ecologists and researchers.

arXiv:2409.18057공식 코드 · Papers with Code

LightAvatar: Efficient Head Avatar as Dynamic Neural Light Field

Recent works have shown that neural radiance fields (NeRFs) on top of parametric models have reached SOTA quality to build photorealistic head avatars from a monocular video. However, one major limitation of the NeRF-based avatars is the slow rendering speed due to the dense point sampling of NeRF, preventing them from broader utility on resource-constrained devices. We introduce LightAvatar, the first head avatar model based on neural light fields (NeLFs). LightAvatar renders an image from 3DMM parameters and a camera pose via a single network forward pass, without using mesh or volume rendering. The proposed approach, while being conceptually appealing, poses a significant challenge towards real-time efficiency and training stability. To resolve them, we introduce dedicated network designs to obtain proper representations for the NeLF model and maintain a low FLOPs budget. Meanwhile, we tap into a distillation-based training strategy that uses a pretrained avatar model as teacher to synthesize abundant pseudo data for training. A warping field network is introduced to correct the fitting error in the real data so that the model can learn better. Extensive experiments suggest that our method can achieve new SOTA image quality quantitatively or qualitatively, while being significantly faster than the counterparts, reporting 174.1 FPS (512x512 resolution) on a consumer-grade GPU (RTX3090) with no customized optimization.

arXiv:2409.17422공식 코드 · Papers with Code

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction

Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long context inputs, but this comes at the cost of increased computational resources and latency. Our research introduces a novel approach for the long context bottleneck to accelerate LLM inference and reduce GPU memory consumption. Our research demonstrates that LLMs can identify relevant tokens in the early layers before generating answers to a query. Leveraging this insight, we propose an algorithm that uses early layers of an LLM as filters to select and compress input tokens, significantly reducing the context length for subsequent processing. Our method, GemFilter, demonstrates substantial improvements in both speed and memory efficiency compared to existing techniques, such as standard attention and SnapKV/H2O. Notably, it achieves a 2.4$\times$ speedup and 30\% reduction in GPU memory usage compared to SOTA methods. Evaluation on the Needle in a Haystack task shows that GemFilter significantly outperforms standard attention, SnapKV and demonstrates comparable performance on the LongBench challenge. GemFilter is simple, training-free, and broadly applicable across different LLMs. Crucially, it provides interpretability by allowing humans to inspect the selected input sequence. These findings not only offer practical benefits for LLM deployment, but also enhance our understanding of LLM internal mechanisms, paving the way for further optimizations in LLM design and inference. Our code is available at \url{https://github.com/SalesforceAIResearch/GemFilter}.

arXiv:2409.17372공식 코드 · Papers with Code

Search for Efficient Large Language Models

Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting memory reduction and inference acceleration, which underscore the redundancy in LLMs. However, most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures. Besides, traditional architecture search methods, limited by the elevated complexity with extensive parameters, struggle to demonstrate their effectiveness on LLMs. In this paper, we propose a training-free architecture search framework to identify optimal subnets that preserve the fundamental strengths of the original LLMs while achieving inference acceleration. Furthermore, after generating subnets that inherit specific weights from the original LLMs, we introduce a reformation algorithm that utilizes the omitted weights to rectify the inherited weights with a small amount of calibration data. Compared with SOTA training-free structured pruning works that can generate smaller networks, our method demonstrates superior performance across standard benchmarks. Furthermore, our generated subnets can directly reduce the usage of GPU memory and achieve inference acceleration. Code: https://github.com/shawnricecake/search-llm

arXiv:2409.17870

Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores

Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor Core support and inefficient memory management, leading to suboptimal acceleration. To address these challenges, we propose a comprehensive acceleration scheme for arbitrary precision LLMs. At its core, we introduce a novel bipolar-INT data format that facilitates parallel computing and supports symmetric quantization, effectively reducing data redundancy. Building on this, we implement an arbitrary precision matrix multiplication scheme that decomposes and recovers matrices at the bit level, enabling flexible precision while maximizing GPU Tensor Core utilization. Furthermore, we develop an efficient matrix preprocessing method that optimizes data layout for subsequent computations. Finally, we design a data recovery-oriented memory management system that strategically utilizes fast shared memory, significantly enhancing kernel execution speed and minimizing memory access latency. Experimental results demonstrate our approach's effectiveness, with up to 2.4\times speedup in matrix multiplication compared to NVIDIA's CUTLASS. When integrated into LLMs, we achieve up to 6.7\times inference acceleration. These improvements significantly enhance LLM inference efficiency, enabling broader and more responsive applications of LLMs.

arXiv:2409.13221

Optimizing RLHF Training for Large Language Models with Stage Fusion

We present RLHFuse, an efficient training system with stage fusion for Reinforcement Learning from Human Feedback (RLHF). Due to the intrinsic nature of RLHF training, i.e., the data skewness in the generation stage and the pipeline bubbles in the training stage, existing RLHF systems suffer from low GPU utilization. RLHFuse breaks the traditional view of RLHF workflow as a composition of individual tasks, splitting each task into finer-grained subtasks, and performing stage fusion to improve GPU utilization. RLHFuse contains two key ideas. First, for generation and inference tasks, RLHFuse splits them into sample-level subtasks, enabling efficient inter-stage fusion to overlap the execution of generation and inference stages, thus mitigating the original generation bottleneck dominated by long-tailed samples. Second, for training tasks, RLHFuse breaks them into subtasks of micro-batches and performs intra-stage fusion to concurrently execute these subtasks in the training stage with a fused pipeline schedule, effectively mitigating the pipeline bubbles. The experiments show that RLHFuse increases the training throughput by up to $3.7\times$, compared to existing systems.

arXiv:2409.16576

FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. We present FusionANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of FusionANNS lies in CPU/GPU collaborative filtering and re-ranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system--SPANN and GPU-accelerated in-memory ANNS system--RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1X higher query per second (QPS) and 5.7-8.8X higher cost efficiency compared with SPANN; 2) and 2-4.9X higher QPS and 2.3-6.8X higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy.

arXiv:2409.16572공식 코드 · Papers with Code

Efficient and generalizable nested Fourier-DeepONet for three-dimensional geological carbon sequestration

Geological carbon sequestration (GCS) involves injecting CO$_2$ into subsurface geological formations for permanent storage. Numerical simulations could guide decisions in GCS projects by predicting CO$_2$ migration pathways and the pressure distribution in storage formation. However, these simulations are often computationally expensive due to highly coupled physics and large spatial-temporal simulation domains. Surrogate modeling with data-driven machine learning has become a promising alternative to accelerate physics-based simulations. Among these, the Fourier neural operator (FNO) has been applied to three-dimensional synthetic subsurface models. Here, to further improve performance, we have developed a nested Fourier-DeepONet by combining the expressiveness of the FNO with the modularity of a deep operator network (DeepONet). This new framework is twice as efficient as a nested FNO for training and has at least 80% lower GPU memory requirement due to its flexibility to treat temporal coordinates separately. These performance improvements are achieved without compromising prediction accuracy. In addition, the generalization and extrapolation ability of nested Fourier-DeepONet beyond the training range has been thoroughly evaluated. Nested Fourier-DeepONet outperformed the nested FNO for extrapolation in time with more than 50% reduced error. It also exhibited good extrapolation accuracy beyond the training range in terms of reservoir properties, number of wells, and injection rate.

arXiv:2409.17016

CNN Mixture-of-Depths

We introduce Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs), a novel approach that enhances the computational efficiency of CNNs by selectively processing channels based on their relevance to the current prediction. This method optimizes computational resources by dynamically selecting key channels in feature maps for focused processing within the convolutional blocks (Conv-Blocks), while skipping less relevant channels. Unlike conditional computation methods that require dynamic computation graphs, CNN MoD uses a static computation graph with fixed tensor sizes which improve hardware efficiency. It speeds up the training and inference processes without the need for customized CUDA kernels, unique loss functions, or finetuning. CNN MoD either matches the performance of traditional CNNs with reduced inference times, GMACs, and parameters, or exceeds their performance while maintaining similar inference times, GMACs, and parameters. For example, on ImageNet, ResNet86-MoD exceeds the performance of the standard ResNet50 by 0.45% with a 6% speedup on CPU and 5% on GPU. Moreover, ResNet75-MoD achieves the same performance as ResNet50 with a 25% speedup on CPU and 15% on GPU.

arXiv:2409.16997공식 코드 · Papers with Code

INT-FlashAttention: Enabling Flash Attention for INT8 Quantization

As the foundation of large language models (LLMs), self-attention module faces the challenge of quadratic time and memory complexity with respect to sequence length. FlashAttention accelerates attention computation and reduces its memory usage by leveraging the GPU memory hierarchy. A promising research direction is to integrate FlashAttention with quantization methods. This paper introduces INT-FlashAttention, the first INT8 quantization architecture compatible with the forward workflow of FlashAttention, which significantly improves the inference speed of FlashAttention on Ampere GPUs. We implement our INT-FlashAttention prototype with fully INT8 activations and general matrix-multiplication (GEMM) kernels, making it the first attention operator with fully INT8 input. As a general token-level post-training quantization framework, INT-FlashAttention is also compatible with other data formats like INT4, etc. Experimental results show INT-FlashAttention achieves 72% faster inference speed and 82% smaller quantization error compared to standard FlashAttention with FP16 and FP8 data format.

arXiv:2409.15373

Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention

The integration of hardware accelerators has significantly advanced the capabilities of modern recommendation systems, enabling the exploration of complex ranking paradigms previously deemed impractical. However, the GPU-based computational costs present substantial challenges. In this paper, we demonstrate our development of an efficiency-driven approach to explore these paradigms, moving beyond traditional reliance on native PyTorch modules. We address the specific challenges posed by ranking models' dependence on categorical features, which vary in length and complicate GPU utilization. We introduce Jagged Feature Interaction Kernels, a novel method designed to extract fine-grained insights from long categorical features through efficient handling of dynamically sized tensors. We further enhance the performance of attention mechanisms by integrating Jagged tensors with Flash Attention. Our novel Jagged Flash Attention achieves up to 9x speedup and 22x memory reduction compared to dense attention. Notably, it also outperforms dense flash attention, with up to 3x speedup and 53% more memory efficiency. In production models, we observe 10% QPS improvement and 18% memory savings, enabling us to scale our recommendation systems with longer features and more complex architectures.

arXiv:2409.15911

A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation

Simultaneous Speech Translation (SimulST) involves generating target language text while continuously processing streaming speech input, presenting significant real-time challenges. Multi-task learning is often employed to enhance SimulST performance but introduces optimization conflicts between primary and auxiliary tasks, potentially compromising overall efficiency. The existing model-level conflict resolution methods are not well-suited for this task which exacerbates inefficiencies and leads to high GPU memory consumption. To address these challenges, we propose a Modular Gradient Conflict Mitigation (MGCM) strategy that detects conflicts at a finer-grained modular level and resolves them utilizing gradient projection. Experimental results demonstrate that MGCM significantly improves SimulST performance, particularly under medium and high latency conditions, achieving a 0.68 BLEU score gain in offline tasks. Additionally, MGCM reduces GPU memory consumption by over 95\% compared to other conflict mitigation methods, establishing it as a robust solution for SimulST tasks.

arXiv:2409.13418공식 코드 · Papers with Code

Occupancy-Based Dual Contouring

We introduce a dual contouring method that provides state-of-the-art performance for occupancy functions while achieving computation times of a few seconds. Our method is learning-free and carefully designed to maximize the use of GPU parallelization. The recent surge of implicit neural representations has led to significant attention to occupancy fields, resulting in a wide range of 3D reconstruction and generation methods based on them. However, the outputs of such methods have been underestimated due to the bottleneck in converting the resulting occupancy function to a mesh. Marching Cubes tends to produce staircase-like artifacts, and most subsequent works focusing on exploiting signed distance functions as input also yield suboptimal results for occupancy functions. Based on Manifold Dual Contouring (MDC), we propose Occupancy-Based Dual Contouring (ODC), which mainly modifies the computation of grid edge points (1D points) and grid cell points (3D points) to not use any distance information. We introduce auxiliary 2D points that are used to compute local surface normals along with the 1D points, helping identify 3D points via the quadric error function. To search the 1D, 2D, and 3D points, we develop fast algorithms that are parallelizable across all grid edges, faces, and cells. Our experiments with several 3D neural generative models and a 3D mesh dataset demonstrate that our method achieves the best fidelity compared to prior works.

arXiv:2409.16154공식 코드 · Papers with Code

Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speed

For efficient and safe autonomous driving, it is essential that autonomous vehicles can predict the motion of other traffic agents. While highly accurate, current motion prediction models often impose significant challenges in terms of training resource requirements and deployment on embedded hardware. We propose a new efficient motion prediction model, which achieves highly competitive benchmark results while training only a few hours on a single GPU. Due to our lightweight architectural choices and the focus on reducing the required training resources, our model can easily be applied to custom datasets. Furthermore, its low inference latency makes it particularly suitable for deployment in autonomous applications with limited computing resources.

arXiv:2409.15889공식 코드 · Papers with Code

CAD: Memory Efficient Convolutional Adapter for Segment Anything

The Foundation model for image segmentation, Segment Anything (SAM), has been actively researched in various fields since its proposal. Various researches have been proposed to adapt SAM to specific domains, with one notable approach involving the addition and training of lightweight adapter modules. While adapter-based fine-tuning approaches have reported parameter efficiency and significant performance improvements, they face a often overlooked issue: the excessive consumption of GPU memory relative to the number of trainable parameters. Addressing this issue, this paper proposes a memory-efficient parallel convolutional adapter architecture. This architecture connects in parallel with SAM's image encoder, eliminating the need to store activations and gradients of the image encoder during model training. Our proposed architecture demonstrated competitive experimental results while using less than half the GPU memory compared to SAM Adapter, indicating its value as an alternative to simple decoder fine-tuning when hardware limitations preclude adapter-based learning. Our code implementation is available at our github.

arXiv:2409.15697

dnaGrinder: a lightweight and high-capacity genomic foundation model

The task of understanding and interpreting the complex information encoded within genomic sequences remains a grand challenge in biological research and clinical applications. In this context, recent advancements in large language model research have led to the development of both encoder-only and decoder-only foundation models designed to decode intricate information in DNA sequences. However, several issues persist, particularly regarding the efficient management of long-range dependencies inherent in genomic sequences, the effective representation of nucleotide variations, and the considerable computational costs associated with large model architectures and extensive pretraining datasets. Current genomic foundation models often face a critical tradeoff: smaller models with mediocre performance versus large models with improved performance. To address these challenges, we introduce dnaGrinder, a unique and efficient genomic foundation model. dnaGrinder excels at managing long-range dependencies within genomic sequences while minimizing computational costs without compromising performance. It achieves results that are not just comparable but often superior to leading DNA models such as Nucleotide Transformer and DNABERT-2. Furthermore, dnaGrinder is designed for easy fine-tuning on workstation-grade GPUs, accommodating input lengths exceeding 17,000 tokens. On a single high-performance GPU, it supports sequences longer than 140,000 tokens, making it a highly efficient and accessible tool for both basic biological research and clinical applications.

arXiv:2409.00301

ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models

In recent years, there has been a notable increase in the development of autonomous vehicle (AV) technologies aimed at improving safety in transportation systems. While AVs have been deployed in the real-world to some extent, a full-scale deployment requires AVs to robustly navigate through challenges like heavy rain, snow, low lighting, construction zones and GPS signal loss in tunnels. To be able to handle these specific challenges, an AV must reliably recognize the physical attributes of the environment in which it operates. In this paper, we define context recognition as the task of accurately identifying environmental attributes for an AV to appropriately deal with them. Specifically, we define 24 environmental contexts capturing a variety of weather, lighting, traffic and road conditions that an AV must be aware of. Motivated by the need to recognize environmental contexts, we create a context recognition dataset called DrivingContexts with more than 1.6 million context-query pairs relevant for an AV. Since traditional supervised computer vision approaches do not scale well to a variety of contexts, we propose a framework called ContextVLM that uses vision-language models to detect contexts using zero- and few-shot approaches. ContextVLM is capable of reliably detecting relevant driving contexts with an accuracy of more than 95% on our dataset, while running in real-time on a 4GB Nvidia GeForce GTX 1050 Ti GPU on an AV with a latency of 10.5 ms per query.

arXiv:2409.14485공식 코드 · Papers with Code

Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding

Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos. Although several existing methods attempt to reduce visual tokens, their strategies encounter severe bottleneck, restricting MLLMs' ability to perceive fine-grained visual details. In this work, we propose Video-XL, a novel approach that leverages MLLMs' inherent key-value (KV) sparsification capacity to condense the visual input. Specifically, we introduce a new special token, the Visual Summarization Token (VST), for each interval of the video, which summarizes the visual information within the interval as its associated KV. The VST module is trained by instruction fine-tuning, where two optimizing strategies are offered. 1.Curriculum learning, where VST learns to make small (easy) and large compression (hard) progressively. 2. Composite data curation, which integrates single-image, multi-image, and synthetic data to overcome the scarcity of long-video instruction data. The compression quality is further improved by dynamic compression, which customizes compression granularity based on the information density of different video intervals. Video-XL's effectiveness is verified from three aspects. First, it achieves a superior long-video understanding capability, outperforming state-of-the-art models of comparable sizes across multiple popular benchmarks. Second, it effectively preserves video information, with minimal compression loss even at 16x compression ratio. Third, it realizes outstanding cost-effectiveness, enabling high-quality processing of thousands of frames on a single A100 GPU.

arXiv:2409.14912

Efficient Tabular Data Preprocessing of ML Pipelines

Data preprocessing pipelines, which includes data decoding, cleaning, and transforming, are a crucial component of Machine Learning (ML) training. Thy are computationally intensive and often become a major bottleneck, due to the increasing performance gap between the CPUs used for preprocessing and the GPUs used for model training. Recent studies show that a significant number of CPUs across several machines are required to achieve sufficient throughput to saturate the GPUs, leading to increased resource and energy consumption. When the pipeline involves vocabulary generation, the preprocessing performance scales poorly due to significant row-wise synchronization overhead between different CPU cores and servers. To address this limitation, in this paper we present the design of Piper, a hardware accelerator for tabular data preprocessing, prototype it on FPGAs, and demonstrate its potential for training pipelines of commercial recommender systems. Piper achieves 4.7 $\sim$ 71.3$\times$ speedup in latency over a 128-core CPU server and outperforms a data-center GPU by 4.8$\sim$ 20.3$\times$ when using binary input. The impressive performance showcases Piper's potential to increase the efficiency of data preprocessing pipelines and significantly reduce their resource consumption.

arXiv:2409.14803

Benchmarking Edge AI Platforms for High-Performance ML Inference

Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often involve scaling down modern hardware, the performance characteristics of neural network workloads on these platforms can vary significantly, especially when it comes to parallel processing, which is a critical consideration for edge deployments. To address this, we conduct a comprehensive study comparing the latency and throughput of various linear algebra and neural network inference tasks across CPU-only, CPU/GPU, and CPU/NPU integrated solutions. {We find that the Neural Processing Unit (NPU) excels in matrix-vector multiplication (58.6% faster) and some neural network tasks (3.2$\times$ faster for video classification and large language models). GPU outperforms in matrix multiplication (22.6% faster) and LSTM networks (2.7$\times$ faster) while CPU excels at less parallel operations like dot product. NPU-based inference offers a balance of latency and throughput at lower power consumption. GPU-based inference, though more energy-intensive, performs best with large dimensions and batch sizes. We highlight the potential of heterogeneous computing solutions for edge AI, where diverse compute units can be strategically leveraged to boost accurate and real-time inference.