PyTorchKR Papers

최신 논문

총 5,357편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2410.10733공식 코드 · Papers with Code

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio (e.g., 8x), but fail to maintain satisfactory reconstruction accuracy for high spatial compression ratios (e.g., 64x). We address this challenge by introducing two key techniques: (1) Residual Autoencoding, where we design our models to learn residuals based on the space-to-channel transformed features to alleviate the optimization difficulty of high spatial-compression autoencoders; (2) Decoupled High-Resolution Adaptation, an efficient decoupled three-phases training strategy for mitigating the generalization penalty of high spatial-compression autoencoders. With these designs, we improve the autoencoder's spatial compression ratio up to 128 while maintaining the reconstruction quality. Applying our DC-AE to latent diffusion models, we achieve significant speedup without accuracy drop. For example, on ImageNet 512x512, our DC-AE provides 19.1x inference speedup and 17.9x training speedup on H100 GPU for UViT-H while achieving a better FID, compared with the widely used SD-VAE-f8 autoencoder. Our code is available at https://github.com/mit-han-lab/efficientvit.

arXiv:2410.10450공식 코드 · Papers with Code

KBLaM: Knowledge Base augmented Language Model

In this paper, we propose Knowledge Base augmented Language Model (KBLaM), a new method for augmenting Large Language Models (LLMs) with external knowledge. KBLaM works with a knowledge base (KB) constructed from a corpus of documents, transforming each piece of knowledge in the KB into continuous key-value vector pairs via pre-trained sentence encoders with linear adapters and integrating them into pre-trained LLMs via a specialized rectangular attention mechanism. Unlike Retrieval-Augmented Generation, KBLaM eliminates external retrieval modules, and unlike in-context learning, its computational overhead scales linearly with KB size rather than quadratically. Our approach enables integrating a large KB of more than 10K triples into an 8B pre-trained LLM of only 8K context window on one single A100 80GB GPU and allows for dynamic updates without model fine-tuning or retraining. Experiments demonstrate KBLaM's effectiveness in various tasks, including question-answering and open-ended reasoning, while providing interpretable insights into its use of the augmented knowledge.

arXiv:2410.09400공식 코드 · Papers with Code

CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation

Recently, large-scale diffusion models have made impressive progress in text-to-image (T2I) generation. To further equip these T2I models with fine-grained spatial control, approaches like ControlNet introduce an extra network that learns to follow a condition image. However, for every single condition type, ControlNet requires independent training on millions of data pairs with hundreds of GPU hours, which is quite expensive and makes it challenging for ordinary users to explore and develop new types of conditions. To address this problem, we propose the CtrLoRA framework, which trains a Base ControlNet to learn the common knowledge of image-to-image generation from multiple base conditions, along with condition-specific LoRAs to capture distinct characteristics of each condition. Utilizing our pretrained Base ControlNet, users can easily adapt it to new conditions, requiring as few as 1,000 data pairs and less than one hour of single-GPU training to obtain satisfactory results in most scenarios. Moreover, our CtrLoRA reduces the learnable parameters by 90% compared to ControlNet, significantly lowering the threshold to distribute and deploy the model weights. Extensive experiments on various types of conditions demonstrate the efficiency and effectiveness of our method. Codes and model weights will be released at https://github.com/xyfJASON/ctrlora.

arXiv:2410.08791

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

The rapid growth in machine learning models, especially in natural language processing and computer vision, has led to challenges when running these models on hardware with limited resources. This paper introduces Superpipeline, a new framework designed to optimize the execution of large AI models on constrained hardware during both training and inference. Our approach involves dynamically managing model execution by dividing models into individual layers and efficiently transferring these layers between GPU and CPU memory. Superpipeline reduces GPU memory usage by up to 60% in our experiments while maintaining model accuracy and acceptable processing speeds. This allows models that would otherwise exceed available GPU memory to run effectively. Unlike existing solutions that focus mainly on inference or specific model types, Superpipeline can be applied to large language models (LLMs), vision-language models (VLMs), and vision-based models. We tested Superpipeline's performance across various models and hardware setups. The method includes two key parameters that allow fine-tuning the balance between GPU memory use and processing speed. Importantly, Superpipeline does not require retraining or changing model parameters, ensuring that the original model's output remains unchanged. Superpipeline's simplicity and flexibility make it useful for researchers and professionals working with advanced AI models on limited hardware. It enables the use of larger models or bigger batch sizes on existing hardware, potentially speeding up innovation across many machine learning applications. This work marks an important step toward making advanced AI models more accessible and optimizing their deployment in resource-limited environments. The code for Superpipeline is available at https://github.com/abbasiReza/super-pipeline.

arXiv:2410.08946

Parallel Watershed Partitioning: GPU-Based Hierarchical Image Segmentation

Many image processing applications rely on partitioning an image into disjoint regions whose pixels are 'similar.' The watershed and waterfall transforms are established mathematical morphology pixel clustering techniques. They are both relevant to modern applications where groups of pixels are to be decided upon in one go, or where adjacency information is relevant. We introduce three new parallel partitioning algorithms for GPUs. By repeatedly applying watershed algorithms, we produce waterfall results which form a hierarchy of partition regions over an input image. Our watershed algorithms attain competitive execution times in both 2D and 3D, processing an 800 megavoxel image in less than 1.4 sec. We also show how to use this fully deterministic image partitioning as a pre-processing step to machine learning based semantic segmentation. This replaces the role of superpixel algorithms, and results in comparable accuracy and faster training times.

arXiv:2410.08592

VIBES -- Vision Backbone Efficient Selection

This work tackles the challenge of efficiently selecting high-performance pre-trained vision backbones for specific target tasks. Although exhaustive search within a finite set of backbones can solve this problem, it becomes impractical for large datasets and backbone pools. To address this, we introduce Vision Backbone Efficient Selection (VIBES), which aims to quickly find well-suited backbones, potentially trading off optimality for efficiency. We propose several simple yet effective heuristics to address VIBES and evaluate them across four diverse computer vision datasets. Our results show that these approaches can identify backbones that outperform those selected from generic benchmarks, even within a limited search budget of one hour on a single GPU. We reckon VIBES marks a paradigm shift from benchmarks to task-specific optimization.

arXiv:2410.07192

PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training

Training Deep Neural Networks (DNNs) with billions of parameters generally involves pipeline-parallel (PP) execution. Unfortunately, PP model training can use GPUs inefficiently, especially at large scale, due to idle GPU time caused by pipeline bubbles, which are often 15-30% and can exceed 60% of the training job's GPU allocation. To improve the GPU utilization of PP model training, this paper describes PipeFill, which fills pipeline bubbles with execution of other pending jobs. By leveraging bubble GPU time, PipeFill reduces the GPU utilization sacrifice associated with scaling-up of large-model training. To context-switch between fill jobs and the main training job with minimal overhead to the main job, and maximize fill job efficiency, PipeFill carefully fits fill job work to measured bubble durations and GPU memory availability, introduces explicit pipeline-bubble instructions, and orchestrates placement and execution of fill jobs in pipeline bubbles. Experiments show that PipeFill can increase overall utilization by up to 63% for GPUs used in large-scale LLM training, with <2% slowdown of the training job, and 5-15% even for low-scale LLM training. For large-scale LLM training on 8K GPUs, the 63% increase translates to up to 2.6K additional GPUs worth of work completed.

arXiv:2410.07348공식 코드 · Papers with Code

MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

In this work, we aim to simultaneously enhance the effectiveness and efficiency of Mixture-of-Experts (MoE) methods. To achieve this, we propose MoE++, a general and heterogeneous MoE framework that integrates both Feed-Forward Network~(FFN) and zero-computation experts. Specifically, we introduce three types of zero-computation experts: the zero expert, copy expert, and constant expert, which correspond to discard, skip, and replace operations, respectively. This design offers three key advantages: (i) Low Computing Overhead: Unlike the uniform mixing mechanism for all tokens within vanilla MoE, MoE++ allows each token to engage with a dynamic number of FFNs, be adjusted by constant vectors, or even skip the MoE layer entirely. (ii) High Performance: By enabling simple tokens to utilize fewer FFN experts, MoE++ allows more experts to focus on challenging tokens, thereby unlocking greater performance potential than vanilla MoE. (iii) Deployment Friendly: Given that zero-computation experts have negligible parameters, we can deploy all zero-computation experts on each GPU, eliminating the significant communication overhead and expert load imbalance associated with FFN experts distributed across different GPUs. Moreover, we leverage gating residuals, enabling each token to consider the pathway taken in the previous layer when selecting the appropriate experts. Extensive experimental results demonstrate that MoE++ achieves better performance while delivering 1.1-2.1x expert forward throughput compared to a vanilla MoE model of the same size, which lays a solid foundation for developing advanced and efficient MoE-related models.

arXiv:2410.07966공식 코드 · Papers with Code

Neural Reasoning Networks: Efficient Interpretable Neural Networks With Automatic Textual Explanations

Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an understanding of the features influencing the prediction is necessary to ensure fairness, safety, and legal compliance. In this paper we consider one class of such tasks, tabular dataset classification, and propose a novel neuro-symbolic architecture, Neural Reasoning Networks (NRN), that is scalable and generates logically sound textual explanations for its predictions. NRNs are connected layers of logical neurons which implement a form of real valued logic. A training algorithm (R-NRN) learns the weights of the network as usual using gradient descent optimization with backprop, but also learns the network structure itself using a bandit-based optimization. Both are implemented in an extension to PyTorch (https://github.com/IBM/torchlogic) that takes full advantage of GPU scaling and batched training. Evaluation on a diverse set of 22 open-source datasets for tabular classification demonstrates performance (measured by ROC AUC) which improves over multi-layer perceptron (MLP) and is statistically similar to other state-of-the-art approaches such as Random Forest, XGBoost and Gradient Boosted Trees, while offering 43% faster training and a more than 2 orders of magnitude reduction in the number of parameters required, on average. Furthermore, R-NRN explanations are shorter than the compared approaches while producing more accurate feature importance scores.

arXiv:2410.07610

CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features

Multimodal encoders like CLIP excel in tasks such as zero-shot image classification and cross-modal retrieval. However, they require excessive training data. We propose canonical similarity analysis (CSA), which uses two unimodal encoders to replicate multimodal encoders using limited data. CSA maps unimodal features into a multimodal space, using a new similarity score to retain only the multimodal information. CSA only involves the inference of unimodal encoders and a cubic-complexity matrix decomposition, eliminating the need for extensive GPU-based model training. Experiments show that CSA outperforms CLIP while requiring $50,000\times$ fewer multimodal data pairs to bridge the modalities given pre-trained unimodal encoders on ImageNet classification and misinformative news caption detection. CSA surpasses the state-of-the-art method to map unimodal features to multimodal features. We also demonstrate the ability of CSA with modalities beyond image and text, paving the way for future modality pairs with limited paired multimodal data but abundant unpaired unimodal data, such as lidar and text.

arXiv:2410.07547

HM-DF SNN: Transcending Conventional Online Learning with Advanced Training and Deployment

Spiking Neural Networks (SNNs) are considered to have enormous potential in the future development of Artificial Intelligence due to their brain-inspired and energy-efficient properties. Compared to vanilla Spatial-Temporal Back-propagation (STBP) training methods, online training can effectively overcome the risk of GPU memory explosion. However, current online learning framework cannot tackle the inseparability problem of temporal dependent gradients and merely aim to optimize the training memory, resulting in no performance advantages compared to the STBP training models in the inference phase. To address the aforementioned challenges, we propose Hybrid Mechanism-Driven Firing (HM-DF) model, which is a family of advanced models that respectively adopt different spiking calculation schemes in the upper-region and lower-region of the firing threshold. We point out that HM-DF model can effectively separate temporal gradients and tackle the mismatch problem of surrogate gradients, as well as achieving full-stage optimization towards computation speed and memory footprint. Experimental results have demonstrated that HM-DF model can be flexibly combined with various techniques to achieve state-of-the-art performance in the field of online learning, without triggering further power consumption.

arXiv:2410.08208공식 코드 · Papers with Code

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation

In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach leverages differentiable neural rendering on multi-view images to endow a vanilla Vision Transformer (ViT) with intrinsic spatial understanding. We present the most comprehensive evaluation of embodied representation learning to date, covering 268 tasks across 8 simulators with diverse policies in both single-task and language-conditioned multi-task scenarios. The results are compelling: SPA consistently outperforms more than 10 state-of-the-art representation methods, including those specifically designed for embodied AI, vision-centric tasks, and multi-modal applications, while using less training data. Furthermore, we conduct a series of real-world experiments to confirm its effectiveness in practical scenarios. These results highlight the critical role of 3D spatial awareness for embodied representation learning. Our strongest model takes more than 6000 GPU hours to train and we are committed to open-sourcing all code and model weights to foster future research in embodied representation learning. Project Page: https://haoyizhu.github.io/spa/.

arXiv:2410.05315

PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms

Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy concerns or impractical due to network connection. Recent advancements (MLC, 2023a; Gerganov, 2023) have facilitated the local deployment of LLMs. However, local deployment also presents challenges, particularly in balancing quality (generative performance), latency, and throughput within the hardware constraints of mobile devices. In this paper, we introduce our lightweight, all-in-one automated benchmarking framework that allows users to evaluate LLMs on mobile devices. We provide a comprehensive benchmark of various popular LLMs with different quantization configurations (both weights and activations) across multiple mobile platforms with varying hardware capabilities. Unlike traditional benchmarks that assess full-scale models on high-end GPU clusters, we focus on evaluating resource efficiency (memory and power consumption) and harmful output for compressed models on mobile devices. Our key observations include i) differences in energy efficiency and throughput across mobile platforms; ii) the impact of quantization on memory usage, GPU execution time, and power consumption; and iii) accuracy and performance degradation of quantized models compared to their non-quantized counterparts; and iv) the frequency of hallucinations and toxic content generated by compressed LLMs on mobile devices.

arXiv:2410.07160

TextToon: Real-Time Text Toonify Head Avatar from Single Video

We propose TextToon, a method to generate a drivable toonified avatar. Given a short monocular video sequence and a written instruction about the avatar style, our model can generate a high-fidelity toonified avatar that can be driven in real-time by another video with arbitrary identities. Existing related works heavily rely on multi-view modeling to recover geometry via texture embeddings, presented in a static manner, leading to control limitations. The multi-view video input also makes it difficult to deploy these models in real-world applications. To address these issues, we adopt a conditional embedding Tri-plane to learn realistic and stylized facial representations in a Gaussian deformation field. Additionally, we expand the stylization capabilities of 3D Gaussian Splatting by introducing an adaptive pixel-translation neural network and leveraging patch-aware contrastive learning to achieve high-quality images. To push our work into consumer applications, we develop a real-time system that can operate at 48 FPS on a GPU machine and 15-18 FPS on a mobile machine. Extensive experiments demonstrate the efficacy of our approach in generating textual avatars over existing methods in terms of quality and real-time animation. Please refer to our project page for more details: https://songluchuan.github.io/TextToon/.

arXiv:2410.06441

Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models

Fine-tuning language models (LMs) with the Adam optimizer often demands excessive memory, limiting accessibility. The "in-place" version of Stochastic Gradient Descent (IP-SGD) and Memory-Efficient Zeroth-order Optimizer (MeZO) have been proposed to address this. However, IP-SGD still requires substantial memory, and MeZO suffers from slow convergence and degraded final performance due to its zeroth-order nature. This paper introduces Addax, a novel method that improves both memory efficiency and performance of IP-SGD by integrating it with MeZO. Specifically, Addax computes zeroth- or first-order gradients of data points in the minibatch based on their memory consumption, combining these gradient estimates to update directions. By computing zeroth-order gradients for data points that require more memory and first-order gradients for others, Addax overcomes the slow convergence of MeZO and the excessive memory requirement of IP-SGD. Additionally, the zeroth-order gradient acts as a regularizer for the first-order gradient, further enhancing the model's final performance. Theoretically, we establish the convergence of Addax under mild assumptions, demonstrating faster convergence and less restrictive hyper-parameter choices than MeZO. Our experiments with diverse LMs and tasks show that Addax consistently outperforms MeZO regarding accuracy and convergence speed while having a comparable memory footprint. When fine-tuning OPT-13B with one A100 GPU, on average, Addax outperforms MeZO in accuracy/F1 score by 14% and runs 15x faster while using memory similar to MeZO. In our experiments on the larger OPT-30B model, on average, Addax outperforms MeZO in terms of accuracy/F1 score by >16 and runs 30x faster on a single H100 GPU. Moreover, Addax surpasses the performance of standard fine-tuning approaches, such as IP-SGD and Adam, in most tasks with significantly less memory requirement.

arXiv:2410.05954공식 코드 · Papers with Code

Pyramidal Flow Matching for Efficient Video Generative Modeling

Video generation requires modeling a vast spatiotemporal space, which demands significant computational resources and data usage. To reduce the complexity, the prevailing approaches employ a cascaded architecture to avoid direct training with full resolution. Despite reducing computational demands, the separate optimization of each sub-stage hinders knowledge sharing and sacrifices flexibility. This work introduces a unified pyramidal flow matching algorithm. It reinterprets the original denoising trajectory as a series of pyramid stages, where only the final stage operates at the full resolution, thereby enabling more efficient video generative modeling. Through our sophisticated design, the flows of different pyramid stages can be interlinked to maintain continuity. Moreover, we craft autoregressive video generation with a temporal pyramid to compress the full-resolution history. The entire framework can be optimized in an end-to-end manner and with a single unified Diffusion Transformer (DiT). Extensive experiments demonstrate that our method supports generating high-quality 5-second (up to 10-second) videos at 768p resolution and 24 FPS within 20.7k A100 GPU training hours. All code and models will be open-sourced at https://pyramid-flow.github.io.

arXiv:2410.05651

ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler

Recent progress in large-scale text-to-video (T2V) and image-to-video (I2V) diffusion models has greatly enhanced video generation, especially in terms of keyframe interpolation. However, current image-to-video diffusion models, while powerful in generating videos from a single conditioning frame, need adaptation for two-frame (start & end) conditioned generation, which is essential for effective bounded interpolation. Unfortunately, existing approaches that fuse temporally forward and backward paths in parallel often suffer from off-manifold issues, leading to artifacts or requiring multiple iterative re-noising steps. In this work, we introduce a novel, bidirectional sampling strategy to address these off-manifold issues without requiring extensive re-noising or fine-tuning. Our method employs sequential sampling along both forward and backward paths, conditioned on the start and end frames, respectively, ensuring more coherent and on-manifold generation of intermediate frames. Additionally, we incorporate advanced guidance techniques, CFG++ and DDS, to further enhance the interpolation process. By integrating these, our method achieves state-of-the-art performance, efficiently generating high-quality, smooth videos between keyframes. On a single 3090 GPU, our method can interpolate 25 frames at 1024 x 576 resolution in just 195 seconds, establishing it as a leading solution for keyframe interpolation.

arXiv:2410.06511공식 코드 · Papers with Code

TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training

The development of large language models (LLMs) has been instrumental in advancing state-of-the-art natural language processing applications. Training LLMs with billions of parameters and trillions of tokens require sophisticated distributed systems that enable composing and comparing several state-of-the-art techniques in order to efficiently scale across thousands of accelerators. However, existing solutions are complex, scattered across multiple libraries/repositories, lack interoperability, and are cumbersome to maintain. Thus, curating and empirically comparing training recipes require non-trivial engineering effort. This paper introduces TorchTitan, an open-source, PyTorch-native distributed training system that unifies state-of-the-art techniques, streamlining integration and reducing overhead. TorchTitan enables 3D parallelism in a modular manner with elastic scaling, providing comprehensive logging, checkpointing, and debugging tools for production-ready training. It also incorporates hardware-software co-designed solutions, leveraging features like Float8 training and SymmetricMemory. As a flexible test bed, TorchTitan facilitates custom recipe curation and comparison, allowing us to develop optimized training recipes for Llama 3.1 and provide guidance on selecting techniques for maximum efficiency based on our experiences. We thoroughly assess TorchTitan on the Llama 3.1 family of LLMs, spanning 8 billion to 405 billion parameters, and showcase its exceptional performance, modular composability, and elastic scalability. By stacking training optimizations, we demonstrate accelerations of 65.08% with 1D parallelism at the 128-GPU scale (Llama 3.1 8B), an additional 12.59% with 2D parallelism at the 256-GPU scale (Llama 3.1 70B), and an additional 30% with 3D parallelism at the 512-GPU scale (Llama 3.1 405B) on NVIDIA H100 GPUs over optimized baselines.

arXiv:2410.07173

Do better language models have crisper vision?

How well do text-only Large Language Models (LLMs) grasp the visual world? As LLMs are increasingly used in computer vision, addressing this question becomes both fundamental and pertinent. However, existing studies have primarily focused on limited scenarios, such as their ability to generate visual content or cluster multimodal data. To this end, we propose the Visual Text Representation Benchmark (ViTeRB) to isolate key properties that make language models well-aligned with the visual world. With this, we identify large-scale decoder-based LLMs as ideal candidates for representing text in vision-centric contexts, counter to the current practice of utilizing text encoders. Building on these findings, we propose ShareLock, an ultra-lightweight CLIP-like model. By leveraging precomputable frozen features from strong vision and language models, ShareLock achieves an impressive 51% accuracy on ImageNet despite utilizing just 563k image-caption pairs. Moreover, training requires only 1 GPU hour (or 10 hours including the precomputation of features) - orders of magnitude less than prior methods. Code will be released.

arXiv:2410.04466공식 코드 · Papers with Code

Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective

Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLMs like BERT and DeBERTa, generative LLMs like GPT series and Llama series are currently the main focus due to their superior algorithmic performance. The advancements in generative LLMs are closely intertwined with the development of hardware capabilities. Various hardware platforms exhibit distinct hardware characteristics, which can help improve LLM inference performance. Therefore, this paper comprehensively surveys efficient generative LLM inference on different hardware platforms. First, we provide an overview of the algorithm architecture of mainstream generative LLMs and delve into the inference process. Then, we summarize different optimization methods for different platforms such as CPU, GPU, FPGA, ASIC, and PIM/NDP, and provide inference results for generative LLMs. Furthermore, we perform a qualitative and quantitative comparison of inference performance with batch sizes 1 and 8 on different hardware platforms by considering hardware power consumption, absolute inference speed (tokens/s), and energy efficiency (tokens/J). We compare the performance of the same optimization methods across different hardware platforms, the performance across different hardware platforms, and the performance of different methods on the same hardware platform. This provides a systematic and comprehensive summary of existing inference acceleration work by integrating software optimization methods and hardware platforms. We point out that three trends (multimodality, inference-time compute, and higher inference energy efficiency) are promising to redefine the capabilities of edge artificial intelligence systems. Our project is available at https://dai.sjtu.edu.cn/project.html.