Add to Chrome
Add to Firefox
Add to EdgeZhihang Yuan
A Survey on Efficient Inference for Large Language Models
Apr 22, 2024
Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirements of LLM inference pose challenges for deployment in resource-constrained scenarios. Efforts within the field have been directed towards developing techniques aimed at enhancing the efficiency of LLM inference. This paper presents a comprehensive survey of the existing literature on efficient LLM inference. We start by analyzing the primary causes of the inefficient LLM inference, i.e., the large model size, the quadratic-complexity attention operation, and the auto-regressive decoding approach. Then, we introduce a comprehensive taxonomy that organizes the current literature into data-level, model-level, and system-level optimization. Moreover, the paper includes comparative experiments on representative methods within critical sub-fields to provide quantitative insights. Last but not least, we provide some knowledge summary and discuss future research directions.
PillarTrack: Redesigning Pillar-based Transformer Network for Single Object Tracking on Point Clouds
Apr 11, 2024LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving. It aims to obtain accurate 3D BBox from the search area based on similarity or motion. However, existing 3D SOT methods usually follow the point-based pipeline, where the sampling operation inevitably leads to redundant or lost information, resulting in unexpected performance. To address these issues, we propose PillarTrack, a pillar-based 3D single object tracking framework. Firstly, we transform sparse point clouds into dense pillars to preserve the local and global geometrics. Secondly, we introduce a Pyramid-type Encoding Pillar Feature Encoder (PE-PFE) design to help the feature representation of each pillar. Thirdly, we present an efficient Transformer-based backbone from the perspective of modality differences. Finally, we construct our PillarTrack tracker based above designs. Extensive experiments on the KITTI and nuScenes dataset demonstrate the superiority of our proposed method. Notably, our method achieves state-of-the-art performance on the KITTI and nuScenes dataset and enables real-time tracking speed. We hope our work could encourage the community to rethink existing 3D SOT tracker designs.We will open source our code to the research community in https://github.com/StiphyJay/PillarTrack.
LLM Inference Unveiled: Survey and Roofline Model Insights
Mar 11, 2024The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the various methods of LLM Inference to provide a clear understanding of this domain. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems, such as why LLMs are memory-bound, how much memory and computation they need, and how to choose the right hardware. We systematically collate the latest advancements in efficient LLM inference, covering crucial areas such as model compression (e.g., Knowledge Distillation and Quantization), algorithm improvements (e.g., Early Exit and Mixture-of-Expert), and both hardware and system-level enhancements. Our survey stands out by analyzing these methods with roofline model, helping us understand their impact on memory access and computation. This distinctive approach not only showcases the current research landscape but also delivers valuable insights for practical implementation, positioning our work as an indispensable resource for researchers new to the field as well as for those seeking to deepen their understanding of efficient LLM deployment. The analyze tool, LLM-Viewer, is open-sourced.
WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More
Feb 20, 2024Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on the quantization of LLMs, a technique that reduces memory consumption by converting model parameters and activations into low-bit integers. We critically analyze the existing quantization approaches, identifying their limitations in balancing the accuracy and efficiency of the quantized LLMs. To advance beyond these limitations, we propose WKVQuant, a PTQ framework especially designed for quantizing weights and the key/value (KV) cache of LLMs. Specifically, we incorporates past-only quantization to improve the computation of attention. Additionally, we introduce two-dimensional quantization strategy to handle the distribution of KV cache, along with a cross-block reconstruction regularization for parameter optimization. Experiments show that WKVQuant achieves almost comparable memory savings to weight-activation quantization, while also approaching the performance of weight-only quantization.
QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning
Feb 13, 2024Diffusion models have achieved remarkable success in image generation tasks, yet their practical deployment is restrained by the high memory and time consumption. While quantization paves a way for diffusion model compression and acceleration, existing methods totally fail when the models are quantized to low-bits. In this paper, we unravel three properties in quantized diffusion models that compromise the efficacy of current methods: imbalanced activation distributions, imprecise temporal information, and vulnerability to perturbations of specific modules. To alleviate the intensified low-bit quantization difficulty stemming from the distribution imbalance, we propose finetuning the quantized model to better adapt to the activation distribution. Building on this idea, we identify two critical types of quantized layers: those holding vital temporal information and those sensitive to reduced bit-width, and finetune them to mitigate performance degradation with efficiency. We empirically verify that our approach modifies the activation distribution and provides meaningful temporal information, facilitating easier and more accurate quantization. Our method is evaluated over three high-resolution image generation tasks and achieves state-of-the-art performance under various bit-width settings, as well as being the first method to generate readable images on full 4-bit (i.e. W4A4) Stable Diffusion. Code is been made publicly available.
MIM4DD: Mutual Information Maximization for Dataset Distillation
Dec 27, 2023Dataset distillation (DD) aims to synthesize a small dataset whose test performance is comparable to a full dataset using the same model. State-of-the-art (SoTA) methods optimize synthetic datasets primarily by matching heuristic indicators extracted from two networks: one from real data and one from synthetic data (see Fig.1, Left), such as gradients and training trajectories. DD is essentially a compression problem that emphasizes maximizing the preservation of information contained in the data. We argue that well-defined metrics which measure the amount of shared information between variables in information theory are necessary for success measurement but are never considered by previous works. Thus, we introduce mutual information (MI) as the metric to quantify the shared information between the synthetic and the real datasets, and devise MIM4DD numerically maximizing the MI via a newly designed optimizable objective within a contrastive learning framework to update the synthetic dataset. Specifically, we designate the samples in different datasets that share the same labels as positive pairs and vice versa negative pairs. Then we respectively pull and push those samples in positive and negative pairs into contrastive space via minimizing NCE loss. As a result, the targeted MI can be transformed into a lower bound represented by feature maps of samples, which is numerically feasible. Experiment results show that MIM4DD can be implemented as an add-on module to existing SoTA DD methods.
Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
Dec 17, 2023Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources. Network quantization is a powerful technique to compress neural networks, allowing for more efficient and scalable AI deployments. Recently, Re-parameterization has emerged as a promising technique to enhance model performance while simultaneously alleviating the computational burden in various computer vision tasks. However, the accuracy drops significantly when applying quantization on the re-parameterized networks. We identify that the primary challenge arises from the large variation in weight distribution across the original branches. To address this issue, we propose a coarse & fine weight splitting (CFWS) method to reduce quantization error of weight, and develop an improved KL metric to determine optimal quantization scales for activation. To the best of our knowledge, our approach is the first work that enables post-training quantization applicable on re-parameterized networks. For example, the quantized RepVGG-A1 model exhibits a mere 0.3% accuracy loss. The code is in https://github.com/NeonHo/Coarse-Fine-Weight-Split.git
ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
Dec 10, 2023This paper explores a new post-hoc training-free compression paradigm for compressing Large Language Models (LLMs) to facilitate their wider adoption in various computing environments. We delve into the challenges of LLM compression, notably their dependency on extensive training data and computational resources. We propose a training-free approach dubbed Activation-aware Singular Value Decomposition (ASVD) to address these limitations. ASVD effectively manages activation outliers by adjusting the weight matrix based on the activation distribution, improving decomposition accuracy and efficiency. Our method also addresses the varying sensitivity of different LLM layers to decomposition, with an iterative calibration process for optimal layer-specific decomposition. Experiments demonstrate that ASVD can compress network by 10%-20% without losing reasoning capacities. Additionally, it can be seamlessly integrated with other LLM compression paradigms, showcasing its flexible compatibility. Code and compressed models are available at https://github.com/hahnyuan/ASVD4LLM.
PB-LLM: Partially Binarized Large Language Models
Sep 29, 2023This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. Due to previous binarization methods collapsing LLMs, we propose a novel approach, Partially-Binarized LLM (PB-LLM), which can achieve extreme low-bit quantization while maintaining the linguistic reasoning capacity of quantized LLMs. Specifically, our exploration first uncovers the ineffectiveness of naive applications of existing binarization algorithms and highlights the imperative role of salient weights in achieving low-bit quantization. Thus, PB-LLM filters a small ratio of salient weights during binarization, allocating them to higher-bit storage, i.e., partially-binarization. PB-LLM is extended to recover the capacities of quantized LMMs, by analyzing from the perspective of post-training quantization (PTQ) and quantization-aware training (QAT). Under PTQ, combining the concepts from GPTQ, we reconstruct the binarized weight matrix guided by the Hessian matrix and successfully recover the reasoning capacity of PB-LLM in low-bit. Under QAT, we freeze the salient weights during training, explore the derivation of optimal scaling factors crucial for minimizing the quantization error, and propose a scaling mechanism based on this derived scaling strategy for residual binarized weights. Those explorations and the developed methodologies significantly contribute to rejuvenating the performance of low-bit quantized LLMs and present substantial advancements in the field of network binarization for LLMs.The code is available at https://github.com/hahnyuan/BinaryLLM.
Latency-aware Unified Dynamic Networks for Efficient Image Recognition
Sep 02, 2023
Dynamic computation has emerged as a promising avenue to enhance the inference efficiency of deep networks. It allows selective activation of computational units, leading to a reduction in unnecessary computations for each input sample. However, the actual efficiency of these dynamic models can deviate from theoretical predictions. This mismatch arises from: 1) the lack of a unified approach due to fragmented research; 2) the focus on algorithm design over critical scheduling strategies, especially in CUDA-enabled GPU contexts; and 3) challenges in measuring practical latency, given that most libraries cater to static operations. Addressing these issues, we unveil the Latency-Aware Unified Dynamic Networks (LAUDNet), a framework that integrates three primary dynamic paradigms-spatially adaptive computation, dynamic layer skipping, and dynamic channel skipping. To bridge the theoretical and practical efficiency gap, LAUDNet merges algorithmic design with scheduling optimization, guided by a latency predictor that accurately gauges dynamic operator latency. We've tested LAUDNet across multiple vision tasks, demonstrating its capacity to notably reduce the latency of models like ResNet-101 by over 50% on platforms such as V100, RTX3090, and TX2 GPUs. Notably, LAUDNet stands out in balancing accuracy and efficiency. Code is available at: https://www.github.com/LeapLabTHU/LAUDNet.