SEAL: Scaling to Emphasize Attention for Long-Context Retrieval

In this work, we introduce a novel approach called Scaling to Emphasize Attention for Long-context retrieval (SEAL), which enhances the retrieval performance of large language models (LLMs) over extended contexts. Previous studies have shown that each attention head in LLMs has a unique functionality and collectively contributes to the overall behavior of the model. Similarly, we observe that specific heads are closely tied to long-context retrieval, showing positive or negative correlation with retrieval scores. Built on this insight, we propose a learning-based mechanism using zero-shot generated data to emphasize these heads, improving the model's performance in long-context retrieval tasks. By applying SEAL, we can achieve significant improvements in in-domain retrieval performance, including document QA tasks from LongBench, and considerable improvements in out-of-domain cases. Additionally, when combined with existing training-free context extension techniques, SEAL extends the context limits of LLMs while maintaining highly reliable outputs, opening new avenues for research in this field.

PTQ4VM: Post-Training Quantization for Visual Mamba

Visual Mamba is an approach that extends the selective space state model, Mamba, to vision tasks. It processes image tokens sequentially in a fixed order, accumulating information to generate outputs. Despite its growing popularity for delivering high-quality outputs at a low computational cost across various tasks, Visual Mamba is highly susceptible to quantization, which makes further performance improvements challenging. Our analysis reveals that the fixed token access order in Visual Mamba introduces unique quantization challenges, which we categorize into three main issues: 1) token-wise variance, 2) channel-wise outliers, and 3) a long tail of activations. To address these challenges, we propose Post-Training Quantization for Visual Mamba (PTQ4VM), which introduces two key strategies: Per-Token Static (PTS) quantization and Joint Learning of Smoothing Scale and Step Size (JLSS). To the our best knowledge, this is the first quantization study on Visual Mamba. PTQ4VM can be applied to various Visual Mamba backbones, converting the pretrained model to a quantized format in under 15 minutes without notable quality degradation. Extensive experiments on large-scale classification and regression tasks demonstrate its effectiveness, achieving up to 1.83x speedup on GPUs with negligible accuracy loss compared to FP16. Our code is available at https://github.com/YoungHyun197/ptq4vm.

QEFT: Quantization for Efficient Fine-Tuning of LLMs

With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all aspects, including inference speed, fine-tuning speed, memory consumption, and, most importantly, model quality. Previous studies have attempted to achieve this by combining quantization with fine-tuning, but they have failed to enhance all four aspects simultaneously. In this study, we propose a new lightweight technique called Quantization for Efficient Fine-Tuning (QEFT). QEFT accelerates both inference and fine-tuning, is supported by robust theoretical foundations, offers high flexibility, and maintains good hardware compatibility. Our extensive experiments demonstrate that QEFT matches the quality and versatility of full-precision parameter-efficient fine-tuning, while using fewer resources. Our code is available at https://github.com/xvyaward/qeft.

HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization

With the rapid increase in model size and the growing importance of various fine-tuning applications, lightweight training has become crucial. Since the backward pass is twice as expensive as the forward pass, optimizing backpropagation is particularly important. However, modifications to this process can lead to suboptimal convergence, so training optimization should minimize perturbations, which is a highly challenging task. In this study, we introduce a novel optimization strategy called Hadamard Low-rank Quantization (HLQ), focusing on reducing the cost of backpropagation in convolutional and linear layers. We first analyze the sensitivity of gradient computation with respect to activation and weight, and judiciously design the HLQ pipeline to apply 4-bit Hadamard quantization to the activation gradient and Hadamard low-rank approximation to the weight gradient. This combination was found to be the best for maximizing benefits, and our extensive experiments demonstrate the outstanding performance of HLQ in both training from scratch and fine-tuning, achieving significant memory savings and acceleration on real GPUs with negligible quality degradation.

Task-Oriented Diffusion Model Compression

As recent advancements in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged. Despite the impressive results achieved by these I2I models, their practical utility is hampered by their large model size and the computational burden of the iterative denoising process. In this paper, we explore the compression potential of these I2I models in a task-oriented manner and introduce a novel method for reducing both model size and the number of timesteps. Through extensive experiments, we observe key insights and use our empirical knowledge to develop practical solutions that aim for near-optimal results with minimal exploration costs. We validate the effectiveness of our method by applying it to InstructPix2Pix for image editing and StableSR for image restoration. Our approach achieves satisfactory output quality with 39.2% and 56.4% reduction in model footprint and 81.4% and 68.7% decrease in latency to InstructPix2Pix and StableSR, respectively.

FRDiff: Feature Reuse for Exquisite Zero-shot Acceleration of Diffusion Models

The substantial computational costs of diffusion models, particularly due to the repeated denoising steps crucial for high-quality image generation, present a major obstacle to their widespread adoption. While several studies have attempted to address this issue by reducing the number of score function evaluations using advanced ODE solvers without fine-tuning, the decreased number of denoising iterations misses the opportunity to update fine details, resulting in noticeable quality degradation. In our work, we introduce an advanced acceleration technique that leverages the temporal redundancy inherent in diffusion models. Reusing feature maps with high temporal similarity opens up a new opportunity to save computation without sacrificing output quality. To realize the practical benefits of this intuition, we conduct an extensive analysis and propose a novel method, FRDiff. FRDiff is designed to harness the advantages of both reduced NFE and feature reuse, achieving a Pareto frontier that balances fidelity and latency trade-offs in various generative tasks.

OWQ: Lessons learned from activation outliers for weight quantization in large language models

Large language models (LLMs) with hundreds of billions of parameters show impressive results across various language tasks using simple prompt tuning and few-shot examples, without the need for task-specific fine-tuning. However, their enormous size requires multiple server-grade GPUs even for inference, creating a significant cost barrier. To address this limitation, we introduce a novel post-training quantization method for weights with minimal quality degradation. While activation outliers are known to be problematic in activation quantization, our theoretical analysis suggests that we can identify factors contributing to weight quantization errors by considering activation outliers. We propose an innovative PTQ scheme called outlier-aware weight quantization (OWQ), which identifies vulnerable weights and allocates high-precision to them. Our extensive experiments demonstrate that the 3.01-bit models produced by OWQ exhibit comparable quality to the 4-bit models generated by OPTQ.

Temporal Dynamic Quantization for Diffusion Models

The diffusion model has gained popularity in vision applications due to its remarkable generative performance and versatility. However, high storage and computation demands, resulting from the model size and iterative generation, hinder its use on mobile devices. Existing quantization techniques struggle to maintain performance even in 8-bit precision due to the diffusion model's unique property of temporal variation in activation. We introduce a novel quantization method that dynamically adjusts the quantization interval based on time step information, significantly improving output quality. Unlike conventional dynamic quantization techniques, our approach has no computational overhead during inference and is compatible with both post-training quantization (PTQ) and quantization-aware training (QAT). Our extensive experiments demonstrate substantial improvements in output quality with the quantized diffusion model across various datasets.

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization

Robust quantization improves the tolerance of networks for various implementations, allowing reliable output in different bit-widths or fragmented low-precision arithmetic. In this work, we perform extensive analyses to identify the sources of quantization error and present three insights to robustify a network against quantization: reduction of error propagation, range clamping for error minimization, and inherited robustness against quantization. Based on these insights, we propose two novel methods called symmetry regularization (SymReg) and saturating nonlinearity (SatNL). Applying the proposed methods during training can enhance the robustness of arbitrary neural networks against quantization on existing post-training quantization (PTQ) and quantization-aware training (QAT) algorithms and enables us to obtain a single weight flexible enough to maintain the output quality under various conditions. We conduct extensive studies on CIFAR and ImageNet datasets and validate the effectiveness of the proposed methods.

NIPQ: Noise Injection Pseudo Quantization for Automated DNN Optimization

The optimization of neural networks in terms of computation cost and memory footprint is crucial for their practical deployment on edge devices. In this work, we propose a novel quantization-aware training (QAT) scheme called noise injection pseudo quantization (NIPQ). NIPQ is implemented based on pseudo quantization noise (PQN) and has several advantages. First, both activation and weight can be quantized based on a unified framework. Second, the hyper-parameters of quantization (e.g., layer-wise bit-width and quantization interval) are automatically tuned. Third, after QAT, the network has robustness against quantization, thereby making it easier to deploy in practice. To validate the superiority of the proposed algorithm, we provide extensive analysis and conduct diverse experiments for various vision applications. Our comprehensive experiments validate the outstanding performance of the proposed algorithm in several aspects.