Extremely large-scale massive multiple-input multiple-output (XL-MIMO) systems introduce the much higher channel dimensionality and incur the additional near-field propagation effect, aggravating the computation load and the difficulty to acquire the prior knowledge for channel estimation. In this article, an XL-MIMO channel network (XLCNet) is developed to estimate the high-dimensional channel, which is a universal solution for both the near-field users and far-field users with different channel statistics. Furthermore, a compressed XLCNet (C-XLCNet) is designed via weight pruning and quantization to accelerate the model inference as well as to facilitate the model storage and transmission. Simulation results show the performance superiority and universality of XLCNet. Compared to XLCNet, C-XLCNet incurs the limited performance loss while reducing the computational complexity and model size by about $10 \times$ and $36 \times$, respectively.
Sign language discourse is an essential mode of daily communication for the deaf and hard-of-hearing people. However, research on Bangla Sign Language (BdSL) faces notable limitations, primarily due to the lack of datasets. Recognizing wordlevel signs in BdSL (WL-BdSL) presents a multitude of challenges, including the need for well-annotated datasets, capturing the dynamic nature of sign gestures from facial or hand landmarks, developing suitable machine learning or deep learning-based models with substantial video samples, and so on. In this paper, we address these challenges by creating a comprehensive BdSL word-level dataset named BdSLW60 in an unconstrained and natural setting, allowing positional and temporal variations and allowing sign users to change hand dominance freely. The dataset encompasses 60 Bangla sign words, with a significant scale of 9307 video trials provided by 18 signers under the supervision of a sign language professional. The dataset was rigorously annotated and cross-checked by 60 annotators. We also introduced a unique approach of a relative quantization-based key frame encoding technique for landmark based sign gesture recognition. We report the benchmarking of our BdSLW60 dataset using the Support Vector Machine (SVM) with testing accuracy up to 67.6% and an attention-based bi-LSTM with testing accuracy up to 75.1%. The dataset is available at https://www.kaggle.com/datasets/hasaniut/bdslw60 and the code base is accessible from https://github.com/hasanssl/BdSLW60_Code.
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current era of general-purpose large language models (LLMs). Moreover, the recent influx of decoding strategies has further complicated this landscape. This paper provides a comprehensive and multifaceted analysis of various decoding methods within the context of LLMs, evaluating their performance, robustness to hyperparameter changes, and decoding speeds across a wide range of tasks, models, and deployment environments. Our findings reveal that decoding method performance is notably task-dependent and influenced by factors such as alignment, model size, and quantization. Intriguingly, sensitivity analysis exposes that certain methods achieve superior performance at the cost of extensive hyperparameter tuning, highlighting the trade-off between attaining optimal results and the practicality of implementation in varying contexts.
Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity. We observe that when the training set is sufficiently complex, the model encodes sentences that have a common syntactic structure using a systematic attention pattern. Inspired by this observation, we propose SQ-Transformer (Structurally Quantized) that explicitly encourages systematicity in the embeddings and attention layers, even with a training set of low complexity. At the embedding level, we introduce Structure-oriented Vector Quantization (SoVQ) to cluster word embeddings into several classes of structurally equivalent entities. At the attention level, we devise the Systematic Attention Layer (SAL) and an alternative, Systematically Regularized Layer (SRL) that operate on the quantized word embeddings so that sentences of the same structure are encoded with invariant or similar attention patterns. Empirically, we show that SQ-Transformer achieves stronger compositional generalization than the vanilla Transformer on multiple low-complexity semantic parsing and machine translation datasets. In our analysis, we show that SoVQ indeed learns a syntactically clustered embedding space and SAL/SRL induces generalizable attention patterns, which lead to improved systematicity.
Memory-efficient finetuning of large language models (LLMs) has recently attracted huge attention with the increasing size of LLMs, primarily due to the constraints posed by GPU memory limitations and the effectiveness of these methods compared to full finetuning. Despite the advancements, current strategies for memory-efficient finetuning, such as QLoRA, exhibit inconsistent performance across diverse bit-width quantizations and multifaceted tasks. This inconsistency largely stems from the detrimental impact of the quantization process on preserved knowledge, leading to catastrophic forgetting and undermining the utilization of pretrained models for finetuning purposes. In this work, we introduce a novel quantization framework, ApiQ, designed to restore the lost information from quantization by concurrently initializing the LoRA components and quantizing the weights of LLMs. This approach ensures the maintenance of the original LLM's activation precision while mitigating the error propagation from shallower into deeper layers. Through comprehensive evaluations conducted on a spectrum of language tasks with various LLMs, ApiQ demonstrably minimizes activation error during quantization. Consequently, it consistently achieves superior finetuning results across various bit-widths.
The LoRA-finetuning quantization of LLMs has been extensively studied to obtain accurate yet compact LLMs for deployment on resource-constrained hardware. However, existing methods cause the quantized LLM to severely degrade and even fail to benefit from the finetuning of LoRA. This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention. The proposed IR-QLoRA mainly relies on two technologies derived from the perspective of unified information: (1) statistics-based Information Calibration Quantization allows the quantized parameters of LLM to retain original information accurately; (2) finetuning-based Information Elastic Connection makes LoRA utilizes elastic representation transformation with diverse information. Comprehensive experiments show that IR-QLoRA can significantly improve accuracy across LLaMA and LLaMA2 families under 2-4 bit-widths, e.g., 4- bit LLaMA-7B achieves 1.4% improvement on MMLU compared with the state-of-the-art methods. The significant performance gain requires only a tiny 0.31% additional time consumption, revealing the satisfactory efficiency of our IR-QLoRA. We highlight that IR-QLoRA enjoys excellent versatility, compatible with various frameworks (e.g., NormalFloat and Integer quantization) and brings general accuracy gains. The code is available at https://github.com/htqin/ir-qlora.
Domain generalization (DG) is an important problem that learns a model which generalizes to unseen test domains leveraging one or more source domains, under the assumption of shared label spaces. However, most DG methods assume access to abundant source data in the target label space, a requirement that proves overly stringent for numerous real-world applications, where acquiring the same label space as the target task is prohibitively expensive. For this setting, we tackle the multimodal version of the unsupervised domain generalization (MUDG) problem, which uses a large task-agnostic unlabeled source dataset during finetuning. Our framework does not explicitly assume any relationship between the source dataset and target task. Instead, it relies only on the premise that the source dataset can be accurately and efficiently searched in a joint vision-language space. We make three contributions in the MUDG setting. Firstly, we show theoretically that cross-modal approximate nearest neighbor search suffers from low recall due to the large distance between text queries and the image centroids used for coarse quantization. Accordingly, we propose paired k-means, a simple clustering algorithm that improves nearest neighbor recall by storing centroids in query space instead of image space. Secondly, we propose an adaptive text augmentation scheme for target labels designed to improve zero-shot accuracy and diversify retrieved image data. Lastly, we present two simple but effective components to further improve downstream target accuracy. We compare against state-of-the-art name-only transfer, source-free DG and zero-shot (ZS) methods on their respective benchmarks and show consistent improvement in accuracy on 20 diverse datasets. Code is available: https://github.com/Chris210634/mudg
Post-training quantization (PTQ) reduces the memory footprint of LLMs by quantizing their weights to low-precision. In this work, we introduce QuIP#, a weight-only PTQ method that achieves state-of-the-art results in extreme compression regimes ($\le$ 4 bits per weight) using three novel techniques. First, QuIP# improves QuIP's (Chee et al., 2023) incoherence processing by using the randomized Hadamard transform, which is faster and has better theoretical properties. Second, QuIP# uses vector quantization to take advantage of the ball-shaped sub-Gaussian distribution that incoherent weights possess: specifically, we introduce a set of hardware-efficient codebooks based on the highly symmetric $E_8$ lattice, which achieves the optimal 8-dimension unit ball packing. Third, QuIP# uses fine-tuning to improve fidelity to the original model. Our experiments show that QuIP# outperforms existing PTQ methods, enables new behaviors in PTQ scaling, and supports fast inference. Our code can be found at https://github.com/Cornell-RelaxML/quip-sharp.
Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources. As a powerful compression technology, binarization can extremely reduce model weights to a mere 1 bit, lowering the expensive computation and memory requirements. However, existing quantization techniques fall short of maintaining LLM performance under ultra-low bit-widths. In response to this challenge, we present BiLLM, a groundbreaking 1-bit post-training quantization scheme tailored for pretrained LLMs. Based on the weight distribution of LLMs, BiLLM first identifies and structurally selects salient weights, and minimizes the compression loss through an effective binary residual approximation strategy. Moreover, considering the bell-shaped distribution of the non-salient weights, we propose an optimal splitting search to group and binarize them accurately. BiLLM achieving for the first time high-accuracy inference (e.g. 8.41 perplexity on LLaMA2-70B) with only 1.08-bit weights across various LLMs families and evaluation metrics, outperforms SOTA quantization methods of LLM by significant margins. Moreover, BiLLM enables the binarization process of the LLM with 7 billion weights within 0.5 hours on a single GPU, demonstrating satisfactory time efficiency. Our code is available at https://github.com/Aaronhuang-778/BiLLM.
The practical deployment of diffusion models still suffers from the high memory and time overhead. While quantization paves a way for compression and acceleration, existing methods unfortunately fail when the models are quantized to low-bits. In this paper, we empirically 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 available \href{https://github.com/hatchetProject/QuEST}{here}.
Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale with the input size and choice of algorithm. Moreover, the models proposed here are designed to work on the type of data and under the foreseen conditions at the CERN LHC during its high-luminosity phase. Through quantization-aware training and efficient synthetization for a specific field programmable gate array, we show that $O(100)$ ns inference of complex architectures such as Deep Sets and Interaction Networks is feasible at a relatively low computational resource cost.
Efficiently serving large language models (LLMs) requires batching of many requests to reduce the cost per request. Yet, with larger batch sizes and longer context lengths, the key-value (KV) cache, which stores attention keys and values to avoid re-computations, significantly increases memory demands and becomes the new bottleneck in speed and memory usage. Additionally, the loading of the KV cache causes the computational core to be idle, which limits the inference speed. A straightforward and effective solution to reduce KV cache size is quantization, which decreases the total bytes taken by KV cache. However, there is a lack of in-depth studies that explore the element distribution of KV cache to understand the hardness and limitation of KV cache quantization. To fill the gap, we conducted a comprehensive study on the element distribution in KV cache of popular LLMs. Our findings indicate that the key cache should be quantized per-channel, i.e., group elements along the channel dimension and quantize them together. In contrast, the value cache should be quantized per-token. From this analysis, we developed a tuning-free 2bit KV cache quantization algorithm named KIVI. With hardware-friendly implementation, KIVI can enable Llama, Falcon, and Mistral models to maintain almost the same quality while using $\mathbf{2.6\times}$ less peak memory (including model weight). This reduction in memory usage enables up to $\mathbf{4\times}$ larger batch size, bringing $\mathbf{2.35\times \sim 3.47\times}$ throughput on real LLM inference workload. The source code is available at https://github.com/jy-yuan/KIVI.
Real-world analog systems intrinsically suffer from noise that can impede model convergence and accuracy on a variety of deep learning models. We demonstrate that differentiable activations like GELU and SiLU enable robust propagation of gradients which help to mitigate analog quantization error that is ubiquitous to all analog systems. We perform analysis and training of convolutional, linear, and transformer networks in the presence of quantized noise. Here, we are able to demonstrate that continuously differentiable activation functions are significantly more noise resilient over conventional rectified activations. As in the case of ReLU, the error in gradients are 100x higher than those in GELU near zero. Our findings provide guidance for selecting appropriate activations to realize performant and reliable hardware implementations across several machine learning domains such as computer vision, signal processing, and beyond. Code available at: \href{https://github.com/Vivswan/GeLUReLUInterpolation}{https://github.com/Vivswan/GeLUReLUInterpolation}.}
Post-training quantization of Large Language Models (LLMs) is challenging. In this work, we introduce Low-rank Quantization Error Reduction (LQER), which combines quantization and low-rank approximation to recover the model capability. LQER leverages an activation-induced scale matrix to drive the singular value distribution of quantization error towards a desirable distribution, which enables nearly-lossless W4A8 quantization on various LLMs and downstream tasks without the need for knowledge distillation, grid search, or gradient-base iterative optimization. Unlike existing methods, the computation pattern of LQER eliminates the need for specialized Scatter and Gather processes to collect high-precision weights from irregular memory locations. Our W4A8 LLMs achieve near-lossless performance on six popular downstream tasks, while using 1.36$\times$ fewer hardware resources than the leading state-of-the-art method. We open-source our framework at https://github.com/ChengZhang-98/lqer
Large Language Models (LLMs) have seen significant use in domains such as natural language processing and computer vision. Going beyond text, image and graphics, LLMs present a significant potential for analysis of time series data, benefiting domains such as climate, IoT, healthcare, traffic, audio and finance. This survey paper provides an in-depth exploration and a detailed taxonomy of the various methodologies employed to harness the power of LLMs for time series analysis. We address the inherent challenge of bridging the gap between LLMs' original text data training and the numerical nature of time series data, and explore strategies for transferring and distilling knowledge from LLMs to numerical time series analysis. We detail various methodologies, including (1) direct prompting of LLMs, (2) time series quantization, (3) aligning techniques, (4) utilization of the vision modality as a bridging mechanism, and (5) the combination of LLMs with tools. Additionally, this survey offers a comprehensive overview of the existing multimodal time series and text datasets and delves into the challenges and future opportunities of this emerging field. We maintain an up-to-date Github repository which includes all the papers and datasets discussed in the survey.
LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in sub-4-bit precision. Our work, KVQuant, facilitates low precision KV cache quantization by incorporating several novel methods: (i) Per-Channel Key Quantization, where we adjust the dimension along which we quantize the Key activations to better match the distribution; (ii) Pre-RoPE Key Quantization, where we quantize Key activations before the rotary positional embedding to mitigate its impact on quantization; (iii) Non-Uniform KV Cache Quantization, where we derive per-layer sensitivity-weighted non-uniform datatypes that better represent the distributions; and (iv) Per-Vector Dense-and-Sparse Quantization, where we isolate outliers separately for each vector to minimize skews in quantization ranges. By applying our method to the LLaMA, Llama-2, Llama-3, and Mistral models, we achieve < 0.1 perplexity degradation with 3-bit quantization on both Wikitext-2 and C4, outperforming existing approaches. Our method enables serving LLaMA-7B with a context length of up to 1 million on a single A100-80GB GPU and up to 10 million on an 8-GPU system. We develop custom CUDA kernels for KVQuant, showing that we can achieve up to ~1.7x speedups, compared to baseline fp16 matrix-vector multiplications, for the LLaMA-7B model.
Weight quantization is an effective technique to compress deep neural networks for their deployment on edge devices with limited resources. Traditional loss-aware quantization methods commonly use the quantized gradient to replace the full-precision gradient. However, we discover that the gradient error will lead to an unexpected zig-zagging-like issue in the gradient descent learning procedures, where the gradient directions rapidly oscillate or zig-zag, and such issue seriously slows down the model convergence. Accordingly, this paper proposes a one-step forward and backtrack way for loss-aware quantization to get more accurate and stable gradient direction to defy this issue. During the gradient descent learning, a one-step forward search is designed to find the trial gradient of the next-step, which is adopted to adjust the gradient of current step towards the direction of fast convergence. After that, we backtrack the current step to update the full-precision and quantized weights through the current-step gradient and the trial gradient. A series of theoretical analysis and experiments on benchmark deep models have demonstrated the effectiveness and competitiveness of the proposed method, and our method especially outperforms others on the convergence performance.
The remote wireless control of industrial systems is one of the major use cases for 5G and beyond systems: in these cases, the massive amounts of sensory information that need to be shared over the wireless medium may overload even high-capacity connections. Consequently, solving the effective communication problem by optimizing the transmission strategy to discard irrelevant information can provide a significant advantage, but is often a very complex task. In this work, we consider a prototypal system in which an observer must communicate its sensory data to a robot controlling a task (e.g., a mobile robot in a factory). We then model it as a remote Partially Observable Markov Decision Process (POMDP), considering the effect of adopting semantic and effective communication-oriented solutions on the overall system performance. We split the communication problem by considering an ensemble Vector Quantized Variational Autoencoder (VQ-VAE) encoding, and train a Deep Reinforcement Learning (DRL) agent to dynamically adapt the quantization level, considering both the current state of the environment and the memory of past messages. We tested the proposed approach on the well-known CartPole reference control problem, obtaining a significant performance increase over traditional approaches.
Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning methods have proven promising in terms of performance but their memory requirements increase proportionally to the size of the LLMs. In this work, we scale sparse fine-tuning to state-of-the-art LLMs like LLaMA 2 7B and 13B. We propose SpIEL, a novel sparse fine-tuning method which, for a desired density level, maintains an array of parameter indices and the deltas of these parameters relative to their pretrained values. It iterates over: (a) updating the active deltas, (b) pruning indices (based on the change of magnitude of their deltas) and (c) regrowth of indices. For regrowth, we explore two criteria based on either the accumulated gradients of a few candidate parameters or their approximate momenta estimated using the efficient SM3 optimizer. We experiment with instruction-tuning of LLMs on standard dataset mixtures, finding that SpIEL is often superior to popular parameter-efficient fine-tuning methods like LoRA (low-rank adaptation) in terms of performance and comparable in terms of run time. We additionally show that SpIEL is compatible with both quantization and efficient optimizers, to facilitate scaling to ever-larger model sizes. We release the code for SpIEL at https://github.com/AlanAnsell/peft and for the instruction-tuning experiments at https://github.com/ducdauge/sft-llm.
Due to highly constrained computing power and memory, deploying 3D lidar-based detectors on edge devices equipped in autonomous vehicles and robots poses a crucial challenge. Being a convenient and straightforward model compression approach, Post-Training Quantization (PTQ) has been widely adopted in 2D vision tasks. However, applying it directly to 3D lidar-based tasks inevitably leads to performance degradation. As a remedy, we propose an effective PTQ method called LiDAR-PTQ, which is particularly curated for 3D lidar detection (both SPConv-based and SPConv-free). Our LiDAR-PTQ features three main components, \textbf{(1)} a sparsity-based calibration method to determine the initialization of quantization parameters, \textbf{(2)} a Task-guided Global Positive Loss (TGPL) to reduce the disparity between the final predictions before and after quantization, \textbf{(3)} an adaptive rounding-to-nearest operation to minimize the layerwise reconstruction error. Extensive experiments demonstrate that our LiDAR-PTQ can achieve state-of-the-art quantization performance when applied to CenterPoint (both Pillar-based and Voxel-based). To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying $3\times$ inference speedup. Moreover, our LiDAR-PTQ is cost-effective being $30\times$ faster than the quantization-aware training method. Code will be released at \url{https://github.com/StiphyJay/LiDAR-PTQ}.