We investigate how different compression techniques -- such as weight and activation quantization, and weight sparsity -- affect the scaling behavior of large language models (LLMs) during pretraining. Building on previous work showing that weight sparsity acts as a constant multiplier on model size in scaling laws, we demonstrate that this "effective parameter" scaling pattern extends to quantization as well. Specifically, we establish that weight-only quantization achieves strong parameter efficiency multipliers, while full quantization of both weights and activations shows diminishing returns at lower bitwidths. Our results suggest that different compression techniques can be unified under a common scaling law framework, enabling principled comparison and combination of these methods.

The emergence of accurate open large language models (LLMs) has led to a race towards quantization techniques for such models enabling execution on end-user devices. In this paper, we revisit the problem of "extreme" LLM compression--defined as targeting extremely low bit counts, such as 2 to 3 bits per parameter, from the point of view of classic methods in Multi-Codebook Quantization (MCQ). Our work builds on top of Additive Quantization, a classic algorithm from the MCQ family, and adapts it to the quantization of language models. The resulting algorithm advances the state-of-the-art in LLM compression, outperforming all recently-proposed techniques in terms of accuracy at a given compression budget. For instance, when compressing Llama 2 models to 2 bits per parameter, our algorithm quantizes the 7B model to 6.93 perplexity (a 1.29 improvement relative to the best prior work, and 1.81 points from FP16), the 13B model to 5.70 perplexity (a .36 improvement) and the 70B model to 3.94 perplexity (a .22 improvement) on WikiText2. We release our implementation of Additive Quantization for Language Models AQLM as a baseline to facilitate future research in LLM quantization.

This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research. JaxPruner aims to accelerate research on sparse neural networks by providing concise implementations of popular pruning and sparse training algorithms with minimal memory and latency overhead. Algorithms implemented in JaxPruner use a common API and work seamlessly with the popular optimization library Optax, which, in turn, enables easy integration with existing JAX based libraries. We demonstrate this ease of integration by providing examples in four different codebases: Scenic, t5x, Dopamine and FedJAX and provide baseline experiments on popular benchmarks.

Large Language Models (LLMs) from the GPT family have become extremely popular, leading to a race towards reducing their inference costs to allow for efficient local computation. Yet, the vast majority of existing work focuses on weight-only quantization, which can reduce runtime costs in the memory-bound one-token-at-a-time generative setting, but does not address them in compute-bound scenarios, such as batched inference or prompt processing. In this paper, we address the general quantization problem, where both weights and activations should be quantized. We show, for the first time, that the majority of inference computations for large generative models such as LLaMA, OPT, and Falcon can be performed with both weights and activations being cast to 4 bits, in a way that leads to practical speedups, while at the same time maintaining good accuracy. We achieve this via a hybrid quantization strategy called QUIK, which compresses most of the weights and activations to 4-bit, while keeping some outlier weights and activations in higher-precision. The key feature of our scheme is that it is designed with computational efficiency in mind: we provide GPU kernels matching the QUIK format with highly-efficient layer-wise runtimes, which lead to practical end-to-end throughput improvements of up to 3.4x relative to FP16 execution. We provide detailed studies for models from the OPT, LLaMA-2 and Falcon families, as well as a first instance of accurate inference using quantization plus 2:4 sparsity. Large language models (LLMs) from the Generative Pretrained Joint weight-activation quantization methods, which can Transformer (GPT) family (Radford et al., 2019) provide computational improvements, but either focus exclusively are massively popular.

The breakthrough performance of large language models (LLMs) comes with major computational footprints and high deployment costs. In this paper, we progress towards resolving this problem by proposing a novel structured compression approach for LLMs, called ZipLM. ZipLM achieves state-of-the-art accuracy-vs-speedup, while matching a set of desired target runtime speedups in any given inference environment. Specifically, given a model, a dataset, an inference environment, as well as a set of speedup targets, ZipLM iteratively identifies and removes components with the worst loss-runtime trade-off. Unlike prior methods that specialize in either the post-training/one-shot or the gradual compression setting, and only for specific families of models such as BERT (encoder) or GPT (decoder), ZipLM produces state-of-the-art compressed models across all these settings. Furthermore, ZipLM achieves superior results for a fraction of the computational cost relative to prior distillation and pruning techniques, making it a cost-effective approach for generating an entire family of smaller, faster, and highly accurate models, guaranteed to meet the desired inference specifications. In particular, ZipLM outperforms all prior BERT-base distillation and pruning techniques, such as CoFi, MiniLM, and TinyBERT. Moreover, it matches the performance of the heavily optimized MobileBERT model, obtained via extensive architecture search, by simply pruning the baseline BERT-large model. When compressing GPT2, ZipLM outperforms DistilGPT2 while being 60% smaller and 30% faster. Our code is available at: https://github.com/IST-DASLab/ZipLM.

Mixture-of-Experts (MoE) architectures offer a general solution to the high inference costs of large language models (LLMs) via sparse routing, bringing faster and more accurate models, at the cost of massive parameter counts. For example, the SwitchTransformer-c2048 model has 1.6 trillion parameters, requiring 3.2TB of accelerator memory to run efficiently, which makes practical deployment challenging and expensive. In this paper, we present a solution to this memory problem, in form of a new compression and execution framework called QMoE. Specifically, QMoE consists of a scalable algorithm which accurately compresses trillion-parameter MoEs to less than 1 bit per parameter, in a custom format co-designed with bespoke GPU decoding kernels to facilitate efficient end-to-end compressed inference, with minor runtime overheads relative to uncompressed execution. Concretely, QMoE can compress the 1.6 trillion parameter SwitchTransformer-c2048 model to less than 160GB (20x compression, 0.8 bits per parameter) at only minor accuracy loss, in less than a day on a single GPU. This enables, for the first time, the execution of a trillion-parameter model on affordable commodity hardware, like a single server with 4x NVIDIA A6000 or 8x NVIDIA 3090 GPUs, at less than 5% runtime overhead relative to ideal uncompressed inference. The source code and compressed models are available at github.com/IST-DASLab/qmoe.

We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard loss-based fine-tuning may fail to recover accuracy, especially at high sparsities. To address this, we perform a detailed study of distillation-type losses, determining an L2-based distillation approach we term SquareHead which enables accurate recovery even at higher sparsities, across all model types. On the practical efficiency side, we show that sparse LLMs can be executed with speedups by taking advantage of sparsity, for both CPU and GPU runtimes. While the standard approach is to leverage sparsity for computational reduction, we observe that in the case of memory-bound LLMs sparsity can also be leveraged for reducing memory bandwidth. We exhibit end-to-end results showing speedups due to sparsity, while recovering accuracy, on T5 (language translation), Whisper (speech translation), and open GPT-type (MPT for text generation). For MPT text generation, we show for the first time that sparse fine-tuning can reach 75% sparsity without accuracy drops, provide notable end-to-end speedups for both CPU and GPU inference, and highlight that sparsity is also compatible with quantization approaches. Models and software for reproducing our results are provided in Section 6.

We explore the impact of parameter sparsity on the scaling behavior of Transformers trained on massive datasets (i.e., "foundation models"), in both vision and language domains. In this setting, we identify the first scaling law describing the relationship between weight sparsity, number of non-zero parameters, and amount of training data, which we validate empirically across model and data scales; on ViT/JFT-4B and T5/C4. These results allow us to characterize the "optimal sparsity", the sparsity level which yields the best performance for a given effective model size and training budget. For a fixed number of non-zero parameters, we identify that the optimal sparsity increases with the amount of data used for training. We also extend our study to different sparsity structures (such as the hardware-friendly n:m pattern) and strategies (such as starting from a pretrained dense model). Our findings shed light on the power and limitations of weight sparsity across various parameter and computational settings, offering both theoretical understanding and practical implications for leveraging sparsity towards computational efficiency improvements.

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the community. Yet, much less is known about the interaction between sparsity and the standard stochastic optimization techniques used for training sparse networks, and most existing work uses standard dense schedules and hyperparameters for training sparse networks. In this work, we examine the impact of high sparsity on model training using the standard computer vision and natural language processing sparsity benchmarks. We begin by showing that using standard dense training recipes for sparse training is suboptimal, and results in under-training. We provide new approaches for mitigating this issue for both sparse pre-training of vision models (e.g. ResNet50/ImageNet) and sparse fine-tuning of language models (e.g. BERT/GLUE), achieving state-of-the-art results in both settings in the high-sparsity regime, and providing detailed analyses for the difficulty of sparse training in both scenarios. Our work sets a new threshold in terms of the accuracies that can be achieved under high sparsity, and should inspire further research into improving sparse model training, to reach higher accuracies under high sparsity, but also to do so efficiently.

Our approach is informed by the target architecture Focusing specifically on generative inference, where the and a performance model, including both hardware size of the weights is the main bottleneck, the currently bestperforming characteristics and method-specific accuracy method is GPTQ (Frantar et al., 2022), which constraints. Results on CPU-based inference achieves near-lossless quantization to 4-bit weights, and can for LLaMA models show that our approach even accurately support 2 and 3-bit weights by reducing the can lead to high performance and high accuracy, granularity to smaller weight groups, e.g., by jointly quantizing comparing favorably to the best existing blocks of 64 weights using a shared scale and zero-point.