Compressing Large Language Models with Automated Sub-Network Search

• URL: http://arxiv.org/abs/2410.06479v3
• Date: Wed, 05 Feb 2025 12:50:46 GMT
• Title: Compressing Large Language Models with Automated Sub-Network Search
• Authors: Rhea Sanjay Sukthanker, Benedikt Staffler, Frank Hutter, Aaron Klein,
• Abstract summary: We consider model compression for Large Language Models to reduce model size while improving downstream task performance.<n>We phrase this as a neural architecture search problem that automatically prunes structural components.<n>Our method achieves upto 9.85% improvement on average on 11 diverse downstream tasks, while achieving up to 22% improvement of on-device latency.
• Score: 41.452512557226335
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become increasingly prohibitive, accumulating significantly over their life cycle. In this paper we consider model compression for LLMs to reduce model size while improving downstream task performance. We phrase this as a neural architecture search problem that automatically prunes structural components, such as attention heads, neurons, and layers by searching for the Pareto-optimal set of sub-networks balancing between performance and on-device latency. Compared to state-of-the-art structural pruning approaches and fine-tuned smaller sub-networks extracted from the pre-trained model, our method achieves upto 9.85% improvement on average on 11 diverse downstream tasks, while achieving up to 22% improvement of on-device latency.

Related papers

• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Low-Rank Adapters Meet Neural Architecture Search for LLM Compression [1.8434042562191815]
  The rapid expansion of Large Language Models (LLMs) has posed significant challenges regarding the computational resources required for fine-tuning and deployment. Recent advancements in low-rank adapters have demonstrated their efficacy in parameter-efficient fine-tuning (PEFT) of these models. This paper comprehensively discusses innovative approaches that synergize low-rank representations with Neural Architecture Search (NAS) techniques.
  arXiv  Detail & Related papers  (2025-01-23T02:14:08Z)
• FASP: Fast and Accurate Structured Pruning of Large Language Models [24.185245582500876]
  We introduce FASP (Fast and Accurate Structured Pruning), a novel structured pruning framework for large language models (LLMs) FASP employs a distinctive pruning structure that interlinks sequential layers, allowing for the removal of columns in one layer while simultaneously eliminating corresponding rows in the preceding layer without incurring additional performance loss. We evaluate FASP on the OPT and LLaMA model families, demonstrating superior performance in terms of perplexity and accuracy on downstream tasks compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-01-16T09:38:39Z)
• LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment [36.958867918858296]
  Large language models (LLMs) have demonstrated their strong intelligence ability, but high demand for computation and storage hinders their practical application. We present the Large Language Model Compression Benchmark (LLMCBench), a rigorously designed benchmark with an in-depth analysis for LLM compression algorithms.
  arXiv  Detail & Related papers  (2024-10-28T14:45:01Z)
• SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization [8.121663525764294]
  Large language models (LLMs) play a crucial role in our daily lives due to their ability to understand and generate human-like text. In this report, we design a collaborative inference architecture between a server and its clients to alleviate the throughput limit. We show in the experiments that we are able to efficiently distribute the workload allowing for roughly 1/3 reduction in the server workload.
  arXiv  Detail & Related papers  (2024-10-14T17:38:41Z)
• Search for Efficient Large Language Models [52.98684997131108]
  Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Weight pruning, quantization, and distillation have been embraced to compress LLMs, targeting memory reduction and inference acceleration. Most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures.
  arXiv  Detail & Related papers  (2024-09-25T21:32:12Z)
• Contemporary Model Compression on Large Language Models Inference [7.307436175842646]
  Large Language Models (LLMs) have revolutionized natural language processing by achieving state-of-the-art results across a variety of tasks. The computational demands of LLM inference, including high memory consumption and slow processing speeds, pose significant challenges for real-world applications. This survey explores techniques in model compression that address these challenges by reducing the size and computational requirements of LLMs.
  arXiv  Detail & Related papers  (2024-09-03T15:35:01Z)
• Performance Law of Large Language Models [58.32539851241063]
  Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources. Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources without extensive experiments.
  arXiv  Detail & Related papers  (2024-08-19T11:09:12Z)
• LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models [3.4070166891274263]
  Large language models (LLMs) solve natural language processing, complex reasoning, sentiment analysis and other tasks. These abilities come with very high memory and computational costs which precludes the use of LLMs on most hardware platforms. We propose an effective method of finding Pareto-optimal network architectures based on LLaMA2-7B using one-shot NAS. We show that, for certain standard benchmark tasks, the pre-trained LLaMA2-7B network is unnecessarily large and complex.
  arXiv  Detail & Related papers  (2024-05-28T17:20:44Z)
• Structural Pruning of Pre-trained Language Models via Neural Architecture Search [7.833790713816726]
  Pre-trained language models (PLM) mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. This paper explores neural architecture search (NAS) for structural pruning to find sub-parts of the fine-tuned network that optimally trade-off efficiency.
  arXiv  Detail & Related papers  (2024-05-03T17:34:57Z)
• Lightweight Diffusion Models with Distillation-Based Block Neural Architecture Search [55.41583104734349]
  We propose to automatically remove structural redundancy in diffusion models with our proposed Diffusion Distillation-based Block-wise Neural Architecture Search (NAS) Given a larger pretrained teacher, we leverage DiffNAS to search for the smallest architecture which can achieve on-par or even better performance than the teacher. Different from previous block-wise NAS methods, DiffNAS contains a block-wise local search strategy and a retraining strategy with a joint dynamic loss.
  arXiv  Detail & Related papers  (2023-11-08T12:56:59Z)
• LLM Performance Predictors are good initializers for Architecture Search [28.251129134057035]
  We construct Performance Predictors (PP) that estimate the performance of specific deep neural network architectures on downstream tasks. In machine translation (MT) tasks, GPT-4 with our PP prompts (LLM-PP) achieves a SoTA mean absolute error and a slight degradation in rank correlation coefficient compared to baseline predictors. For Neural Architecture Search (NAS), we introduce a Hybrid-Search algorithm (HS-NAS) employing LLM-Distill-PP for the initial search stages and reverting to the baseline predictor later.
  arXiv  Detail & Related papers  (2023-10-25T15:34:30Z)
• Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity [0.0]
  Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference latency. We propose a solution to induce semi-structured activation sparsity exploitable through minor runtime modifications. Our approach yields a speed improvement of $1.25 times$ with a minimal accuracy drop of $1.1%$ for the ResNet18 model on the ImageNet dataset.
  arXiv  Detail & Related papers  (2023-09-12T22:28:53Z)
• In-context Autoencoder for Context Compression in a Large Language Model [70.7621953091318]
  We propose the In-context Autoencoder (ICAE) to compress a long context into short compact memory slots. ICAE is first pretrained using both autoencoding and language modeling objectives on massive text data.
  arXiv  Detail & Related papers  (2023-07-13T17:59:21Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks [76.8112416450677]
  Siamese networks are one of the most trending methods to achieve self-supervised visual representation learning (SSL) NASiam is a novel approach that uses for the first time differentiable NAS to improve the multilayer perceptron projector and predictor (encoder/predictor pair) NASiam reaches competitive performance in both small-scale (i.e., CIFAR-10/CIFAR-100) and large-scale (i.e., ImageNet) image classification datasets while costing only a few GPU hours.
  arXiv  Detail & Related papers  (2023-01-31T19:48:37Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search [55.164053971213576]
  convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure. Existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space.
  arXiv  Detail & Related papers  (2020-11-04T07:43:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.