Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy

• URL: http://arxiv.org/abs/2404.06954v1
• Date: Wed, 10 Apr 2024 12:12:07 GMT
• Title: Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy
• Authors: Yijin Liu, Fandong Meng, Jie Zhou,
• Abstract summary: Dynamic computation methods have shown notable acceleration for Large Language Models (LLMs) by skipping several layers of computations. We propose a Unified Layer Skipping strategy, which selects the number of layers to skip computation based solely on the target speedup ratio. Experimental results on two common tasks, i.e., machine translation and text summarization, indicate that given a target speedup ratio, the Unified Layer Skipping strategy significantly enhances both the inference performance and the actual model throughput.
• Score: 67.45518210171024
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, dynamic computation methods have shown notable acceleration for Large Language Models (LLMs) by skipping several layers of computations through elaborate heuristics or additional predictors. However, in the decoding process of existing approaches, different samples are assigned different computational budgets, which cannot guarantee a stable and precise acceleration effect. Furthermore, existing approaches generally skip multiple contiguous layers at the bottom or top of the layers, leading to a drastic change in the model's layer-wise representations, and thus a consequent performance degeneration. Therefore, we propose a Unified Layer Skipping strategy, which selects the number of layers to skip computation based solely on the target speedup ratio, and then skips the corresponding number of intermediate layer computations in a balanced manner. Since the Unified Layer Skipping strategy is independent of input samples, it naturally supports popular acceleration techniques such as batch decoding and KV caching, thus demonstrating more practicality for real-world applications. Experimental results on two common tasks, i.e., machine translation and text summarization, indicate that given a target speedup ratio, the Unified Layer Skipping strategy significantly enhances both the inference performance and the actual model throughput over existing dynamic approaches.

Related papers

• A-SDM: Accelerating Stable Diffusion through Model Assembly and Feature Inheritance Strategies [51.7643024367548]
  Stable Diffusion Model is a prevalent and effective model for text-to-image (T2I) and image-to-image (I2I) generation. This study focuses on reducing redundant computation in SDM and optimizing the model through both tuning and tuning-free methods.
  arXiv  Detail & Related papers  (2024-05-31T21:47:05Z)
• You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model [37.24203191658052]
  Large-scale Transformer models bring significant improvements for various downstream vision language tasks with a unified architecture. Performance improvements come with increasing model size, resulting in slow inference speed and increased cost for severing. We propose a novel early exiting strategy for unified visual language models, which allows dynamically skip the layers in encoder and decoder simultaneously.
  arXiv  Detail & Related papers  (2022-11-21T02:32:25Z)
• Layer-Wise Partitioning and Merging for Efficient and Scalable Deep Learning [16.38731019298993]
  We have proposed a novel layer-wise partitioning and merging, forward and backward pass parallel framework to provide better training performance. The experimental evaluation on real use cases shows that the proposed method outperforms the state-of-the-art approaches in terms of training speed.
  arXiv  Detail & Related papers  (2022-07-22T11:47:34Z)
• Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization [61.26619639722804]
  We propose a conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. The proposed method, equipped with an average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques.
  arXiv  Detail & Related papers  (2022-02-26T19:10:48Z)
• Layer-wise Model Pruning based on Mutual Information [27.583869809219244]
  The proposed strategy avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup. The proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level.
  arXiv  Detail & Related papers  (2021-08-28T07:51:47Z)
• Layer Pruning on Demand with Intermediate CTC [50.509073206630994]
  We present a training and pruning method for ASR based on the connectionist temporal classification (CTC) We show that a Transformer-CTC model can be pruned in various depth on demand, improving real-time factor from 0.005 to 0.002 on GPU.
  arXiv  Detail & Related papers  (2021-06-17T02:40:18Z)
• Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency [31.572652956170252]
  Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. We experimentally achieve 7.8X parameter reduction, 41.9% training speedup and 37.7% inference speedup while maintaining comparable performance with conventional BERT-like self-supervised methods.
  arXiv  Detail & Related papers  (2021-04-08T08:21:59Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)
• BERT Loses Patience: Fast and Robust Inference with Early Exit [91.26199404912019]
  We propose Patience-based Early Exit as a plug-and-play technique to improve the efficiency and robustness of a pretrained language model. Our approach improves inference efficiency as it allows the model to make a prediction with fewer layers.
  arXiv  Detail & Related papers  (2020-06-07T13:38:32Z)
• A Hybrid-Order Distributed SGD Method for Non-Convex Optimization to Balance Communication Overhead, Computational Complexity, and Convergence Rate [28.167294398293297]
  We propose a method of distributed gradient descent (SGD) with low communication load and computational complexity, and still fast. To reduce the computational complexity in each iteration, the worker nodes approximate the directional derivatives with zeroth-order gradient estimation.
  arXiv  Detail & Related papers  (2020-03-27T14:02:15Z)

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.