NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks

• URL: http://arxiv.org/abs/2410.20650v1
• Date: Mon, 28 Oct 2024 01:12:20 GMT
• Title: NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
• Authors: Yongchang Hao, Yanshuai Cao, Lili Mou,
• Abstract summary: NeuZip is a new weight compression scheme based on the entropy of floating-point numbers in neural networks. We significantly reduce the memory footprint of training a Llama-3 8B model from 31GB to less than 16GB. In inference, our method can reduce memory usage by more than half while maintaining near-lossless performance.
• Score: 30.224822087562163
• License:
• Abstract: The performance of neural networks improves when more parameters are used. However, the model sizes are constrained by the available on-device memory during training and inference. Although applying techniques like quantization can alleviate the constraint, they suffer from performance degradation. In this work, we introduce NeuZip, a new weight compression scheme based on the entropy of floating-point numbers in neural networks. With NeuZip, we are able to achieve memory-efficient training and inference without sacrificing performance. Notably, we significantly reduce the memory footprint of training a Llama-3 8B model from 31GB to less than 16GB, while keeping the training dynamics fully unchanged. In inference, our method can reduce memory usage by more than half while maintaining near-lossless performance. Our code is publicly available.

Related papers

• CompAct: Compressed Activations for Memory-Efficient LLM Training [7.837209773889032]
  CompAct is a technique that reduces peak memory utilization on GPU by 25-30% for pretraining and 50% for fine-tuning of LLMs. By storing low-rank, compressed activations to be used in the backward pass we greatly reduce the required memory. We expect CompAct's savings to scale even higher for larger models.
  arXiv  Detail & Related papers  (2024-10-20T10:24:38Z)
• OLLA: Decreasing the Memory Usage of Neural Networks by Optimizing the Lifetime and Location of Arrays [6.418232942455968]
  OLLA is an algorithm that optimize the lifetime and memory location of the tensors used to train neural networks. We present several techniques to simplify the encoding of the problem, and enable our approach to scale to the size of state-of-the-art neural networks.
  arXiv  Detail & Related papers  (2022-10-24T02:39:13Z)
• DIVISION: Memory Efficient Training via Dual Activation Precision [60.153754740511864]
  State-of-the-art work combines a search of quantization bit-width with the training, which makes the procedure complicated and less transparent. We propose a simple and effective method to compress DNN training. Experiment results show DIVISION has better comprehensive performance than state-of-the-art methods, including over 10x compression of activation maps and competitive training throughput, without loss of model accuracy.
  arXiv  Detail & Related papers  (2022-08-05T03:15:28Z)
• On-Device Training Under 256KB Memory [62.95579393237751]
  We propose an algorithm-system co-design framework to make on-device training possible with only 256KB of memory. Our framework is the first solution to enable tiny on-device training of convolutional neural networks under 256KB and 1MB Flash.
  arXiv  Detail & Related papers  (2022-06-30T17:59:08Z)
• Memory Replay with Data Compression for Continual Learning [80.95444077825852]
  We propose memory replay with data compression to reduce the storage cost of old training samples. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.
  arXiv  Detail & Related papers  (2022-02-14T10:26:23Z)
• Mesa: A Memory-saving Training Framework for Transformers [58.78933015299703]
  We present Mesa, a memory-saving training framework for Transformers. Mesa uses exact activations during forward pass while storing a low-precision version of activations to reduce memory consumption during training. Experiments on ImageNet, CIFAR-100 and ADE20K demonstrate that Mesa can reduce half of the memory footprints during training.
  arXiv  Detail & Related papers  (2021-11-22T11:23:01Z)
• COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression [8.080129426746288]
  Training wide and deep neural networks (DNNs) require large amounts of storage resources such as memory. We propose a memory-efficient CNN training framework (called COMET) that leverages error-bounded lossy compression. Our framework can significantly reduce the training memory consumption by up to 13.5X over the baseline training and 1.8X over another state-of-the-art compression-based framework.
  arXiv  Detail & Related papers  (2021-11-18T07:43:45Z)
• BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge [2.2191297646252646]
  Training on the Edge enables neural networks to learn continuously from new data after deployment on memory-constrained edge devices. Existing incremental training methods fine-tune the last few layers sacrificing accuracy gains from re-training the whole model. In BitTrain, we exploit activation sparsity and propose a novel bitmap compression technique that reduces the memory footprint during training.
  arXiv  Detail & Related papers  (2021-10-29T16:30:57Z)
• Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings [89.63764845984076]
  We present Stored Embeddings for Efficient Reinforcement Learning (SEER) SEER is a simple modification of existing off-policy deep reinforcement learning methods. We show that SEER does not degrade the performance of RLizable agents while significantly saving computation and memory.
  arXiv  Detail & Related papers  (2021-03-04T08:14:10Z)
• Neural Network Compression Framework for fast model inference [59.65531492759006]
  We present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF) It leverages recent advances of various network compression methods and implements some of them, such as sparsity, quantization, and binarization. The framework can be used within the training samples, which are supplied with it, or as a standalone package that can be seamlessly integrated into the existing training code.
  arXiv  Detail & Related papers  (2020-02-20T11:24:01Z)

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.