GWQ: Gradient-Aware Weight Quantization for Large Language Models

• URL: http://arxiv.org/abs/2411.00850v1
• Date: Wed, 30 Oct 2024 11:16:04 GMT
• Title: GWQ: Gradient-Aware Weight Quantization for Large Language Models
• Authors: Yihua Shao, Siyu Liang, Xiaolin Lin, Zijian Ling, Zixian Zhu, Minxi Yan, Haiyang Liu, Siyu Chen, Ziyang Yan, Yilan Meng, Chenyu Zhang, Haotong Qin, Michele Magno, Yang Yang, Zhen Lei, Yan Wang, Jingcai Guo, Ling Shao, Hao Tang,
• Abstract summary: gradient-aware weight quantization (GWQ) is the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers. GWQ retains the corresponding to the top 1% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit format. In the zero-shot task, GWQ quantized models have higher accuracy compared to other quantization methods.
• Score: 61.17678373122165
• License:
• Abstract: Large language models (LLMs) show impressive performance in solving complex languagetasks. However, its large number of parameterspresent significant challenges for the deployment and application of the model on edge devices. Compressing large language models to low bits can enable them to run on resource-constrained devices, often leading to performance degradation. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the weights corresponding to the top 1% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit format. GWQ found experimentally that utilizing the sensitive weights in the gradient localization model is more scientific compared to utilizing the sensitive weights in the Hessian matrix localization model. Compared to current quantization methods, GWQ can be applied to multiple language models and achieves lower PPL on the WikiText2 and C4 dataset. In the zero-shot task, GWQ quantized models have higher accuracy compared to other quantization methods.GWQ is also suitable for multimodal model quantization, and the quantized Qwen-VL family model is more accurate than other methods. zero-shot target detection task dataset RefCOCO outperforms the current stat-of-the-arts method SPQR. GWQ achieves 1.2x inference speedup in comparison to the original model, and effectively reduces the inference memory.

Related papers

• QERA: an Analytical Framework for Quantization Error Reconstruction [12.110441045050223]
  An increasing interest in quantizing weights to extremely low precision while offsetting the resulting error with low-rank, high-precision error reconstruction terms. The combination of quantization and low-rank approximation is now popular in both adapter-based, parameter-efficient fine-tuning methods. We formulate an analytical framework, named Quantization Error Reconstruction Analysis (QERA), and offer a closed-form solution to the problem.
  arXiv  Detail & Related papers  (2024-10-08T13:37:34Z)
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [67.67135738642547]
  Post-training quantization (PTQ) is a powerful compression technique investigated in large language models (LLMs) Existing PTQ methods are not ideal in terms of accuracy and efficiency, especially with below 4 bit-widths. This paper presents a Salience-Driven Mixed-Precision Quantization scheme for LLMs, namely SliM-LLM.
  arXiv  Detail & Related papers  (2024-05-23T16:21:48Z)
• Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization [62.15918574997175]
  It is known that language models contain outlier channels whose values on average are orders of magnitude higher than other channels. We propose a strategy which regularizes a layer's inputs via quantization-aware training (QAT) and its outputs via activation kurtosis regularization. We show that regularizing both the inputs and outputs is crucial for preventing a model's "migrating" the difficulty in input quantization to the weights.
  arXiv  Detail & Related papers  (2024-04-04T17:25:30Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Norm Tweaking: High-performance Low-bit Quantization of Large Language Models [21.855106896725598]
  We introduce a technique called norm tweaking, which can be used as a plugin in current PTQ methods to achieve high precision. Our method demonstrates significant improvements in both weight-only quantization and joint quantization of weights and activations. Our simple and effective approach makes it more practical for real-world applications.
  arXiv  Detail & Related papers  (2023-09-06T06:51:15Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models [15.461748851931588]
  outlier-aware weight quantization (OWQ) method minimizes large language models' footprint through low-precision representation. OWQ prioritizes a small subset of structured weights sensitive to quantization, storing them in high-precision, while applying highly tuned quantization to the remaining dense weights. Experiments demonstrate that 3.1-bit models using OWQ perform comparably to 4-bit models optimized by OPTQ.
  arXiv  Detail & Related papers  (2023-06-04T06:33:13Z)
• ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation [24.34969722921442]
  Post-training quantization (PTQ) has emerged as a promising technique for mitigating memory consumption and computational costs in large language models (LLMs) We conduct a comprehensive analysis of these factors by investigating the effects of PTQ on weight-only, activation-only, and weight-and-activation quantization. We propose an optimized method called Low-Rank Compensation (LoRC) to enhance model quality recovery with a minimal increase in model size.
  arXiv  Detail & Related papers  (2023-03-15T01:27:15Z)
• Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition [65.7040645560855]
  We propose Q-ASR, an integer-only, zero-shot quantization scheme for ASR models. We show negligible WER change as compared to the full-precision baseline models. Q-ASR exhibits a large compression rate of more than 4x with small WER degradation.
  arXiv  Detail & Related papers  (2021-03-31T06:05:40Z)
• Learnable Companding Quantization for Accurate Low-bit Neural Networks [3.655021726150368]
  Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed. It is still hard for extremely low-bit models to achieve accuracy comparable with that of full-precision models. We propose learnable companding quantization (LCQ) as a novel non-uniform quantization method for 2-, 3-, and 4-bit models.
  arXiv  Detail & Related papers  (2021-03-12T09:06:52Z)

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.