BiSup: Bidirectional Quantization Error Suppression for Large Language Models
- URL: http://arxiv.org/abs/2405.15346v1
- Date: Fri, 24 May 2024 08:39:27 GMT
- Title: BiSup: Bidirectional Quantization Error Suppression for Large Language Models
- Authors: Minghui Zou, Ronghui Guo, Sai Zhang, Xiaowang Zhang, Zhiyong Feng,
- Abstract summary: We introduce BiSup, a Bi-directional quantization error Suppression method.
We show that BiSup can improve performance over two state-of-the-art methods.
- Score: 13.042992673384466
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: As the size and context length of Large Language Models (LLMs) grow, weight-activation quantization has emerged as a crucial technique for efficient deployment of LLMs. Compared to weight-only quantization, weight-activation quantization presents greater challenges due to the presence of outliers in activations. Existing methods have made significant progress by exploring mixed-precision quantization and outlier suppression. However, these methods primarily focus on optimizing the results of single matrix multiplication, neglecting the bidirectional propagation of quantization errors in LLMs. Specifically, errors accumulate vertically within the same token through layers, and diffuse horizontally across different tokens due to self-attention mechanisms. To address this issue, we introduce BiSup, a Bidirectional quantization error Suppression method. By constructing appropriate optimizable parameter spaces, BiSup utilizes a small amount of data for quantization-aware parameter-efficient fine-tuning to suppress the error vertical accumulation. Besides, BiSup employs prompt mixed-precision quantization strategy, which preserves high precision for the key-value cache of system prompts, to mitigate the error horizontal diffusion. Extensive experiments on Llama and Qwen families demonstrate that BiSup can improve performance over two state-of-the-art methods (the average WikiText2 perplexity decreases from 13.26 to 9.41 for Atom and from 14.33 to 7.85 for QuaRot under the W3A3-g128 configuration), further facilitating the practical applications of low-bit weight-activation quantization.
Related papers
- Pushing the Limits of Large Language Model Quantization via the Linearity Theorem [71.3332971315821]
We present a "line theoremarity" establishing a direct relationship between the layer-wise $ell$ reconstruction error and the model perplexity increase due to quantization.
This insight enables two novel applications: (1) a simple data-free LLM quantization method using Hadamard rotations and MSE-optimal grids, dubbed HIGGS, and (2) an optimal solution to the problem of finding non-uniform per-layer quantization levels.
arXiv Detail & Related papers (2024-11-26T15:35:44Z) - ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization [18.017182472532415]
ASER is an algorithm consisting of low-rank compensation for quantization error with LoRA-style matrices constructed by whitening SVD.
ASER is capable of quantizing typical outliers to low-bit ones, particularly preserving accuracy even in W4A8 per-channel setup.
arXiv Detail & Related papers (2024-11-12T12:52:04Z) - GPTQT: Quantize Large Language Models Twice to Push the Efficiency [1.3149617027696827]
This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed.
Practice has shown that minimizing the quantization error of weights is ineffective, leading to overfitting.
GPTQT employs a progressive two-step approach: initially quantizing weights using Linear quantization to a relatively high bit, followed by converting obtained int weight to lower bit binary coding.
arXiv Detail & Related papers (2024-07-03T08:08:01Z) - 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) - PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks [4.827161693957252]
Non-quantized elementwise operations dominate the inference cost of low-precision models.
PikeLPN model addresses these issues by applying quantization to both elementwise operations and multiply-accumulate operations.
arXiv Detail & Related papers (2024-03-29T18:23:34Z) - DB-LLM: Accurate Dual-Binarization for Efficient LLMs [83.70686728471547]
Large language models (LLMs) have significantly advanced the field of natural language processing.
Existing ultra-low-bit quantization always causes severe accuracy drops.
We propose a novel Dual-Binarization method for LLMs, namely DB-LLM.
arXiv Detail & Related papers (2024-02-19T09:04:30Z) - 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) - OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models [57.27101446992148]
Large language models (LLMs) have revolutionized natural language processing tasks.
Recent post-training quantization (PTQ) methods are effective in reducing memory footprint and improving the computational efficiency of LLM.
We introduce an Omnidirectionally calibrated Quantization technique for LLMs, which achieves good performance in diverse quantization settings.
arXiv Detail & Related papers (2023-08-25T02:28:35Z) - Automatic Mixed-Precision Quantization Search of BERT [62.65905462141319]
Pre-trained language models such as BERT have shown remarkable effectiveness in various natural language processing tasks.
These models usually contain millions of parameters, which prevents them from practical deployment on resource-constrained devices.
We propose an automatic mixed-precision quantization framework designed for BERT that can simultaneously conduct quantization and pruning in a subgroup-wise level.
arXiv Detail & Related papers (2021-12-30T06:32:47Z) - Mixed Precision of Quantization of Transformer Language Models for
Speech Recognition [67.95996816744251]
State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications.
Current low-bit quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of the system to quantization errors.
The optimal local precision settings are automatically learned using two techniques.
Experiments conducted on Penn Treebank (PTB) and a Switchboard corpus trained LF-MMI TDNN system.
arXiv Detail & Related papers (2021-11-29T09:57:00Z)
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.