ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization

• URL: http://arxiv.org/abs/2411.07762v1
• Date: Tue, 12 Nov 2024 12:52:04 GMT
• Title: ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization
• Authors: Weibo Zhao, Yubin Shi, Xinyu Lyu, Wanchen Sui, Shen Li, Yong Li,
• Abstract summary: 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.
• Score: 18.017182472532415
• License:
• Abstract: Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The limited numerical mapping makes the quantized model produce a non-trivial error, bringing out intolerable performance degration. This paper is anchored in the basic idea of model compression objectives, and delves into the layer-wise error distribution of LLMs during post-training quantization. Subsequently, we introduce ASER, an algorithm consisting of (1) Error Reconstruction: low-rank compensation for quantization error with LoRA-style matrices constructed by whitening SVD; (2) Activation Smoothing: outlier extraction to gain smooth activation and better error compensation. ASER is capable of quantizing typical LLMs to low-bit ones, particularly preserving accuracy even in W4A8 per-channel setup. Experimental results show that ASER is competitive among the state-of-the-art quantization algorithms, showing potential to activation quantization, with minor overhead.

Related papers

• Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other [10.292252814921714]
  We introduce Learnable Singular value Increment (LSI) as an advanced solution to quantization problems. LSI uses Singular Value Decomposition to extract singular values of the weights and make them learnable to help weights compensate each other conditioned on activation. We achieve state-of-the-art performance in diverse quantization settings, no matter in weight-only, weight-activation or extremely low bit scenarios.
  arXiv  Detail & Related papers  (2024-06-24T03:52:52Z)
• 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)
• WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More [55.0856305773081]
  Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on the quantization of LLMs, a technique that reduces memory consumption by converting model parameters and activations into low-bit integers.
  arXiv  Detail & Related papers  (2024-02-19T11:33:21Z)
• OneBit: Towards Extremely Low-bit Large Language Models [66.29839811207617]
  This paper boldly quantizes the weight matrices of LLMs to 1-bit, paving the way for the extremely low bit-width deployment of LLMs. Experiments indicate that OneBit achieves good performance (at least 81% of the non-quantized performance on LLaMA models) with robust training processes.
  arXiv  Detail & Related papers  (2024-02-17T14:26:57Z)
• ApiQ: Finetuning of 2-Bit Quantized Large Language Model [12.328293460903911]
  ApiQ is designed to restore the lost information from quantization by concurrently initializing the LoRA components and quantizing the weights of LLMs. It consistently achieves superior finetuning results across various bit-widths.
  arXiv  Detail & Related papers  (2024-02-07T09:36:54Z)
• LQER: Low-Rank Quantization Error Reconstruction for LLMs [13.205129808742862]
  We introduce Low-rank Quantization Error Reduction (LQER), which combines quantization and low-rank approximation to recover the model capability. Unlike existing methods, the computation pattern of LQER eliminates the need for specialized Scatter and Gather processes. Our W4A8 LLMs achieve near-lossless performance on six popular downstream tasks, while using 1.36$times$ fewer hardware resources than the leading state-of-the-art method.
  arXiv  Detail & Related papers  (2024-02-04T10:59:52Z)
• Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models [88.80146574509195]
  Quantization is a promising approach for reducing memory overhead and accelerating inference. We propose a novel-aware quantization (ZSAQ) framework for the zero-shot quantization of various PLMs.
  arXiv  Detail & Related papers  (2023-10-20T07:09:56Z)
• PB-LLM: Partially Binarized Large Language Models [14.244537605866864]
  This paper explores network binarization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. We propose a novel approach, Partially-Binarized LLM (PB-LLM), which can achieve extreme low-bit quantization while maintaining the linguistic reasoning capacity of quantized LLMs.
  arXiv  Detail & Related papers  (2023-09-29T14:35:27Z)
• QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models [85.02796681773447]
  We propose a quantization-aware low-rank adaptation (QA-LoRA) algorithm. The motivation lies in the imbalanced degrees of freedom of quantization and adaptation. QA-LoRA is easily implemented with a few lines of code.
  arXiv  Detail & Related papers  (2023-09-26T07:22:23Z)
• Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study [90.34226812493083]
  This work aims to investigate the impact of quantization on emphemergent abilities, which are important characteristics that distinguish LLMs from small language models. Our empirical experiments show that these emergent abilities still exist in 4-bit quantization models, while 2-bit models encounter severe performance degradation. To improve the performance of low-bit models, we conduct two special experiments: (1) fine-gained impact analysis that studies which components (or substructures) are more sensitive to quantization, and (2) performance compensation through model fine-tuning.
  arXiv  Detail & Related papers  (2023-07-16T15:11:01Z)

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.