Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs

• URL: http://arxiv.org/abs/2405.14428v1
• Date: Thu, 23 May 2024 10:54:14 GMT
• Title: Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs
• Authors: Jaewoo Yang, Hayun Kim, Younghoon Kim,
• Abstract summary: Post-training quantization (PTQ) has become a popular approach, quantizing weights and activations to lower precision. We show the challenges of activation quantization in GLU variants, which are widely used in feed-forward network (FFN) of modern large language models. We propose two empirical methods, Quantization-free Module (QFeM) and Quantization-free Prefix (QFeP), to isolate the activation spikes during quantization.
• Score: 5.408684636210501
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern large language models (LLMs) have established state-of-the-art performance through architectural improvements, but still require significant computational cost for inference. In an effort to reduce the inference cost, post-training quantization (PTQ) has become a popular approach, quantizing weights and activations to lower precision, such as INT8. In this paper, we reveal the challenges of activation quantization in GLU variants, which are widely used in feed-forward network (FFN) of modern LLMs, such as LLaMA family. The problem is that severe local quantization errors, caused by excessive magnitudes of activation in GLU variants, significantly degrade the performance of the quantized LLM. We denote these activations as activation spikes. Our further observations provide a systematic pattern of activation spikes: 1) The activation spikes occur in the FFN of specific layers, particularly in the early and late layers, 2) The activation spikes are dedicated to a couple of tokens, rather than being shared across a sequence. Based on our observations, we propose two empirical methods, Quantization-free Module (QFeM) and Quantization-free Prefix (QFeP), to isolate the activation spikes during quantization. Our extensive experiments validate the effectiveness of the proposed methods for the activation quantization, especially with coarse-grained scheme, of latest LLMs with GLU variants, including LLaMA-2/3, Mistral, Mixtral, SOLAR, and Gemma. In particular, our methods enhance the current alleviation techniques (e.g., SmoothQuant) that fail to control the activation spikes. Code is available at https://github.com/onnoo/activation-spikes.

Related papers

• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [53.571195477043496]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE) RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers. Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• 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)
• Sparsing Law: Towards Large Language Models with Greater Activation Sparsity [62.09617609556697]
  Activation sparsity denotes the existence of substantial weakly-contributed elements within activation outputs that can be eliminated. We propose PPL-$p%$ sparsity, a precise and performance-aware activation sparsity metric. We show that ReLU is more efficient as the activation function than SiLU and can leverage more training data to improve activation sparsity.
  arXiv  Detail & Related papers  (2024-11-04T17:59:04Z)
• Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization [13.475050661770796]
  We develop a simple yet effective strategy to facilitate per-tensor activation quantization by preventing the generation of problematic tokens. We tune the token cache to regularize the activations of subsequent tokens to be more quantization-friendly. We thoroughly evaluate our method over a wide range of models and benchmarks and find that it significantly surpasses the established baseline of per-tensor W8A8 quantization.
  arXiv  Detail & Related papers  (2024-06-17T18:33:44Z)
• I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models [20.070306492164427]
  Post-training quantization serves as a potent technique to accelerate the inference of large language models. Existing works still necessitate a considerable number of floating-point (FP) operations during inference. This limitation hinders the deployment of large language models on the edge and cloud devices. We propose I-LLM, a novel integer-only fully-quantized PTQ framework tailored for large language models.
  arXiv  Detail & Related papers  (2024-05-28T05:56:11Z)
• 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)
• 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)
• ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs [91.31204876440765]
  We introduce a general method that defines neuron activation through neuron output magnitudes and a tailored magnitude threshold. To find the most efficient activation function for sparse computation, we propose a systematic framework. We conduct thorough experiments on LLMs utilizing different activation functions, including ReLU, SwiGLU, ReGLU, and ReLU$2$.
  arXiv  Detail & Related papers  (2024-02-06T08:45:51Z)
• 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)
• PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models [52.09865918265002]
  We propose a novel quantize before fine-tuning'' framework, PreQuant. PreQuant is compatible with various quantization strategies, with outlier-aware fine-tuning incorporated to correct the induced quantization error. We demonstrate the effectiveness of PreQuant on the GLUE benchmark using BERT, RoBERTa, and T5.
  arXiv  Detail & Related papers  (2023-05-30T08:41:33Z)
• RPTQ: Reorder-based Post-training Quantization for Large Language Models [46.03754730678076]
  Large-scale language models (LLMs) have demonstrated impressive performance, but their deployment presents challenges due to their significant memory usage. We introduce a quantization method called RPTQ, which utilizes a reorder-based approach. In our experiments, RPTQ achieved a significant breakthrough by utilizing 3-bit activation in LLMs for the first time, resulting in a substantial reduction in memory usage.
  arXiv  Detail & Related papers  (2023-04-03T15:46:15Z)

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.