PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization

• URL: http://arxiv.org/abs/2410.05265v2
• Date: Mon, 27 Jan 2025 13:39:25 GMT
• Title: PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
• Authors: Mengzhao Chen, Yi Liu, Jiahao Wang, Yi Bin, Wenqi Shao, Ping Luo,
• Abstract summary: We propose PrefixQuant, a novel quantization method that achieves state-of-the-art performance across various precision levels.<n>First, PrefixQuant eliminates token-wise outliers by prefixing outlier tokens in the KV cache.<n>Second, PrefixQuant introduces new trainable parameters for block-wise training to compensate for quantization error.
• Score: 44.547992997369875
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing weight-activation quantization methods for Large Language Models (LLMs) primarily address channel-wise outliers but often neglect token-wise outliers, which limits the accuracy of quantized models. In this work, we propose PrefixQuant, a novel quantization method that achieves state-of-the-art performance across various precision levels (W4A4KV4 and W4A8KV4) and granularities (dynamic and static quantization) by effectively isolating token-wise outliers. First, PrefixQuant eliminates token-wise outliers by prefixing outlier tokens in the KV cache, a process that is training-free and highly efficient (e.g., 1 minutes for Llama-3-70B). Second, PrefixQuant introduces new trainable parameters for block-wise training to compensate for quantization error. Our experiments show that PrefixQuant significantly outperforms existing dynamic quantization methods, even under coarser static quantization settings. For instance, PrefixQuant achieves an average accuracy improvement of +3.08 and +2.85 points over SpinQuant (dynamic quantization) on five zero-shot reasoning tasks under dynamic and static quantization settings, respectively, on W4A4KV4 Llama-3-8B. Additionally, we demonstrate up to 2.74x prefilling speedup and 2.16x decoding speedup for LLMs using W4A4 PrefixQuant. Our code is available at https://github.com/ChenMnZ/PrefixQuant.

Related papers

• Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics [65.37942405146232]
  We present a novel type of overload that carries with extremely lightweight state elements, achieved through ultra-low-precision quantization. The proposed SOLO achieves substantial memory savings (approximately 45 GB when training a 7B model) with minimal accuracy loss.
  arXiv  Detail & Related papers  (2025-05-01T06:47:45Z)
• QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition [21.13478769431063]
  QUAD (Quantization with Activation Decomposition) is a framework leveraging Singular Value Decomposition (SVD) to suppress activation outliers for effective 4-bit quantization. We show QUAD achieves 94% 96% accuracy under W4A4 quantization and 98% accuracy with W4A4/A8 and parameter-efficient fine-tuning for Llama-3 and Qwen-2.5 models.
  arXiv  Detail & Related papers  (2025-03-25T05:03:56Z)
• MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration [23.752021919501207]
  We propose MergeQuant, an accurate and efficient per-channel static quantization framework. MergeQuant integrates the per-channel quantization steps with the corresponding scalings and linear mappings through a Quantization Step Migration (QSM) method. On Llama-2-7B model, MergeQuant achieves up to 1.77x speedup in decoding, and up to 2.06x speedup in end-to-end compared to FP16 baseline.
  arXiv  Detail & Related papers  (2025-03-07T04:52:28Z)
• ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization [58.84018707089315]
  We present a unified framework for rigorous comparisons across 1-bit, 1.58-bit, 2-bit, 3-bit, and 4-bit quantization settings. We show that ternary, 2-bit, and 3-bit quantization maintains comparable performance in the size-accuracy trade-off. Considering hardware constraints, 2-bit quantization offers promising potential for memory reduction and speedup.
  arXiv  Detail & Related papers  (2025-02-04T18:59:26Z)
• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models [58.5019443418822]
  Diffusion models have been proven highly effective at generating high-quality images. As these models grow larger, they require significantly more memory and suffer from higher latency. In this work, we aim to accelerate diffusion models by quantizing their weights and activations to 4 bits.
  arXiv  Detail & Related papers  (2024-11-07T18:59:58Z)
• 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)
• 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)
• LLM-FP4: 4-Bit Floating-Point Quantized Transformers [38.23587031169402]
  We propose LLM-FP4 for quantizing both weights and activations in large language models (LLMs) down to 4-bit floating-point values. Compared to integer quantization, floating-point (FP) quantization is more flexible and can better handle long-tail or bell-shaped distributions. Our method, for the first time, can quantize both weights and activations in the LLaMA-13B to only 4-bit and achieves an average score of 63.1.
  arXiv  Detail & Related papers  (2023-10-25T17:59:32Z)
• QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models [57.04178959678024]
  We show that the majority of inference computations for large generative models can be performed with both weights and activations being cast to 4 bits. We achieve this via a hybrid quantization strategy called QUIK, which compresses most of the weights and activations to 4-bit. We provide GPU kernels matching the QUIK format with highly-efficient layer-wise runtimes, which lead to practical end-to-end throughput improvements of up to 3.4x.
  arXiv  Detail & Related papers  (2023-10-13T17:15:05Z)
• 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)
• 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)
• Post-Training Sparsity-Aware Quantization [2.2530496464901106]
  Quantization is a technique used in deep neural networks (DNNs) to increase execution performance and hardware efficiency. We propose a sparsity-aware quantization (SPARQ) method, in which the unstructured and dynamic activation sparsity is leveraged in different representation granularities. SPARQ achieves minor accuracy degradation, 2x speedup over widely used hardware architectures, and a practical hardware implementation.
  arXiv  Detail & Related papers  (2021-05-23T20:12:35Z)
• One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment [36.75157407486302]
  We propose a method to train a model for all quantization that supports diverse bit-widths. We use wavelet decomposition and reconstruction to increase the diversity of weights. Our method can achieve accuracy comparable to dedicated models trained at the same precision.
  arXiv  Detail & Related papers  (2021-05-04T08:10:50Z)
• 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)

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.