CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs

• URL: http://arxiv.org/abs/2412.09282v2
• Date: Wed, 19 Feb 2025 05:50:37 GMT
• Title: CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs
• Authors: Yuzhuang Xu, Shiyu Ji, Qingfu Zhu, Wanxiang Che,
• Abstract summary: Post-training quantization (PTQ) has emerged as a star approach to achieve this ambition.<n>We propose Channel-Relaxed Vector Quantization (CRVQ), a novel technique that significantly improves the performance of PTQ baselines.
• Score: 43.769229349666396
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Powerful large language models (LLMs) are increasingly expected to be deployed with lower computational costs, enabling their capabilities on resource-constrained devices. Post-training quantization (PTQ) has emerged as a star approach to achieve this ambition, with best methods compressing weights to less than 2 bit on average. In this paper, we propose Channel-Relaxed Vector Quantization (CRVQ), a novel technique that significantly improves the performance of PTQ baselines at the cost of only minimal additional bits. This state-of-the-art extreme compression method achieves its results through two key innovations: (1) carefully selecting and reordering a very small subset of critical weight channels, and (2) leveraging extended codebooks to relax the constraint of critical channels. With our method, we demonstrate a 38.9\% improvement over the current strongest sub-2-bit PTQ baseline, enabling nearer lossless 1-bit compression. Furthermore, our approach offers flexible customization of quantization bit-width and performance, providing a wider range of deployment options for diverse hardware platforms.

Related papers

• Arbitrary Ratio Feature Compression via Next Token Prediction [52.10426317889982]
  Arbitrary Ratio Feature Compression (ARFC) framework supports any compression ratio with a single model.<n>ARC is an auto-regressive model that performs compression via next-gressive prediction.<n>MoS module refines the compressed tokens by utilizing multiple compression results.<n>ERGC is integrated into the training process to preserve semantic and structural relationships during compression.
  arXiv  Detail & Related papers  (2026-02-12T02:38:57Z)
• AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression [17.374453570006448]
  AngelSlim is a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team.<n>It consolidates cutting-edge algorithms, including quantization, speculative decoding, token pruning, and distillation.<n>By integrating these compression strategies from low-level implementations, AngelSlim enables algorithm-focused research and tool-assisted deployment.
  arXiv  Detail & Related papers  (2026-02-07T07:02:56Z)
• PT$^2$-LLM: Post-Training Ternarization for Large Language Models [52.4629647715623]
  Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment.<n>We propose PT$2$-LLM, a post-training ternarization framework tailored for LLMs.<n>At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline.
  arXiv  Detail & Related papers  (2025-09-27T03:01:48Z)
• Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding [56.066799081747845]
  The ever-growing size of neural networks poses serious challenges on resource-constrained devices.<n>We propose a novel post-training compression framework that combines rate-aware quantization with entropy coding.<n>Our method allows for very fast decoding and is compatible with arbitrary quantization grids.
  arXiv  Detail & Related papers  (2025-05-24T15:52:49Z)
• PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models [64.84734437930362]
  Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization. We propose an extremely low-bit PTQ method called PTQ1.61, which enables weight quantization to 1.61-bit for the first time. Experiments indicate our PTQ1.61 achieves state-of-the-art performance in extremely low-bit quantization.
  arXiv  Detail & Related papers  (2025-02-18T08:04:58Z)
• Enhanced Quantum Circuit Cutting Framework for Sampling Overhead Reduction [25.01488143369413]
  ShotQC is an enhanced circuit cutting framework with effective sampling overhead reduction. It achieves significant reductions in sampling overhead without increasing classical postprocessing complexity.
  arXiv  Detail & Related papers  (2024-12-23T16:34:57Z)
• GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference [5.358880304650258]
  Group Quantization and Sparse Acceleration (GQSA) is a novel compression technique tailored for LLMs. We propose a two-stage sparse optimization strategy that ensures the performance superiority of the compressed model. Experimental results demonstrate that, under the GQSA W4S50% compression setting, the model's accuracy surpasses that of both 2:4 pruning and W2 quantization.
  arXiv  Detail & Related papers  (2024-12-23T13:28:15Z)
• PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution [95.98801201266099]
  Diffusion-based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. We propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR. Our PassionSR achieves significant advantages over recent leading low-bit quantization methods for image SR.
  arXiv  Detail & Related papers  (2024-11-26T04:49:42Z)
• 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution [83.09117439860607]
  Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment. It is notorious that low-bit quantization degrades the accuracy of SR models compared to their full-precision (FP) counterparts. We present a dual-stage low-bit post-training quantization (PTQ) method for image super-resolution, namely 2DQuant, which achieves efficient and accurate SR under low-bit quantization.
  arXiv  Detail & Related papers  (2024-06-10T06:06:11Z)
• PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression [31.30170080420504]
  State-of-the-art quantization methods include fine-tuning (part of) the compressed parameters over a limited amount of calibration data. We propose PV-Tuning - a representation-agnostic framework that generalizes and improves upon existing fine-tuning strategies.
  arXiv  Detail & Related papers  (2024-05-23T17:57:04Z)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)
• CBQ: Cross-Block Quantization for Large Language Models [66.82132832702895]
  Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs. We propose CBQ, a cross-block reconstruction-based PTQ method for LLMs. CBQ employs a cross-block dependency using a reconstruction scheme, establishing long-range dependencies across multiple blocks to minimize error accumulation.
  arXiv  Detail & Related papers  (2023-12-13T07:56:27Z)
• 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)
• Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning [29.284147465251685]
  We introduce a new compression framework which covers both weight pruning and quantization in a unified setting. We show that it can improve significantly upon the compression-accuracy trade-offs of existing post-training methods.
  arXiv  Detail & Related papers  (2022-08-24T14:33:35Z)
• OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization [32.60139548889592]
  We propose a novel One-shot Pruning-Quantization (OPQ) in this paper. OPQ analytically solves the compression allocation with pre-trained weight parameters only. We propose a unified channel-wise quantization method that enforces all channels of each layer to share a common codebook.
  arXiv  Detail & Related papers  (2022-05-23T09:05:25Z)

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.