KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models

• URL: http://arxiv.org/abs/2602.11184v1
• Date: Fri, 30 Jan 2026 06:57:17 GMT
• Title: KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
• Authors: Zukang Xu, Zhixiong Zhao, Xing Hu, Zhixuan Chen, Dawei Yang,
• Abstract summary: Vector Quantization (VQ) offers a promising approach for ultra-low-bit compression in Large Language Models (LLMs)<n>We propose KBVQ-MoE, a novel VQ framework to enhance extremely low-bit quantization for MoE-based LLMs.<n> Experiments on various MoE LLMs demonstrate that KBVQ-MoE preserves accuracy substantially better than existing quantization methods.
• Score: 13.773876289947323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mixture of Experts (MoE) models have achieved great success by significantly improving performance while maintaining computational efficiency through sparse expert activation. However, their enormous parameter sizes and memory demands pose major challenges for deployment in resource-constrained environments. Vector Quantization (VQ) offers a promising approach for ultra-low-bit compression in Large Language Models (LLMs) by leveraging a codebook, where weight vectors are mapped to the most similar discrete codewords. Yet, directly applying VQ to MoEs often leads to substantial performance degradation due to two critical obstacles: (1) redundant representations among experts cause VQ to repeatedly quantize similar representations for each expert, resulting in inefficient use of limited codebook capacity; and (2) cumulative output bias is amplified by expert aggregation in MoE layers, leading to distributional shifts in the quantized outputs. To address these issues, we propose KBVQ-MoE, a novel VQ framework to enhance extremely low-bit quantization for MoE-based LLMs. KBVQ-MoE integrates two techniques: (1) input-driven redundancy elimination, where a Karhunen-Loeve Transform (KLT) guided singular value decomposition (SVD) extracts dominant weight components and shares them across experts; and (2) bias-corrected output stabilization, where vector quantization is applied only to expert-specific (non-redundant) representations and the quantized outputs are corrected via channel-wise affine compensation. Experiments on various MoE LLMs demonstrate that KBVQ-MoE preserves accuracy substantially better than existing quantization methods. For example, 3-bit quantization of Qwen1.5-MoE-A2.7B achieves an average accuracy of 67.99, nearly identical to the FP16 baseline of 68.07, underscoring KBVQ-MoE's potential for efficient deployment on edge devices and other resource-constrained platforms.

Related papers

• VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models [41.557274086591924]
  Post-Training Quantization (PTQ) is an effective training-free technique to address the massive memory and computation overhead.<n>Visual Expert Quantization (VEQ) is a dual-aware quantization framework designed to accommodate cross-modal differences and heterogeneity between experts.<n>Our method achieves significant average accuracy gains of 2.04% on Kimi-VL and 3.09% on Qwen3-VL compared to the previous SOTA quantization methods.
  arXiv  Detail & Related papers  (2026-02-01T05:53:09Z)
• Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models [41.677469535447024]
  Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-constrained devices.<n>Post-training quantization (PTQ) is widely adopted for its efficiency, as it requires no retraining and only a small dataset for calibration.<n>Recent advances for post-training quantization have demonstrated that even sub-4-bit methods can maintain most of the original model performance.
  arXiv  Detail & Related papers  (2025-12-25T12:39:36Z)
• R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization [20.861971198175674]
  Residual Refinement Quantization (R2Q) is a novel 2-bit quantization framework that decomposes the process into two sequential 1-bit sub-quantizations.<n>R2Q consistently outperforms existing 2-bit quantization methods in both fine-grained and coarse-grained settings.
  arXiv  Detail & Related papers  (2025-11-21T12:39:44Z)
• Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression [57.54335545892155]
  We introduce a Grouped Lattice Vector Quantization (GLVQ) framework that assigns each group of weights a customized lattice codebook.<n>Our approach achieves a better trade-off between model size and accuracy compared to existing post-training quantization baselines.
  arXiv  Detail & Related papers  (2025-10-23T20:19:48Z)
• MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation [74.34220141721231]
  We present MPQ-DMv2, an improved textbfMixed textbfPrecision textbfQuantization framework for extremely low-bit textbfDiffusion textbfModels.
  arXiv  Detail & Related papers  (2025-07-06T08:16:50Z)
• PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling [53.91873442457923]
  Vector Quantization (VQ) serves as a prevalent solution to this issue for its extremely low-bit (even at 2-bit) and considerable accuracy.<n>This paper proposes Polar Coordinate Decoupled Vector Quantization (PCDVQ), an effective and efficient VQ framework.<n> Experimental results show that PCDVQ outperforms baseline methods at 2-bit level by at least 1.5% zero-shot accuracy.
  arXiv  Detail & Related papers  (2025-06-05T08:58:58Z)
• MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance [10.817003682434425]
  Mixture-of-Experts (MoE) large language models (LLMs) leverage dynamic routing and sparse activation to enhance efficiency and scalability.<n>Post-training quantization (PTQ) encounters severe accuracy degradation and diminished performance when applied to MoE models.<n>This paper investigates the impact of MoE's sparse and dynamic characteristics on quantization.
  arXiv  Detail & Related papers  (2025-05-02T08:51:55Z)
• 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)
• QSpec: Speculative Decoding with Complementary Quantization Schemes [53.960146187821685]
  Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs)<n>We propose QSpec, a novel quantization paradigm that decouples efficiency from quality.<n>QSpec reuses both weights and KV cache across stages, enabling near-zero-cost switching without retraining or auxiliary models.
  arXiv  Detail & Related papers  (2024-10-15T05:57:51Z)
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [63.118592279833656]
  Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs)<n>We propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise.<n> Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths.
  arXiv  Detail & Related papers  (2024-05-23T16:21:48Z)
• RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization [8.827794405944637]
  Post-training quantization (PTQ) is a promising solution for compressing large transformer models. Existing PTQ methods typically exhibit non-trivial performance loss. We propose RepQuant, a novel PTQ framework with quantization-inference decoupling paradigm.
  arXiv  Detail & Related papers  (2024-02-08T12:35:41Z)
• 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.<n>We propose CBQ, a cross-block reconstruction-based PTQ method for LLMs.<n> 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)
• 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)

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.