BAQ: Efficient Bit Allocation Quantization for Large Language Models

• URL: http://arxiv.org/abs/2506.05664v1
• Date: Fri, 06 Jun 2025 01:27:01 GMT
• Title: BAQ: Efficient Bit Allocation Quantization for Large Language Models
• Abstract summary: Post-training model quantization is a widely adopted technique for reducing memory and computational costs of large language models.<n>Most existing methods rely on uniform or bitwidth assignments, failing to account for the nonuniform sensitivity of weights to quantization noise.<n>We propose a novel framework for allocating quantization bitwidths based on sensitivity metrics derived from a Hessian proxy.
• Score: 8.427223431012454
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Post-training model quantization is a widely adopted technique for reducing the memory and computational costs of large language models (LLMs). However, most existing methods rely on uniform or heuristic bitwidth assignments, failing to account for the nonuniform sensitivity of weights to quantization noise. In this paper, we propose a novel framework for allocating quantization bitwidths based on sensitivity metrics derived from a Hessian proxy. We make key assumptions, which allow the layer/component-wise loss function to be expressed as an explicit function of the bitwidths. This enables a neat formulation of the bit allocation problem as a convex optimization task, whose closed-form solution adapts precision across weights to minimize the layer-wise quantization loss. Inspecting the solution provides several insights (such as the equal-loss structure), which are then exploited to design the proposed \textbf{BAQ} (Bit Allocation Quantization) algorithm. The proposed algorithm achieves a good trade-off between loss minimization and complexity and allows BAQ to be integrated into standard quantization pipelines with minimal overhead. Experimental results show that BAQ consistently outperforms GPTQ, achieving up to 56$\times$ lower perplexity at the same bitwidth on large language models ranging from 125M to 30B parameters. Leveraging our analytical results derived from solving the optimal bit allocation problem, we also provide a theoretical explanation for the observed gains. All codes of this paper are available at https://github.com/CSU-ModelCompression/BAQ.

Related papers

• Optimal Post-Training Quantization Scales and Where to Find Them [1.3048920509133808]
  Post-training quantization (PTQ) compresses large language models by mapping weights to low representations.<n>We present PiSO, an algorithm that computes the optimal channel-wise weight scales exactly and efficiently under round-to-nearest quantization.
  arXiv  Detail & Related papers  (2026-06-09T14:03:04Z)
• EQE-QAOA: An Equivalence-Preserving Qubit Efficient Framework for Combinatorial Optimization [54.05451096499336]
  Existing techniques rely on qubit reduction at the cost of information loss, leading to degraded computational performance.<n>We propose the Equivalence-preserving Qubit Efficient QAOA, which significantly reduces the required number of qubits without degrading performance.<n>We show that it is broadly applicable to large-scale optimization problems, excluding only unconstrained problems with completely independent variables.
  arXiv  Detail & Related papers  (2026-04-20T13:57:49Z)
• 1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization [6.530091512185435]
  Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs.<n>We show that k-means based weight quantization outperforms integer formats and can be implemented efficiently on standard hardware.
  arXiv  Detail & Related papers  (2026-02-17T13:23:26Z)
• BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models [56.504879072674015]
  We propose Bit-Plane Decomposition Quantization (BPDQ), which constructs a variable quantization grid via bit-planes and scalar coefficients.<n>BPDQ enables serving Qwen2.5-72B on a single GTX 3090 with 83.85% GSM8K accuracy (vs. 90.83% at 16-bit)
  arXiv  Detail & Related papers  (2026-02-04T02:54:37Z)
• 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)
• Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment [15.802372921412198]
  We study weight-only post-training quantization (PTQ), which quantizes the weights of a large language model (LLM) without retraining, using little or no calibration data.<n>We first derive the information-theoretically optimal bit allocation for Gaussianized weights under given bit budgets, revealing that fine-grained fractional-bit quantizers approaching the Gaussian distortion-rate bound are essential to achieve near-optimal quantization performance.
  arXiv  Detail & Related papers  (2025-09-24T15:10:44Z)
• 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)
• Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model [0.0]
  Mix-QSAM is a mixed-precision Post-Training Quantization (PTQ) framework for the Segment Anything Model (SAM)<n>We introduce a layer-wise importance score, derived using Kullback-Leibler (KL) divergence, to quantify each layer's contribution to the model's output.<n>We also introduce cross-layer synergy, a novel metric based on causal mutual information, to capture dependencies between adjacent layers.
  arXiv  Detail & Related papers  (2025-05-08T00:08:31Z)
• 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)
• MixQuant: Mixed Precision Quantization with a Bit-width Optimization Search [7.564770908909927]
  Quantization is a technique for creating efficient Deep Neural Networks (DNNs) We propose MixQuant, a search algorithm that finds the optimal custom quantization bit-width for each layer weight based on roundoff error. We show that combining MixQuant with BRECQ, a state-of-the-art quantization method, yields better quantized model accuracy than BRECQ alone.
  arXiv  Detail & Related papers  (2023-09-29T15:49:54Z)
• Designing strong baselines for ternary neural network quantization through support and mass equalization [7.971065005161565]
  Deep neural networks (DNNs) offer the highest performance in a wide range of applications in computer vision. This computational burden can be dramatically reduced by quantizing floating point values to ternary values. We show experimentally that our approach allows to significantly improve the performance of ternary quantization through a variety of scenarios.
  arXiv  Detail & Related papers  (2023-06-30T07:35:07Z)
• 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)
• Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective [74.48124653728422]
  Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically. We argue that an overlooked problem of oscillation is in the PTQ methods.
  arXiv  Detail & Related papers  (2023-03-21T14:52:52Z)
• End-to-end resource analysis for quantum interior point methods and portfolio optimization [63.4863637315163]
  We provide a complete quantum circuit-level description of the algorithm from problem input to problem output. We report the number of logical qubits and the quantity/depth of non-Clifford T-gates needed to run the algorithm.
  arXiv  Detail & Related papers  (2022-11-22T18:54:48Z)
• Learning Quantization in LDPC Decoders [14.37550972719183]
  We propose a floating-point surrogate model that imitates quantization effects as additions of uniform noise. A deep learning-based method is then applied to optimize the message bitwidths. We report an error-rate performance within 0.2 dB of floating-point decoding at an average message quantization bitwidth of 3.1 bits.
  arXiv  Detail & Related papers  (2022-08-10T07:07:54Z)
• BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization [32.770842274996774]
  Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks. Previous methods either examine only a small manually-designed search space or utilize a cumbersome neural architecture search to explore the vast search space. This work proposes bit-level sparsity quantization (BSQ) to tackle the mixed-precision quantization from a new angle of inducing bit-level sparsity.
  arXiv  Detail & Related papers  (2021-02-20T22:37:41Z)
• AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
  We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation. Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
  arXiv  Detail & Related papers  (2020-07-14T09:07:29Z)
• VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization [19.66522714831141]
  We develop a new quantization solution called VecQ, which can guarantee minimal direct quantization loss and better model accuracy. In addition, in order to up the proposed quantization process during training, we accelerate the quantization process with a parameterized estimation and probability-based calculation.
  arXiv  Detail & Related papers  (2020-05-18T07:38:44Z)

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.