Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations

• URL: http://arxiv.org/abs/2505.06653v1
• Date: Sat, 10 May 2025 14:00:15 GMT
• Title: Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
• Authors: Patrick Blumenberg, Thomas Graave, Tim Fingscheidt,
• Abstract summary: Large language models (LLMs) demand extensive memory capacity during both fine-tuning and inference.<n>Existing methods apply block-wise quantization techniques, such as NF4 and AF4, to the network weights.<n>We show that these quantization techniques incur suboptimal quantization errors.
• Score: 22.127873567034825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) demand extensive memory capacity during both fine-tuning and inference. To enable memory-efficient fine-tuning, existing methods apply block-wise quantization techniques, such as NF4 and AF4, to the network weights. We show that these quantization techniques incur suboptimal quantization errors. Therefore, as a first novelty, we propose an optimization approach for block-wise quantization. Using this method, we design a family of quantizers named 4-bit block-wise optimal float (BOF4), which consistently reduces the quantization error compared to both baseline methods. We provide both a theoretical and a data-driven solution for the optimization process and prove their practical equivalence. Secondly, we propose a modification to the employed normalization method based on the signed absolute block maximum (BOF4-S), enabling further reduction of the quantization error and empirically achieving less degradation in language modeling performance. Thirdly, we explore additional variations of block-wise quantization methods applied to LLMs through an experimental study on the importance of accurately representing zero and large-amplitude weights on the one hand, and optimization towards various error metrics on the other hand. Lastly, we introduce a mixed-precision quantization strategy dubbed outlier-preserving quantization (OPQ) to address the distributional mismatch induced by outlier weights in block-wise quantization. By storing outlier weights in 16-bit precision (OPQ) while applying BOF4-S, we achieve top performance among 4-bit block-wise quantization techniques w.r.t. perplexity.

Related papers

• Fine-tuning Quantized Neural Networks with Zeroth-order Optimization [18.645267970472936]
  Quantized Zeroth-order Optimization (QZO) is a novel approach that perturbs the continuous quantization scale for estimation and uses a directional derivative clipping method to stabilize training.<n>QZO can reduce the total memory cost by more than 18$times$ for 4-bit LLMs, and enables fine-tuning Llama-2-13B and Stable Diffusion 3.5 Large within a single 24GB GPU.
  arXiv  Detail & Related papers  (2025-05-19T17:55:15Z)
• 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.<n>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)
• Achieving binary weight and activation for LLMs using Post-Training Quantization [32.247768389896144]
  Quantizing large language models (LLMs) to 1-bit precision significantly reduces computational costs.<n>Existing quantization techniques suffer from noticeable performance degradation when using weight and activation precisions below 4 bits (W4A4)
  arXiv  Detail & Related papers  (2025-04-07T04:50:04Z)
• 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.<n>We propose an extremely low-bit PTQ method called PTQ1.61, which enables weight quantization to 1.61-bit for the first time.<n>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)
• BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference [8.136601122570347]
  Post-training quantization (PTQ) is a promising approach to reducing the storage and computational requirements of large language models (LLMs) without additional training cost.<n>Recent PTQ studies have primarily focused on quantizing only weights to sub-8-bits while maintaining activations at 8-bits or higher.
  arXiv  Detail & Related papers  (2025-02-07T23:06:03Z)
• 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.<n>We show that ternary, 2-bit, and 3-bit quantization maintains comparable performance in the size-accuracy trade-off.<n>Considering hardware constraints, 2-bit quantization offers promising potential for memory reduction and speedup.
  arXiv  Detail & Related papers  (2025-02-04T18:59:26Z)
• 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)
• AffineQuant: Affine Transformation Quantization for Large Language Models [58.45460102764]
  Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its compression efficiency and cost-effectiveness in the context of training. Existing PTQ methods for Large-scale Language Models (LLMs) limit the optimization scope to scaling transformations between pre- and post-quantization weights. In this paper, we advocate for the direct optimization using equivalent Affine transformations in PTQ (AffineQuant)
  arXiv  Detail & Related papers  (2024-03-19T08:40:21Z)
• 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)
• 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)
• NF4 Isn't Information Theoretically Optimal (and that's Good) [0.38073142980733]
  I show that this can't quite be the case, as the distribution of the values to be quantized depends on the block-size. I attempt to apply these insights to derive an improved code based on minimizing the expected L1 reconstruction error, rather than the quantile based method.
  arXiv  Detail & Related papers  (2023-06-12T08:52:14Z)

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.