SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization

• URL: http://arxiv.org/abs/2605.12245v1
• Date: Tue, 12 May 2026 15:13:18 GMT
• Title: SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization
• Abstract summary: NVFP4 has recently emerged as an efficient 4-bit microscaling format for large language models.<n>Existing methods often yield suboptimal performance due to inflexible scale selection and the coupled treatment of quantization and dequantization scales.<n>We propose Scale Optimization for Accurate Reconstruction (SOAR), a novel post-training quantization framework that improves the accuracy of NVFP4 quantization.
• Score: 19.022444007775896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: NVFP4 has recently emerged as an efficient 4-bit microscaling format for large language models (LLMs), offering superior numerical fidelity with native hardware support. However, existing methods often yield suboptimal performance due to inflexible scale selection and the coupled treatment of quantization and dequantization scales. To address these issues, we propose Scale Optimization for Accurate Reconstruction (SOAR), a novel post-training quantization framework that improves the accuracy of NVFP4 quantization. At its core, SOAR features Closed-form Joint Scale Optimization (CJSO), which jointly optimizes global and block-wise scales via analytical solutions derived from reconstruction error minimization. Furthermore, it incorporates Decoupled Scale Search (DSS). DSS decouples the high-precision quantization scale from its constrained dequantization counterpart, and performs discrete search to mitigate precision loss from scale quantization. Extensive experiments across multiple LLMs show that our method consistently outperforms existing NVFP4 quantization baselines, achieving superior accuracy under the same memory footprint with no additional hardware overhead. The code and models will be available at https://github.com/steven-bao1/SOAR.

Related papers

• FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling [23.78963716646984]
  FOCUS is a post-training quantization framework with end-to-end scale learning for FP4 optimization.<n>It relaxes the tight coupling between quantization and dequantization scales with a learnable full-precision coefficient.<n>Experiments show that FOCUS achieves state-of-the-art FP4 accuracy under both MXFP4 and NVFP4 formats.
  arXiv  Detail & Related papers  (2026-08-03T07:54:56Z)
• Stable FP4 Training via Transposition-Invariant Block Quantization [14.373963304887754]
  In conventional 1D block quantization, forward and backward passes assign di erent scaling factors to the same values after transposition.<n>We propose a low-precision training framework based on 2D block FP4 quantization, which enforces transposition-invariant scaling and preserves consistency between forward and backward computations.<n>Our approach achieves stable end-to-end FP4 training and closely matches BF16 performance, with less than 1.3% degradation in perplexity and downstream accuracy.
  arXiv  Detail & Related papers  (2026-07-27T18:03:34Z)
• ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization [40.425536766574844]
  We propose ScaleSweep as a simple and efficient scale optimization method for NVFP4 quantization.<n> Experiments on Llama and Qwen models demonstrate that ScaleSweep consistently improves quantization performance.<n>In particular, under aggressive end-to-end quantization of weights, activations, KV cache, and query states, ScaleSweep preserves more than 93% of the full-precision performance.
  arXiv  Detail & Related papers  (2026-05-30T08:26:16Z)
• CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training [73.46600457802693]
  We introduce a new method that counteracts the loss induced by quantization.<n>CAGE significantly improves upon the state-of-theart methods in terms of accuracy, for similar computational cost.<n>For QAT pre-training of Llama models, CAGE matches the accuracy achieved at 4-bits (W4A4) with the prior best method.
  arXiv  Detail & Related papers  (2025-10-21T16:33:57Z)
• Beyond Outliers: A Study of Optimizers Under Quantization [82.75879062804955]
  We study impact of choice on model robustness under quantization.<n>We evaluate how model performance degrades when trained with different baselines.<n>We derive scaling laws for quantization-aware training under different parameters.
  arXiv  Detail & Related papers  (2025-09-27T21:15:22Z)
• 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)
• Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning [14.145862114439831]
  Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed.<n>Existing methods, primarily based on integer quantization and post-training quantization fine-tuning, struggle with inconsistent performance.<n>We propose a mixup-sign floating-point quantization framework, first introducing unsigned FP quantization in model quantization, along with timestep-aware LoRA and denoising-factor loss alignment.
  arXiv  Detail & Related papers  (2025-05-27T13:40:47Z)
• Efficient Fine-Tuning of Quantized Models via Adaptive Rank and Bitwidth [10.872650037112255]
  QLoRA effectively combines low-bit quantization and LoRA to achieve memory-friendly fine-tuning for large language models (LLM)<n>We propose textbfQR-Adaptor, a unified, gradient-free strategy that uses partial calibration data to jointly search the quantization components and the rank of low-rank spaces for each layer.<n>Our approach achieves a 4.89% accuracy improvement on GSM8K, and in some cases even outperforms the 16-bit fine-tuned model while maintaining the memory footprint of the 4-bit setting.
  arXiv  Detail & Related papers  (2025-05-02T08:46:01Z)
• Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics [64.62231094774211]
  Statefuls (e.g., Adam) maintain auxiliary information even 2x the model size in order to achieve optimal convergence.<n>SOLO enables Adam-styles to maintain quantized states with precision as low as 3 bits, or even 2 bits.<n>SOLO can thus be seamlessly applied to Adam-styles, leading to substantial memory savings with minimal accuracy loss.
  arXiv  Detail & Related papers  (2025-05-01T06:47:45Z)
• Optimizing Large Language Model Training Using FP4 Quantization [73.55459961002371]
  Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce costs.<n>This work introduces the first FP4 training framework for large language models (LLMs)
  arXiv  Detail & Related papers  (2025-01-28T18:04:50Z)
• GAQAT: gradient-adaptive quantization-aware training for domain generalization [54.31450550793485]
  We propose a novel Gradient-Adaptive Quantization-Aware Training (GAQAT) framework for DG.<n>Our approach begins by identifying the scale-gradient conflict problem in low-precision quantization.<n>Extensive experiments validate the effectiveness of the proposed GAQAT framework.
  arXiv  Detail & Related papers  (2024-12-07T06:07:21Z)
• AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference [6.699442219974261]
  AMXFP4 is a 4-bit asymmetric FP format that handles both issues using asymmetric shared scales.<n>AMXFP4 outperforms MXFP4 by 3% on VQA and exceeds rotation-based methods by 1.6% on CSQA.
  arXiv  Detail & Related papers  (2024-11-15T03:11:19Z)
• SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression [7.6131620435684875]
  SLIM is a new one-shot compression framework that holistically integrates hardware-friendly quantization, sparsity, and low-rank approximation.<n>SLIM improves model accuracy by up to 5.66% (LLaMA-2-7B) for 2:4 sparsity with 4-bit weight quantization, outperforming prior methods.
  arXiv  Detail & Related papers  (2024-10-12T18:36:07Z)
• 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)
• LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit [55.73370804397226]
  Quantization, a key compression technique, can effectively mitigate these demands by compressing and accelerating large language models. We present LLMC, a plug-and-play compression toolkit, to fairly and systematically explore the impact of quantization. Powered by this versatile toolkit, our benchmark covers three key aspects: calibration data, algorithms (three strategies), and data formats.
  arXiv  Detail & Related papers  (2024-05-09T11:49:05Z)

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.