FAAR: Format-Aware Adaptive Rounding for NVFP4

• URL: http://arxiv.org/abs/2603.22370v1
• Date: Mon, 23 Mar 2026 06:29:01 GMT
• Title: FAAR: Format-Aware Adaptive Rounding for NVFP4
• Abstract summary: Large language models (LLMs) on edge devices require extremely low-bit quantization.<n>Existing quantization methods fail to account for the non-uniformity of the NVFP4 numerical grid.<n>We propose Format-Aware Adaptive Rounding (FAAR), a learnable rounding strategy tailored for the NVFP4 format.
• Score: 10.642666144689787
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying large language models (LLMs) on edge devices requires extremely low-bit quantization. Ultra-low precision formats such as NVFP4 offer a promising solution for reducing memory footprint and accelerating computation. However, existing quantization methods typically rely on conventional rounding strategies and fail to account for the non-uniformity of the NVFP4 numerical grid, resulting in suboptimal rounding decisions and amplified quantization errors. To address this, we propose Format-Aware Adaptive Rounding (FAAR), a learnable rounding strategy tailored for the NVFP4 format. Unlike conventional quantization paradigms, FAAR explicitly incorporates the non-uniform NVFP4 grid into the optimization process. By adaptively adjusting rounding decisions guided by loss gradients, our method effectively approximates the theoretically optimal quantization. To complement FAAR, we introduce a 2-stages Format Alignment (2FA) fine-tuning scheme that aligns LLM parameters layer-by-layer to the NVFP4 numerical space, further narrowing the performance gap. Remarkably, this learnable optimization incurs a minimal training overhead of only 4 GPU hours on Llama3-1B. Extensive experiments demonstrate the effectiveness of our approach. Compared with Round-to-Nearest (RTN), our method reduces perplexity on WikiText-2 from 14.28 to 12.60 on Llama3-1B and from 23.06 to 21.27 on Qwen3-1.7B. Additionally, our method consistently outperforms state-of-the-art approaches across various zero-shot downstream tasks.

Related papers

• H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference [27.189669587707858]
  H-Scale is a lightweight post-processing method for NVFP4 per-group scale refinement.<n>It is designed as a drop-in replacement for RTN-style scale selection in diverse NVFP4 pipelines.<n> experiments show that H-Scale generally improves a broad range of NVFP4 baselines.
  arXiv  Detail & Related papers  (2026-08-28T09:22:17Z)
• 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)
• Convex Optimization for Alignment and Preference Learning on a Single GPU [52.997197698288936]
  Fine-tuning large language models to align with human preferences has driven the success of systems such as Gemini and ChatGPT.<n>Direct Preference Optimization (DPO) offers a simpler alternative but has limitations such as inconsistent ranking accuracy and high dependence on GPU resources.<n>We propose the Convex Optimization for Alignment and Preference Learning Algorithm (COALA), a novel lightweight strategy with strong theoretical guarantees.
  arXiv  Detail & Related papers  (2026-05-22T05:25:00Z)
• BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design [71.97035034203275]
  We analyze zero-point distortion in binarization and propose a Binary Weights & Ternary Activations (BWTA) quantization scheme.<n>For training, we propose Smooth Multi-Stage Quantization, combining a Levelwise Degradation Strategy and a MagnitudeAlignment Projection Factor.<n>Experiments show that BWTA approaches full-precision performance for Transformer-based models, with an average 3.5% drop on GLUE and less than 2% drop on five tasks.
  arXiv  Detail & Related papers  (2026-04-05T04:25:07Z)
• ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs [4.431548809730958]
  ARCQuant is a framework that boosts NVFP4 performance via Augmented Residual Channels.<n>We show that ARCQuant achieves state-of-the-art accuracy, comparable to full-precision baselines in perplexity and downstream tasks.
  arXiv  Detail & Related papers  (2026-01-12T12:27:22Z)
• INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats [51.72056104795248]
  Modern AI hardware, such as Nvidia's Blackwell architecture, is increasingly embracing low-precision floating-point (FP) formats.<n>This paper systematically investigates the trade-offs between FP and integer (INT) formats.<n>We reveal a critical performance crossover: while FP excels in coarse-grained quantization, the comparison at fine-grained (block-wise) levels is more nuanced.
  arXiv  Detail & Related papers  (2025-10-29T15:11:53Z)
• Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization [77.67818998672516]
  We present the first comprehensive study of MXFP4 and NVFP4 for post-training quantization.<n>We introduce Micro-Rotated-GPTQ (MR-GPTQ), a variant of the classic GPTQ quantization algorithm.<n>We show that MR-GPTQ matches or outperforms state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2025-09-27T09:22:21Z)
• FP4 All the Way: Fully Quantized Training of LLMs [26.195547788434908]
  We demonstrate fully quantized training (FQT) of large language models (LLMs) using predominantly 4-bit floating-point (FP4) precision.<n>We investigate key design choices for FP4, including block sizes, scaling formats, and rounding methods.
  arXiv  Detail & Related papers  (2025-05-25T12:14:25Z)
• 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)
• Progressive Mixed-Precision Decoding for Efficient LLM Inference [49.05448842542558]
  We introduce Progressive Mixed-Precision Decoding (PMPD) to address the memory-boundedness of decoding.<n>PMPD achieves 1.4$-$12.2$times$ speedup in matrix-vector multiplications over fp16 models.<n>Our approach delivers a throughput gain of 3.8$-$8.0$times$ over fp16 models and up to 1.54$times$ over uniform quantization approaches.
  arXiv  Detail & Related papers  (2024-10-17T11:46:33Z)
• 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)

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.