Grid Games: The Power of Multiple Grids for Quantizing Large Language Models

• URL: http://arxiv.org/abs/2605.12327v1
• Date: Tue, 12 May 2026 16:09:02 GMT
• Title: Grid Games: The Power of Multiple Grids for Quantizing Large Language Models
• Abstract summary: A major recent advance in quantization is given by microscaled 4-bit formats such as NVFP4 and MXFP4, quantizing values into small groups sharing a scale.<n>We formalize the power-of-two-grids (PO2) problem, and provide theoretical results showing that practical small-group formats such as MXFP or NVFP can benefit significantly from PO2 grids.<n>Results for post-training quantization of standard open models and pre-training of Llama-like models show that adaptive grids consistently improve accuracy vs single-grid FP4 under both weight-only and weight+activation.
• Score: 50.885349461958384
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A major recent advance in quantization is given by microscaled 4-bit formats such as NVFP4 and MXFP4, quantizing values into small groups sharing a scale, assuming a fixed floating-point grid. In this paper, we study the following natural extension: assume that, for each group of values, we are free to select the "better" among two or more 4-bit grids marked by one or more bits in the scale value. We formalize the power-of-two-grids (PO2) problem, and provide theoretical results showing that practical small-group formats such as MXFP or NVFP can benefit significantly from PO2 grids, while the advantage vanishes for very large groups. On the practical side, we instantiate several grid families, including 1) PO2(NF4), which pairs the standard NF4 normal grid with a learned grid, 2) MPO2, a grid pair that is fully learned over real weights and activations, 3) PO2(Split87), an explicit-zero asymmetric grid and 4) SFP4, a TensorCore-implementable triple which pairs NVFP4 with two shifted variants. Results for post-training quantization of standard open models and pre-training of Llama-like models show that adaptive grids consistently improve accuracy vs single-grid FP4 under both weight-only and weight+activation. Source code is available at https://github.com/IST-DASLab/GridGames.

Related papers

• SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference [4.219937026460372]
  SharQ bridges activation sparsity and FP4 quantization through an online sparse--dense decomposition.<n>A sparse FP4 GEMM processes the backbone while a dense FP4 GEMM compensates for both mask-induced activation loss and sparse-path quantization error.
  arXiv  Detail & Related papers  (2026-06-25T04:19:04Z)
• DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization [47.19478866645546]
  We propose DuQuant++, which adapts the outlier-aware fine-grained rotation of DuQuant to the MXFP4 format.<n>Experiments on the LLaMA-3 family under MXFP4 W4A4 quantization show that DuQuant++ consistently achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-20T04:27:28Z)
• Adaptive Block-Scaled Data Types [7.634741713346681]
  NVFP4 suffers from its error distribution, resulting in large amounts of quantization error on near-maximal values.<n>We design new Adaptive Block-Scaled Data Types that can adapt to the distribution of their input values.<n> IF4 outperforms existing 4-bit block-scaled formats, achieving lower loss during quantized training and achieving higher accuracy on many tasks in post-training quantization.
  arXiv  Detail & Related papers  (2026-03-30T17:59:33Z)
• 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)
• Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling [13.357423392911036]
  We introduce Four Over Six (4/6), a modification to the NVFP4 quantization algorithm that evaluates two potential scale factors for each block of values.<n>We find that for some blocks, scaling to smaller FP4 values makes the distribution of representable values more uniform.<n>We also find that 4/6 can be easily incorporated into many different post-training quantization methods and generally improves downstream accuracy.
  arXiv  Detail & Related papers  (2025-12-01T18:59:45Z)
• 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)
• LLM-FP4: 4-Bit Floating-Point Quantized Transformers [38.23587031169402]
  We propose LLM-FP4 for quantizing both weights and activations in large language models (LLMs) down to 4-bit floating-point values. Compared to integer quantization, floating-point (FP) quantization is more flexible and can better handle long-tail or bell-shaped distributions. Our method, for the first time, can quantize both weights and activations in the LLaMA-13B to only 4-bit and achieves an average score of 63.1.
  arXiv  Detail & Related papers  (2023-10-25T17:59:32Z)
• QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models [57.04178959678024]
  We show that the majority of inference computations for large generative models can be performed with both weights and activations being cast to 4 bits. We achieve this via a hybrid quantization strategy called QUIK, which compresses most of the weights and activations to 4-bit. We provide GPU kernels matching the QUIK format with highly-efficient layer-wise runtimes, which lead to practical end-to-end throughput improvements of up to 3.4x.
  arXiv  Detail & Related papers  (2023-10-13T17:15:05Z)

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.