paper-with-me

Papers

Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error Reduction

2026-01-30 · Jatin Chhugani, Geonhwa Jeong, Bor-Yiing Su, Yunjie Pan, Hanmei Yang, Aayush Ankit, Jiecao Yu, Summer Deng, Yunqing Chen, Nadathur Satish, Changkyu Kim arxiv

Large Language Models (LLMs) have intensified the need for low-precision formats that enable efficient, large-scale inference. The Open Compute Project (OCP) Microscaling (MX) standard is attractive due to its favorable hardware efficiency, but its 4-bit variant (MXFP4) lags behind NVIDIA's NVFP4 in accuracy, limiting adoption. We introduce two software-only techniques, Overflow-Aware Scaling (OAS) and Macro Block Scaling (MBS), that improve MXFP4 quantization fidelity without requiring hardware changes. OAS reduces overall errors by increasing effective dynamic range under power-of-two block scaling, while MBS allocates higher-precision scaling at a coarser granularity to better preserve outliers. Across multiple LLMs and standard downstream benchmarks, OAS and MBS reduce the end-to-end accuracy gap between MXFP4 and NVFP4 from about 10% to below 1% on average, while incurring modest GEMM overhead (6.2% on average). These results re-establish MXFP4 as a practical alternative to NVFP4, enabling near-NVFP4 accuracy while retaining MX's hardware-efficiency advantages (e.g., 12% relative area savings in tensor cores).

📄 PDF Abstract BibTeX arXiv:2603.08713

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats

2026-01-14 · Manyi Zhang, Ji-Fu Li, Zhongao Sun, Haoli Bai 외 arxiv

Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms being proposed, they mostly focus on intege…

AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference

2024-11-15 · Janghwan Lee, Jiwoong Park, Jinseok Kim, Yongjik Kim 외

Scaling Large Language Models (LLMs) with extended context lengths has increased the need for efficient low-bit quantization to manage their substantial computational demands. However, reducing precision to 4 bits freque…

QuantizationQuestion AnsweringVisual Question Answering

TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization

2026-05-19 · Zukang Xu, Xing Hu, Dawei Yang arxiv

As Large Language Models (LLMs) advance toward practical deployment, the Microscaling FP4 (MXFP4) format has emerged as a cornerstone for next-generation low-bit inference, owing to its ability to balance high dynamic ra…

MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models

2025-08-04 · Wenyuan Liu, Haoqian Meng, Yilun Luo, Yafei Zhao 외 arxiv

Quantization significantly accelerates inference in large language models (LLMs) by replacing original high-precision matrices with low-precision counterparts. Recent advances in weight-activation quantization have prima…

Mathematical ReasoningCode Generation

A Comprehensive Evaluation on Quantization Techniques for Large Language Models

2025-07-23 · Yutong Liu, Cairong Zhao, Guosheng Hu arxiv

For large language models (LLMs), post-training quantization (PTQ) can significantly reduce memory footprint and computational overhead. Model quantization is rapidly evolving. Though many papers report breakthrough resu…