paper-with-me

홈 › Papers

Recipes for Pre-training LLMs with MXFP8

2025-05-30 · Asit Mishra, Dusan Stosic, Simon Layton

Precision scaling - using fewer bits to represent model parameters and related tensors during pre-training - has emerged as a compelling technique for improving GPU efficiency without sacrificing accuracy. Microscaling (MX) formats in NVIDIA's latest Blackwell GPUs represent a major leap in enabling this precision scaling aspect. These formats combine narrow floating-point data types with per-block scaling factors, offering a fine-grained approach to quantizing tensors. Although MX-formats offer the promise of improved numeric stability compared to other reduced-precision representations, in practice they must be used carefully in order to successfully converge an LLM on a multi-trillion token dataset. In this paper, we show that the rounding mode suggested in OCP specification can lead to divergence when pre-training an LLM. We show an improved rounding mode, which uses round-to-infinity to compute scaling factors, enables successful pre-training in MXFP8 for an 8B model on 15T tokens.

📄 PDF Abstract BibTeX arXiv:2506.08027

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

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…

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…

Block Rotation is All You Need for MXFP4 Quantization

2025-11-06 · Yuantian Shao, Peisong Wang, Yuanteng Chen, Chang Xu 외 arxiv

Large language models (LLMs) have achieved remarkable success, but their rapidly growing scale imposes prohibitive costs in memory, computation, and energy. Post-training quantization (PTQ) is a promising solution for ef…

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

2026-01-30 · Jatin Chhugani, Geonhwa Jeong, Bor-Yiing Su, Yunjie Pan 외 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 …

BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization

2026-03-17 · Ji-Fu Li, Manyi Zhang, Xiaobo Xia, Han Bao 외 arxiv

Microscaling floating-point (MXFP) formats have emerged as a promising standard for deploying Multi-modal Large Language Models (MLLMs) and Large Language Models (LLMs) on modern accelerator architectures. However, exist…