arXiv AI June 15, 2026 By Hengjie Cao, Zhendong Huang, Mengyi Chen, Yifeng Yang, Fang Dong, Anrui Chen, Ruijun Huang, Xin Zhang, Mingzhi Dong, Yujiang Wang, Jinlong Hou, Qin Lv, Robert P. Dick, Yuan Cheng, Tun Lu, Fan Yang, Yixuan Chen, Li Shang

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

Read the original on arXiv AI →

arXiv:2603. 10444v2 Announce Type: replace-cross Abstract: FP4 training promises substantial memory and compute savings for large language models, but remains fragile because blockwise quantization is dictated by extreme activation magnitudes, which inflate dynamic range and compress long-tail signals.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 2

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

arXiv:2601. 22813v2 Announce Type: replace Abstract: The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs.

By Andrei Panferov, Erik Schultheis, Soroush Tabesh, Dan Alistarh

llms efficiency

arXiv AI

Aug 11

Attn-QAT: 4-Bit Attention With Quantization-Aware Training

arXiv:2603. 00040v3 Announce Type: replace-cross Abstract: Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic range and attention's heavy-tailed activations.

By Peiyuan Zhang, Matthew Noto, Wenxuan Tan, Chengquan Jiang, Will Lin, Wei Zhou, Hao Zhang

llms diffusion efficiency

arXiv Machine Learning

Jun 16

MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization

arXiv:2606. 15652v1 Announce Type: new Abstract: 4-bit quantization significantly reduces the memory footprint and accelerates the inference of large language models (LLMs).

By Yangjia Hu, Haodong Wang, Zicong Hong, Qianli Liu, Quanxin Shou, Jian Lin, Song Guo, Xiaowei Shen, Xiangjun Huang, Dian Wang, Jian Yang

llms efficiency

arXiv AI

Jul 29

Stable FP4 Training via Transposition-Invariant Block Quantization

arXiv:2607. 24953v1 Announce Type: cross Abstract: Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization.

By Mehdi Rahimifar, Amin Darabi, Mehran Taghian Jazi, Xing Huang, Yao Wang, Zhijun Tu, Yufei Cui, Yunke Peng, Hongliang Li

llms efficiency

arXiv AI

Jun 26

SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference

arXiv:2606. 26587v1 Announce Type: cross Abstract: Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging: activations contain input-dependent outliers that dominate block scales in FP4 quantization, and directly applying N:M sparsity masks discards moderate values, coupling sparsification loss with quantization error.

By Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Huaqing Zheng, Xindian Ma, Peng Zhang

llms diffusion efficiency multimodal

arXiv AI

Jun 4

QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy

arXiv:2606. 04620v1 Announce Type: cross Abstract: LLMs have become the state-of-the-art algorithms for solving NLP tasks.

By Pasindu Wickramasinghe, Achyuta Muthuvelan, Rachmad Vidya Wicaksana Putra, Minghao Shao, Muhammad Shafique

llms nlp efficiency benchmarks

Related stories

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

Attn-QAT: 4-Bit Attention With Quantization-Aware Training

MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization

Stable FP4 Training via Transposition-Invariant Block Quantization

SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference

QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy