UE5M3 FP4 Block Scaling for Stable Language Model Pretraining
cs.LG
Submitted: 2026-09-02
Updated: 2026-09-02
Code: https://github.com/MrHuff/ue5m3-fp4
Terminology
Sources
- QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
- TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
- Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
- Pretraining large language models with MXFP4 on Native FP4 Hardware
- Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
- Microscaling Data Formats for Deep Learning
- Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention
- Is Finer Better? The Limits of Microscaling Formats in Large Language Models
- Measuring Massive Multitask Language Understanding
- Elucidating the Design Space of FP4 training
- FP8 Formats for Deep Learning
- Pretraining Large Language Models with NVFP4
- Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
- Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
- Stable FP4 Training via Transposition-Invariant Block Quantization
- With Shared Microexponents, A Little Shifting Goes a Long Way
- HiFloat4 Format for Language Model Pre-training on Ascend NPUs
- Towards Efficient Pre-training: Exploring FP4 Precision in Large Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks