QuantForge: Discovering Residual Decompositions for MXFP4 Post-Training Quantization

arXiv:2609.34680 · cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Quantization — 1× in this paper · explained in 12 episodes

Sources

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• The Llama 3 Herd of Models
• OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining
• CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• Microscaling Data Formats for Deep Learning
• GLU Variants Improve Transformer
• TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization
• FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks