QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs

arXiv:2609.39223 · cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.LG

Submitted: 2026-09-30

Updated: 2026-10-01

Code: https://github.com/QATFactory/QATFactory

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Quantization-Aware Training — 1× in this paper · explained in 3 episodes

Sources

• Pretraining Large Language Models with NVFP4
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Low-Rank Quantization-Aware Training for LLMs
• The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
• Scaling Law for Quantization-Aware Training
• Miles v0.1: Production-Level Post-Training
• PACT: Parameterized Clipping Activation for Quantized Neural Networks
• Pretraining large language models with MXFP4 on Native FP4 Hardware
• Training Verifiers to Solve Math Word Problems
• Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention
• Learned Step Size Quantization
• Training with Quantization Noise for Extreme Model Compression
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Measuring Massive Multitask Language Understanding
• QKD: Quantization-aware Knowledge Distillation
• Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models
• Decoupled Weight Decay Regularization
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open 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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks