StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs

arXiv:2610.05977 · cs.LG, cs.CL · Submitted 2026-10-05 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-10-05

Updated: 2026-10-05

Comments: 17 pages, 4 figures, 8 tables

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

Terminology

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

Sources

• Phi-4 Technical Report
• BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models
• SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference
• SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• The Llama 3 Herd of Models
• SqueezeLLM: Dense-and-Sparse Quantization
• MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models
• Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs
• 2 OLMo 2 Furious
• Qwen3 Technical Report

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