MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations
cs.LG
Submitted: 2026-11-07
Updated: 2026-11-11
Code: https://github.com/huawei-csl/MACaQ
Terminology
Sources
- QuantEase: Optimization-based Quantization for Language Models
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- The Llama 3 Herd of Models
- GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
- DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization
- SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
- Qwen3.5-Omni Technical Report
- Microscaling Data Formats for Deep Learning
- Block Rotation is All You Need for MXFP4 Quantization
- Qwen3 Technical Report
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis