HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression
Abstract
Post-training quantization is essential for deploying Large Language Models (LLMs) on resource-constrained devices. However, standard integer quantization (e.g., INT4) fundamentally degrades performance by imposing a uniform grid on the heavy-tailed distribution of weight parameters, particularly in smaller-scale models (e.g.,
Fields of Study & Subjects
Advanced Neural Network Applications
Topic Modeling
Advanced Data Compression Techniques
Publication details
- Journal / source
- arXiv (Cornell University)
- Publication date
- 11 January 2026
- Document type
- Preprint