1
LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
LLM极低比特量化新突破，线性约束向量量化实现2比特数据高效训练，已被ICML 2026收录。
arXiv:2606.10531v1 Announce Type: cross Abstract: Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs). C…