AI 中文总结
SchurQuant结合SCHUROPT与多种技术，在8个Llama和Qwen模型的2位量化任务中，使无反向传播PTQ的平均零样本精度比最强基线高9.65pp，提升了2位大语言模型量化的精度。
AI 中文摘要
仅权值的后训练量化（PTQ）可让大语言模型在严格内存预算下部署，但在2-3位时精度常崩溃。现有无反向传播的PTQ优化器有两个局限：分组决策忽略了剩余连续后缀可吸收的校正量，离散细化通常保持仿数量化网格固定。我们提出SCHUROPT，它可解析消除后缀的最优连续响应，产生具有舒尔补曲率的精确分组二次型，随后交替进行闭式行尺度/零点重拟合与整数码的坐标下降。在固定GPTQ目标下，SCHUROPT使2位Qwen3-4B的平均零样本精度提升11.88个百分点（pp）。然而在更高精度下，更紧密的重构并不总能提升最终模型指标。因此SCHURQUANT将SCHUROPT与量化前缀教师重构、参考权值正则化、残差加目标及教师决策令牌加权相结合。在8个Llama和Qwen模型上，SCHURQUANT在评估的无反向传播PTQ基线中达到最高平均零样本精度，在2位时比最强基线高出9.65个百分点（pp）。
英文摘要
Weight-only post-training quantization (PTQ) enables the deployment of large language models under tight memory budgets, but accuracy often collapses at 2-3 bits. Existing backpropagation-free PTQ optimizers have two limitations: group decisions ignore the correction that the remaining continuous suffix can absorb, and discrete refinements typically keep the affine quantization grid fixed. We introduce SCHUROPT, which analytically eliminates the suffix's optimal continuous response, yielding an exact groupwise quadratic with Schur-complement curvature. It then alternates closed-form row-wise scale/zero-point refitting with coordinate descent over integer codes. With the GPTQ objective fixed, SCHUROPT improves mean zero-shot accuracy on 2-bit Qwen3-4B by 11.88 percentage points (pp). At higher precision, however, tighter reconstruction does not consistently improve end-model metrics. SCHURQUANT therefore combines SCHUROPT with quantized-prefix teacher reconstruction, reference-weight regularization, residual-add targets, and teacher-decision token weighting. Across eight Llama and Qwen models, SCHURQUANT achieves the highest mean zero-shot accuracy among the evaluated backpropagation free PTQ baselines, outperforming the strongest baseline by 9.65 pp at 2 bits.
Comments14 pages, 6 tables
