Quantization techniques are essential for the deployment of Large Language Models (LLMs) on edge devices. However, prevailing methods often rely on mixed-precision multiplication that lacks efficient hardware support, making it not feasible. Ternary weight quantization addresses this by constraining weights to {-1, 0, 1}, replacing expensive multiplications with hardware-efficient additions. However, such aggressive compression leads to significant accuracy degradation, even after costly quantization-aware training with massive data. We identify the core issue as deadzone trapping: a large number of weights are trapped at the deadzone boundary. This occurs because these weights receive only noisy, uninformative gradients, preventing stable escape from the deadzone and severely impeding model capacity and optimization. To address this issue, we propose Tequila, a trapping-free quantization optimization method that reactivates deadzone-trapped weights by repurposing them as dynamic biases. This allows the repurposed weights to provide a continuous signal in the forward pass and, critically, receive direct, meaningful gradient signals during backpropagation, thereby enhancing model capacity and optimization with nearly zero inference overhead. Extensive evaluations demonstrate that Tequila outperforms state-of-the-art (SOTA) ternary quantization methods across five benchmarks. Specifically, on the ARC benchmark, it achieves >4% accuracy gain over the SOTA baseline, nearly matching full-precision performance (within <1% gap) with a 3.0x inference speedup. Consequently, Tequila offers a highly practical and efficient implementation for the deployment of advanced LLMs in resource-constrained environments. The code is available at https://github.com/Tencent/AngelSlim.

翻译：量化技术对于在边缘设备上部署大语言模型至关重要。然而，现有方法通常依赖于缺乏高效硬件支持的混合精度乘法，导致实际部署困难。三元权重量化通过将权重约束为{-1, 0, 1}，用硬件高效的加法替代昂贵的乘法运算。然而，即使经过海量数据的高成本量化感知训练，这种激进压缩仍会导致显著的精度损失。我们发现其核心问题在于死区陷波现象：大量权重被困在死区边界。这是因为这些权重仅接收到噪声化、无信息的梯度，无法稳定逃离死区，严重限制了模型容量和优化效果。为解决该问题，我们提出Tequila——一种无陷波量化优化方法，通过将被困权重重新定义为动态偏置来激活死区陷波权重。这使得重构后的权重能在前向传播中提供连续信号，并关键地在反向传播期间接收直接有效的梯度信号，从而以近乎零的推理开销提升模型容量和优化效果。大量实验表明，Tequila在五项基准测试中均优于最先进的三元量化方法。具体而言，在ARC基准测试中，其准确率较最优基线提升超过4%，在实现3.0倍推理加速的同时，几乎达到全精度性能（差距<1%）。因此，Tequila为在资源受限环境中部署先进大语言模型提供了高度实用高效的解决方案。代码已开源：https://github.com/Tencent/AngelSlim。