E-PMQ：基于专家引导的合并后量化与合并权重锚定

摘要

低资源部署约束使模型量化成为在保持性能的同时部署神经网络的关键技术。与此同时，模型合并已成为一种日益实用的低资源策略，可将多个任务或领域专长的专家模型整合为单一模型，无需联合训练或多模型服务。量化与模型合并相结合，通过将多个专家模型集成到一个低位宽模型中，实现了高效的低资源部署流程。我们将这一设定定义为合并后量化（PMQ）。研究表明，直接对合并后的模型应用训练后量化（PTQ）并不可靠，因为两种不同的偏差会耦合：低位宽重建引入的量化偏差以及模型合并固有的专家相对合并偏差。为减轻这些偏差，我们提出E-PMQ，一种专家引导的PMQ框架。该框架利用源专家权重，在逐层校准过程中提供专家引导的输出目标，同时结合合并权重锚定来稳定校准过程，并保持合并模型的集成行为。在CLIP-ViT-B/32的八任务合并中，E-PMQ将任务算术下的4位GPTQ从65.0%提升至73.6%，将TIES-合并下的GPTQ从69.1%提升至74.8%。在更具挑战性的设定下，E-PMQ将CLIP-ViT-L/14二十任务合并的GPTQ从34.8%提升至76.7%，将FLAN-T5-base在GLUE上的GPTQ从78.26%提升至83.34%。这些结果表明，E-PMQ能够实现有效的合并后量化与低位宽部署。

English

Low-resource deployment constraints have made model quantization essential for deploying neural networks while preserving performance. Meanwhile, model merging has become an increasingly practical low-resource strategy for integrating multiple task- or domain-specialized experts into a single model without joint training or multi-model serving. Together, quantization and model merging enable an efficient low-resource deployment pipeline by integrating multiple experts into one low-bit model. We formulate this setting as Post-Merge Quantization (PMQ). We show that directly applying post-training quantization (PTQ) to a merged model is unreliable because two distinct deviations are coupled: the quantization deviation introduced by low-bit reconstruction and the expert-relative merging deviation inherited from model merging. To mitigate these deviations, we propose E-PMQ, an expert-guided PMQ framework that uses source expert weights to provide expert- guided output targets during layer-wise calibration, together with merged-weight anchoring to stabilize the calibration and preserve the integrated behavior of the merged model. On CLIP-ViT-B/32 eight-task merging, E-PMQ improves 4-bit GPTQ from 65.0% to 73.6% under Task Arithmetic and from 69.1% to 74.8% under TIES-Merging. On harder settings, E-PMQ improves GPTQ from 34.8% to 76.7% on 20-task CLIP-ViT-L/14 and from 78.26% to 83.34% on FLAN-T5- base GLUE. These results demonstrate that E-PMQ enables effective post-merge quantization and low-bit deployment.