MoE模型部署内存瓶颈的团队终于有了无需微调的压缩方案——ConMoE通过原型重分配直接减少专家数量，做模型推理优化的开发者可以试试这个即插即用的方法。
ConMoE提出了一种新的MoE模型压缩方法，通过原型重分配将原始专家映射到保留的少量原型专家上，无需权重更新或微调。该方法将压缩视为专家池整合，利用校准数据选择贡献大且可替换性高的专家作为原型，并支持跨层共享。在deepseek-moe-16b-base、Qwen3-30B-A3B和OLMoE-1B-7B-0125三个模型上，ConMoE在25%和50%专家缩减下均达到或超越现有剪枝与合并方法。实验表明确定性重分配是最稳定的组件，而跨层共享和权重融合效果依赖具体模型。这项工作为部署MoE模型提供了低成本的压缩方案。
ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression
Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intensive. Existing post-training compression methods mainly shrink this cost by pruning experts or merging their weights. We formulate post-training MoE compression as expert-pool consolidation: retaining a smaller set of pretrained experts as reusable prototypes and deterministically remapping each original expert reference to one selected prototype. This view separates the reduced expert pool from the reuse structure that represents the original expert slots, and allows prototype sharing within local layer scopes while preserving the original router interface. We propose ConMoE, a train-free prototype remapping framework that selects retained experts using calibration-based contribution and replaceability signals, then redirects original expert calls to the selected prototypes without weight updates or post-compression fine-tuning. Experiments on three pretrained MoE language models show that ConMoE matches or outperforms strong pruning and merging baselines in several settings, achieving the best average score on deepseek-moe-16b-base at both 25% and 50% routed-expert reduction, while remaining competitive on Qwen3-30B-A3B and OLMoE-1B-7B-0125. Ablations indicate that deterministic reassignment is the most stable component, whereas broader cross-layer sharing and post-hoc weight fusion are model-dependent.