Abstract: To address the complexity of multi-warehouse replenishment decision-making and the difficulty of balancing inventory cost and service levels in distributed warehousing systems for medical consumables, a collaborative inventory optimization method for multi-warehouse replenishment is proposed. To this end, an inventory optimization model is developed to minimize inventory holding, shortage, and transportation costs, while incorporating practical operational constraints such as product shelf life, batch management, transportation mode selection, and replenishment quantity limits. Furthermore, a two-stage hybrid algorithm integrating particle swarm optimization (PSO) and simulated annealing (SA) is proposed. On this basis, global search is first performed to obtain high-quality initial solutions. Then, the probabilistic jumping mechanism of SA is introduced to escape local optima, enabling coordinated optimization of multi-period replenishment quantities and transportation schemes. A rolling horizon mechanism is further incorporated to dynamically generate replenishment plans for the next four periods, thereby improving the adaptability of replenishment decisions. Case study results show that, compared with the enterprise′s current replenishment strategy, the proposed optimization scheme reduces the total operating cost by approximately 39.23%, including reductions of 38.60% in inventory holding cost, 62.31% in transportation cost, and 39.43% in shortage cost. The results also demonstrate that the proposed method can effectively support replenishment decision-making in multi-warehouse environments and provide practical decision support for inventory optimization in medical consumables supply chains.