Medical Vision-and-Language Pre-training (MedVLP), which learns generic vision-language representations from medical images and texts to benefit various downstream medical tasks, has drawn remarkable attention in both artificial intelligence and clinical medicine. However, existing works ignore the privacy issues and the heavy computation burden in MedVLP. In this study, we propose a FedMedVLP model, which adopts federated learning to unify the datasets from different clients, e.g., centers and hospitals, to form a large-scale pre-training dataset. As a result, the unified large-scale pre-training dataset can be used to pre-train the MedVLP to achieve strong performance. Overall, our FedMedVLP can improve the performance of MedVLP while preventing data leakage. Extensive experiments prove that the proposed model sets new state-of-the-art results on five benchmark datasets across three medical mainstream tasks, i.e., medical image–text retrieval, medical text-image retrieval, and medical visual question answering tasks. Besides, we further evaluate our method on our curated well-balanced medical dataset COVID-Fed.