The rapid growth of online services has led to the emergence of many with similar functionalities, making it necessary to predict their non-functional attributes, namely quality of service (QoS). Traditional QoS prediction approaches require users to upload their QoS data to the cloud for centralized training, leading to high user data upload latency. With the help of edge computing, users can upload data to edge servers (ESs) adjacent to them for training, reducing the upload latency. However, shallow models like matrix factorization (MF) are still used, which cannot sufficiently extract context features, resulting in low prediction accuracy. In this paper, we propose a context-aware edge-cloud collaboration framework for QoS prediction, named CQEC. Specially, to reduce the users upload latency, a distributed model training algorithm is designed with the collaboration of ESs and cloud. Furthermore, a context-aware prediction model based on convolutional neural network (CNN) and integrating attention mechanism is proposed to improve the performance. Experiments based on real-world dataset demonstrate that CQEC outperforms the baselines.