Pedestrian path prediction is an essential topic in computer vision and video\nunderstanding. Having insight into the movement of pedestrians is crucial for\nensuring safe operation in a variety of applications including autonomous\nvehicles, social robots, and environmental monitoring. Current works in this\narea utilize complex generative or recurrent methods to capture many possible\nfutures. However, despite the inherent real-time nature of predicting future\npaths, little work has been done to explore accurate and computationally\nefficient approaches for this task. To this end, we propose a convolutional\napproach for real-time pedestrian path prediction, CARPe. It utilizes a\nvariation of Graph Isomorphism Networks in combination with an agile\nconvolutional neural network design to form a fast and accurate path prediction\napproach. Notable results in both inference speed and prediction accuracy are\nachieved, improving FPS considerably in comparison to current state-of-the-art\nmethods while delivering competitive accuracy on well-known path prediction\ndatasets.\n