This message was deleted.

Hey @Afiq Johari I think some of the bottle neck can be traced back to these forecast parsing functions: • https://github.com/Nixtla/neuralforecast/blob/main/neuralforecast/core.py#L41 • https://github.com/Nixtla/neuralforecast/blob/main/neuralforecast/core.py#L80 • https://github.com/Nixtla/neuralforecast/blob/main/neuralforecast/core.py#L102 We would need to confirm the bottleneck. My intuition is to that vectorizing the functions can improve the speed.