google-research/timesfm

Best practice for deploying TimesFM on SageMaker

Opened this issue ยท 1 comments

๐Ÿ‘‹ What are the best practices for running TimesFM on Amazon SageMaker, considering the dynamic nature of horizon_len. Can the model be loaded and initialized first, so I can specify the horizon_len parameter at inference/forecast time?

I think its best to set the horizon_len to the maximum of what you would need at init. This way it will be jitted and all subsequent forecasts would be very fast.