@szhengac after having merged #1080, the problem should be solved if you set the following at the beginning of your jobs

@szhengac after having merged #1080, the problem should be solved if you set the following at the beginning of your jobs

import multiprocessing
multiprocessing.set_start_method("spawn", force=True)

Could you verify that?

Originally posted by @lostella in https://github.com/awslabs/gluon-ts/issues/1054#issuecomment-706161305