time-series-foundation-models / lag-llama

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Apache License 2.0
1.08k stars 121 forks source link

what do we need to set the device parameter when we use macos ? #53

Open hvacking opened 2 months ago

hvacking commented 2 months ago

It seems that it is not correct when we set from 'device = "cuda' to device = "cpu"?

ashok-arjun commented 2 months ago

I think it should be torch.device("mps")