Aaron Rizzuto

I have a general question about how to handle training where some of the covariates are themselves forecasts. I am building a TFT model where the decoder part of each...

[BUG] Temporal Fusion Transformer trained on GPU then loaded on CPU does not propagate map_location into the loss metrics as expected

17

**Describe the bug** I have trained a TFT on a machine with several GPU's. When loading the model on a smaller CPU-only machine as with: ``` model = TemporalFusionTransformer.load_from_checkpoint(model_file, map_location=torch.device('cpu'))...

[BUG] TimeseriesDataset _set_target_normalizer no longer functions as expected for a setter function.

6

**Describe the bug** Latest release has breaking changes for people building extensions to TimeseriesDataset. Because one of the internal setting fuctions no longer behaves as would be expeceted. The function...

Path issues when running multiple solves at the same time with COIN-OR CBC

3

## Summary I'm running a series of sequential MIP solves with COIN-OR CBC. The process runs a solution and then uses the solution as input to a new problem. This...

### What happened + What you expected to happen installing an environment with mlforecast = {extras=["dask"], version="*"} does not install all required dependencies. An extra line is required: dask =...