sudongwang-upc

> When sampling, we require that we generate `self.model.num_parallel_samples` at every sampling iteration. Hence, we repeat all the tensors that many times. Thank you for your response to this issue....

> So, in all decoder-only models, the "predict" part actually makes no sense during training, as all the points are used for the loss. Note that this is for all...

https://github.com/time-series-foundation-models/lag-llama/blob/7454088166d02cb49d3d364a56c8379ac60325f5/lag_llama/gluon/lightning_module.py#L229-L261

> Hi @srggrs, currently this is not possible out of the box: Chronos models only makes predictions based on historical data of the target series. This is definitely something to...