Nixtla's Open Source Time Series Ecosystem.

Nixtla Community

Hi :slightly_smiling_face:,

I have testing Temporal Fusion Transformer in the package, but I tend to run out of cuda memory.
```OutOfMemoryError: CUDA out of memory.
```
Is there a parameter to limit that or any recommendations on how to avoid that?

Hi <@U05378ZMZ96>. In our experience TFT is highly memory intensive. You can limit the memory usage with `windows_batch_size` and `hidden_size`  parameters

You can also try to reduce the size of the autorregresive features through the `input_size`

Hey <@U05378ZMZ96>,

We fixed this week TFT's memory usage: <https://github.com/Nixtla/neuralforecast/pull/597>
We will merge that PR into main soon.

If you want to try the changes, you can install them with this line:
```!pip install git+<https://github.com/Nixtla/neuralforecast.git>```
