[AIR] Enable GPU prediction #25111
Labels
enhancement
Request for new feature and/or capability
P1
Issue that should be fixed within a few weeks
Milestone
Description
Predictors for neural network inference (TorchPredictor, TFPredictor) can often leverage GPUs for inference (either offline or online).
Currently our deep learning predictors do not provide the ability to move the model to a GPU device for prediction.
Use case
GPU inference with AIR predictors.
The text was updated successfully, but these errors were encountered: