Utilisation of Tensor core in training.

[ChataingT]

When using the subcommand train a log is displayed :

INFO:lightning.pytorch.utilities.rank_zero:You are using a CUDA device ('NVIDIA RTX 1000 Ada Generation Laptop GPU') that has Tensor Cores. To properly utilize them, you should set torch.set_float32_matmul_precision('medium' | 'high') which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision

For the moment, the model does not take into account the possiblity of Tensore core. Does the use of Tensor core have any impact in perfromance or precesion the use case of lisbet ?