batch_encoding_wrapper

lightning_ir.base.model.batch_encoding_wrapper(func: BatchEncodingWrapper) BatchEncodingWrapper[source]

Decorator to enable sub-batching for models that support it. Lowers the batch size of the input batch encoding if the model runs out of memory.

Parameters:

func (BatchEncodingWrapper) – Function to wrap that takes a batch encoding.

Returns:

Wrapped function that handles sub-batching.

Return type:

BatchEncodingWrapper

Raises:
  • RuntimeError – If CUDA runs out of memory and the batch size cannot be lowered further.

  • ValueError – If no output was generated.