MLServer
MLServer copied to clipboard
Allow explanation of batched inputs for explaines that dont allow batch.
If an explainer (e.g. anchors) does not allow batched explanation, then we could in the runtime loop over each element in the batch and conduct explanation of each item.
This pattern is more generally considered also in SCv2 Pipeline so we should think carefully about whether this "loop" should be done: library (alibi), runtime (mlserver) or framework (scv2).