Fix 0-d tensors, dynamic output sizes and integer reductions, and default to float32 on CPU, in the OpenVINO backend - #24294

Fix 0-d tensors, dynamic output sizes and integer reductions, and default to float32 on CPU, in the OpenVINO backend#24294

shoumikhin merged 21 commits into

pytorch:mainpytorch/executorch:mainfrom

shoumikhin:openvino-precision-and-scalarsshoumikhin/executorch:openvino-precision-and-scalarsCopy head branch name to clipboard