Fix 0-d tensors, dynamic output sizes and integer reductions, and default to float32 on CPU, in the OpenVINO backend - #24377

Fix 0-d tensors, dynamic output sizes and integer reductions, and default to float32 on CPU, in the OpenVINO backend#24377

pytorchbot wants to merge 34 commits into

release/1.6pytorch/executorch:release/1.6from

cherry-pick-24294-by-pytorch_bot_bot_pytorch/executorch:cherry-pick-24294-by-pytorch_bot_bot_Copy head branch name to clipboard