onnxruntime
44fd98eb - [DORT] Enable aten::full by implementing extra logics to select EP (#16699)

Commit
2 years ago
[DORT] Enable aten::full by implementing extra logics to select EP (#16699) DORT only select devices from inputs arguments' (type: torch.Tensor). However, it errors out when a graph doesn't have any inputs (e.g., a single aten::full graph). This PR address this problem by changing the EP selection to - First, inspect graph inputs. If there are some valid devices, use them plus a default one (`OrtBackend.ep: str`). - Otherwise, inspect graph outputs carried by `torch.fx.GraphModule` and use all valid devices plus the default `OrtBackend.ep`. - When both (1) and (2) fail, it uses the default EP specified by `OrtBackend.ep`.
Author
Parents
Loading