mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-24 19:43:35 +00:00
b71ebf91a5
There are several global configs used by DORT.
```py
DEFAULT_ONNX_EXPORTER_OPTIONS = torch.onnx._internal.exporter.ResolvedExportOptions(
torch.onnx._internal.exporter.ExportOptions()
)
# TODO(wechi): This line must generate result identical to the call of
# _create_onnx_supports_op_overload_table(...) inside
# create_onnx_friendly_decomposition_table(...) in
# torch/onnx/_internal/fx/decomposition_table.py.
_SUPPORT_DICT = torch.onnx._internal.fx.decomposition_table._create_onnx_supports_op_overload_table(
DEFAULT_ONNX_EXPORTER_OPTIONS.onnx_registry
) # type: ignore
_EXTRA_SUPPORT_DICT: Dict[str, Any] = {
"getattr": None,
"_operator.getitem": None,
}
DORT_DECOMPOSITION_TABLE = DEFAULT_ONNX_EXPORTER_OPTIONS.decomposition_table
```
We can see all but `_EXTRA_SUPPORT_DICT` are extracted from deduced from
ONNX exporter's options. As there are many ways to configure ONNX
exporter's options, we decided to move these variables to `OrtBackend`'s
`__init__` so that the construction of `OrtBackend` becomes more
flexible (especially for enabling dynamic shape or not).
|
||
|---|---|---|
| .. | ||
| amp | ||
| api | ||
| experimental | ||
| onnxblock | ||
| optim | ||
| ort_triton | ||
| ortmodule | ||
| torchdynamo | ||
| utils | ||
| __init__.py | ||
| _checkpoint_storage.py | ||
| _utils.py | ||
| artifacts.py | ||
| checkpoint.py | ||
| model_desc_validation.py | ||
| orttrainer.py | ||
| orttrainer_options.py | ||
| postprocess.py | ||