Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/development.md
Original file line number Diff line number Diff line change
Expand Up @@ -507,8 +507,8 @@ The following assumes you are in the `projects/pt1` directory:
./tools/e2e_test.sh
# Run tests that match the regex `Conv2d`, with verbose errors.
./tools/e2e_test.sh --filter Conv2d --verbose
# Run tests on the TOSA backend.
./tools/e2e_test.sh --config tosa
# Run tests on the TOSA backend via fx_importer path
./tools/e2e_test.sh --config fx_importer_tosa
```

Alternatively, you can run the tests via Python directly:
Expand Down
8 changes: 4 additions & 4 deletions projects/pt1/e2e_testing/main.py
Original file line number Diff line number Diff line change
Expand Up @@ -86,12 +86,12 @@ def _get_argparse():
"-c",
"--config",
choices=config_choices,
default="linalg",
default="fx_importer",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ideally, this should have been named fx_importer_linalg to make it consistent with fx_importer_tosa and stablehlo. Will it be very invasive?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

AFAIK, tosa/stablehlo paths were introduced after the linalg backend path. So that's probably why the names are the way they are currently. I think changing fx_importer to fx_importer_linalg may cause issues for downstream users.

help=f"""
Meaning of options:
"linalg": run through torch-mlir"s default Linalg-on-Tensors backend.
"tosa": run through torch-mlir"s default TOSA backend.
"stablehlo": run through torch-mlir"s default Stablehlo backend.
"linalg": run the model through JIT importer frontend with torchscript (deprecated) and execute the graph using Linalg-on-Tensors backend.
"tosa": run the model through JIT importer frontend with torchscript (deprecated) and execute the graph using TOSA backend.
"stablehlo": run the model through JIT importer frontend with torchscript (deprecated) and execute the graph using Stablehlo backend.
"native_torch": run the torch.nn.Module as-is without compiling (useful for verifying model is deterministic; ALL tests should pass in this configuration).
"torchscript": compile the model to a torch.jit.ScriptModule, and then run that as-is (useful for verifying TorchScript is modeling the program correctly).
"lazy_tensor_core": run the model through the Lazy Tensor Core frontend and execute the traced graph.
Expand Down
Loading