torch-mlir/python/torch_mlir_e2e_test/torchscript
Sean Silva 075464fa74 Add a new `torch_mlir.compile` method.
This makes it much easier to convert models and hides all the
ClassAnnotator complexity.

This also adds a new example `torchscript_resnet18_all_output_types.py`
which shows the ResNet18 IR for all output types.

Also,

- This moves `run_pipeline_with_repro_report` to
  `torch_mlir.compiler_utils`.
2022-04-20 10:06:01 -07:00
..
configs Add a new `torch_mlir.compile` method. 2022-04-20 10:06:01 -07:00
CMakeLists.txt Move external/torch-mlir to the root of the repo. 2021-09-27 17:11:08 -07:00
__init__.py Move external/torch-mlir to the root of the repo. 2021-09-27 17:11:08 -07:00
annotations.py Centralize all test serialization logic. 2022-03-28 10:17:13 -07:00
framework.py Centralize all test serialization logic. 2022-03-28 10:17:13 -07:00
registry.py Dual license the torch-mlir project. 2021-10-01 10:46:08 -07:00
reporting.py Introduce new shape library design. 2022-03-15 12:41:58 -07:00
serialization.py Centralize all test serialization logic. 2022-03-28 10:17:13 -07:00