mirror of https://github.com/llvm/torch-mlir
075464fa74
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`. |
||
---|---|---|
.. | ||
__init__.py | ||
abc.py | ||
linalg_on_tensors.py |