mirror of https://github.com/llvm/torch-mlir
074f112d6a
We can route the torch tests via `onnx` using the `torch.onnx.export` tooling. We can then reimport, lower to torch, and compile to linalg to validate the onnx path is working correctly. The current implementation exposes some failures in the `onnx` path so we cannot enable the onnx test suite yet due to segmentation faults. |
||
|---|---|---|
| .. | ||
| ci | ||
| cmake | ||
| docker | ||
| python_deploy | ||
| autogen_ltc_backend.py | ||
| autogen_ltc_backend.yaml | ||
| build_libtorch.sh | ||
| build_python_wheels.sh | ||
| build_standalone.sh | ||
| scrape_releases.py | ||
| update_abstract_interp_lib.sh | ||
| update_torch_ods.sh | ||
| write_env_file.sh | ||