mirror of https://github.com/llvm/torch-mlir
fe9db78120
This PR adds support to `fx_importer.py` for handling custom ops that return an array of tensors. As long as the length of the array is consistent across runs (determined statically), then this patch will work. This does not require that the number of tensors returned is determined by the op's definition. CC @sjain-stanford |
||
|---|---|---|
| .. | ||
| _mlir_libs | ||
| dialects | ||
| extras | ||
| tools/import_onnx | ||
| compiler_utils.py | ||
| fx.py | ||