max fe8ac57e6d This PR implements an eager mode backend for PyTorch through the torch-mlir framework. This is accomplished by overriding the `__torch_dispatch__` class method on wrapper subclass `TorchMLIRTensor(torch.Tensor)`. ... Effectively, this mode works by compiling op by op as the NN is eagerly executed by PyTorch. Entailed in that compilation is building a representation of the op that can be `torch.jit.script`ed, importing using `ModuleBuilder`, and then executing (e.g., with `RefBackendLinalgOnTensorsBackend`). This mode includes a fallback to conventional PyTorch if anything in the torch-mlir compilation process fails (e.g., unsupported op). Currently, all e2e tests pass execpt for two that involve an upstream PyTorch bug (https://github.com/pytorch/pytorch/issues/74400). High priority next steps: 1. A compile cache in order to speed up reruns of the same NN. 2. Integration with IREE (though not in this repo). 3. Integration with `torch.distributed`.		2022-03-22 14:42:57 -07:00
..
linalg_on_tensors_backends	Bump LLVM at 8361c5da30588d3d4a48eae648f53be1feb5cfad	2022-03-18 13:16:14 -04:00
torchscript	This PR implements an eager mode backend for PyTorch through the torch-mlir framework. This is accomplished by overriding the `__torch_dispatch__` class method on wrapper subclass `TorchMLIRTensor(torch.Tensor)`.	2022-03-22 14:42:57 -07:00
tosa_backends	[tosa] Enable tosa-to-linalg-named so Matmul works again (#530)	2022-01-19 12:10:04 -08:00
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
utils.py	Include IR dump options on e2e failure report	2022-02-09 11:19:34 -05:00