Ramiro Leal-Cavazos 3260a1ea6e Allow passing traced `torch.nn.Module`s into `torch_mlir.compile` (#1743) ... This commit adds support for passing to `torch_mlir.compile` the result of running `torch.jit.trace` on a model by relaxing the condition that checks if the model is already in JIT IR to allow any `torch.jit.ScriptModule`. Fixes https://github.com/llvm/torch-mlir/issues/1739		2022-12-22 08:39:55 -08:00
..
already_scripted.py	[torch_mlir.compile] Handle the case of already-scripted models better	2022-11-16 10:47:13 -08:00
already_traced.py	Allow passing traced `torch.nn.Module`s into `torch_mlir.compile` (#1743)	2022-12-22 08:39:55 -08:00
backend_legal_ops.py	torch_mlir.compile: allow custom backend_legal_ops set	2022-10-12 04:21:22 -07:00
basic.py	Update test to pass with newer versions of tanh (#990)	2022-06-28 20:28:13 -07:00
make_fx.py	Automatically strip overloads for FX-based models.	2022-11-29 22:19:09 -05:00
multiple_methods.py	[torch_mlir.compile] Handle the case of already-scripted models better	2022-11-16 10:47:13 -08:00
output_type_spec.py	torch_mlir.compile: Allow OutputType as a string.	2022-07-08 17:37:27 -07:00
tracing.py	[cleanup] Be consistent about apostrophe	2022-11-10 07:42:15 -08:00