You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/_functorch/_aot_autograd/jit_compile_runtime_wrappers.py", line 434, in aot_dispatch_autograd
compiled_fw_func = aot_config.fw_compiler(fw_module, adjusted_flat_args)
File "/home/trirpi/venv/lib/python3.10/site-packages/torch_mlir/dynamo.py", line 139, in wrapper_backend
user_callable = user_backend(gm, example_inputs)
File "/home/trirpi/torch-mlir/projects/pt1/examples/torchdynamo_resnet18.py", line 78, in refbackend_torchdynamo_backend
mlir_module = torchscript.compile(
File "/home/trirpi/venv/lib/python3.10/site-packages/torch_mlir/torchscript.py", line 350, in compile
scripted = torch.jit.script(model)
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/_script.py", line 1341, in script
return torch.jit._recursive.create_script_module(
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/_recursive.py", line 558, in create_script_module
return create_script_module_impl(nn_module, concrete_type, stubs_fn)
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/_recursive.py", line 571, in create_script_module_impl
method_stubs = stubs_fn(nn_module)
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/_recursive.py", line 894, in infer_methods_to_compile
stubs.append(make_stub_from_method(nn_module, method))
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/_recursive.py", line 87, in make_stub_from_method
return make_stub(func, method_name)
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/_recursive.py", line 71, in make_stub
ast = get_jit_def(func, name, self_name="RecursiveScriptModule")
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/frontend.py", line 372, in get_jit_def
return build_def(
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/frontend.py", line 422, in build_def
param_list = build_param_list(ctx, py_def.args, self_name, pdt_arg_types)
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/jit/frontend.py", line 448, in build_param_list
raise NotSupportedError(ctx_range, _vararg_kwarg_err)
torch._dynamo.exc.BackendCompilerFailed: backend='compiler_fn' raised:
NotSupportedError: Compiled functions can't take variable number of arguments or use keyword-only arguments with defaults:
File "/home/trirpi/venv/lib/python3.10/site-packages/torch/fx/_lazy_graph_module.py", line 112
def _lazy_forward(self, *args, **kwargs):
~~~~~~~ <--- HERE
As mentioned in Issue #3204, this uses unowned code (make_simple_dynamo_backend). However, this example is displayed very prominently in the Readme, so I think it should be fixed or removed from the readme.
The text was updated successfully, but these errors were encountered:
When executing the TorchScript ResNet18 example in the Readme, I get a
NotSupportedError
.To replicate, execute:
This is part of the stacktrace:
As mentioned in Issue #3204, this uses unowned code (
make_simple_dynamo_backend
). However, this example is displayed very prominently in the Readme, so I think it should be fixed or removed from the readme.The text was updated successfully, but these errors were encountered: