Justin Chu

An import error seen: https://github.com/microsoft/onnxruntime/actions/runs/7547312086/job/20546973767?pr=19156#step:5:12

The error persists in 1.15.1: `onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Type Error: Type (seq(tensor(float16))) of output arg (output0) of node () does not match expected type (seq(tensor(float))).`

### Summary ORT raises `[ONNXRuntimeError] : 1 : FAIL : Type Error: Type (seq(tensor(float16))) of output arg (_val_1) of node (_0x79a4c20_n23) does not match expected type (seq(tensor(float))).` when executing test...

@MaanavD we prob should keep any ort issues tagged with "dynamo" open

This is an ORT issue. We can run the repro script again to validate with the latest version.

It is a torch exported model I experimented with.

[test_fx_to_onnx_with_onnxruntime.TestFxToOnnxWithOnnxRuntime_op_level_debug_True_dynamic_shapes_True.test_gpt2_tiny_from_config.zip](https://github.com/onnx/onnx-mlir/files/12544570/test_fx_to_onnx_with_onnxruntime.TestFxToOnnxWithOnnxRuntime_op_level_debug_True_dynamic_shapes_True.test_gpt2_tiny_from_config.zip) ``` (base) ➜ bin git:(main) ✗ ./onnx-mlir --EmitONNXIR /home/justinchu/dev/onnx-mlir/test_fx_to_onnx_with_onnxruntime.TestFxToOnnxWithOnnxRuntime_op_level_debug_True_dynamic_shapes_True.test_gpt2_tiny_from_config.onnx [1] 312747 segmentation fault (core dumped) ./onnx-mlir --EmitONNXIR (base) ➜ bin git:(main) ✗ ./onnx-mlir /home/justinchu/dev/onnx-mlir/test_fx_to_on nx_with_onnxruntime.TestFxToOnnxWithOnnxRuntime_op_level_debug_True_dynamic_shapes_True.test_gpt2_tiny_from_config.onnx [1] 312898 segmentation fault...

This is going to be the type of models created by the new PyTorch 2.1 so just heads up

#5433 #5348

An embedding op can be expressed as a function. Please feel free to reopen as needed.