conversion inference

[riyajatar37003]

Hi ,
I am following this notebook to convert the model https://github.com/NVIDIA/NeMo/blob/main/tutorials/llm/embedding/llama_embedding_export_deploy.ipynb
but i am getting this error during forward pass of model .

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/opt/NeMo/nemo/export/onnx_llm_exporter.py", line 416, in forward
    output = self.onnx_runtime_session.run(self.model_output_names, prompt)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/tmp/.local/lib/python3.12/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 270, in run
    return self._sess.run(output_names, input_feed, run_options)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: run(): incompatible function arguments. The following argument types are supported:
    1. (self: onnxruntime.capi.onnxruntime_pybind11_state.InferenceSession, arg0: list[str], arg1: dict[str, object], arg2: onnxruntime.capi.onnxruntime_pybind11_state.RunOptions) -> list

Invoked with: <onnxruntime.capi.onnxruntime_pybind11_state.InferenceSession object at 0x7f87c4381b70>, ['embeddings'], {'input_ids': [[128000, 15339], [128000, 14957]], 'attention_mask': [[1, 1], [1, 1]], 'dimensions': [[2]]}, None```

i am using 25.02 ngc image of nemo.

[janekl]

Hi, the MR #13262 should address this. Please verify to close the issue if possible.