RuntimeError: Unable to find data type for weight_name='/model/layers.0/self_attn/k_proj/MatMul_output_0'

[dongwonmoon]

optimum-cli onnxruntime quantize --avx512 --onnx_model llama-3.2-3b-instruct-
qa-onnx -o quantized_llama-3.2-3b-instruct-qa-onnx

Traceback (most recent call last):
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\Scripts\optimum-cli.exe\__main__.py", line 7, in <module>
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\site-packages\optimum\commands\optimum_cli.py", line 208, in main
    service.run()
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\site-packages\optimum\onnxruntime\subpackage\commands\quantize.py", line 105, in run
    q.quantize(
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\site-packages\optimum\onnxruntime\quantization.py", line 403, in quantize
    quantizer.quantize_model()
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\site-packages\onnxruntime\quantization\onnx_quantizer.py", line 211, in quantize_model
    op_quantizer.quantize()
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\site-packages\onnxruntime\quantization\operators\matmul.py", line 78, in quantize
    otype = self.quantizer.get_tensor_type(node.output[0], mandatory=True)     
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\site-packages\onnxruntime\quantization\onnx_quantizer.py", line 271, in get_tensor_type
    return self._get_default_tensor_type(tensor_name)
  File "C:\Users\MoonDongWon\anaconda3\envs\rl_trader\lib\site-packages\onnxruntime\quantization\onnx_quantizer.py", line 250, in _get_default_tensor_type    
    raise RuntimeError(
RuntimeError: Unable to find data type for weight_name='/model/layers.0/self_attn/k_proj/MatMul_output_0'. shape_inference failed to return a type probably this node is from a different domain or using an input produced by such an operator. This may happen if you quantize a model already quantized. You may use extra_options `DefaultTensorType` to indicate the default weight type, usually `onnx.TensorProto.FLOAT`.

[dongwonmoon]

read error message 😅😅😅