use my own vela .ini to convert and face error

[kris-himax]

Hi,
I want to try the example model by my own vela.ini file,but face the following error.
my own vela.ini
python 3.10
executorch 1.0.1

(executorch_env_py_3_10_dev_251209) kris@kris-HP-ProBook-430-G7:~/Desktop/2025/1209_executorch_1_0/executorch$ python3 -m examples.arm.aot_arm_compiler --model_name=mv2 --target=ethos-u55-64 --delegate --quantize --config=himax_vela.ini --system_config=My_Sys_Cfg --memory_mode=My_Mem_Mode_Parent --output=mv2_quant.pte

Skipping import of cpp extensions due to incompatible torch version 2.9.1+cu128 for torchao version 0.14.0         Please see GitHub issue #2919 for more info
[WARNING 2025-12-10 10:02:04,240 aot_arm_compiler.py:98] Using a model from examples/models not all of these are currently supported
/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/backends/arm/quantizer/quantization_config.py:82: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.detach().clone() or sourceTensor.detach().clone().requires_grad_(True), rather than torch.tensor(sourceTensor).
  return torch.tensor(act_scale * weight_scale).to(
[WARNING 2025-12-10 10:02:54,389 to_tosa_memory_format_pass.py:284] Ignoring dim_order kwarg '[0, 1]' for 'dim_order_ops__clone_dim_order_default'.
Traceback (most recent call last):
  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home/kris/Desktop/2025/1209_executorch_1_0/executorch/examples/arm/aot_arm_compiler.py", line 859, in <module>
    model_int8, edge = to_edge_TOSA_delegate(
  File "/home/kris/Desktop/2025/1209_executorch_1_0/executorch/examples/arm/aot_arm_compiler.py", line 769, in to_edge_TOSA_delegate
    edge = to_edge_transform_and_lower(
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/exir/program/_program.py", line 114, in wrapper
    return func(*args, **kwargs)
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/exir/program/_program.py", line 1371, in to_edge_transform_and_lower
    edge_manager = edge_manager.to_backend(method_to_partitioner)
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/exir/program/_program.py", line 114, in wrapper
    return func(*args, **kwargs)
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/exir/program/_program.py", line 1672, in to_backend
    new_edge_programs = to_backend(method_to_programs_and_partitioners)
  File "/usr/lib/python3.10/functools.py", line 889, in wrapper
    return dispatch(args[0].__class__)(*args, **kw)
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/exir/backend/backend_api.py", line 762, in _
    lower_all_submodules_to_backend(
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/exir/backend/backend_api.py", line 591, in lower_all_submodules_to_backend
    backend_name_to_subclass[backend_id].preprocess_multimethod(
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/exir/backend/backend_details.py", line 129, in preprocess_multimethod
    preprocess_result = cls.preprocess(program, compile_spec_for_program)
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/backends/arm/ethosu/backend.py", line 81, in preprocess
    binary = EthosUBackend._compile_tosa_flatbuffer(
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/backends/arm/ethosu/backend.py", line 55, in _compile_tosa_flatbuffer
    binary = vela_compile(
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/executorch/backends/arm/arm_vela.py", line 70, in vela_compile
    vela.main(" ".join(args).split(" "))
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/ethosu/vela/vela.py", line 1266, in main
    process_regor(
  File "/home/kris/1_python_env/executorch_env_py_3_10_dev_251209/lib/python3.10/site-packages/ethosu/vela/vela.py", line 142, in process_regor
    compiled_model = regor.compile(accelerator, network, fmt, system_config, options=options, verbose=True)
IndexError: _Map_base::at

But without the config ini file, I can pass.

 python3 -m examples.arm.aot_arm_compiler --model_name=mv2 --target=ethos-u55-64 --delegate --quantize --output=mv2_quant.pte

cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai

[zingo]

Hi thanks for your report, there is an issue with the init parser have problem with spaces in the end of you lines, if I remove those I can run it. This has been fixed in vela 4.5.0 and it's on it's way into the project as #16075
until this it merged you can work around this by removing the extra spaces at the end of each line in your ini file. Sorry for the extra trouble!

[perheld]

@kris-himax If you are happy with changing the ini until vela 4.5.0 we could close the ticket?

[zingo]

And as this seem to be your first issue in a while welcome back to the Executorch project!
Please let us know if there is anything more we can help you with or you want to discuss on how to get this working in your projects, just open a ticket of if needed or we can setup some better channel.
There is for example a discord here https://discord.com/channels/1334270993966825602/1344814722150567997 that might also be good.

[kris-himax]

@perheld @zingo

Thank you. I can change the ini until vela 4.5.0.
We can close it.