supports_precompiled_qnn_onnx error generating Genie-compatible QNN binaries for Lllama 3.1 8b chat quantized

[theoctopusride]

I followed the instructions in the README file here. This error didn't occur with either Llama 3-8b-chat or Llama 3.2 3b chat. The binaries were generated for both of those versions, but not for the Llama 3.1 8b chat quantized version.

After entering the following command, got the error pasted below

python3 -m qai_hub_models.models.llama_v3_1_8b_chat_quantized.export --device "Samsung Galaxy S24 (Family)" --skip-inferencing --skip-profiling --output-dir genie_bundle_llama-3.1-8b-chat-quantized

Error:

Traceback (most recent call last):
  File "/home/apps/miniconda3/envs/llm_on_genie/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/apps/miniconda3/envs/llm_on_genie/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home/apps/miniconda3/envs/llm_on_genie/lib/python3.10/site-packages/qai_hub_models/models/llama_v3_1_8b_chat_quantized/export.py", line 57, in <module>
    main()
  File "/home/apps/miniconda3/envs/llm_on_genie/lib/python3.10/site-packages/qai_hub_models/models/llama_v3_1_8b_chat_quantized/export.py", line 34, in main
    parser = export_parser(
TypeError: export_parser() got an unexpected keyword argument 'supports_precompiled_qnn_onnx'

Let me know if you need additional information.

[Ashish527test]

How were you able to build the binaries, I currently face lot of errors, can you help me with what documentation have you followed @theoctopusride