problem running code
vivian@vivian-Z390-UD:/test$ python phi4-mm.py -m gpu/gpu-int4-rtn-block-32 -e cuda/test$
Loading model...
Setting model to cuda...
Model loaded
Image Path (comma separated; leave empty if no image):
Audio Path (comma separated; leave empty if no audio):
No image provided
No audio provided
Prompt: hi
Processing inputs...
/opt/rh/gcc-toolset-12/root/usr/include/c++/12/string_view:239: constexpr const std::basic_string_view<_CharT, _Traits>::value_type& std::basic_string_view<_CharT, _Traits>::operator const [with _CharT = char32_t; _Traits = std::char_traits; const_reference = const char32_t&; size_type = long unsigned int]: Assertion '__pos < this->_M_len' failed.
Aborted (core dumped)
vivian@vivian-Z390-UD:
problem running code i'm getting this error and i don't understand why
This issue has been resolved in the lates main branch of the repo: https://github.com/microsoft/onnxruntime-genai. A new package will be published soon with the fix.