[MINOR] OMP compiled .so fails on macos-m1-stable

[mikekgfb]

This is running a back-level version of macos but may be supported by PyTorch? maybe treat it as PT improvement opportunity, not Torchchat launch blocker? (x-ref: https://github.com/pytorch/pytorch/issues/125856)

https://github.com/pytorch/torchchat/actions/runs/9006021620/job/24742618846?pr=723

ld: warning: -undefined dynamic_lookup may not work with chained fixups The generated DSO model can be found at: /Users/ec2-user/runner/_work/torchchat/torchchat/pytorch/torchchat/exportedModels/stories15M.so

• python3 torchchat.py generate stories15M --dso-path exportedModels/stories15M.so --prompt 'Hello my name is' OMP: Error #15: Initializing libomp.dylib, but found libomp.dylib already initialized. OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://openmp.llvm.org/ ./run-readme.sh: line 30: 32241 Abort trap: 6 python3 torchchat.py generate stories15M --dso-path exportedModels/stories15M.so --prompt "Hello my name is" Error: Process completed with exit code 1.