Hansong Zhang

We will update the app in https://github.com/pytorch/torchchat/pull/1292

Hi @haowhsu-quic seems that you still need to rebase it.

Seems that we are very close. Just android ci. ``` 2025-04-29T17:48:52.5972976Z ld.lld: error: undefined symbol: __tls_get_addr 2025-04-29T17:48:52.5974053Z >>> referenced by thread_parallel.cpp:32 (/pytorch/executorch/extension/threadpool/thread_parallel.cpp:32) 2025-04-29T17:48:52.5975826Z >>> thread_parallel.cpp.o:(executorch::extension::get_thread_num()) in archive /pytorch/executorch/cmake-out-android-x86_64/lib/libextension_threadpool.a 2025-04-29T17:48:52.5977441Z >>>...

Thank you @DannyYuyang-quic !! Let's import and do another round of internal CI!

Track by https://github.com/pytorch/executorch/issues/8290

Already done 😄

When I make vulkan_backend static_lib, got ```U executorch::runtime::register_backend(executorch::runtime::Backend const&)``` That's good. It depends on ET runtime register_backend symbol. However, When I make vulkan_backend shared_lib, got ``` 00000000003a20ac T executorch::runtime::register_backend(executorch::runtime::Backend const&)...

I probably have some proof of concept, but refactor required. https://github.com/pytorch/executorch/compare/experiment-so?expand=1

Could you please paste full log? You can check something like ``` Command - /home/hsz/.conda/envs/executorch/bin/python;-m;codegen.tools.gen_oplist;--output_path=/home/hsz/e3/executorch/pip-out/temp.linux-x86_64-cpython-310/cmake-out/kernels/optimized/optimized_ops_lib/selected_operators.yaml;--ops_schema_yaml_path="/home/hsz/e3/executorch/kernels/optimized/optimized-oss.yaml" ``` I'm not sure why ops_schema_yaml_path is not valid

cc @dbort