How to bundle libtorch with my rust binary?
I am developing an AI chat desktop application targeting Apple M chips. The app utilizes embedding models and reranker models, for which I chose Rust-Bert due to its capability to handle such models efficiently. Rust-Bert relies on tch, the Rust bindings for LibTorch.
To enhance the user experience, I want to bundle the LibTorch library, specifically for the MPS (Metal Performance Shaders) backend, with the application. This would prevent users from needing to install LibTorch separately, making the app more user-friendly.
However, I am having trouble locating precompiled binaries of LibTorch for the MPS backend that can be bundled directly into the application via the cargo build.rs file. I need help finding the appropriate binaries or an alternative solution to bundle the library with the app during the build process.
I have set the LD
export DYLD_LIBRARY_PATH=/opt/homebrew/Cellar/pytorch/2.2.0_10/lib:$DYLD_LIBRARY_PATH
but after compilation and running.
*[main][~/Programs/pyano/rust-backend]$ ./target/release/rust-backend
dyld[93114]: Symbol not found: __ZN2at4_ops10layer_norm4callERKNS_6TensorEN3c108ArrayRefINS5_6SymIntEEERKNS5_8optionalIS2_EESC_db
Referenced from: <1138FCDA-AB1A-3CC6-B540-4DE31C13A6CF> /Users/saurav/Programs/pyano/rust-backend/target/release/rust-backend
Expected in: <8F36AFD3-91CB-3828-BD48-4381DB5297F2> /opt/homebrew/Cellar/pytorch/2.2.0_10/libexec/lib/python3.12/site-packages/torch/lib/libtorch_cpu.dylib