inference using onnx - Githubissues

guillaume-be / rust-bert

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

https://docs.rs/crate/rust-bert

Apache License 2.0

2.67k stars 217 forks source link

inference using onnx #472

Open yaniv5678 opened 1 month ago

yaniv5678 commented 1 month ago

Hi, Is it possible to compile rust-bert without libtorch, but just with onnxruntime support? We do not want to rely on libtorch if it isn't needed (huge library size, cumbersome compilation process) Thanks :)