https://github.com/tracel-ai/burn-onnx
I maintain this project at the moment.
It convert ONNX models into native, backend-agnostic Burn code for inference and fine-tuning.
Have used it with wasm and it's lovely, but I was kindof disappointed to learn internally it's basically another serialisation format. I imagined gigabytes of generated Rust code hehe
Have used it with wasm and it's lovely, but I was kindof disappointed to learn internally it's basically another serialisation format. I imagined gigabytes of generated Rust code hehe