WASI NN is a proposal that allows WebAssembly guest modules running outside the browser to perform neural network inferencing by using host-provided implementations that can leverage CPU multi-threading, host optimizations, or hardware devices such as GPUs or TPUs. This article explores the goals of WASI NN, existing implementations, and details a new experimental implementation targeting ONNX, the Open Neural Network Exchange , which allows the either usage of models built with PyTorch or Te...
