Accelerate PyTorch models with ONNX Runtime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

llama/alpaca onnx models, quantization and testcase

Open standard for machine learning interoperability

Emscripten: An LLVM-to-WebAssembly Compiler

C++ Documentation

Introduction to Parallel Programming class code

resurrected LLVM "C Backend", with improvements

An open-source Python implementation using JIT techniques.