onnxruntime and onnx2c
These are ecosystem siblings where one is a widely-adopted runtime for executing ONNX models across platforms, while the other is a specialized compiler that transpiles ONNX models to C code for embedded or resource-constrained deployment scenarios where a full runtime is impractical.
About onnxruntime
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Supports inference across diverse ML frameworks (PyTorch, TensorFlow, scikit-learn, XGBoost, LightGBM) through the ONNX standard, applying graph optimizations and hardware acceleration (CPUs, GPUs, NPUs) for optimal performance. Training acceleration targets PyTorch transformer models on multi-GPU setups with minimal code changes. Operates as a portable runtime layer abstracting hardware and framework differences across Windows, Linux, and macOS.
About onnx2c
kraiskil/onnx2c
Open Neural Network Exchange to C compiler.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work