onnxruntime and onnxconverter-common
These are complements: onnxconverter-common provides shared conversion utilities that multiple ONNX converters depend on to transform models into ONNX format, which ONNX Runtime then executes across platforms.
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 onnxconverter-common
microsoft/onnxconverter-common
Common utilities for ONNX converters
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work