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

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

oneAPI Deep Neural Network Library (oneDNN)

Intel® Performance Counter Monitor (Intel® PCM)

A JIT assembler for x86/x64 architectures supporting MMX, SSE (1-4), AVX (1-2, 512), FPU, APX, and AVX10.2

Examples for using ONNX Runtime for machine learning inferencing.