migraphx

Efficient CPU/GPU ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet, ArtCNN and more!)

AMD's graph optimization engine.

Example on how to use pytorch/yolov8 object detection on computers with AMD integrated GPUs

AMD-first Linux AI video enhancer using C++, MiGraphX, ROCm, Vulkan and FFmpeg — with measured GPU optimizations submitted upstream to ROCm.

Efficient CPU/GPU ML Runtimes for VapourSynth (API 4)

Windows MIGraphX Libraries and Python Wheels with full CK, rocMILR and ONNXRUNTIME supports for ROCm7 supported AMD GPUs

Single-binary Rust embedding and reranking service (BGE-M3, bge-reranker-v2-m3) on the GPU that is present: DirectML, CUDA, MIGraphX or CPU as compile-time features.

Cross-stack GPU inference benchmark isolating compilation vs precision gains — CUDA/TensorRT vs ROCm/MIGraphX

ONNX Runtime acceleration via ROCm 7.1 and MIGraphX for AMD RDNA2 GPUs (RX 6600M).

Detailed documentation for MIGraphX from AMD

Pre-built ROCm/MIGraphX-accelerated ONNX Runtime native libraries for Linux x64 — AMD GPU inference for .NET without source builds