The Harlinn.AI library delivers a high performance API for implementing AI workloads on the Windows platform on top of DirectML.

Yolo v9

Yolo 9 Object Detection app based on Harlinn.AI.

Harlinn.AI DirectML (DML)

The DirectML wrappers are a key component of Harlinn.AI, providing an API on top of the DirectML API, facilitating faster, cleaner, and safer, C++ DirectML development. more…

Harlinn.AI DirectML eXtensions (DML.X)

Harlinn.AI DirectML eXtensions (DML.X) is a C++ header-only helper library for the DirectML wrappers, intended to make it easier to compose DirectML operators into graphs that can be compiled into a CompiledOperator using the Device1::CompileGraph function. more…

Harlinn.AI.ONNX.DirectML

Harlinn.AI.ONNX.DirectML executes an AI workload asynchronously using DirectML. Currently a successful experiment, demonstrating how the ONNX runtime, with the DirectML Execution Provider, can be used to to run inference on the GPU while, at the same time, rendering a video smoothly on the same GPU. more…