Model-agnostic NPU+GPU+CPU inference engine for AMD Strix Halo. FastFlowLM reverse-engineered — 19 architectures, 46+ 1BP models, 5 backends. GGUF/ONNX/Q4NX/1BP. Zero Python. MIT.
-
Updated
Aug 10, 2026 - C++
Model-agnostic NPU+GPU+CPU inference engine for AMD Strix Halo. FastFlowLM reverse-engineered — 19 architectures, 46+ 1BP models, 5 backends. GGUF/ONNX/Q4NX/1BP. Zero Python. MIT.
All in one binary web server with embedded static files.
Add a description, image, and links to the one-binary topic page so that developers can more easily learn about it.
To associate your repository with the one-binary topic, visit your repo's landing page and select "manage topics."