fastflowlm

NPU-first LLM runtime for AMD Ryzen AI (XDNA2) processors

FastFlowLM (FLM) is a lightweight LLM inference runtime purpose-built for AMD Ryzen AI NPUs (XDNA2 architecture). It provides an Ollama-style CLI and OpenAI-compatible server API for running language models entirely on the NPU with no GPU or CPU compute required. Supported hardware: Ryzen AI 300-series (Strix Point, Strix Halo), 400-series (Gorgon Point), and Z2 Extreme. XDNA1 (Ryzen AI 7000/8000) is NOT supported. The orchestration code and CLI are MIT-licensed. NPU compute kernels (xclbins) are proprietary binaries, free for commercial use under $10M annual company revenue.

homepage ↗homepage ↗ github: FastFlowLM/FastFlowLM

Available in

Overlay	Newest	Ebuilds	Last activity
stuff GitHub ↗	0.9.45	3	2 d	details ›

Versions & arches

Version	Overlay	amd64	Committed
9999 LIVE ^≈	stuff	follows upstream — no keywords	2 mo	view · download · history ↗
0.9.45 ^≈	stuff	amd64 testing	17 d	view · download · history ↗
0.9.44 ^≈	stuff	amd64 testing	22 d	view · download · history ↗

Use flags of 0.9.45

openrc Install OpenRC init.d/conf.d files for a supervise-daemon-managed service
systemd Install a systemd template service unit ([email protected])