amd-npu

Fedora COPR packaging for FastFlowLM - Run LLMs on AMD Ryzen AI NPUs

LLM and speech-to-text on the AMD Ryzen AI NPU with custom AI Engine kernels: LFM2.5-230M at 58 tok/s, Parakeet TDT 0.6B encoder at 185 ms per 10 s audio with FP32 accuracy. IRON/MLIR-AIE, XRT.

100% device-resident Post-Quantum Cryptography (FIPS 202/203/204) on AMD Phoenix NPU — 736/736 silicon-validated test cases

Start, stop and switch FastFlowLM models from the KDE Plasma system tray, with your AMD Ryzen AI NPU doing the work.

AMD NPU Enabler (aie2p) for Strix Point/Krackan (Zen 5, Ryzen AI 7 350) on Ubuntu 26.04. Validated 4.3 TOPS / 68us latency. Includes amdxdna v0.11.0 & XRT v2.23.0.

NPU embeddings for Retrieval Augmented Generation to feed context to AI agents. Windows. AMD SoC.

Game of Life on all 32 AI Engine cores of an AMD Ryzen AI NPU at 30 Gcell/s, with IRON on plain Linux: no Ubuntu, no root

Talk to a 27B model on one Ryzen AI mini PC: Open WebUI + Qwen3.8-27B on the iGPU, speech in and out on the NPU. Nothing leaves the machine.

Fetch is a sorting manager for your existing sample library.

CosyVoice3 text-to-speech and Whisper speech-to-text on the AMD XDNA1 NPU (Ryzen AI 7040/8040), int8, next to an LLM on the same chip.