neuron-explorer
Qwen3.5‑4B 전용 조향형 뉴런 탐색기, 모든 MLP 뉴런을 밀어 결과를 보관·탐색
!!! MIRROR !!! Lightweight, bare-metal inference engine and async vision runtime for AMD Ryzen AI (XDNA1) silicon.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
Real-time YOLO on the AMD Ryzen™ AI NPU: YOLOv8n, YOLO11n and YOLOv8n-pose run faster end to end than on AMD's own runtime, and more accurately, from a fraction of the install size.
Ignition compiles a YOLO model into an .ignite container that runs every layer on the NPU of a Windows 11 PC with an
AMD Phoenix processor.
Paste into PowerShell, and again later to update:
It sets up everything under %LOCALAPPDATA%\Ignition. To also install AMD's NPU driver:README 전문 보기 ↗지금 README 전체를 불러올 수 없습니다. 원문 링크에서 읽을 수 있습니다. 아래는 저장된 발췌입니다.
Real-time YOLO on the AMD Ryzen™ AI NPU: YOLOv8n, YOLO11n and YOLOv8n-pose run faster end to end than on AMD's own runtime, and more accurately, from a fraction of the install size.
Ignition compiles a YOLO model into an .ignite container that runs every layer on the NPU of a Windows 11 PC with an
AMD Phoenix processor.
Paste into PowerShell, and again later to update:
It sets up everything under %LOCALAPPDATA%\Ignition. To also install AMD's NPU driver:README 전문 보기 ↗