[ARCHIVED 2026-04-20 — stampby retired; see bong-water-water-bong] no longer actively developed

vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, /v1/responses with separated reasoning, via TheRock ROCm.

AMD ISP4 camera driver module for Ryzen AI laptops

llama.cpp + Qwen3.6-27B (Q8_0 GGUF) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). 256K context, ~7.5 t/s decode via TheRock ROCm Docker.

ComfyUI on AMD Strix Halo (RDNA 3.5 / gfx1151) via Docker. Ubuntu Rolling + UV-managed Python 3.12 + ROCm preview wheels. Solves the silent CPU fallback Debian/Python 3.13 images hit on gfx1151.

Talos-O (Omni): A sovereign, embodied agentic organism forged on AMD Strix Halo. Integrating the Chimera Kernel (Linux 7.0), Zero-Copy Introspection, and the Phronesis Engine. Built from First Principles.

Experiments, notes, and benchmarks for AMD Ryzen AI (Krackan Point NPU + Radeon iGPU) on Linux

Docker infrastructure for AMD Strix Halo (RDNA 3.5 / gfx1151): PyTorch + ROCm base container and a separate Ollama LLM service. Two folders, two Compose files, one Strix Halo box.

Experimental local LLM API for AMD Strix Halo (gfx1151) on ROCm 7.10 (TheRock). Two-service split: vLLM inference engine + FastAPI gateway with OpenAI protocol normalization, auth, management. Docker Compose.

A fully offline, air-gapped desktop AI workspace for legal, medical, and financial professionals. Runs entirely on the AMD Ryzen NPU with zero cloud calls and zero telemetry. All AI processing happens locally so no data leaves the device, ensuring complete privacy and confidentiality.

A lightweight TUI monitor for AMD Ryzen AI NPUs

Stable Diffusion image generation on AMD Ryzen AI NPUs for Linux

StretchCam is a stretching app that uses the MoveNet quantized by Ryzen AI Software to efficiently estimate your pose from the camera.