Run LLMs at 0% CPU on the GPU and object detection in 206ms on the NPU — both on the same Orange Pi 4A. This guide covers building Mesa + MNN from source, fixing the broken NPU driver, and running both accelerators in parallel.
| Component | Spec | Status |
|---|---|---|
| Board | Orange Pi 4A | |
| SoC | Allwinner T527 (8× Cortex-A55 @ 1.8GHz) |
The Epson TM-M30II has a 4KB receive buffer. Send data too fast → buffer overflow → gibberish and crash. Send data too slow → visible horizontal banding where the print head paused.
Think: pouring water into a cup with a hole in the bottom. Too fast overflows. Too slow leaves pour-marks.
The fix: make each raster strip fit inside the 4KB buffer.
Goal: observe a real 30-pin auth sequence end-to-end, then be able to move the auth IC to your own board.
Teuta DT-1 is an open-hardware iPod digital transport. Goal: extract Red Book digital audio (16-bit/44.1kHz PCM) from an iPod Classic via its 30-pin male dock port, route it through a hi-fi DAC (DACBerry ONE+ — WM8804 + PCM5142), output analog.
Purpose: Interface between Apple 30-pin accessories (MB129LL/A cables, docks) and Raspberry Pi for MFi chip authentication analysis, digital audio extraction, and accessory feature testing.
Design Approach: Two-board system
End-to-end GPU-accelerated NVR on a $90 used desktop: NVDEC video decode + ONNX/CUDA object detection across 6 cameras, with semantic search, face recognition, and LPR — all on a 4 GB Quadro P1000 at 49% VRAM. Replaces a $300/yr cloud NVR subscription.
Covers: ONNX model selection & the CUDA Graphs trap, Podman Quadlet for systemd-native NVR, Synology RTSP token gotchas, and Prometheus/Grafana monitoring.
Notes from migrating a production NAS running bare-metal Xpenology (DSM on generic hardware) to a Proxmox VM using ARC loader and full HBA passthrough. 76 TB across 3 RAID arrays on a Lenovo SA120 DAS. Zero data migration — the drives never moved, only the hypervisor changed.