Reproducible ML inference benchmarking across heterogeneous hardware: one YAML config drives llama.cpp and ONNX Runtime sweeps on laptops, Raspberry Pi (SSH) and GPUs, with TTFT, throughput, per-rail power, thermal and utilization telemetry in self-describing records, plus publication-quality tables and figures.
Scriptable power measurement and logic analysis for the Nordic Power Profiler Kit II (PPK2): capture current and D0-D7, decode low-speed UART/SPI, measure per-event energy, and run power assertions in CI — from Python, the CLI, or AI agents.
