NightRun

NightRun is a single no_std Rust UEFI application that boots directly into a chat prompt for a quantized local LLM (Llama 3.2, Qwen3, or dense Granite 4.1) — no Linux, no kernel, no browser, no network stack. The model is streamed into RAM with inline CRC-32 verification, storage is sealed once loaded, and inference runs entirely on-CPU (AVX2+FMA+F16C on x86_64, NEON on Pi 5). This skill drives the build → convert → test → flash workflow safely.

When to use this skill

• Building BOOTX64.EFI or a full bootable nightrun.img from source
• Converting a GGUF checkpoint into the .nrm container with nrconvert
• Running/debugging the inference engine on the host (nrhost) before reaching for QEMU
• Booting NightRun in QEMU/OVMF (cargo xtask run) for screenshots or scripted verification
• Flashing a real USB stick or Raspberry Pi 5 SD card via install.sh
• Diagnosing tokenizer/parity failures against llama.cpp reference fixtures