Compile your own LLM for the Hailo-10H — an open pipeline from Hugging Face checkpoint to a self-contained HEF, served with hailo-ollama.
Latest release v0.3.0-dfc5.3.0 — v0.3.0 — Loadable quantization recipes, faster deep-model compiles (DFC 5.3.0) · 2 Oct 2026
4 files for Claude Code: device-debug, new-finding, preflight, hailo-10h-llm-compiler CLAUDE.md — 924 tokens loaded in every session.
CLAUDE.md A 924 tok .claude/skills/device-debug/SKILL.md A 46 tok .claude/skills/new-finding/SKILL.md A 46 tok .claude/skills/preflight/SKILL.md A 39 tok These files are l-nmch/hailo-10h-llm-compiler's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.