hal0 docs

Welcome to the hal0 documentation. hal0 is a polished, reliable inference platform for running LLMs at home — it manages model slots, exposes an OpenAI-compatible API, and ships with a built-in dashboard and prewired chat UI.

Status: v1 pre-alpha. The docs below describe v1 as planned — some features (FLM NPU, ROCm/CUDA toolboxes, Hugging Face pulls) are still on the way. Pages marked “Coming soon” are stubs.

Start here

Install The one-line installer, the pre-flight checks, and what `hal0 status` should say after.

Strix Halo The crown-jewel platform. Unified memory + iGPU performance notes.

Slot architecture The lifecycle state machine and how single-flight dispatch works.

API reference OpenAI-compatible endpoints, model registry, dispatcher.