documentation · versioned

everything, and where it lives

Reference for the version you actually run. Start at the top if the box is new; otherwise every section, and the whole knowledge base, is one click from here.

start here

bare box to first token

01Install hal0One line: fetch, verify, unpack, bring the API up.02Load your first modelPull from Hugging Face and assign it to a slot.03Send your first chatOpenWebUI, or curl the OpenAI-compatible endpoint.
docs

five sections, in reading order

Diátaxis, roughly: learn it, then apply it, then run it, then look it up.

getting started

Install, first model, first chat. Bare metal, Proxmox, WSL.

all 8 pages →

concepts

Slots, stacks, profiles, memory, agents, and the Strix Halo itself.

all 8 pages →

guides

Task by task: pull models, manage slots, wire MCP, roll back.

all 12 pages →

operate

Services, auth, and error reporting for a box you actually run.

all 3 pages →

reference

CLI, config schema, slot lifecycle, env vars, and the API.

all 13 pages →
knowledge base

things that stay true

Undated on purpose — every page carries a last-reviewed stamp instead, and gets revised rather than superseded.

getting started

Install, first slot, first request. The path from a bare box to a working /v1/ endpoint.

  • Your first slot
  • Talking to /v1/chat/completions · planned
  • Picking a loadout · planned

hardware notes

What each machine can actually hold, and where the wall is.

runtime & backends

ROCm, Vulkan, the NPU lane, and how to tell which one you are on.

models & quants

Choosing a model that fits, and a quant that does not ruin it.

operating hal0

Running the box day to day: slots, eviction, logs, upgrades.

tool reviews

Honest notes on the things people plug into hal0.

elsewhere

not documentation, still worth reading

changelogEvery release, newest first — derived from CHANGELOG.md.blogReleases, sweeps and post-mortems, in order.benchmarksDecode, prefill and first-token, measured on one box.profilesCommunity hardware profiles and tuned flag bundles.