Documentation

Everything the runtime does, written down.

Start with the quickstart if you have fifteen minutes. Use the references when you have a specific key, flag or header in front of you.

Start here

Deploy your first endpoint in fifteen minutes.

The quickstart walks through installation, authentication, a two-region deployment and how to read the runtime view. It is the fastest way to understand what the platform does for you.

Open the quickstart
terminal 
$ npm i -g @terrane/cli
$ terrane login
$ terrane init --template inference
$ terrane deploy
✓ iad  runtime ready   6m 12s
✓ fra  runtime ready   0m 48s
→ https://embed.acme.terrane.example
Index

Six chapters

Guides are written to be followed with a terminal open. References are written to be searched.

  1. 01 15 min

    Quickstart

    Install the CLI, write your first terrane.yaml, deploy to two regions and read the runtime view.

  2. 02 reference

    Runtime configuration

    Every key in the deployment file: services, regions, hardware tiers, autoscaling, batching budgets and rollout policies.

  3. 03 reference

    CLI reference

    The terrane command, subcommand by subcommand, with flags and exit codes.

  4. 04 20 min

    Routing and failover

    How requests are scored, how regions shed load, how to pin traffic and how to read the x-terrane-region header.

  5. 05 20 min

    Observability and alerts

    Panels, percentiles, log retention, alert rules and exporting metrics to your own stack.

  6. 06 reference

    SDKs

    Typed clients for Python and TypeScript with per-request batching overrides and streaming helpers.

Hands-on

Guides from the journal

Longer walkthroughs and engineering notes that explain the why behind the reference.

  1. 01 Engineering Cutting p99 latency in half with region-aware routing How the Terrane router picks a runtime path using live health, queue depth and network distance, and what it did to our tail latency across 24 regions.
  2. 02 Engineering Dynamic batching: more throughput without wrecking the tail Batching requests is the cheapest way to raise GPU utilisation and the easiest way to ruin latency. Here is how Terrane decides when to wait and when to fire.
  3. 03 Tutorials Deploying a vLLM endpoint to 24 regions in one afternoon A start-to-finish walkthrough: package a Llama 3 endpoint with vLLM, deploy it to four regions, verify routing, then roll out globally with a canary.