Skip to content
saylek

Sharing your GPU

Sharing a machine is how its models become reachable by someone else. It is always an explicit choice: nothing you do as a consumer ever turns your machine into one that serves other people.

What sharing commits you to

When you share a machine, it serves requests from the people you shared it with while your GPU is idle. Sharing yours does not share theirs with you: each direction is a separate decision by the person whose machine it is.

Two things are worth being clear about before you start:

  • Your own work takes priority on your own GPU. A request from someone you share with is dropped when your own work arrives, at the next step of the work rather than instantly.
  • You will see what you serve. Serving a request means your machine handles that person's prompt in the clear, because that is how it computes the answer. The other side of this is documented for consumers in Privacy and egress; sharing puts you on the receiving end of that trust.

The full version of what sharing a machine commits you to, including what serving does not expose and who is answerable for what, is the Acceptable Use Policy. Read it before you run the wizard below rather than after: running it is the act that agrees to it.

Requirements

HardwareA GPU the daemon can serve from. NVIDIA via cuda, Apple Silicon via metal.
BinaryA build with an inference backend compiled in. Released binaries have one.
An accountYou must be signed in with an active Saylek account.

A from-source build with no --features flag compiles but cannot serve: the first call returns HTTP 503 no inference backend compiled in. Build with cpu, cuda, or metal.

Start sharing

Get a model serving first, if you have not already:

saylek gpu wizard

Then turn sharing on:

saylek host wizard

The wizard is what actually turns sharing on: it sets [host].enabled, resolves and writes the models you will advertise, mints the machine credential and installs the background service. saylek gpu wizard above gets a model serving locally, which is a different thing and does not start sharing. Bare saylek host is the serve verb for a machine that is already set up; on one that is not, it refuses and points you back here.

Afterwards, saylek host runs the up-path in the foreground if you want to watch it.

Confirm what your machine is offering:

saylek models     # what this machine can serve right now
saylek status     # health, and whether you are connected

Stopping: three different scopes

These are easy to confuse, and one of them is much larger than people expect.

You want toCommandWhat keeps working
Stop serving other people, keep using Saylek yourselfsaylek host pauseYour own inference, and who you share with
Stop the daemon entirelysaylek stopNothing. saylek call will not answer until saylek start
Step away from Saylek but keep your accountsaylek settings account deactivateReversible with activate

saylek host pause is the small, targeted one, and it is what the "Pause contributing" control on your home page does.

There is no bare saylek pause. "Pause" means two different things at two different scopes, so the CLI does not guess which one you meant: it answers with both commands and lets you pick. Use saylek host pause when you mean serving other people, and saylek stop when you mean the daemon.

Checking what your machine served

saylek statement <YYYY-MM>

A record of where each request ran. Nothing is owed in either direction.

Next steps

Last checked 2026-09-03 · read as markdown at /docs/share-your-models.md