SilentSwarm documentation¶
SilentSwarm is a community compute pool: members share their GPUs so the pool can run and train models no single machine in it could hold. Under that, it is a leader/fellow runtime for distributed transformer experiments with explicit control-plane orchestration, tensor data-plane transport, and cluster-backed experiment runs.
-
Get started
Bring up a leader, add a GPU machine with one command, and chat with a model. About ten minutes.
-
How it works
The leader/fellow split, how a model is cut into stages, and what actually crosses the wire between them.
-
Run it
Bootstrap workers, deploy behind a domain, manage accounts, and understand the public web surface.
-
Look something up
Exact routes, contracts and commands, for when you already know what you are looking for.
-
Is this the right tool?
Where Petals, Exo, GPUStack, Ray or a plain single-node stack is the better answer - and what SilentSwarm has not built yet.
-
The numbers
What we intend to measure, the rules we hold ourselves to, and why the results table is still empty.
A reading path¶
If you would rather be led than choose:
- Start a local cluster and run one smoke sweep - Get started.
- Read the architecture overview and the runtime model.
- Use the experiments and operations pages for day-to-day work.
- Reach for the reference pages when you need exact commands, routes or contracts.
Writing docs rather than reading them? The conventions and the local build are in Contributing.