Skip to main content

GPU Splitting

GPU splitting lets a single node serve multiple customers at once — each renting an integer subset of GPUs. It increases utilization and lets you price flexibly.

Host prerequisite: Docker storage​

GPU splitting requires Docker on overlay2 + XFS with pquota and ftype=1. Run the CLI workflow in Docker Storage Setup before enabling the feature in the portal — the Edit button only unlocks once preflight passes. (This same storage layout will be required for every node in the near future, so the work is not GPU-splitting specific.)

Enable GPU splitting in the portal​

After the host meets the prerequisites:

  1. Open the node's details page in the Provider Portal.
  2. Find the GPU Splitting panel — an Edit button appears once preflight passes.
  3. Set the minimum GPU count per rental (must be greater than 1).

Customers can then rent any integer count between your minimum and the node's total. To disable splitting, clear the minimum — only allowed when no pod is currently using a partial allocation.

When splitting actually helps​

GPU splitting does not unlock any extra validator score, emission, or platform-side incentive — payouts are unchanged whether splitting is enabled or not. The upside is purely demand-side: a meaningful share of customers want a single GPU rather than the full 8× node, and an 8-GPU node with no splitting is invisible to that segment. Enabling splitting widens the renter pool that can match your node, which typically raises utilization on multi-GPU hosts. On single-GPU nodes the feature has no effect.