- Setup Type - On-chain or off-chain
- Setup Path - What software is installed
- Operational Mode - Whether you control and handle all operational requirements or delegate them
- Workload Mode - What compute job workloads the node processes
Setup Type
On-chainOff-chainProtocol connection, discovery, and reward eligibility. Applies to Solo O-T Split Siphon
Software Path
go-livepeerOrchestratorSiphonWhat runs on each machine. Solo and O-T Split use go-livepeer only. Siphon adds OrchestratorSiphon for keystore isolation.
Operational Mode
SoloPool NodeO-T SplitWho handles protocol operations, who provides GPU compute. Determines LPT requirement, machine count, and operational responsibility.
Workload Mode
VideoAIDualWhat compute jobs the node processes. Any operational mode supports any workload mode.
Setup Type
Software Path
go-livepeer is the Livepeer protocol implementation. It runs as a single process or in split orchestrator/transcoder mode. Handles protocol operations, GPU compute, and job routing. All setup paths use go-livepeer for the compute side. OrchestratorSiphon is a Python companion tool that handles keystore operations, reward calling, and governance on a separate secure machine. The GPU machine still runs go-livepeer in transcoder mode. Siphon exists because GPU machines restart - and a missed reward round is permanent LPT loss.Operational Mode
Running a pool (accepting external GPU operators) is an extension of the O-T split pattern. See in Advanced Operations.
Workload Mode
The Livepeer protocol routes video and AI as separate job types through different mechanisms. Video jobs flow through the segment-based transcoding pipeline. AI jobs flow through the capability-based inference pipeline. Dual mode runs both from one orchestrator process - the most common production configuration. NVENC/NVDEC (video) and CUDA (AI) use separate execution paths on the GPU. A 24 GB card runs both workloads with one warm AI model loaded.Next Steps
Requirements
Hardware, software, network, and token prerequisites by node mode.
Setup Guide
Install, configure, connect, verify.
Join a Pool
Contribute GPU via an existing pool operator.
Operator Rationale
Cost, revenue, and viability analysis.