4.4 KiB
Distributed Inference Network
A volunteer GPU network where nodes independently load model shards, a tracker routes inference through optimal node chains, and contributors earn tokens for serving compute.
Language
Nodes & compute
Node: A volunteer machine that runs the node client, holds one or more shards on disk, and serves inference requests for those shards. Avoid: worker, peer, miner, server
Shard: A contiguous range of transformer layers from a model that a node loads and serves. Shards are the unit of storage, assignment, and reward. Avoid: partition, slice, chunk, segment
Shard Swarm: The P2P group of nodes that collectively seed and download a specific shard. One swarm exists per shard. Avoid: torrent, cluster, pool
Inference Route: An ordered sequence of nodes whose shards together cover all layers of a model. The tracker selects the optimal route per request. Avoid: pipeline, chain, path
Gateway: The network entry point that accepts client requests (OpenAI-compatible HTTP), selects an inference route from the tracker, and streams results back. Avoid: proxy, relay, orchestrator, primary
Tracker
Tracker: The coordinator service that maintains the node registry, scores nodes by throughput/latency, and assigns inference routes. Runs as a centralized service with a P2P gossip fallback. Avoid: coordinator, scheduler, director
Node Score: A throughput/latency rating the tracker maintains per node, used for route selection. Updated continuously from inference telemetry. Avoid: reputation, rating, rank
Payments & fraud
Stake: Tokens a node locks as collateral that can be slashed for fraud. Stake protects the network economically, but route selection is not based on a node's token balance. Avoid: deposit, bond, escrow
Tax: The share of caller payments distributed to compute nodes as rewards. Taxes are weighted by completed work and historical node speed so faster, larger nodes earn proportionally more. Avoid: fee, toll, commission
Caller Credit: Free starting balance granted to a new caller/API key so they can try the network before topping up. Avoid: signup bonus, faucet, airdrop
Free Compute Job: Work a compute node performs without earning immediate rewards, usually during probation or bootstrap phases. Avoid: unpaid labor, warmup request
Slash: The act of reducing a node's stake as a penalty for a proven fraud incident. Avoid: penalize, burn, fine
Strike: A fraud incident recorded on-chain against a node. Enough strikes result in a ban. Avoid: infraction, violation, flag
Ban: Permanent exclusion of a wallet from the network after exceeding the strike threshold. Recorded on-chain. Avoid: blacklist, block, suspension
Probationary Period: The first N jobs a new wallet must complete without earning, to raise the cost of re-entering after a ban. Avoid: trial period, warmup, grace period
Token: Our native Solana L2 token. Used by nodes for staking and received as inference rewards. Clients never need to hold it. Avoid: coin, reward token, native token
Contract Boundary:
The Python interface in packages/contracts that represents registry, payment, and settlement behavior. During the prototype it is implemented by deterministic local wrappers; later the same boundary is backed by real Solana programs.
Avoid: mock contract, fake chain, temporary hack
Validator: A trusted node (or the tracker itself) that re-runs a sample of inference requests to detect fraud. Avoid: auditor, checker, referee
Validation Event: A completed inference record that contains enough information for a validator to decide whether to sample and re-run the request: session id, model preset, messages, inference route, node wallets, and observed output. Avoid: audit log, trace, receipt
Slash Proof: The record submitted by a validator when a sampled re-run diverges from the observed output beyond tolerance. In the prototype this is deterministic local contract state; later it maps to an on-chain proof transaction. Avoid: accusation, report, claim
Client-facing
Client: Any application or user that sends inference requests to the gateway. Pays in SOL or USDC. Avoid: user, caller, consumer
Model Preset:
A named, versioned model available on the network (e.g. llama-3-70b). The tracker knows which nodes hold which shards for each preset.
Avoid: model, checkpoint, version