Decentralized AI: Permissionless LLM Inference on POKT Network

TL;DR

This paper presents POKT Network's decentralized infrastructure enabling permissionless large language model inference, fostering an open marketplace for AI services that enhances accessibility, incentivizes participation, and competes with centralized providers.

Contribution

It introduces a decentralized, permissionless framework for LLM inference using POKT's existing RPC infrastructure, with a novel Relay Mining algorithm and marketplace dynamics.

Findings

Over 740 billion requests handled since 2020

Decentralized AI inference can match centralized quality of service

Marketplace incentivizes diverse participants to contribute

Abstract

POKT Network's decentralized Remote Procedure Call (RPC) infrastructure, surpassing 740 billion requests since launching on MainNet in 2020, is well-positioned to extend into providing AI inference services with minimal design or implementation modifications. This litepaper illustrates how the network's open-source and permissionless design aligns incentives among model researchers, hardware operators, API providers and users whom we term model Sources, Suppliers, Gateways and Applications respectively. Through its Relay Mining algorithm, POKT creates a transparent marketplace where costs and earnings directly reflect cryptographically verified usage. This decentralized framework offers large model AI researchers a new avenue to disseminate their work and generate revenue without the complexities of maintaining infrastructure or building end-user products. Supply scales naturally with demand, as evidenced in recent years and the protocol's free market dynamics. POKT Gateways facilitate network growth, evolution, adoption, and quality by acting as application-facing load balancers, providing value-added features without managing LLM nodes directly. This vertically decoupled network, battle tested over several years, is set up to accelerate the adoption, operation, innovation and financialization of open-source models. It is the first mature permissionless network whose quality of service competes with centralized entities set up to provide application grade inference.