SubQuery Unveils Decentralized AI Inference Hosting at Web3 Summit - Chainwire

21Aug

SubQuery Unveils Decentralized AI Inference Hosting at Web3 Summit

Singapore, Singapore, August 21st, 2024, Chainwire

SubQuery has taken a significant leap forward in decentralized technology by unveiling its latest innovation: decentralized AI inference hosting. This exciting development was showcased at the Web3 Summit in Berlin, where SubQuery’s COO, James Bayly, delivered a live demonstration of the LLama model running on a decentralized network of Node Operators on SubQuery’s internal test network.

SubQuery’s core mission is to empower developers with the tools they need to decentralize without compromise. The company is leading a movement to build the next generation of Web3 applications for millions, prioritizing decentralization as the foundation of this new era.

The SubQuery Network is a pioneering infrastructure layer, already instrumental in supporting decentralized data indexers and RPCs—critical elements for developers building decentralized applications (dApps). SubQuery has established itself as a credible alternative to centralized service providers, offering an open network where anyone can participate as a node operator or delegator.

The integration of AI has been transformative across industries, and Web3 is no exception. Recognizing this, SubQuery has been diligently working to bring AI capabilities to its decentralized platform. “The web3 summit in Berlin with its focus on decentralised technologies is the perfect place for us to announce this next step, and demonstrate it live,” said James Bayly.

Unlike traditional AI services, SubQuery’s network focuses on AI inference—using pre-trained models to make predictions on new data—rather than model training. “There are already some commercial services providing inference hosting for custom models, but not many yet in web3,” James noted. ” It’s much more suitable for long-term hosting on our decentralised network.”

Today, AI inference services are largely controlled by centralized cloud providers, who charge high fees and often use user data to train their proprietary models. “Providers like OpenAI and Google Cloud AI are not only expensive but also use your data to enhance their closed-source models,” James explained. SubQuery’s mission is to offer an affordable, open-source alternative for hosting production AI models. “Our aim is to make AI model deployment as simple as possible, with users able to get started in just 10 minutes,” he added.

“We’re concerned that if the world is forced to use closed source AI models, we’re giving those big corporations a bigger moat in which to train and enhance newer models, a vicious cycle giving power to the wrong people,” James stated. “By running on a decentralised network and distributing prompts across hundreds of node operators, no single party can track you or front-run you via your plaintext prompts or use them to build a moat against open source.”

The SubQuery Network will offer leading-edge hosting for the latest open-source AI models, bringing scalable and accessible AI services to Web3. With a community-driven approach, SubQuery will enable decentralized AI inference at scale, empowering a network of independent Node Operators.

About SubQuery

SubQuery Network is innovating web3 infrastructure with tools that empower builders to decentralise the future – without compromise. Our flexible DePIN infrastructure network powers the fastest data indexers, the most scalable RPCs, innovative Data Nodes, and leading open source AI models. We are the roots of the web3 landscape, helping blockchain developers and their cutting-edge applications to flourish. We’re not just a company – we’re a movement driving an inclusive and decentralised web3 era. Let’s shape the future of web3, together.