Lilypad is developing a serverless, distributed compute network that enables internet-scale data processing, AI, ML, and other arbitrary computation while unleashing idle processing power and unlocking a new marketplace for compute.
You can use Lilypad to run AI workload models, including Stable Diffusion and Stable Diffusion Video, or add your module to the Lilypad Network. Using Lilypads distributed compute nodes, you can build and run your own containerized workloads that require high-performance computing.
Overview
Lilypad provides distributed computational services underpinned by the Bacalhau Project. The network provides infrastructure for use cases like AI inference, ML training, DeSci, and more. Lilypad strategically collaborates with decentralized infrastructure networks, such as Filecoin, to formulate a transparent, efficient, and accessible computational ecosystem.
Perform off-chain decentralized compute over data, with on-chain guarantees. Call this functionality directly from a smart contract, CLI, and an easy to use abstraction layer.
In the video above, Ally Haire, Co-Founder of Lilypad, introduces the project and its goals.
The network is laying the groundwork for multi-chain integration and deploying an incentivized testnet.
Lilypad has evolved from earlier versions (v0, v1 & v2), where the network served as a proof of concept for verifiable, decentralized compute directly from smart contracts. These earlier iterations established the groundwork for a robust, scalable platform with expanded features and multichain support.
Bacalhau has been integral to Lilypad since its early versions (v0 and v1), serving as the backbone for verifiable off-chain compute. In these early iterations, Bacalhau was used for Proof of Concept projects, helping users execute decentralized compute jobs from smart contracts.
Find Lilypad on GitHub or visit the blog.
Objective and problem statement
Lilypad aims to mitigate the challenges predominantly associated with the accessibility of high-performance computational hardware. Numerous barriers impede developers and organizations from smoothly integrating projects that require high-performance computing, such as AI technologies, into their applications.
Unlike conventional centralized systems, where access to powerful compute hardware is restricted and costly, Lilypad endeavors to democratize this access. Through its verifiable, trustless, and decentralized computational network, Lilypad extends unrestricted, global access to computational power. By leveraging decentralized infrastructure networks such as Filecoin, Lilypad is strategically positioned to enhance the efficiency, transparency, and accessibility of high-performance computing hardware.
Lilypad Architecture
The architecture consists of several components:
Controller: A public-facing contract that acts as the network gateway and understands a job’s end-to-end workflow.
Storage: Stores deals, agreements, results, and disputes. Acts as a “database” for the controller contract.
Mediation: Starts as a “single mediator” and can be upgraded to a “consortium of mediators.”
Payments: Manages the movement of funds for Lilypad actions and handles the escrow account in the token on behalf of jobs.
ERC-20: A standard ERC-20 contract with additional methods for handling escrow.
Lilypad Services
Mediator: The “Ticket Inspector” that checks results if the client requests.
Smart Contracts: Deployed to IPC, these contracts need to be initialized by both parties to start a job.
Job Creator: The “Client” that posts a “Job Offer” to the solver and pays money into the smart contract as collateral.
Solver: Off-chain market maker that matches resource providers and job creators.
Resource Provider: Posts a “Resource Offer” to the solver and pays money into the smart contract as collateral against its results.
Applications
Perform off-chain decentralized compute over data, with on-chain guarantees, and to call this functionality directly from a smart contract, CLI, API, and an easy-to-use abstraction layer opens the door to a multitude of possible applications, including:
Inference AI jobs
ML training jobs
Invoking & supporting generic ZK computations
Cross-chain interoperability complements to bridge protocols
Utilizing inbuilt storage on IPFS
Federated Learning consensus (with Bacalhau insulated jobs)
IoT & Sensor Data integrations
Providing a platform for Digital twins
Supply chain tracking & analysis
ETL & data preparation jobs
Key features of Lilypad
Some of the key features of Lilypad include:
Verifiable Serverless Decentralized Compute Network: Lilypad is a decentralized compute network that aims to provide global, permissionless access to compute power. The Network orchestrates off-chain compute (a global GPU marketplace) and uses on-chain verification (Arbitrum L2 on Ethereum) to guarantee compute success.
Mainstream Web3 Application Support: Lilypad is designed to enable mainstream web3 applications to use its compute network with the Lilypad CLI and Smart Contracts. It aims to make decentralized AI compute more accessible, efficient, and transparent for developers and users.
Open Compute Network: Lilypad is an open compute network allowing users to access and run AI models/other programs in a serverless manner. Module creators and general users can access a curated set of modules or can easily create their own Lilypad module to run an AI model/other program on the network.
Multichain Support: The Lilypad Incentivized Testnet first launched on Arbitrum in June 2024 and plans to go multi-chain in the near future. Supporting multiple blockchain networks will increase scalability and interoperability, allowing users to choose the best blockchain that suits their needs.
Incentivized Test Net: The Lilypad IncentiveNet is live! The IncentiveNet program provides users with Lilybit_ rewards to participate in running nodes, testing, and improving the network. Learn more by checking out the IncentiveNet Leaderboard.
Decentralization of Mediators: The team also aims to decentralize the mediators in the network. This means that the decision-making process and governance of the network will be distributed among multiple participants, ensuring a more decentralized and resilient system.
What is the Bacalhau Project?
Bacalhau is a peer-to-peer computation network that enables compute-over-data jobs like GPU-enabled AI, ML, analytics, data engineering, data science, de-sci, and more. With the open-source Bacalhau Project, you can streamline your existing workflows without rewriting by running Docker containers and WebAssembly (WASM) images as tasks. This architecture is also referred to as Compute-over-Data (or CoD).
To find out more about it, see the Bacalhau Docs!
Lilypad Roadmap
For the latest Lilypad Project Report: October 10, 2024, you can go here and check out the full details.
Lilypad Leadership Team
Lilypad is assembling a cross-functional and experienced team to drive innovation in the decentralized compute network space, addressing complex R&D challenges related to verification, privacy, and token economics. The leadership and core team bring expertise from leading tech companies and academic institutions, offering a diverse range of skills and backgrounds to develop a robust decentralized computing infrastructure.
Alison Haire (CEO)With previous experience at Filecoin, IBM, and Accenture, Alison leads Lilypad, drawing on her deep expertise in decentralized networks and enterprise solutions.
Steve King (COO)Steve has held leadership positions at Atlassian, Canva, and is a founder himself, bringing extensive operational experience to Lilypad.
Kartika Chendorain-Tulusan (CPO)Kartika, formerly of IBM and EvolutionAI, leads product strategy with a strong background in product management and AI-driven innovation.
Stanley Bishop, PhD (Head of Research)An AI and ML engineer with research credentials from Stanford University, Stanley oversees the research efforts at Lilypad, pushing the boundaries of decentralized computing.
Emma Coochin (CMO)With marketing experience at LaunchVIC, Paypal, and ENTO, Emma leads the company’s marketing and outreach strategies.
Steve Coochin (CIO)Steve brings experience from IBM, Lumigo, Paypal, and Snyk, overseeing the company’s information systems and technological innovation.
Spheron X Lilypad: Powering the Future of AI and Beyond
Lilypad and Spheron have come together to revolutionize the decentralized compute landscape. This strategic collaboration combines the power of Lilypad’s innovative distributed compute network with Spheron’s secure and scalable decentralized infrastructure, offering unmatched computational solutions for AI, LLM, machine learning, and distributed data processing by unleashing untapped compute power across the globe. Key highlights include:
Running Lilypad Nodes on Spheron: Lilypad will leverage Spheron’s robust infrastructure to run its distributed compute nodes, enhancing the network’s performance and scalability.
Spheron as a Trusted GPU Provider: Spheron will supply high-performance GPUs to the Lilypad network, empowering AI workloads like Stable Diffusion and Stable Diffusion Video.
Onboarding Spheron to Lilypad’s GPU Marketplace: Lilypad will integrate Spheron as a stable GPU provider, allowing developers to access cutting-edge decentralized GPU resources.
Integration with SuperNoderz: Lilypad nodes will be added to Spheron’s SuperNoderz platform, simplifying the deployment process and improving the user experience.
Co-Marketing and Branding Initiatives: Both teams will collaborate on marketing efforts to spotlight the powerful synergy between the two networks.
This partnership unlocks new horizons for developers and enterprises seeking efficient, cost-effective, scalable compute solutions for AI, ML, and other high-performance workloads. Stay tuned as we continue to innovate and build a decentralized compute future together!
Contribute to the Lilypad Network during Hactoberfest! They have joined the open source fun and will support contributions of all types.
Improvements to the IncentiveNet slashing mechanism, rewards calculation, and more are underway. This work aims to improve the system’s economics and job reliability. As the network scaled quickly, the Lilypad team has carefully implemented changes to scale up the network infrastructure accordingly.
Follow the updates-rp channel in the Lilypad Discord to keep updated with the latest RP updates and announcements!
Lilypad Linktree – Learn more and join the community!
